papers_data.txt

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Molecular biology studies of uveal melanoma have resulted in the development of novel immunotherapy approaches including tebentafusp—a T cell–redirecting bispecific fusion protein. More biomarkers are currently being studied. As a result, combined immunotherapy is being developed as well as immunotherapy with bifunctional checkpoint inhibitory T cell engagers and natural killer cells. Current trials cover tumor-infiltrating lymphocytes (TIL), vaccination with IKKb-matured dendritic cells, or autologous dendritic cells loaded with autologous tumor RNA. Another potential approach to treat UM could be based on T cell receptor engineering rather than antibody modification. Immune-mobilizing monoclonal T cell receptors (TCR) against cancer, called ImmTAC TM molecules, represent such an approach. Moreover, nanomedicine, especially miRNA approaches, are promising for future trials. Finally, theranostic radiopharmaceuticals enabling diagnosis and therapy with the same molecule bring hope to this research.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2. Methodology Databases Pubmed, Scopus, and Google Scholar were used. We defined the following keywords as a string of search terms: “uveal melanoma”, “uveal melanoma” AND “molecular biology”, “uveal melanoma” AND “therapy”, “immunotherapy” OR “ICI” OR “Immune checkpoint inhibitor”, “bispecific antibodies”, “cell-based therapies”, “CAR-T” AND “uveal melanoma”, “tebentafusp”, “theranostics”, “nanomedicine” OR “nanoparticles” OR “photosensitizers”, “photodynamic therapy” AND “uveal melanoma”, “targeted cancer treatments”. The search was modified according to the mentioned databases. Language restrictions included literature described in English and Polish. For clinical trials, we searched two databases: “www.clinicaltrials.gov” and “https://euclinicaltrials.eu/”, with no restrictions on race, place, age, or language.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? This review provides insights at the molecular level into the current and old for treating meniscal injuries. Meniscal injuries have been found to have a substantial impact on the progression of osteoarthritis. In line with the “save the meniscus” approach, meniscectomy is considered a last-resort treatment. Nevertheless, it is important to note that mechanical repair alone may not achieve the complete restoration of the meniscus. A deep understanding of the healing pathways could lead to future improvements in meniscal healing. The inclusion of cytokines and chemokines has the potential to facilitate the process of tear repair or impede the inflammatory catabolic cascade. MicroRNA (miRNA) could serve as a potential biomarker for meniscal degeneration, and RNA injections might promote collagen and growth factor production. The critical aspect of the healing process is angiogenesis within the inner zone of the meniscus. The use of collagen scaffolds and the implantation of autologous meniscus fragments have been successfully integrated into clinical settings. These findings are encouraging and underscore the need for well-designed clinical trials to explore the most effective factors that can enhance the process of meniscal repair.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2. A PubMed search was conducted in October and November 2023, utilizing search terms, such as ‘meniscus’, ‘menisci’, ‘molecular’, ‘TNF-α’, ‘endostatin’, ‘FGF’, ‘biological healing’, ‘interleukin’, ‘cytokine’, ‘Growth Factor’, ‘avascular’, ‘vascularization’, ‘meniscus tear’, ‘meniscus lesion’, ‘hyaluronic acid’, and ‘MiRNA’. The inquiry encompassed articles published over the last 30 years, with a preferential focus on the most recent studies. The objective is to present the latest advancements in meniscus healing research within the genetic domain, reflecting the continuous evolution of this scientific field.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Simple Summary In ovarian cancer, about 70% of patients experience relapse despite primary cytoreductive surgery and platinum-based chemotherapy. The occurrence of resistance to chemotherapeutic agents remains a major obstacle in this context. Various factors are involved. The use of immunotherapy has widened the spectrum of therapeutic options in ovarian cancer. There are many different molecular parameters that have become relevant in recent years. The prognosis for relapsed patients is very poor, so an examination of such parameters and possible subsequent individualized therapy is desirable. In this work, we evaluate biomarkers that can or should be used in decision making about which therapy, but also which immunotherapy, is best. So far, there are some relevant biomarkers in ovarian cancer that can be used in primary therapy or recurrence therapy, such as genetic markers. The aim is to obtain additional parameters that can be used predictively, are of therapeutic relevance, and are prognostically relevant. The objective is to highlight the molecular mechanisms of the most promising targeted agents under clinical investigation to demonstrate their potential relevance in recurrent/refractory ovarian cancer. Ovarian cancer (OC) has a high rate of mortality and is the fifth most common cause of death in females all over the world. The etiology is still unclear. Numerous factors such as smoking, obesity, and unhealthy diet may affect the risk of OC. Having a family history of breast and OC is one of the main risks for developing OC. Mutations of BRCA1/2 are associated with OC risk as well. The histopathological classification of OC reveals the four most common types: serous, clear cell, endometrioid, and mucinous; these are epithelial OC types, and other types are rare. Furthermore, OC can be subdivided into types I and II. Type I tumors are most probably caused by atypical proliferative tumors. Type II tumors include high-grade carcinoma of the serous type, carcinosarcoma, and carcinoma, which are not differentiated and generally originate from tubal intraepithelial carcinoma of the serous type. Typically, type I tumors are present in early stages, usually with good prognosis. Type II tumors are classified as high-grade tumors and are most often diagnosed at advanced FIGO stages with poor prognosis. High-grade serous OC accounts for 90% of serous OC. Tumor heterogeneity aggravates OC treatment. The standard care for primary epithelial ovarian cancer (EOC) is cytoreductive surgery followed by platinum-based chemotherapy. Neoadjuvant chemotherapy can be used in certain cases followed by cytoreductive surgery. The main prognostic factor is complete tumor resection. However, about 70% of patients relapse. Resistance to chemotherapeutic agents remains a major challenge in EOC treatment, in which many different factors are involved. In recent years, the examination of molecular parameters and their prognostic impact has become increasingly relevant in EOC, and furthermore, the use of immunotherapy has expanded the therapeutic range. As the clinical need is greatest for relapsed patients, this systematic review will focus on recent advances in molecular biology with prognostic and predictive markers and treatment options for recurrent/refractory OC. Inclusion criteria for the review: potential prospective or predictive biomarkers in preclinical or clinical use in relapsed and refractory OC, prognostic impact, clinical and preclinical trials, and immunotherapy. Exclusion criteria for the review: primary OC, no full text or available, not the topic mentioned above, and text not available in English. Risk of bias: the included studies were evaluated descriptively for the topics mentioned above, and data were not compared with each other. The objective is to highlight the molecular mechanisms of the most promising targeted agents under clinical investigation to demonstrate their potential relevance in recurrent/refractory OC.
Completion: Here is what we may expect the methods section for such an experiment to look like. 18. A systematic literature search was performed with PubMed and Cochrane Library for relevant references from 2018 through 11 May 2023 using ovarian cancer, refractory, biomarkers, and immunotherapy as search terms (Figure 1). The search string was ((((ovarian cancer[MeSH Terms]) OR (Ovarian cancer[Title/])) OR ((refractory ovarian cancer[MeSH Terms]) OR (refractory ovarian cancer[Title/]))) AND ((biomarkers[MeSH Terms]) OR (biomarkers[Title/]))) AND ((immunotherapies[MeSH Terms]) OR (immunotherapies[Title/])). Two reviewers collected data from each report and worked independently. Selection criteria leading to inclusion: all manuscripts found using the above search including the search terms ovarian cancer, refractory, recurrent, prognosis, biomarkers. Selection criteria leading to exclusion were no full text or available, not relevant to the above-mentioned topic, text not available in English. Further articles like guidelines and ongoing and completed trials from clinicalgov.com were considered. The systematic review followed the recommendations of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). The protocol has not been registered. Risk of bias: the included studies were evaluated descriptively for the above-mentioned topics, data were not compared with each other. The literature search diagram is included in Figure 1. A total of 154 articles were extracted and a further 12 citations were identified from other sources. Therefore, 162 full texts were assessed and reviewed. A total of 67 full texts were excluded because they did not correspond to the intended topic or were not suitable for other reasons.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Simple Summary This review aims to shed light on the proliferative markers important in the everyday clinical management of colorectal cancer (CRC), ranging from simple of assessing cellular proliferation (e.g., DNA ploidy, BrdUrd/IdUrd/tritiated thymidine binding index) to the use of immunohistochemistry (IHC) and modern molecular biology techniques (e.g., qRT-PCR, in situ hybridization, RNA/DNA sequencing) for the detection of genetic and epigenetic markers. Among the examined markers, the prognostic utility was demonstrated for aneuploidy and the overexpression of IHC markers (e.g., TS, cyclin B1, and D1, PCNA, and Ki-67). Classical genetic markers of prognostic significance mostly comprise mutations in commonly examined genes such as APC, KRAS/BRAF, TGF-β, and TP53. Chromosomal markers include CIN and MSI, while CIMP is indicated as a potential epigenetic marker with many other candidates such as SERP, p14, p16, LINE-1, and RASSF1A. Modern technology-based approaches to study non-coding fragments of the human genome have also yielded some candidates for CRC prognostic markers among the lncRNAs (e.g., SNHG1, SNHG6, MALAT-1, CRNDE) and miRNAs (e.g., miR-20a, miR-21, miR-143, miR-145, miR-181a/b). With growing knowledge of the human genome structure and the rapid development of molecular biology techniques, it is hoped that a panel of reliable prognostic markers could improve the assessment of survival as well as allow for the better estimation of the treatment outcomes for CRC patients. Colorectal cancer (CRC) is one of the most common and severe malignancies worldwide. Recent advances in diagnostic allow for more accurate identification and detection of several molecular biomarkers associated with this cancer. Nonetheless, non-invasive and effective prognostic and predictive testing in CRC patients remains challenging. Classical prognostic genetic markers comprise mutations in several genes (e.g., APC, KRAS/BRAF, TGF-β, and TP53). Furthermore, CIN and MSI serve as chromosomal markers, while epigenetic markers include CIMP and many other candidates such as SERP, p14, p16, LINE-1, and RASSF1A. The number of proliferation-related long non-coding RNAs (e.g., SNHG1, SNHG6, MALAT-1, CRNDE) and microRNAs (e.g., miR-20a, miR-21, miR-143, miR-145, miR-181a/b) that could serve as potential CRC markers has also steadily increased in recent years. Among the immunohistochemical (IHC) proliferative markers, the prognostic value regarding the patients’ overall survival (OS) or disease-free survival (DFS) has been confirmed for thymidylate synthase (TS), cyclin B1, cyclin D1, proliferating cell nuclear antigen (PCNA), and Ki-67. In most cases, the overexpression of these markers in tissues was related to worse OS and DFS. However, slowly proliferating cells should also be considered in CRC therapy (especially radiotherapy) as they could represent a reservoir from which cells are recruited to replenish the rapidly proliferating population in response to cell-damaging factors. Considering the above, the aim of this article is to review the most common proliferative markers assessed using various including IHC and selected molecular biology techniques (e.g., qRT-PCR, in situ hybridization, RNA/DNA sequencing, next-generation sequencing) as prognostic and predictive markers in CRC.
Completion: Here is what we may expect the methods section for such an experiment to look like. 4. to Assess Cell Proliferation in Colorectal Cancer In clinical practice and basic research, several exist for assessing the growth rate of normal and tumor cells. The most common is the assessment of (1) the “density” of ongoing mitoses in the tissue material, known as the mitotic index (the percentage of mitoses in the assessed pool of tumor cells per 1 mm2), the so-called mitotic rate, the rate at which cells enter the mitotic phase (M phase) (% of the cells/h) [96,97,98]; (2) the percentage of cells in the S phase by calculating the so-called bromo-, iododeoxyuridine labeling index (LIBrdIUdR) [99,100,101,102] with in vitro tritiated thymidine [103,104], or with a new thymidine analog, 5-ethynyl-2-deoxyuridine (EdU) labeling [82]; (3) IHC expression of classical proliferative markers (e.g., cyclins, proliferating cell nuclear antigen (PCNA), and Ki-67 [105,106,107,108,109]); (4) computed tomography (CT) with dual-layer spectral detector CT [110] or positron emission tomography (PET) [111,112,113]. The cancerogenic process of the colonic mucosa is associated with the development of cell proliferation abnormalities, which precede the onset of morphological alterations such as epithelial dysplasia. Individuals with gastrointestinal (GI) tract cancer risk factors and animals exposed to carcinogens mainly show an increase in the cell proliferation rate and abnormalities in the distribution of proliferating cells. The so-called extension of the proliferative compartment was observed even when the mucosa was not yet affected by morphological abnormalities. This proliferative feature seems to be related to the presence of defects in cell differentiation [114]. There is also a report in which a significantly lower expression of multi-gene proliferation signature (GPS) was observed in CRLMs, confirming lower levels of their proliferation using qRT-PCR and Ki-67 immunostaining. According to the authors, slow proliferation is a biological feature of both CRLMs and primary tumors with metastasis capacity [115]. In the context of the stem cell hypothesis of CRC development, in vitro studies based on the exposure of CSC480 cells to a 2 h pulse of 10 μg EdU have recently allowed for the identification of as many as five different cell populations, of which the EdU-negative and CD44-positive population may represent the ‘true’ CSC lineage [82]. In formalin-fixed, paraffin-embedded tissues, changes in DNA content or the expression of proteins involved in the cell cycle in dysplastic, precancerous, and neoplastic tissues of the human colon were most often comparatively assessed. However, changes in the expression of IHC markers (e.g., PCNA, p53, Ki-67) at different developmental stages of CRC were not always clear enough to serve as reliable prognostic markers [31,116,117]. 4.1. Assessment of Mitosis in Cancer Tissues The mitosis count/mitotic index in pathological samples allows for the assessment of tumor proliferative activity, facilitates tumor classification and diagnosis, assesses grade malignancy, determines aggressive behavior, allows for intratumoral lymphocyte counts, and may present prognostic significance [98,118]. The preferred sites for mitosis counting include invasive fronts (rich in viable tumor cells) or the periphery of the tumors. The tissue area for counting mitotic activity for different tumors was standardized as the number of mitoses in a fixed number of high-power fields (HPFs) (typically 10 fields of view at x 400 magnification) [118]. HPFs for digital pathology, different from glass-slide HPFs in conventional light microscopy, require re-evaluation [119]. The current recommendation for CRC is not to report the number of mitoses in HPFs, but to report them per square millimeter [98], or per 2 mm2 (this is approximately equivalent to 10 HPFs on modern microscopes) [97,118]. 4.2. DNA Ploidy and Percentage of Cells in S Phase Aneuploidy refers to an abnormal number of chromosomes in a cell, different from a multiplication of the haploid set, resulting from several genetic alterations. It reflects both gain/loss of whole chromosomes and unbalanced chromosome rearrangements (e.g., deletions, amplifications, translocations of large genome regions) [120]. For more than 100 years, aneuploidy has been postulated as a tumor-promoting factor, and its clinical relevance is still highlighted as a prognostic marker [121,122]. Interestingly, it has been suggested that tissue SCs have also developed their distinct response to aneuploidy, being able to survive and proliferate as aneuploid [121]. DNA content and ploidy were evaluated as prognostic factors in CRC [123,124,125,126], with DNA aneuploidy demonstrated to be a feature of tumors with a higher proliferation rate [124,126,127]. On the other hand, ploidy alone, determined by flow cytometry (FCM), had no prognostic significance in CRC (DFS). In a group of more than 400 CRC patients, it was shown that nearly 73% of patients showed aneuploid tumors. Still, the DNA pattern was not correlated with either age, gender, location, differentiation, or stage of the tumors [128]. Review studies [129,130] and a meta-analysis [127] indicate a significant association of aneuploidy with tumor progression and a worse prognosis. An older meta-analysis (2007) showed that patients undergoing surgical resection of aneuploid CRC have a higher risk of death after five years [129]. Later meta-analysis (2015) including more than 7000 CRC patients showed a higher prevalence of aneuploidy in late versus early stage sporadic CRC (OD 1.51, 95% CI 1.37–1.67), indicating that genomic instability increases with CRC progression. In 54.1% of studies, a significant effect of aneuploidy on prognosis was described for OS, disease-specific survival (DSS), and recurrence (relapse)-free survival (RFS). Hence, aneuploidy may be considered as a tumor stage-specific prognostic marker [127]. Other to assess the proliferation of different cell populations in CRC include evaluating the number of cells in which DNA synthesis occurs using LIBrdIUdR, with tritiated thymidine [103,104] and EdU labeling [82]. Such procedures allow in vivo calculation of the S-phase fraction labeling index (LI), the duration of the S phase (Ts), and the potential tumor doubling time (Tpot) [131]. Evaluation of the binding index of BrdUrd/IdUrd/tritiated thymidine, etc., is possible (1) following the use of monoclonal antibodies (mAbs) against thymidine analogs in FCM or (2) by using the IHC method. Although these method variations are inexpensive and easy to perform, they are characterized by high subjectivity in the evaluation of specimens, poor reproducibility of results, and the lack of standardization between centers [104,124,128,132]. Studies from the 1990s showed that examining only the total and aneuploid LI in CRC is not sufficient as an indicator of proliferation, as Ts also can vary between tumors and even within a single tumor (from 4.0 to 28.6 h). The mean Tpot ranged from 1.7 to 21.4 days. None of the cellular kinetic parameters correlated with Dukes’ classification or histologic examination [133]. Wilson et al. showed that while IUdR assessed by FCM (IUdRfmc) and assessed by IHC (IUdRimm) correlated with each other, and their LIs were significantly higher in aneuploid than diploid tumors, no prognostic property of these markers was demonstrated [124]. Similar results were reported by other authors [126]. On the other hand, Palmqvist et al., using both IUdR detection techniques (FCM + IHC), demonstrated that patients with Dukes’ B tumors with higher IUdR LI (in invasive margin) and/or low Tpot (at both the invasive margin and the luminal border) had longer survival [100]. FCM studies on the prognostic value of the DNA index or S-phase fraction also did not demonstrate prognostic significance for disease recurrence in CRC stages II and III [125], survival in the overall group, or within stages [132]. In contrast, the kinetic parameters assessed by Michel et al. using in vivo injection of Brd and FCM, were independent prognostic factors in diploid tumors. These included lymph node (LN) involvement, ploidy, and Tpot in all tumors, and Tpot only in diploid tumors [131]. In summary, most studies failed to demonstrate the prognostic value of the CRC proliferation markers assessed. Moreover, using these , more accurate results for evaluating normal and tumor cell proliferation are obtained after analyzing material at different stages of CRC development. On the other hand, performing such tests before and during treatment allows one to predict the outcome of CRC radiotherapy. For example, BrdUrd LI before RT treatment of RC was not a predictor of early clinical and pathological tumor response. In contrast, the BrdUrd LI ratio before/after RT was correlated with the inhibition of proliferation in responsive tumors. Thus, the rapid growth rate of preoperatively irradiated rectal cancer was a favorable prognostic factor [134]. 4.3. Immunohistochemical for the Detection of Proliferative Markers The immunohistochemical (IHC) technique is based on antibodies against specific antigens in tissues and cells. In histopathology, IHC testing is most commonly performed on formalin-fixed, paraffin-embedded tissues that can be stored for long periods of time [135,136]. Increasingly, tissue microarrays (TMAs), which contain selected tissue material from tumors, normal tissues (control), and tumor metastases on a single slide, are being used for IHC. Although the cost of producing TMAs remains high, their selection saves labor time and the number of reagents used (including sometimes expensive antibodies), allowing for better result reproducibility [137]. The markers most commonly used to assess tumor proliferation rate (including CRC) are discussed below. 4.3.1. Thymidylate Synthase (TS) in CRC Thymidylate synthase (TS, EC 2.1.1.45) is an enzyme protein required to synthesize and repair DNA. It catalyzes the conversion of 2’-deoxyuridine-5-monophosphate (dUMP) to deoxythymidine-5’-monophosphate (dTMP), which is phosphorylated to the triphosphate state (dTTP), a direct precursor for DNA synthesis. It is also an important cellular target for cytotoxic drugs of the fluoropyrimidine group, which are widely used to treat solid tumors [138]. The first clinically used TS inhibitor was the 5-fluorouracil (5-FU) antimetabolite drug, a metabolite of 5-fluorouracil, fluoro-deoxyuridine monophosphate, which forms a ternary complex with TS and 5,10-methylenetetrahydrofolate [139]. IHC studies of TS are used to determine proliferative indices and drug resistance [138]. The role of ectopic production of human TS in the neoplastic transformation of mouse cells in vitro and in vivo has also been demonstrated, suggesting a role for TS as an oncogene [140]. Overexpression of TS is responsible for the resistance of tumor cells to TS-targeted chemotherapeutics and correlates with response to targeted CTx [141,142,143,144]. With the generation of mAbs against TS, particularly TS 106 and TS 109, it was possible to use IHC to detect TS in normal and tumor tissues. The color reaction is granular and occurs in the cytoplasm of cells. TS has been shown to be overexpressed in tumors including CRC. The prognostic significance of this IHC marker has also been studied [141,142,143,145,146,147]. Observations on the prognostic role of TS indicate that increased tissue expression of TS may serve as an independent factor of poor prognosis for DFS and OS [141,143,145,146,148,149,150] or RFS and OS [147]. However, there are also results in which the prognostic role of TS in the survival of CRC patients could not be proven. Moreover, it was shown that high levels of Ki-67 were associated with increased (decreased) survival in patients with a low (high) expression of TS [142]. The meta-analysis by Popat et al. showed that tumors with high TS levels appeared to have worse OS compared to tumors with low TS levels (HR 1.74, 95% CI 1.34 to 2.26) [151]. The predictive role of TS in CRC adjuvant therapy has also been investigated in various combinations (e.g., 5-FU-based CTx, oxaliplatin followed by 5-FU). One study showed a significantly higher degree of TS immunoreactivity in primary tumors compared to corresponding metastases. Still, the response rates after CTx for metastatic disease were similar for patients with low and high levels of TS shown in their primary tumors. In contrast, response rates were found to be higher in patients with low versus high TS in metastatic disease (71% and 23%, respectively) [152]. Thus, TS levels in primary tumors cannot be reliably used to predict the response to adjuvant therapy [147,152]. An opinion questioning the benefit of TS labeling for predicting the effect of 5-FU in CRC can also be found in a review paper [139]. Moreover, while an extensive prospective analysis showed that high TS levels in the tumor were associated with improved DFS and OS after adjuvant treatment of CRC, TS expression in the tumor did not predict the benefit of 5-FU-based CTx [153]. However, a recent study by Badary et al. showed that high TS expression is a predictor of early failure in CRC therapy. Hence, high TS expression may help identify patients who will benefit less from oxaliplatin and 5-FU CTx (FOLFOX) [143]. 4.3.2. Cyclins in CRC The human cyclin family includes about 30 genes encoding protein products containing the so-called cyclin box. Only a few subfamilies of these proteins (A-, B-, C-, D-, and E-cyclins) play a role in cell cycle regulation [57,58,61,154]. Others distinguish between ‘primary’ cyclins (A, B1, D1, D3, and E), crucial for cell cycle progression, and ‘secondary’ cyclins (C and H), with indirect cell cycle-related effects. Few papers have addressed the secondary prognostic role of cyclins in cancer including CRC [155]. Cyclin A can activate two different Cdks, playing a role in both the S phase and mitosis (M) [156], controlling various phenomena related to DNA replication and progression through the G2 phase [58]. Cyclin B is a regulator of the mitotic phase, responsible for M phase entry and chromosome segregation. In turn, cyclin C, encoded by the CCNC gene, is involved in G1/S progression. It forms complexes with cdk8 and cdk19, modulating DNA initiation and duplication by binding Mdm2 binding protein (MTBP), an interaction required for proper entry into the M phase with complete DNA replication [157]. D-type cyclins are a major determinant of cell cycle initiation and progression in many cell types. Cyclins D1, D2, and D3 (encoded by CCND1, CCND2, and CCND3) are identified as cell type-specific G1 mitogen sensors. The E-type cyclins control DNA replication. Cyclin E1, encoded by the human CCNE1 gene, interacts mainly with Cdk1 and Cdk2 and plays an essential role in transition of human cells from G1 to the S phase [58,158]. In some studies, cyclin A (A2) overexpression was observed in 77–80% of CRC cases [159,160]. In rectal cancer, a linear correlation was observed between cyclin A and Ki-67-positive cell expression, whereas no such relationship was found between TS and cyclin A [161]. Several publications have recognized cyclin A overexpression as an independent unfavorable prognostic factor in CRC patients [159,160,162]. There are also reports showing that high cyclin A expression was independently associated with improved survival [155], and its level above the median predicted a better prognosis in CRC patients (HR 0.71, 95% CI 0.53–0.95) [163]. Cyclin B (B1) is classified as a mitotic cyclin [164,165]. Its elevated expression may promote the development of CRC, but its prognostic significance is controversial. Decreased expression of this cyclin has been shown in pCRC cases characterized by large size, mucinous type, deep invasion, or short postoperative survival. High cyclin B1 expression has been associated with increased p53 levels in ADs, and high Ki-67 in ADs and primary carcinomas [164]. Cyclin B1 is overexpressed and promotes cell proliferation in early-stage CRC [165,166]. No correlation was found between cyclin B1 expression and DFS or OS [165]. Other authors have reported that after CRC cells invade surrounding tissues and metastasize to distant tissues, cyclin B1 expression is reduced. Furthermore, it was observed that patients with a low level of cyclin B1 had lower survival rates than those with a high level of cyclin B1 expression. Suppression of cyclin B1 may promote tumor cell migration and invasion and reduce E-cadherin expression. Cyclin B1 may thus promote tumor growth but inhibit metastasis in CRC [166]. As shown in a recent meta-analysis regarding the prognostic role of cyclin B1 in solid tumors, in CRC, elevated cyclin B1 expression was associated with better prognosis, reflected by favorable 5-year OS of CRC (OR 0.49, 95% CI 0.30–0.82) [167]. Cyclin C overexpression was observed in 88% of CRCs, and CCNC (qRT-PCR) amplification was independently associated with poor prognosis. The association between CCNC amplification and impaired survival appears independent of its gene product [155]. However, further studies on the role of cyclin C itself as a prognostic factor in CRC are lacking. In contrast, a study by Firestein et al. found the expression of Cdk8, a kinase functionally related to cyclin C, in 70% of CRCs. This expression was independently associated with β-catenin activation, female gender, and fatty acid synthase (FASN) overexpression. Cdk8 expression also significantly increased the colon cancer-related mortality. However, no such association was observed among RC patients. These data support a potential association between Cdk8 and β-catenin and suggest that CDK8 may identify a subgroup of CRC patients with poor prognoses [168]. D-type cyclins play a central role in cell cycle entry. Changes in the activity of the D-Cdk4/6 cyclin complex are an almost universal feature of cancer cells [60]. Their expression increases in response to oncogenic alterations in key oncogenic pathways (e.g., K-RAS, PI3K/AKT, WNT) [58]. Overexpression of cyclin D1 is observed in CRC, particularly in advanced disease [160,169,170,171]. However, opinions are divided on the prognostic significance of this cyclin. Overall, more than 20 publications have been published on the prognostic value of cyclin D1 expression in case–control studies, as reviewed by other authors [171]. Maeda et al. showed a shortening of both OS and DFS, and an increase in the CRC recurrence rate in patients with strong cyclin D1 expression [172]. In the study by Bahnassy et al., as mentioned, cyclin D1 overexpression in CRC, similarly to cyclin A, was also correlated with shorter OS. This study indicated that cyclin D1 amplification was also associated with reduced OS. Both cyclin D1 and cyclin A were independent prognostic factors in CRC patients [160]. Another study showed an association between increased cyclin D2 and D3 expression and vascular invasion, CRLM, and decreased DSS [173]. In turn, a study by Mao et al. showed that positive cyclin D1 expression was associated with shorter survival in patients with colon adenocarcinoma [174]. Another publication demonstrated worse 5-year survival in patients with positive cyclin D1 expression in advanced-stage CRC (III, IV) [169]. Moreover, a recent study showed that cyclin D1 and epidermal growth factor receptor (EGFR) overexpression and late pathological stage after surgery were characterized by shorter relapse-free time (RFT) [175]. It has also been shown that the early recurrence of CRC in high-risk Duke B and Duke C stages is associated with high cyclin D1 expression [176]. However, some studies reported no prognostic role for cyclin D1 in RC or CC [155,177,178,179,180]. Finally, some studies have considered cyclin D1 overexpression to be a good predictor of survival [181,182], both in terms of cytoplasmic and nuclear expression [183]. There are also two meta-analyses on the prognostic significance of cyclin D1. One of them (2014) showed that cyclin D1 overexpression is a factor for poor prognosis in CRC, both in terms of OS (HR 0.73, 95% CI 0.63–0.85) and DFS (HR 0.60, 95% CI 0.44–0.82) [170]. Another meta-analysis (2022) confirmed these results, reporting both shorter OS (HR 0.36, 95% CI 0.94–0.22) and DFS (HR 0.46, 95% CI 0.77–0.20) [184]. In contrast, in a study by Jun et al. based on a large cohort of pCRC patients (n = 495), in which high cyclin D1 expression was observed in nearly 80% of patients, high cyclin D1 expression was a marker for better OS and RFS. Multivariate analysis showed that cyclin D1 overexpression and the young age of patients remained independent predictors of higher OS rate. In turn, high cyclin D1, female gender, CTx, absence of nodal metastasis, and lower T category remained independent predictors of better RFS. The authors believe that cyclin D1 expression can be a favorable prognostic indicator in CRC patients [171]. Studies on the prognostic role of cyclin E in CRC have also been conducted, most often together with other markers of cellular proliferation (e.g., cyclin D1 and Ki-67) [176,179,185,186]. Ioachim et al. demonstrated cyclin E overexpression in 30% of CRC patients, but the prognostic significance in determining the risk of recurrence and OS was not confirmed [179]. Elevated cyclin E expression correlated with increasing TNM staging and decreasing tumor differentiation. In turn, PFS and median survival were reduced in patients with positive cyclin E expression [185]. Another group found cyclin E expression in a similar proportion of CRC patients (~35%) but did not report prognostic significance in CRC as a single marker [186]. The data in Table 1, arranged chronologically, show variable results regarding the tissue expression of various cyclins in CRC. In general, the overexpression of these cell cycle markers is detected in most patients (up to almost 90%). When it comes to the evaluation of the prognostic value of cyclins, most data concern cyclins A (A2), B (B1), and D (D1). However, as with other tissue markers, the data are not consistent. Cyclins of the D family show the strongest association with signaling pathways involved in CRC development (e.g., KRAS, PI3K/AKT, WNT). Moreover, while some studies have also associated cyclin D1 overexpression with poor prognosis, some present results describe no prognostic significance or indicate cyclin D1 as a good prognostic factor. In conclusion, examining the expression of these proteins alone seems insufficient to determine the prognosis for survival of CRC patients. Hence, further research is needed to determine the role of cyclin C and E as prognostic markers in CRC. 4.3.3. Proliferating Cell Nuclear Antigen (PCNA) in CRC In eukaryotic cell physiology, PCNA plays a vital role in DNA replication and many replication-associated processes. It is a 36 kDa non-histone nuclear protein, accompanying delta and epsilon DNA polymerase. It is referred to as a cyclin, playing a prominent role in cell proliferation. It is mainly produced in proliferating and transformed cells as a specific marker of cell division [187]. PCNA expression is detected in all phases of the cell cycle, confirming the function of this polypeptide in DNA repair, synthesis, and regulation [108]. There is a significant variability of results regarding PCNA expression in ‘adenoma–carcinoma sequence’ changes in CRC. Either no increase in PCNA-positive cells was detected in adenocarcinoma [116], or a gradual increase in PCNA expression was shown in HP-AC lesion sequences [117]. Some authors observed high PCNA expression in more aggressive forms of ADs, which can progress to malignant lesions [188]. As for the value of PCNA expression in predicting CRC, results also vary. One publication recognized PCNA as an independent predictor of relapse and shorter survival in CRC patients [189]. Choi et al. demonstrated a significantly higher relapse rate in CRC patients, with higher-than-average PCNA-LI. Also, the four-year survival rates in cases with higher-than-average PCNA-LI were considerably worse than those with lower-than-average PCNA-LI [190]. Other studies either failed to demonstrate the prognostic value of PCNA in this cancer [123,124,191] or showed an inverse relationship between the percentage of PCNA-positive cells and the survival time of CRC patients [192]. Increased PCNA-LI of tumors was often associated with tumor progression (venous invasion, lymph node metastasis, or liver metastasis), while higher PCNA-LI was also associated with less differentiated tumors. Thus, PCNA testing could have prognostic significance for assessing higher malignant potential [193]. However, Neoptolemos et al., in RC studies, showed that PCNA-LI was not prognostic in this cancer subtype and that patients with the smallest LI exhibited the worst survival times [191]. In contrast, Nakamura et al. showed longer survival for CRC patients with lower PCNA expression, which was true for both CEA-positive and serum CEA-negative patients [194]. Some authors have indicated that while higher proliferation is associated with a higher incidence of rectal ADs, PCNA-LI is not useful for predicting future colorectal neoplasia [195]. Others have found lower PCNA-LI expression to be a good predictor of survival, especially in combination with HLA-DR expression [196]. Studies of the entire cell cycle panel (e.g., cyclins D1, E, cyclin-dependent kinase (CDK) inhibitors: p21 and p27) and other cell cycle regulators including PCNA have not proven the prognostic value of any of them in terms of predicting the risk of relapse or OS. These molecules have mainly been considered as cell growth regulators during colorectal carcinogenesis [179]. Moreover, studies by Guzinska et al. confirmed correlations between PCNA expression and lymph node metastasis and tumor location (lower in RC). However, the prognostic value of PCNA was not evaluated [197]. The only available meta-analysis on the level of immunohistochemical PCNA expression as a prognostic factor in CRC considered OS, cancer-specific survival (CSS), and DFS in 1372 CRC patients [198]. It showed that patients with high PCNA expression were characterized by shorter OS (HR 1.81, 95% CI 1.51–2.17) and CSS (HR 1.99, 95% CI 1.04–3.79). However, there was no significant association between PCNA and DFS. Thus, it was shown that high PCNA expression can predict a poor prognosis in CRC patients. However, this analysis needs to be confirmed in a larger number of studies based on bigger groups of patients. Table 2 shows, in chronological order, the results that illustrate the difficulty in forming a clear opinion on the prognostic significance of PCNA. The tissue expression of PCNA was studied simultaneously with various histopathological classifications and/or with other tumor biomarkers (e.g., CEA, HLA-DR, Bcl-2) to analyze the interactions of these proteins and/or to expand the panel of prognostic factors in CRC. 4.3.4. Ki-67 Antigen in CRC The prototype of the Ki-67 antigen was the IgG1 class, murine mAb, directed against the nuclear fraction of the Hodgkin’s lymphoma-derived cells (L428) [106,199]. Recognition of the structure of the Ki-67 protein (pKi-67) has enabled this protein to be placed in a new category of cell cycle-related, nuclear non-histone proteins. pKi-67 is encoded by the MKI67 gene on chromosome 11 (10q26) and has two major splice variants of 320 and 352 kDa [200]. The pioneering generation of anti-Ki-67 mAbs [199], characterization of the Ki-67 antigen using molecular biology techniques [201] and experimental studies demonstrated the presence of pKi-67 in the S, G2, and M phases of the cell cycle, and its absence in the G0 phase [105]. Thus, Ki-67 exhibits the so-called growth fraction in non-cancerous cells and tumors, indicating it as a marker of cellular proliferation [105,202]. It is worth mentioning that Ki-67 positivity does not always indicate that the cell entered the division phase. It can also signify a transition into a quiescent state and the possibility of entering the cell cycle after removing the inhibiting factor. Subcellular localization during interphase shows the presence of Ki-67 mainly in the cell nucleus, while in mitosis, it is translocated to the surface of chromosomes [106]. Recent studies have also indicated the extranuclear translocation of pKi-67 in non-cancerous cells to eliminate the protein, with initial accumulation in the endoplasmic reticulum (ER) and later in the Golgi apparatus. This mechanism is less effective in cancer cells [203]. Numerous publications over the years have discussed the role of Ki-67 as a marker of proliferation [106,202,204,205,206] and thus as a prognostic factor in many diseases, primarily cancer (including CRC) [207]. At the same time, studies have been conducted on the structure and biological role of pKi-67 in normal cells [207,208,209,210]. The multifactorial regulation of Ki-67 in non-cancerous and cancerous human cells has been described [203,206,210]. The role of Ki-67 in cell cycle progression is debated, most notably its almost opposite role in the initial phase of mitosis (prometaphase) (chromosome individualization) and exit from mitosis (chromosome clustering) [211]. Ki-67 has been shown to form repulsive molecular brushes during the early stages of mitosis [212]. In turn, the brushes collapse during mitotic exit, and Ki-67 promotes chromosome clustering [213]. Other significant advancements regarding the structure and functional role of pKi-67 in recent years include the demonstration of (1) the putative role of this protein in the higher-order organization of perinucleolar chromatin [208]; (2) the involvement of pKi-67 in the early stages of rRNA synthesis in vivo [209]; (3) the involvement of Ki-67 as a PP1 interacting protein (PIP) in the phosphorylation of nucleophosmin/B23 by casein kinase II (CKII) and the organization of the perichromosomal layer [214]; (4) the role in the generation of a spherical and electrostatic charge barrier, enabling independent chromosome mobility and efficient interaction with the mitotic spindle [212]; (5) the role in the spatial organization of heterochromatin in proliferating cells and in the control of gene expression [215]; (6) the differential regulation of the two main splice variants of the protein (i.e., α and β) in non-cancerous and cancerous cells; (7) the continuous regulation and degradation of Ki-67 by proteasomes in normal and cancerous cells and the extranuclear pathway of protein elimination [203]; (8) changes in expression depending on cell cycle regulation as a reliable indicator of the effect of CDK4/CDK6 inhibitors on cell proliferation [109]; (9) accumulation of the protein during the S, G2, and M phases, and degradation during the G1 and G0 phases; (10) the graded, rather than binary, nature of the protein, with a stable decrease in pKi-67 levels in quiescent cells [210]; (11) the presence of a gradient of Ki-67 expression depending on the phase of the cell cycle, (fast-growing tumors exhibit high levels of this protein in G2 phase cells, while in slow-growing tumors, these levels are notably lower) [216]; (12) the involvement in the regulation of chromosome clustering conditioning the removal of mature ribosomes from the nucleus after mitosis [213]. Although Ki-67 is widely recognized as a proliferation marker, genetic studies indicate that its levels do not correlate directly with this process. Indeed, the downregulation of Ki-67 did not affect the proliferation of HeLa cells [212,214,215], BJ-hTERT cells, and U2OS cells [215]. To evaluate the Ki-67-positive cells (the Ki-67 labeling/proliferating index, LI, PI) in paraffin-embedded sections during histopathology, an antibody called MIB-1 is most commonly used. Sometimes, in the literature, the name pKi-67 is used interchangeably with anti-Ki-67 antibody, or both are used together (Ki-67/MIB-1). Using IHC, it is possible to not only determine the presence of Ki-67 LI but also identify the type of proliferation, which could be a potential prognostic factor [70]. Ki-67 and Clinicopathologic Data in CRC Patients The study of the tissue expression of Ki-67, as the most common proliferative marker, is widely used to assess tumor grade or stage, predict tumor progression, or identify potential therapeutic targets [106,202,204]. Lower Ki-67 LI with medium intensity has been described in non-neoplastic polyps compared to neoplastic lesions [217]. In colorectal ADs, the Ki-67 expression was lower [218] or comparable to CRC [217]. Moreover, a higher positive rate was observed in AD cases with high atypia and carcinoma in situ [219] and in more severe dysplastic adenomatous lesions [220]. The latter study indicated that the severity of dysplasia is associated with greater cellular proliferation, as opposed to the morphological type of AD (tubular, tubulovillous, and villous). High levels of Ki-67 expression in pCRC are most often correlated with more severe histopathological changes (stage, grade) [217,218,221,222,223,224,225,226,227,228,229,230]. An inverse correlation between Ki-67 expression and the degree of differentiation in non-mucinous AC was observed [231]. A higher Ki-67 LI (≥30%) was present in lymphatic and venous invasion as well as in lymph nodes and CRLMs. The same LI (≥30%) in the primary tumor was associated with a significantly higher incidence of metachronous CRLMs. However, the mean Ki-67 LI was higher in primary tumors compared to CRLMs [221], which was also confirmed at the mRNA level [115]. Moreover, other researchers observed a positive correlation of Ki-67 LI with LN metastasis [88,197,224,228,229,232]. At the same time, Lei et al. showed Ki-67 level ≥ 60% to be associated with a high risk of distant metastasis and death, compared with a Ki-67 below this level [230]. Some authors did not show any significant correlation with the clinicopathological data [96,124,126,142,233,234,235]. In contrast, other authors have shown better clinicopathological variables in CRC patients with higher Ki-67 expression [147,236,237] and an inverse relationship between Ki-67 expression and tumor aggressiveness [115]. Similarly, the percentage of Ki-67-positive cells in poorly differentiated and mucinous AC was significantly lower than in well-differentiated and moderately differentiated AC. In contrast, lower Ki-67 LI in the primary lesion in cases with metachronous liver or lung metastases, compared to synchronous cases, may indicate that metachronous hematogenous metastases occur even in tumors with low proliferative activity [219]. In numerous publications, IHC studies have also evaluated other proliferation markers and their correlation with Ki-67 expression levels. IudR [124] and BrdUrd [126] were positively correlated with Ki-67, while TS expression correlated with Ki-67 in one study of RC [161] but not in others [142,238]. Positive correlations with Ki-67 were observed for cyclin A [141,159,160], cyclin B1 [164], cyclin D1 [160,169], cyclin E [185], cyclin E, and the p21waf1/cip1 cdk inhibitor [179]. Many authors have investigated the extent of cellular proliferation, measured by the expression of Ki-67 and the mutated tumor suppressor gene product p53, as an example of the most common genetic aberration in CRC [125,142,147,218,224,228,232,235,237,239,240,241,242]. As for the reciprocal correlations of the two proteins, either a directly proportional correlation [228,235,241], no significant correlation [224,238], or an inverse correlation of Ki-67 and p53 was detected [218]. Ki-67 as a Prognostic Marker in CRC Cell proliferation is significantly associated with CRC progression and can be used to identify patients with a predicted unfavorable disease outcome after surgery [223,243]. The prognosis of CRC is not solely determined by the proliferative capacity of tumor cells [224]. Many clinicopathological prognostic factors have been documented, related to the advanced pathological TNM stage (pTNM) and the so-called TNM-independent factors (e.g., tumor subtype and histological grade, lymphovascular invasion, tumor-infiltrating lymphocytes, perineural invasion, microvessel density, tumor margin configuration, and poorly differentiated clusters (PDCs) [55,244,245,246]. One publication provided an algorithm to profile ‘bad’ and ‘good’ prognostic biomarkers in CRC that considered the clinical features, histopathology, biochemical markers, and response factors. Of those discussed in this review, typical proliferative markers and, at the same time, unfavorable prognosis factors, included cyclin D, TS, and PCNA [244,245]. Another review reported that more than 100 differentially expressed CRC molecular markers (including proliferative markers), representing more than 1000 biological pathways, have been demonstrated in CRC [55]. It should also be mentioned that MSI-H status and impaired signaling pathways resulting from common gene mutations in CRC (e.g., WNT, TP53, KRAS, BRAF, PI3K, TGF-β, phosphatase and tensin homolog protein (PTEN)) or amplifications of specific genes (e.g., IGF-2, IGFBP2, EGFR, VEGF, SMAD) are usually associated with the overexpression of markers and lead to increased cell proliferation and the inhibition of apoptosis [55,244,245]. Many studies from different regions around the world have also shown the importance of the tissue overexpression of Ki-67 in pCRC and/or CRLM as a poor prognostic predictor of survival for patients with this cancer. Most publications have shown that high Ki-67 expression was associated with inferior OS, but some reports have demonstrated that high Ki-67 expression was correlated with favorable/longer survival [237,247,248,249,250], also in CRLM [238]. There was also a study in which the Ki-67 LI analysis results demonstrated various proliferation extents in the central areas of the tumor (cPDCs) (high) and at the tumor periphery (pPDCs) (low) and a range of different correlations with the clinical data [246]. It should be noted that few publications have investigated the prognostic significance of Ki-67 expression in different CRC locations (colon/rectum), resulting in divided opinions. One research group reported no correlation between Ki-67 expression, tumor location, and prognosis [237]. In contrast, Hilska et al. demonstrated a better prognosis for Ki-67 LI values ≥ 5% compared to a lower index, only in the group of patients with rectal cancer [182]. Several authors have indicated Ki-67 as an independent prognostic factor. For some, an increase in Ki-67 is a poor prognostic factor for survival [96,223,228], while others have reported a longer survival in patients with high Ki-67 levels [237,250]. An analysis by Valera et al. showed that tumor Ki-67 PI was an independent prognostic variable, consistently used by the classification and regression tree (CART) algorithm to classify patients with similar clinical features and survival [243]. Studies on Ki-67 expression in CRLM indicate the overexpression of this protein as an independent factor of poor OS prognosis [238,251,252]. The meta-analysis by Luo et al., focused on Ki-67 validation using IHC expression, covering 34 studies based on 6180 primary CRC patients, confirmed that the high expression of Ki-67 is a poor predictor for OS (HR 1.54, 95% CI 1.17–2.02) and DFS (HR 1.43, 95% CI 1.12–1.83) based on an univariate analysis. In multivariate analysis after adjusting for other prognostic factors, an association was shown only for OS (HR 1.50, 95% CI 1.02–2.22) [175]. Another meta-analysis investigated the determination of prognostic biomarkers in CRLM. Ki-67 was included among the 26 independent OS biomarkers in resected CRLM [253]. More than a dozen research publications on Ki-67 as a prognostic factor in CRC have also investigated the prognostic significance of potential apoptosis proteins (e.g., p53, bcl-2, programmed death ligand 1 (PD-L1), survivin) [125,134,142,147,182,197,218,224,228,232,235,237,238,241,254,255] (Table 3). There is also a summary of studies on the segmental distribution of some commonly used molecular markers (including proliferative and apoptotic markers) in CRC, which could also potentially affect their prognostic or predictive value [256]. One such marker is Ki-67, a component of the 12-gene Oncotype DX® Colon Cancer Assay, with potential significance for predicting the risk of disease recurrence, DFS, and OS in stages II and III CRC [257]. However, more recent studies indicate that routine use of the Oncotype DX Colon Recurrence Score in stage IIa CC may be unnecessary, especially in patients with normal levels of additional biomarkers [258]. Table 3 shows the potential correlations between Ki-67 expression, clinicopathological data, and survival as prognostic factors in CRC. Moreover, it illustrates the broad geographical coverage of the studies conducted, which include several countries in America, Europe, and Asia. The studies mainly used mAbs (MIB-1) rather than polyclonal antibodies, allowing for better result comparability. However, the publications varied in the semi-quantitative used to estimate the results, which may be one reason for the differences between the investigators. Most articles, revealing significant correlations between Ki-67 expression and clinicopathological data, also provided answers regarding the prognosis and survival of patients (OS, DFS). Traditionally, pathologists examine the expression of IHC markers visually and calculate it semi-quantitatively by considering the intensity and distribution of specific staining. Visual assessment is fraught with problems due to the subjectivity of interpretation. There is a lack of standardized systems for evaluating performance, relying on different cut-off values and inconsistent criteria to define the threshold value of marker/antigen positive expression by IHC. A lower reproducibility of results may also be affected by differences in the preparation conditions, antibodies used, their dilutions, and IHC reaction detection systems [135,136,198,210]. Automated IHC measurements promise to overcome these limitations. Nowadays, spatial visualization of digital images are used to quantify IHC data [262]. 4.4. Modern Molecular Biology Techniques for the Assessment of Proliferative Markers in CRC With the rapid development of complex molecular biology techniques (e.g., qRT-PCR, in situ hybridization (ISH), RNA/DNA sequencing, NGS, and DNA methylation detection ), there is a constant search for new biomarkers of cellular proliferation with potential diagnostic, prognostic, and/or predictive significance in cancers including CRC [115,236,259,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278]. Quantitative RT-PCR is generally used as the ‘gold standard’ method to measure RNA expression [115,259,267,276,277]. In situ hybridization is a research tool to detect protein production and provides invaluable information regarding the localization of gene expression in heterogeneous tissues. For example, it was used to detect Ki-67 mRNA in CRC tissues with the digoxigenin-labelled cRNA probe [236]. RNA sequencing is used to study the expression of non-coding RNAs (ncRNAs) [275,276], often complementary to for assessing protein expression (e.g., IHC, BrdU staining, Western blotting, qRT-PCR, and ISH). Among the sequencing techniques, NGS is currently the only method that enables the parallel sequencing of thousands of short DNA sequences in a single assay, replacing many less advanced profiling technologies. NGS is used to analyze the genome (whole and partial genome), methylome, transcriptome, or available chromatin using techniques including DNA-Seq, RNA-Seq, or chromatin profiling with such as ChIP-Seq. This technology offers a better approach for detecting multiple genetic changes with a minimal amount of DNA. What is particularly important is that it is also possible to sequence RNA transcripts from single cells (scRNA-Seq) [46]. Detection for DNA methylation in CRC include methylation-specific polymerase chain reaction (MSR), DNA sequencing (e.g., bisulfide sequencing, pyrosequencing), methylation-specific high resolution melting curve analysis (MS-HRM), and MethyLight assay (reviewed in [278]). 4.4.1. PCNA mRNA Expression PCNA expression was also studied at the RNA level. Yue et al., using RT-PCR, showed higher PCNA mRNA expression (94.1%) in patients with CRC and venous invasion and LM than in CRC without metastasis (70.6%), confirming the increased production of this marker with CRC progression [263]. However, PCNA was not indicated as a prognostic marker but only as a useful marker for evaluating the LM of cancer cells. In contrast, Cui et al., using qRT-PCR, demonstrated increased PCNA antisense RNA1 (PCNA-AS1) expression in CRC relative to the controls, and detected correlations of this biomarker with the clinical data (tumor invasion and TNM stage). A higher expression of PCNA-AS1 was also confirmed by in vitro studies. These data suggest a role for PCNA-AS1 mainly as a diagnostic rather than a prognostic marker in CRC [264]. 4.4.2. Ki-67 mRNA Expression Possible correlations between the Ki-67 mRNA and clinicopathological data were also analyzed, investigating its prognostic significance in CRC [115,236,259]. A positive correlation was described between protein LI, Ki-67 mRNA, and TNM. The mRNA level was also prognostically important as it correlated with patient survival, similarly to the pKi-67 index [259]. The correlation between pKi-67 LI (median: 59%) and the mRNA level detected using ISH (median: 42%) was slightly more difficult to obtain as a positive correlation was observed in 32/47 resected tumors, with a significant difference detected in 15 cases. In the latter tumors, more than 30% of the cells were pKi-67-positive but did not exhibit the presence of its mRNA. The authors explain this by the likelihood of cell cycle arrest. Interestingly, the latter patients were characterized by a better prognosis. In other words, tumors with high pKi-67 and low mRNA are likely to proliferate more slowly and, hence, be attributed to a better prognosis [236]. On the other hand, comparative studies between pCRC and CRLMs, using qRT-PCR and IHC, showed significantly lower multi-gene proliferation signature (GPS) expression in CRLM and confirmed their lower proliferation rate. Interestingly, proliferative activity was significantly lower for primary cancers with recurrence or those with established metastases than for CRCs that did not metastasize and had no recurrences [115]. Such studies need to be continued, as they may shed new light on tumor proliferation. 4.4.3. Non-Coding RNAs (ncRNAs) Expression Particular value is attributed to fragments of the human genome that do not encode proteins but play a specific role in many of the biological processes involved in colon carcinogenesis including cell cycle regulation. These are the so-called non-coding RNAs (ncRNAs), among which there are two main classes: small non-coding RNAs with less than 200 nucleotides (nc) (e.g., microRNAs, small interfering RNAs, Piwi-interacting RNAs, small nuclear RNAs, and small circular RNAs) and long non-coding RNAs (lncRNAs) (greater than 200 nc in length [270,273,274]. Studies have consistently demonstrated that the majority of both miRNAs and lncRNAs are dysregulated in CRC. The role of hundreds of different ncRNAs has been demonstrated in CRC cell proliferation in vivo and in vitro. Non-coding RNAs most often show increased expression in CRC compared to the controls. Depending on what function a given ncRNA has in the tumor (oncogene, tumor suppressor), its overexpression or downregulation enhances proliferative activity and tumor progression [266,268,270,279,280,281]. Numerous reviews have illustrated the underlying mechanisms of the biological action of miRNAs in CRC and/or reported downstream targets linked to known signaling pathways in colorectal carcinogenesis (mostly responsible for cell proliferation) [276,279,282,283]. For example, microRNAs can activate the KRAS pathway (downregulation of tumor suppressors: miR-96-5b, miR-384, mi-143, Let-7) [279,283] as well as WNT (miR-135, miR-145, miR-17-92) and EGFR signaling (miR-126, miR-143, miR-18a, Let-7, miR-196a, miR-21), and inactivate the TGF-β pathway (miR-200c) [282]. They can result in the downregulation of the TP53 pathway (overexpression of miR-34a, miR-34b, miR-34c, miR-192, miR-194-2, miR-215), epithelial–mesenchymal transition (EMT) (overexpression of miR-181a, miR-17-5p, miR-494; miR-21, miR-22) and SMAD4 (overexpression of miR-20a, miR20a-5p, miR-888). Moreover, the miR-21, miR-31, and miR-200 families are involved in EMT regulation [282,283]. In addition to miRNAs, lncRNAs are also closely involved in enhancing cellular proliferation, acting through the CRC’s well-known signaling pathways, as already described in some excellent reviews [268,281,284,285]. These include (i) JAK/STAT (downregulation of cancer susceptibility candidate 2, CASC2), (ii) MAPK (overexpression of H19 imprinted maternally expressed transcript, H19 and a newly discovered lncRNA with a length of 2685 nc, i.e., LINC00858), (iii) EGFR/MAPK (overexpression of solute carrier organic anion transporter family member 4A1-antisense RNA 1, SLCO4A1-AS1), (iv) Ras/MAPK (overexpression of colorectal neoplasia differentially expressed, CRNDE), and (v) AKT (overexpression of nuclear-enriched abundant transcript 1, NEAT1). A further example would be WNT-β-catenin signaling, which is activated by the overexpression of lncRNAs including small nucleolar RNA host gene 1 (SNHG1), HOX transcript antisense RNA (HOTAIR), SLCO4A1-AS1, taurine upregulated gene 1 (TUG1), and the downregulation of growth arrest specific 5 (GAS5). In turn, the TGF-β1 pathway is affected by the downregulation of maternally expressed 3 (MEG3) and the upregulation of LINC00858, whereas TGF-β/Smad is activated by the upregulation of SNHG6. Many lncRNAs are involved in the regulation of the EMT process. These mainly include TUG1, sprouty RTK signaling antagonist 4 intronic transcript 1 (SPRY4-IT1), and promoter of CDKN1A antisense DNA damage activated RNA (PANDAR) [281,284,286,287]. The activation of proliferation through STAT3 or β-catenin-mediated signaling pathways is also mediated by the upregulation of lncRNAs such as BC200, CASC15, colon cancer-associated transcript 2 (CCAT2), focally amplified lncRNA on chromosome 1 (FAL1), SNHG1, and SnaR. The ERK (MAPK)/JNK pathway is also affected by lncRNA DMTF1V4. Moreover, lncRNA SNHG7 acts in the K-RAS/ERK (MAPK)/cyclin D1 pathway (reviewed in [268]), while the MIR22 host gene (MIR22HG) is responsible for blocking the SMAD complex, resulting in the inhibition of EMT signaling [270,288]. Some of the lncRNAs above-mentioned interact with other cell cycle markers. For example, the zinc finger NFXT-type containing 1 antisense RNA 1 (ZFAS1) affects cell proliferation through a mechanism that destabilizes p53 via the CDK1/cyclin B1 complex [289]. Another lncRNA (i.e., ENSG00000254615), inhibits CRC cell proliferation and attenuates CRC resistance to 5-FU by regulating p21 and cyclin D1 expression [290]. Cyclin D1 also belongs to one of the target proteins of lncRNAs such as SNHG1 [291], SNHG7 [292], and XIST [293]. PCNA, on the other hand, is one of the target proteins for the lncRNA FAL1 [294]. These studies suggest a complex network of functional relationships between ncRNAs and classical cell cycle proteins, which may result in their variable expression at different stages of CRC development. In turn, any epigenetic modifications and interactions of lncRNAs with both miRNAs and proteins as well as the action of lncRNAs as precursors or pseudogenes of miRNAs may regulate the expression of multiple genes [272]. The prognostic role of ncRNAs in CRC has also been increasingly demonstrated. A summary of the activity of both subtypes of ncRNAs (miRNAs and lncRNAs) as regulatory and prognostic factors in CRC is provided in other reviews [266,279,280,295]. MicroRNA (miRNAs, miRs) There has been a rapidly increasing number of original publications and systematic reviews [276,283,296] addressing the prognostic role of miRNAs in CRC. A worse prognosis for survival (worse OS/DFS) is related to both miRNAs that are downregulated and overexpressed in CRC [276,283]. Representative miRNAs detected in tissues and body fluids are often compared in the literature [276]. An analysis of 115 articles identified hundreds of miRNAs with oncogene properties including miR-21, miR-181a, miR-182, miR-183, mi-R210, and miR-224. Overexpression of these miRNAs was associated with CRC progression and shorter patient survival. The most frequently described tumor suppressors among miRNAs included miR-126, miR-199b, and miR-22. Decreased expression of the latter was also associated with poor prognosis and a higher risk of relapse (worse DFS) [283]. A detailed review addresses the mechanisms of methylation of miRNAs as a cause of their silencing and the prognostic value of such altered miRNAs in CRC [296]. In addition, dozens of meta-analyses are available on the prognostic role of single miRNA types (e.g., miR-21 [297], miR-181a/b [298], miR-20a [299], miR-155 [300]) or the entire group of miRNAs tested (e.g., miR-21, miR-215, miR-143-5p, miR-106a, and miR-145) in specific stages of CRC development [301]. Gao et al., in their meta-analysis, showed that the strongest markers of poor prognosis included high levels of miR-141 in blood (HR 2.52, 95% CI 1.68–3.77) and miR-224 in tissue (HR 2.12, 95% CI 1.04–4.34) [302]. Long Non-Coding RNAs (LncRNAs) Modern molecular techniques and the TCGA dataset allow for the identification of an increasing number of different lncRNA subtypes as new prognostic and predictive factors in CRC [267,272]. Representative lncRNAs detected in CRC tissues and plasma/serum (circulating lncRNAs) have already been compared in the literature [303]. A prognostic role was shown for lncRNAs with tumor suppressor and oncogene properties. For example, the reduced expression of tumor suppressors such as LOC285194 [304] or MIR22HG [288] is associated with poor prognosis. Upregulation of lncRNA-oncogenes in CRC has also been associated with poor prognosis through various mechanisms. These include, among others, plasmacytoma variant translocation 1 (PVT1) [275,305], differentiation antagonizing non-protein coding RNA (DANCR) [306], HOXA distal transcript antisense RNA (HOTTIP) [307], BRAF-activated non-protein coding RNA (BANCR) [308], SPRY4-IT1 [309], CCAT1/CCAT2 [310], and X inactive specific transcript (XIST) [311]. Although many ncRNAs have been reported as proliferative markers, only a few meta-analyses have provided evidence for the actual role of selected lncRNAs in CRC prognosis [265,312,313,314,315,316]. These include, among others, overexpressed oncogene urothelial cancer-associated 1 (UCA1) for OS (HR 2.25, 95% CI 1.77–2.87) [312], or SNHG6 for OS (HR 1.92, 95% Cl 1.48–2.49), and DFS (HR 1.84, 95% CI 1.02–3.34) [313]. As shown in a recent meta-analysis based on 25 publications and more than 2000 patients, the overexpression of various SNHGs (especially SNHG1) is a poor prognostic factor in CRC (HR 1.64, 95% CI 1.40–1.86). The authors also presented all the signaling pathways interacting with this type of lncRNA. Many lncRNAs enhance cancer cell proliferation, acting directly or through different miRNAs [316]. For example, SNHG20 exerts this effect by directly affecting cyclin A1, and its expression is a poor prognostic factor in CRC (HR 2.97, 95% CI 1.51–5.82) [317]. Zhuang et al., in their meta-analysis, showed that the overexpression of lncRNA HNF1A antisense RNA 1 (HNF1A-AS1) could also be a recognized factor for poor prognosis (HR 3.10, 95% CI 1.58–6.11) [318]. A meta-analysis of numerous solid tumors (including CRC) revealed that increased expression of five prime to Xist (FTX) [314] and KCNQ1 opposite strand/antisense transcript 1 (KCNQ1OTI) correlated with shorter OS in CRC [315]. A previous study on metastasis-associated lung adenocarcinoma transcript 1 (MALAT-1/NEAT1) in six different tumors (including CRC) showed that the high expression of MALAT-1 correlated with lymph node and distant metastases (OR 3.52, 95% CI 1.06–11.71) [265]. In contrast, Xie et al. demonstrated a prognostic role for high levels of CRNDE in various cancer types including CRC (poor OS) (HR 2.11, 95% CI 1.63–2.75) [319]. Table 4 summarizes the examples of lncRNAs as prognostic markers in CRC, published in recent years. In a previous review focused on the expression of some ncRNAs (miRNAs and lncRNAs), attention was drawn to the low reproducibility of the results and the poor power of statistical analyses for the reliability of the study. This may be due to both the small amount of material assessed or the over-sampling of ncRNAs, resulting in false positive or negative results [280]. The limitations of ncRNA detection in archival tissue material include high tumor heterogeneity, leading to an increasing preference to detect these molecules in serum/plasma or stool for prognostic purposes [276,303]. It should be noted that protein-coding mRNAs have a short half-life, and their expression changes enormously depending on the physiological/pathological state. Therefore, they are not ideal as prognostic indicators. The correlation between mRNA expression and protein translation is not always guaranteed, especially in heterogeneous tumors (including CRC), prompting the need for more sophisticated molecular techniques to assess the actual expression of biomarkers. In addition, studying complex interactions between different RNA types requires modern technology (e.g., high-throughput CLIP-Seq, degradome-Seq, and RNA–RNA interactome sequencing ) [46,320]. 4.4.4. Prognostic Genetic and Epigenetic Biomarkers The most relevant genetic and epigenetic alterations have been described as ‘potential prognostic markers’ [244] or ‘potential emerging biomarkers’ of clinical utility [321,322,323]. Initially, numerous panels of genes have been identified for metastatic CRC patients. For example, among the common core of five genes including BRAF, EGFR, KRAS, NRAS, and phosphatidylinositol-4,5-biphosphate 3 kinase catalytic subunit alpha (PIK3CA), two of them, EGFR and PIK3CA, have been named as ‘emerging biomarkers’ [321]. In an era of revolutionary advances in molecular biology techniques and bioinformatical , different strategies are being adopted to classify biomarkers in CRC. Considering the mechanisms of carcinogenesis, KRAS, BRAF, APC, and TP53 genes have a permanent place among genomic biomarkers, whose role can be retrospectively traced to the Vogelstein model [7,45,245,324]. Mutations in protooncogenes (including KRAS) confer a strong growth signal to cancer cells and are closely associated with the development of CRC [5,55]. Notably, the KRAS mutation is currently the only marker with proven benefit for routine clinical use and selection for anti-EGFR mAbs therapy [324]. However, the presence of KRAS mutations does not always correlate with cell proliferation or the survival of patients with CRLMs [251]. In contrast, a meta-analysis by Sorich et al. showed that patients with metastatic CRC without RAS mutations (either KRAS exon 2 or new RAS mutation) treated with anti-EGFR mAbs had longer PFS and OS compared to patients with the presence of these mutations [325]. A recent study performed in a group of 73 CRC patients from South Korea reported no differences in DSF and OS treated with the FOLFOX regimen in groups divided according to the presence of KRAS mutations and the expression status of the excision repair cross-complementing 1 (ERCC1) protein. Interestingly, it was shown that the subgroup of patients with wild-type KRAS and increased IHC expression of the ERCC1 protein had lower OS compared to the subgroup with decreased ERCC1. No significant difference was found in the group of patients with mutated KRAS. In addition, the authors suggest that the presence of wild-type KRAS in combination with ERCC1 overexpression may be associated with oxaliplatin resistance. In other words, the KRAS status and ERCC1 expression in CRC patients treated with oxaliplatin-based CTx exhibit significant prognostic value [326]. An association has also been found between the loss of TP53 (17q-TP53) and poorer survival rates, but TP53 is not considered as a useful prognostic marker as the current data are insufficient to validate it [44]. Similarly, mutations in TGF-β, rare in CRC, cannot be indicated as significant prognostic factors in this cancer [5]. One meta-analysis showed a weak correlation between short OS and loss of 18q (HR 2.0, 95% CI 1.49–2.69), which encodes two crucial tumor suppressor genes (SMAD2 and SMAD4) of the TGF-β family. Loss of function of these two genes leads, among others, to cell cycle deregulation [327]. In turn, the prognostic value of chromosomal instability in the form of CIN and MSI has been confirmed (also in meta-analyses) [245,327,328]. Erstad et al. listed genes including matrix metalloproteinases (MMPs), tumor inhibitor of metalloproteinase-1 (TIMP-1), manganese superoxide dismutase (mnSOD), TGF-β, Survivin, and prolactin receptor (PRLR) among the prognostic factors of survival. From the classical proliferative markers, they mention the genes for TS and PCNA. The publication also provides an algorithm for the determination of prognostic biomarker profiles in CRC [244]. The following have also been cited as prognostic or predictive markers related to disease recurrence after surgery or resistance to treatment: ‘SC signature’ circulating tumor (ct)DNA and cell-free (cf)DNA, RAS, PIK3CA mutations, loss of PTEN (shorter PFS), low expression of EGFR (increase tumor regression), high density of TILs (better survival), loss of Bcl-2 expression (tumor recurrence), and somatic mutation of BRAF (mainly V600E) [323]. Epigenetic alterations in CRC mainly comprise abnormal methylated DNAs, abnormal histone modifications, and changes in the expression levels of abundant ncRNAs [329,330,331]. The prognostic significance of ncRNAs is described in Section 4.4.3. While the studied epigenetic aberrations in CRC include CIMP [50,323,332], opinions on the prognostic value of this marker differ and are debated by others [323,324]. Several DNA-methylation markers with prognostic value in CRC have also been demonstrated. These include the methylation of genes such as secreted frizzled-related protein (SFRP), p16, and long interspersed nucleotide element-1 (LINE-1). Methylation of SFRP, which acts as a tumor suppressor gene, is associated with increased CRC cell proliferation and tumor growth [333]. In turn, the methylation of LINE-1 is associated with poor prognosis, shorter survival, and advanced stage [334,335]. A meta-analysis on LINE-1 also suggests that its methylation is significantly related to the survival of CRC patients and may be a prognostic factor [336]. Another gene that undergoes DNA methylation in CRC is the DNA-binding protein Ikaros (IKZF1), which regulates the cell cycle. Methylation of the IKZF1 promoter is associated with the loss of regulation of tumor cell proliferation and differentiation [337]. Recent studies also indicate high sensitivity and specificity in the detection of circulating DNA methylated in branched-chain aminotransferase 1 (BCAT1)/IKZF1 in CRC compared to other cancers (breast, prostate) [338]. Other reviews additionally included methylated biomarkers of prognostic importance such as p14, Ras association domain-containing protein 1A (RASSF1A) and APC (poor prognosis), O-6-methylguanine-DNA methyltransferase (MGMT), DNA mismatch repair protein (hMLH1) (improved survival), homeodomain-only protein (HOPX-β) (worse prognosis in stage III CRC) and several EMC genes (worse survival), and IGF-2 hypomethylation (poor prognosis, short survival) [245,329]. Moreover, a recent study combined classical histopathology, the IHC method (p53 and Ki-67 expression), and MSP (aberrant methylation of p16, E-cadherin, APC, RUNX family transcription factor 3 (RUNX3), and hMLH1) with autofluorescence imaging (AFI) to assess the proliferative capacity of CRC. Abnormal expression of p53 and Ki-67 and the altered methylation of p16 correlated with a lower AFI intensity [339]. It is important to note that the DNA methylation of genes in CRC also plays a role as predictive markers and/or can be a basis for the development of novel methylation-based therapies. Recent publications point to the important role of selected DNA methylation markers for the screening and early diagnosis of CRC [323,331,340]. One such plasma PCR-based test is the Epi proColon®, which is used to detect methylated SEPT9 and has been approved by the U.S. Food and Drug Administration (FDA) for CRC screening in the U.S. The test, which is performed in conjunction with a stool test for methylated DNA from CRC cells, is used in patients who reject traditional screening [55]. Modern marker testing strategies in CRC potentially allow for the discovery of thousands of new genomic and transcriptomic factors. At least some of these are expected to become sensitive and specific proliferative markers with prognostic significance [55,323,324,340,341]. Considering the mechanisms of colorectal carcinogenesis associated with familial CRC, clinically useful markers such as dMMR, MSI, KRAS, BRAF, APC, SMAD4, and BMPR1A have already been indicated [47,323]. Markers with crucial roles in the pathogenesis of CRC also include key genes in the cell cycle process [324,328]. Moreover, a range of state-of-the-art molecular technologies used to detect a whole range of diagnostic markers in the human body (blood/plasma, tissue, stool) have also been described [340,342]. There are several recent summaries regarding the available technologies in for the search for the most sensitive, specific, low-cost, and reliable diagnostic, prognostic, and predictive markers in CRC [55,322,323,340,342]. Several publications have summarized the data on the clinical application of NGS technology in CRC [46,321,322,324,342,343]. Additionally, NGS allows for the identification of unknown interactions between genetic variation in CRCs and the relationship of CRCs to the structure of the gut microbiota composition [342]. Regarding the prognostic value in CRC, the activity of many protumoral genes (e.g., CD74, CLCA1, and DPEP1) has been described using this method. Additionally, using this technique revealed intra-tumor cell heterogeneity in ulcerative colitis (UC)-associated CRC [344]. Another study, based on several complementary techniques including scRNA-Seq, revealed that kinesin family member 21B (KIF21B) was highly expressed in CRC and was associated with poor survival. KIF21B expression was positively correlated with infiltrating CD4+ T cells and neutrophil levels, cell apoptosis, and metastasis. In vitro studies confirmed the role of KIF21B in enhancing proliferation, migration, and invasion [345]. In addition, one study based on scRNA-Seq, RNA-Seq, and microarray cohorts established a prognostic model based on the composition of prognosis-related cell subsets in TME including nine specific immune cell lineages [346]. Other publications have described the advantages and technical challenges of using liquid biopsies in the form of circulating tumor cells (CTCs) [347] and ctDNA as a promising alternative to molecular tissue analysis [323,348,349]. ctDNA detection in blood can be used to predict CRC recurrence after surgical resection [323]. In turn, a meta-analysis (2016) showed strong associations between cfDNA, RFS (HR 2.78, 95% CI 2.08–3.72), and OS (HR 3.03, 95% CI 2.51–3.66) in CRC patients. Thus, the appearance of cfDNA in the blood can predict shorter OS and worse RFS regardless of the tumor stage, study size, tumor markers, detection , and marker origin [349]. Nonetheless, targeted NGS analysis of cfDNA from TruSight Tumor 170 (TST170) may be useful for the non-invasive detection of gene variants in metastatic CRC patients. TST170 is an NGS panel that covers 170 cancer-related genes including KRAS [350]. High compatibility was also detected between cfDNA and tumor DNA in metastatic CRCs using a 10-gene NGS panel. TP53 was the most frequently mutated gene (63.2%), followed by APC (49.5%), KRAS (35.8%), and FAT tumor suppressor homolog 4 (FAT4) (15.8%). The concordance of mutation patterns in these 10 genes was as high as 91% between the cfDNA and tumor samples. These results also confirmed the high sensitivity (over 88%) and specificity (100%) of the KRAS status in cfDNA for predicting mutations of this gene in tumor tissue. Significant prognostic correlations (peritoneal, lung metastasis) between TP53, KRAS, and APC mutations in the tumor were also demonstrated [351]. The use of ctDNA-based genotyping of KRAS, NRAS, and BRAF indicates the utility of predicting patient survival depending on the mutations of these genes. The highest mutation frequency is attributed to KRAS (34%). The median OS of patients with RAS/BRAF mutations detected in plasma was 26.6 months, and patients with wild-type RAS/BRAF did not reach median survival during follow-up. The median RFS for RAS/BRAF wild-type and RAS/BRAF mutation patients was 12 and 4 months, respectively [352]. Attempts have been made to determine the prognostic role of markers detected by CTC-based techniques in CRC. However, the results are still not convincing enough for recommendation in clinical practice [340,347]. A recent review paper summarized the use of various molecular techniques (e.g., RT-PCR, PCR, and single nucleotide polymorphism (SNP) genotyping assay, NGS, NanoString analysis, Sanger sequencing, MassArray sequencing, quantitative MSP) to investigate changes at the DNA and RNA level that may predict CRC metastasis to the peritoneum. Only BRAF mutations were associated with peritoneal metastases in 10/17 studies [353]. The development of modern, especially non-invasive molecular technologies in CRC should improve the specificity of tests (above 90%) primarily for disease screening and therapeutic decisions [55,341,354]. Nowadays, numerous molecular techniques can be chosen, and the decision to use specific markers should balance advantages and limitations that may affect the final results. In the case of NGS-based DNA nucleotide variation testing, the difficulty lies in wide variety of NGS platforms and gene panels and the multi-step nature of the study. In terms of sensitivity, ctDNA NGS techniques cannot compete with digital PCR, prompting the need for PCR result validation. The sensitivity issue is important, particularly in liquid biopsy, as random results (false positive mutations) can be obtained from hematopoietic clones rather than from the tumor itself. The significant number of gene variants of unknown roles obtained in the study is also not accepted by experts due to the lack of clinical utility [321,348]. Another author described the limitations of non-standardized , the small cohorts of patients analyzed, and the lack of demonstration of a clear clinical benefit of liquid biopsy studies in CRC [347]. The scientific literature also contains proposals for a systematic review and meta-analysis protocol in detecting KRAS mutations in CRC using liquid biopsy samples, with paired tissue samples serving as the control [355]. 4.5. Positron Emission Tomography (PET) to Assess Tumor Growth Rate PET is the most specific and sensitive method of in vivo molecular interaction and pathway imaging, finding an increasing number of applications in oncology [356]. This non-invasive technique for the functional imaging and assessment of CRC growth rate is based on the use of labelled 18-fluoro-3-deoxy-3-fluorothymidine (FLT). The method can reveal the spatial organization of proliferating cells in the tumor and allows for multiple simultaneous in vivo measurements. However, there are some correlations between FLT uptake and tumor proliferative activity [111,112]. FLT was reported to have high sensitivity in detecting extrahepatic disease but poor sensitivity in imaging CRC liver metastases [112]. A better and currently the most commonly used tracer in CRC is 18F-labelled 2-fluoro-2-deoxy-D-glucose (18F-FDG), with its usefulness resulting from increased glucose consumption by malignant cells. Therefore, this tracer’s uptake is closely linked to cancer cell proliferation, which depends mainly on glycolysis for energy. Many signal transduction pathways in the malignant transformation of cancer cells are regulated by glycolytic metabolism [357]. Therefore, the combination of PET and 18F-FDG has become an established tool for diagnostic tumor imaging and complete preoperative staging in CRC [112,113,358]. PET–18F-FDG results may have implications for the therapeutic management of patients with CRC [358,359] including metastatic CRC [113]. One review recognized that PET in CRC also allows for the metabolic characterization of lesions suspected of recurrence or the identification of latent metastatic disease [358]. Comparative studies indicate lower FLT versus FDG uptake in patients with CRC. However, no correlation was shown between the two radiotracers used and the proliferative activity assessed by the Ki-67 index [360]. A later meta-analysis only confirmed a moderate correlation between 18F-FDG uptake and Ki-67 expression in CRC [361]. A recent study by Watanabe et al. indicated that tumor proliferation in CRLM is reflected by the standardized uptake value (SUV) from FDG-PET. In addition, the authors showed a high correlation between SUV and Ki-67 expression. SUV was also shown to include factors of glucose metabolism (expression of hypoxia-inducible factor 1 alpha (HIF-1α), pyruvate kinase M2 (PKM2), and glucose transporter 1 (GLUT1)). Thus, this test can be a valuable method to assess the proliferative and metabolic viability of the tumor in advanced CRLM [113]. The remaining limitations of PET comprise its high cost and the lack of necessary equipment in cancer centers, limiting the potential for multidisciplinary PET studies. The most significant limitation for the patient is the need for the administration of radioactive tracers, resulting in potential radiation exposure [356]. Figure 1 summarizes the major categories of prognostic proliferative markers in CRC and the most important signaling pathways that are genetically altered in CRC progression.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Atherosclerosis is a complex pathological condition marked by the accumulation of lipids in the arterial wall, leading to the development of plaques that can eventually rupture and cause thrombotic events. In recent years, hydrogen sulfide (H2S) has emerged as a key mediator of cardiovascular homeostasis, with potential therapeutic applications in atherosclerosis. This systematic review highlights the importance of understanding the complex interplay between H2S, oxygen homeostasis, and atherosclerosis and suggests that targeting H2S signaling pathways may offer new avenues for treating and preventing this condition. Oxygen homeostasis is a critical aspect of cardiovascular health, and disruption of this balance can contribute to the development and progression of atherosclerosis. Recent studies have demonstrated that H2S plays an important role in maintaining oxygen homeostasis by regulating the function of oxygen-sensing enzymes and transcription factors in vascular cells. H2S has been shown to modulate endothelial nitric oxide synthase (eNOS) activity, which plays a key role in regulating vascular tone and oxygen delivery to tissues. The comprehensive analysis of the current understanding of H2S in atherosclerosis can pave the way for future research and the development of new therapeutic strategies for this debilitating condition. PROSPERO ID: 417150.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2. For this comprehensive review on H2S and oxygen homeostasis in atherosclerosis, a dedicated protocol was used:Search strategy: For research context, the search-specific syntaxes used were based on the keywords “atherosclerosis” AND “hydrogen sulfide” OR “oxygen homeostasis”. The narrative synthesis was based on a Google search, while the systematic literature review was performed using reputable international medical databases, including Elsevier, Nature, and Web of Science, articles being published between 2018 and 2023, and the selection process was based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines (Table 1 and Figure 1).Article evaluation: An algorithm was developed to evaluate each article’s scientific impact and quality. The Cochrane Risk of Bias Tool, AMSTAR Checklist, and JBI Critical Appraisal Checklist were used to ensure qualitative support and data validation. In addition, the algorithm considered several factors, such as the year of publication, the total number of citations, and the PEDro score. Using this algorithm, the articles were assessed and ranked according to their scientific merit and relevance to the field. The selected papers were inputs for a benchmarking analysis strategy, and the “paradigm funnel” was used to obtain relevant reports.Data extraction: Data were extracted using a standardized form. The information collected included study design, sample size, population characteristics, intervention or exposure intervention, outcome measures, and results.Data analysis and synthesis: A narrative synthesis was performed to summarize the findings of the selected studies. The studies were organized based on their study design, population characteristics, intervention or exposure intervention, outcome measures, and results. Data were analyzed descriptively to identify common themes and patterns.Graphical techniques and tools: Data collection sheets, graphic representations, critical examination matrices, cause–effect diagrams, Pareto charts, control sheets, and correlation diagrams were used to analyze, interpret, and present the obtained data and to elaborate this comprehensive review article.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Significant scientific advances to elucidate the Moniliophthora perniciosa pathosystem have been achieved in recent years, but the molecular biology of this pathogen-host interaction is still a field with many unanswered questions. In order to present insights at the molecular level, we present the first systematic review on the theme. All told, 1118 studies were extracted from public databases. Of these, 109 were eligible for the review, based on the inclusion and exclusion criteria. The results indicated that understanding the transition from the biotrophic-necrotrophic phase of the fungus is crucial for control of the disease. Proteins with strong biotechnological potential or that can be targets for pathosystem intervention were identified, but studies regarding possible applications are still limited. The studies identified revealed important genes in the M. perniciosa-host interaction and efficient molecular markers in the search for genetic variability and sources of resistance, with Theobroma cacao being the most common host. An arsenal of effectors already identified and not explored in the pathosystem were highlighted. This systematic review contributes to the understanding of the pathosystem at the molecular level, offering new insights and proposing different paths for the development of new strategies to control witches’ broom disease.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2. The systematic review was performed using the R program, with the Bibliometrix package and the StArt software (State of the Art through Systematic Review), Beta version 3.0.3, developed at Federal University of São Carlos (UFSCar), available at http://lapes.dc.ufscar.br/tools/start_tool (accessed on 5 May 2022). This review followed the PRISMA guidelines (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) [43] and involved three fundamental steps: planning, execution, and summarization. 2.1. Planning At this stage, a defined protocol was elaborated and discussed in a group. The protocol presented the basic information to guide this review, such as article title, authors, objective, keywords, search strings, research questions, research sources, inclusion/exclusion criteria, database selection and definition of the type of study (https://github.com/ArianaSantos/Santos-et-al.2022_systematic-review.git, accessed on 6 October 2022). To achieve the objective of the systematic review, we formulated 14 questions, listed in Table 1. These questions were based on the Population Intervention Comparison Results (PICOS) research strategy [44], as shown in Table 2. This strategy guided the elaboration of research questions and the specification to search for answers, avoiding biased responses [39,45]. 2.2. Execution In this step, we searched for studies using the string ((theobroma OR cacao OR cocoa OR moniliophthora OR crinipellis) AND (perniciosa OR broom)), in the databases Pubmed, Scopus, Scielo and Web Of Science. Boolean connectors “OR” and “AND” were used in the string to group synonymous keywords and main terms. The selected files were imported in BIBTEX and MEDLINE format into the R program. After screening in R, the files with the same formats were exported to the Start program (v. Beta 3.0.3), where the automated selection was made based on the reading of titles and abstracts, using the inclusion and exclusion criteria established in the protocol as a reference (https://github.com/ArianaSantos/Santos-et-al.2022_systematic-review.git, accessed on 6 October 2022), to characterize the studies as accepted or rejected, and to exclude duplicates. 2.3. Summarization Studies considered to be accepted for meeting one or more inclusion criteria were read completely to extract the data. This process consisted of extracting and summarizing the data that answered the review questions. During this phase, it was also possible to exclude some studies that, after a complete reading, met at least one exclusion criterion. This step also included the elaboration of figures and tables in order to summarize the data found. Data related to the production and dissemination of scientific knowledge were grouped by similarity with the Vosviewer software (version 1.16.17) [46]. The biological models were built based on those available on the Swissbiopics platform. (https://www.swissbiopics.org/, accessed on 15 September 2022). The Protein–Protein Interaction Network (PPI) was obtained from the proteins identified in the selected studies. For this purpose: (i) searches were carried out with the names of the proteins in two databases—NCBI (https://www.ncbi.nlm.nih.gov/, accessed on 5 August 2022) and Uniprot (https://www.uniprot.org/, accessed on 5 August 2022)—to obtain the FASTA sequence; (ii) only proteins for the organisms M. perniciosa or Moniliophthora roreri were admitted in the searches, with the former being preferred; (iii) with the FASTA sequence of the proteins, BLAST was performed, using BLASTp (https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE=Proteins, accessed on 5 August 2022), accepting only proteins with an identity percentage ≥90%; (iv) proteins that were not found through the search organisms terms or had <90% identity were not included in the PPI network. With String v.11.0 (https://stringdbstatic.org, accessed on 19 August 2022) [47], another BLASTp was performed against the available M. perniciosa proteins. Proteins were analyzed individually with the following parameters: meaning of network edges: confidence; active interaction sources: textmining, experiments, databases, co-expression, neighborhood, gene fusion and co-occurrence; minimum required interaction score: high confidence (0.700); and max number of interactors shown for the 1st and 2nd shells: no more than 50 interactions. The file of each network was downloaded in TSV format and later the files were merged and analyzed using the Cytoscape software version 3.8.2 [48]. The centrality properties (betweenness and node degree) and modularity of the protein-protein interaction network were obtained through the igraph package of the R software (version 14.0.3) [49]. For the analysis of genetic ontology enrichment of each cluster in the network, the Analysis tool of the STRING database was used. Biological processes with a false discovery rate (FDR) value closest to 0 were assigned to the corresponding cluster. The FDR identifies how significant enrichment is. Corrected p-values for various tests within each category are shown using the Benjamini–Hochberg procedure (https://string-db.org, accessed on 19 August 2022). To reduce any bias in the elaboration of the systematic review, we used the PRISMA checklist [43] (Supplementary File S1, https://github.com/ArianaSantos/Santos-et-al.2022_systematic-review.git, accessed on 6 October 2022).

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Objective: To explore the potential mechanism of triptolide in diabetic nephropathy (DN) treatment using network pharmacology. : The main targets of triptolide were screened using the TCMSP, DrugBank, and NCBI databases, and gene targets of DN were searched using the DrugBank, DisGeNET, TTD, and OMIM databases. All of the above targets were normalized using the UniProt database to obtain the co-acting genes. The co-acting genes were uploaded to the STRING platform to build a protein-protein interaction network and screen the core acting targets. Gene ontology and Kyoto encyclopedia of genes and genomes analyses of the core targets were performed using Metascape. Molecular docking validation of triptolide with the co-acting genes was performed using the Swiss Dock platform. Results: We identified 76 potential target points for triptolide, 693 target points for DN-related diseases, and 24 co-acting genes. The main pathways and biological processes involved are lipids and atherosclerosis, IL-18 signaling pathway, TWEAK signaling pathway, response to oxidative stress, hematopoietic function, and negative regulation of cell differentiation. Both triptolide and the active site of the core target genes can form more than 2 hydrogen bonds, and the bond energy is less than -5kJ/mol. Bioinformatics analysis showed that triptolide had a regulatory effect on most of the core target genes that are aberrantly expressed in DKD. Conclusion: Triptolide may regulate the body’s response to cytokines, hormones, oxidative stress, and apoptosis signaling pathways in DN treatment by down-regulating Casp3, Casp8, PTEN, GSA3B and up-regulating ESR1, and so forth.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2. Materials and 2.1. Major databases and softwares TCMSP, NCBI, DrugBank, DisGeNET, TTD, OMIM, Uniprot, Venny 2.1, Cytoscape 3.9, String platform, Metascape, Auto Dock Vina, GEO database, and so forth. 2.2. Drug and disease targets acquisition The targets of TP were searched in the TCMSP, DrugBank, and NCBI databases with “Triptolide” as the search term, and the species was limited to “Homo sapiens.” The targets of DN were searched in the DrugBank, DisGeNET, TTD, and OMIM databases with “diabetic nephropathy” as the search term. All the above targets were gene normalized using the UniProt database, and the drug targets and disease targets were integrated and de-weighted to obtain the TP and DN target sets. 2.3. Construction of protein–protein interaction (PPI) networks for the targets of action of triptolide A PPI network was built using the string platform. The co-acting targets of TP and DN were collected using Venny 2.1 software. These were imported into the String platform to work a PPI network, set the protein species to “Homo sapiens,” hide the isolated proteins in the network, and the other parameters were kept at the default settings. The PPI network graph data were exported in TSV format. The data were imported into Cytoscape, and a network analyzer was used to analyze and calculate the network topology characteristic value of the intersection PPI and filter the data to obtain the core acting targets. Simultaneously, the protein functional sub-modules were determined by further analysis of the PPI network using the MCODE plug-in. 2.4. Pathway enrichment analysis The Metascape platform integrates multiple authoritative databases and supports annotation, enrichment analysis, and construction of PPI networks for batch genes or proteins, with more powerful functions, timely updates, and reliable data. The core acting targets were analyzed using the Metascape database for gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG). The results were saved and passed through R software for visualization. 2.5. Molecular docking of TP with core acting targets Molecular docking is an effective method to verify the relationship between molecules and targets. Molecular docking was performed using TP as the ligand and the core targets of TP for DN treatment as the receptor. The 3-dimensional structure of TP was downloaded from PubChem CID, and the core acting target structures were downloaded from the PDB database and routinely processed using Chem-Bio Drew. Then, Pymol software was used to remove redundant protein structures, remove other irrelevant ligands such as water molecules, and import Auto Dock Vina software to select the semi-flexible docking mode with docking parameters as default. A binding energy of less than 0 kJ/mol indicated that the ligand molecule could spontaneously bind to the receptor protein. And the binding energy less than –5.0 kJ/mol indicates good binding, and the smaller the binding energy, the better the docking. 2.6. Expression of co-acting targets in disease or triptolide intervention Most of the therapeutic effects of drugs on diseases are achieved by directly or indirectly regulating the genes that are aberrantly expressed in the disease. Diabetic Kidney Disease and Triptolide were used as the key words to search in the GEO database, and the species was limited to “Homo sapiens.” Appropriate datasets were selected for bioinformatics analysis to clarify the abnormal expression of each co-acting target in DKD, as well as to clarify the effect of TP intervention on gene expression of co-acting targets. If the expression changes of the same gene are opposite in these 2 cases, there is a high degree of certainty that TP will work through that gene; the opposite is less certain.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Background and Objective Although epimedium herb (EH) has been widely used in ancient Chinese medicine to enhance sexual activity, its pharmacological mechanism is not clear. Modern studies have shown that epimedium herb is rich in icariin (ICA, a flavonoid compound), and 91.2% of icariin is converted to icariside II (ICA II) by hydrolytic enzymes in intestinal bacteria after oral administration. YS-10 is a synthetic derivative of icariside II. The aim of this review was to summarize the contemporary evidence regarding the pharmacokinetics, therapeutic properties, and molecular biological mechanisms of ICA and some ICA derivatives for erectile dysfunction therapy. A detailed search was conducted in the PubMed database using keywords and phrases, such as “icariin” AND “erectile dysfunction”, “icariside II” AND “erectile dysfunction”. The publication time is limited to last 20 years. Articles had to be published in peer reviewed journals. Key Content and Findings ICA and its some derivatives showed the specific inhibition on phosphodiesterase type 5 (PDE5) and the promotion of testosterone synthesis. In addition, by regulating various reliable evidence of signaling pathways such as PI3K/AKT, TGFβ1/Smad2, p38/MAPK, Wnt and secretion of various cytokines, ICA and ICA derivatives can activate endogenous stem cells (ESCs) leading to endothelial cell and smooth muscle cell proliferation, nerve regeneration and fibrosis inhibition, repair pathological changes in penile tissue and improve erectile function. Conclusions ICA and some of its derivatives could be a potential treatment for restoring spontaneous erections. In addition ICA and his derivatives may also be valuable as a regenerative medicine approach for other diseases, but more clinical and basic researches with high quality and large samples are recommended.
Completion: Here is what we may expect the methods section for such an experiment to look like. We conducted a literature search for PUBMED in March 2022 following the Table 1 search strategy. The publication time is limited to last 20 years. Articles had to be published in peer reviewed journals. Keyword searches including “erectile dysfunction” AND “icariin”, “erectile dysfunction” AND “icariside II”, “erectile dysfunction” AND “icariin derivative”， “PDE5” AND “icariin”, “PDE5” AND “icariside II”, “PDE5” AND “icariin derivative”, “testis” AND “testosterone” AND “icariin” , and “testis” AND “testosterone” AND “icariside II”, “testis” AND “testosterone” AND “icariin derivative”. Articles without experimental data related to the search terms and data that did not support relevant conclusions were excluded, as well as articles with low quality. The data were extracted from each study by two investigators (JCP and YHF) independently. After the search, summarized the literature and discussed the different literature. Another researcher (ZCX) was invited to discuss and identify the literature on which consensus could not be reached (Table S1). Our literature search covered English-language clinical or basic research articles published from January 1, 2003 to March 1, 2022, as well as related reviews and meta analyses. Table 1 The search strategy summary Items Specification Date of search (specified to date, month and year) January 1, 2003 to March 1, 2022 Databases and other sources searched PubMed Search terms used (including MeSH and free text search terms and filters) (Note: please use an independent supplement table to present detailed search strategy of one database as an example) As shown in Table S1 Timeframe The publication time is limited to last 20 years Inclusion and exclusion criteria (study type, language restrictions etc.) 1. Articles had to be published in peer reviewed journals 2. Articles without experimental data related to the search terms and data that did not support relevant conclusions were excluded, as well as articles with low quality 3. Written by English Selection process (who conducted the selection, whether it was conducted independently, how consensus was obtained, etc.) Two experimenters were searched and screened separately. Discussion of the discrepancy literature and invitation to the other experimenter to participate Any additional considerations, if applicable None

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? Object: Find potential therapeutic targets of triple-negative breast cancer (TNBC) patients by bioinformatics. Screen ideal natural ligand that can bind with the potential target and inhibit it by using molecular biology. : Bioinformatics and molecular biology were combined to analyze potential therapeutic targets. Differential expression analysis identified the differentially expressed genes (DEGs) between TNBC tissues and non-TNBC tissues. The functional enrichment analyses of DEGs shown the important gene ontology (GO) terms and pathways of TNBC. Protein-protein interaction (PPI) network construction screened 20 hub genes, while Kaplan website was used to analyze the relationship between the survival curve and expression of hub genes. Then Discovery Studio 4.5 screened ideal natural inhibitors of the potential therapeutic target by LibDock, ADME, toxicity prediction, CDOCKER and molecular dynamic simulation. Results: 1,212 and 353 DEGs were respectively found between TNBC tissues and non-TNBC tissues, including 88 up-regulated and 141 down-regulated DEGs in both databases. 20 hub genes were screened, and the higher expression of CDC20 was associated with a poor prognosis. Therefore, we chose CDC20 as the potential therapeutic target. 7,416 natural ligands were conducted to bind firmly with CDC20, and among these ligands, ZINC000004098930 was regarded as the potential ideal ligand, owing to its non-hepatotoxicity, more solubility level and less carcinogenicity than the reference drug, apcin. The ZINC000004098930-CDC20 could exist stably in natural environment. Conclusion: 20 genes were regarded as hub genes of TNBC and most of them were relevant to the survival curve of breast cancer patients, especially CDC20. ZINC000004098930 was chosen as the ideal natural ligand that can targeted and inhibited CDC20, which may give great contribution to TNBC targeted treatment.
Completion: Here is what we may expect the methods section for such an experiment to look like. Microarray data We downloaded GSE62931 and GSE76275 databases, which contains 365 samples, from Gene Expression Omnibus (GEO) website (https://www.ncbi.nlm.nih.gov/geo/) [13, 14]. We divided these 2 databases into 2 groups, TNBC tissues and tissues of other type breast cancer. GSE62931 and GSE76275 database were both mRNA expression profiling of TNBC and non-TNBC samples. GSE62931 contains 47 TNBC tissues and 53 other types of breast cancer, while GSE76275 contains 198 TNBC tissues and 67 other types of breast cancer. Meanwhile, we transformed the data of these 2 databases in order to get standardized data, then we compared and analyzed these 2 groups. Identification and analysis of DEGs We used Limma library in R studio and input the code to get the differentially expressed genes (DEGs). The log Fold Change was higher than or equal to 2 and the adjust P-value was less than 0.05. Then we used Morpheus website (https://software.broadinstitute.org/morpheus/) to make the Heat maps of these 2 databases. Meanwhile, we used the Limma library again and input the relevant code to get the Volcano plots. These figures were performed with P-value <0.05 was defined. The log change >0.5 folds of genes were regarded as up-regulated DEGs and log change <−0.5 folds of genes were regarded as down-regulated DEGs, while others were not-significant DEGs. We also labeled the most significant 20 DEGs in Volcano plots. We also get Venn plots by using https://bioinfogp.cnb.csic.es/tools/venny/index.html to get the DEGs which existed in both GSE62931 and GSE76275 databases. Functional and pathway enrichment analyses of DEGs We used metascape website (https://metascape.org/gp/index.html#/main/step1) to make the Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses of DEGs. Then we respectively put up-regulated and down-regulated DEGs into Database for Annotation, Visualization and Integrated Discovery (DAVID) website (https://david.ncifcrf.gov/). DAVID website is a database of biological information and an online free analysis software. It provided users extract biological information from a large list of genes or proteins. And The GO analysis included biological processes (BP), molecular functions (MF) and cellular components (CC) of DEGs. PPI network construction and selection of module We used the Search Tool for the Retrieval of Interacting Genes (STRING) website (https://string-db.org/) and Cytoscape software to build protein-protein interaction (PPI) network. Each node in STRING website represents a protein. In STRING website, different isoforms produced by the same gene were combined, and the letter marked on the node is actually the gene symbol of the corresponding gene. The lines between nodes represent interactions between two proteins, and different colors correspond to different types of interactions. Prognostic analysis of the most important 20 DEGs We used Kaplan website (https://kmplot.com/analysis/) to analyze the survival curve. This website is constructed based on gene microarray and RNA-seq data from public databases such as TCGA and GEO. And it assessed the survival impact of more than 50000 genes across 21 types of cancer, including breast cancer. The Kaplan website integrates gene expression information and clinical prognostic value for meta-analysis and the study, discovery and validation of molecular markers related to survival. We input the 20 hub genes and got the overall survival (OS) and recurrence-free survival (RFS) of these 20 hub genes in breast cancer. Ligand database and the crystal structure of CDC20 We downloaded the natural products database and the chemical structure of apcin (Protein Data Bank identifier: ZINC000008434966) from ZINC website, which is a free virtual screening database of commercial compounds (http://zinc.docking.org/substances/home/). We screened ideal lead compounds form this database, which contains 17931 ligands. Meanwhile, we downloaded the crystal structure of CDC20 (4N14) from RCSB PDB website (https://www.rcsb.org/). The RCSB PDB website is powered by the Protein Data Bank archive-information that provided researchers all aspects of biomedicine and agriculture [15]. ADME and toxicity prediction We employed the ADME and the TOPKAT to calculate absorption, distribution, metabolism, excretion (ADME) and the toxicity of these compounds, by analyzing chemical structure. These modules were very significant to analyze the safety of ligands, which can save a lot of manpower and material resources [16]. LibDock and CDOCKER molecular docking The LibDock module was a simple and fast molecular docking method, which was used to screen large-scale data. While CDOCKER module was a precise docking method, which based on CHARMm flexible docking program. We imported the crystal structure of CDC20 to the Discovery Studio and removed the crystal water and other heteroatoms from it, added, protonation, hydrogen energy minimization and ionization to it. And the apcin’s binding region of CDC20 was chosen as the binding site. Then we ran the LibDock and got 7,416 ligands and their LibDock scores. The top 20 ligands were listed based on the LibDock score [17]. Molecular dynamic simulation We selected the ligand-CDC20 complexes’ best binding conformations among these poses by the molecule docking program. We simulated the physiologic environment by adding sodium chloride to the system, which was relaxed by energy minimization in the CHARMm force field. We can use the molecular dynamic simulation to get the potential energy and the RMSD in natural environment.

Prompt: Here is an example past experiment's abstract which tells you amongst other things the main results of what was studied, what methods do you think were used for it? The key role of oxidative stress (OxSt) and inflammation for the induction of cardiovascular disease, the leading cause of excess morbidity/mortality in chronic kidney disease and dialysis patients, is known and both the activations of NADPH oxidase and RhoA/Rho kinase (ROCK) pathway are pivotal for their effects. While specific hemodialysis procedures, such as hemodiafiltration with on‐line reinfusion of ultrafiltrate and/or the use of vitamin E‐coated dialyzers, are beneficial for OxSt and inflammation, studies in peritoneal dialysis (PD) are instead scarce and results seem not favorable. In nine patients under PD OxSt in terms of mononuclear cell protein level of p22phox (Western blot), subunit of NADPH oxidase, essential for the generation of OxSt, and MYPT‐1 phosphorylation state (Western blot), a marker of ROCK activity, have been measured at the beginning and after 3 and 6 months of PD. Blood levels of interleukin 6 (IL‐6), ferritin, and albumin have been considered for evaluating the inflammatory state. p22phox protein expression, MYPT‐1‐phosphorylation, and ferritin level were increased both at baseline vs healthy subjects (P = .02, P < .0001, P = .004, respectively) and vs baseline after 3 and 6 months of peritoneal dialysis (P = .007, P < .001, P = .004, respectively). Albumin was lower after 6 months of PD (P = .0014). IL‐6 was increased at baseline vs reference values and remained unchanged at 3 and 6 months. OxSt and inflammation increase during PD confirming via molecular biology approach a report at biochemical level. To improve OxSt state in PD, a multitarget approach is necessary. It might include the use of more physiologic pH, low glucose degradation products, low lactate and iso‐osmolar PD solutions, patients’ strict glycemic control, optimal volume management, and antioxidant administration, such as N‐acetylcysteine.
Completion: Here is what we may expect the methods section for such an experiment to look like. 2.2 IL‐6, ferritin, and albumin were assayed at the Padova Hospital Central Laboratory. IL‐6 concentrations were determined using a fully automated chemiluminescence assay (Medical Systems, Genova, Italy), Ferritin was measured using a fully automated electrochemiluminescence immunoassay (ECLIA) (Roche Diagnostics GmbH, Mannheim, Germany) and albumin was measured using a fully automated immunoturbidimetric assay (Roche Diagnostics GmbH, Mannheim, Germany). PD patients’ residual diuresis was considered as an index of renal residual function in addition to the evaluation of standard indexes including eGFR.