An increasing number of patients with metastatic colorectal cancer (mCRC) have achieved no evidence of diseases (NED) status after surgery or other treatments. However, the latest guidelines for colorectal cancer do not recommend an appropriate treatment for patients with mCRC who achieve NED status. Capecitabine metronomic chemotherapy has the advantages of significant efficacy and minimal adverse reactions, it is a potential effective method for maintenance treatment for mCRC, but no RCTs have been reported. Therefore, we designed a randomized controlled trial to evaluate the efficacy and safety of capecitabine metronomic chemotherapy for mCRC patients who achieve NED.

This study is a prospective, randomized controlled study that evaluates the efficacy and safety of capecitabine metronomic chemotherapy for patients with mCRC who achieve NED status. 240 eligible participants will be randomly assigned to either a capecitabine metronomic chemotherapy group or a "watch and wait" group at a 1:1 allocation ratio. Eligible patients diagnosed with stage IV mCRC, both the primary tumor and the metastases, are those who have achieved R0 resection (or complete destruction by ablation) and reached NED. Participants who are enrolled in the capecitabine group will receive capecitabine (500 mg/m2 body surface area twice daily) for 2 years. Meanwhile, those who are assigned to the control group will receive regular imaging examination and follow-up only. All participants will follow up for 1 year after receiving 2 years of intervention. The primary outcomes will be disease-free survival (DFS) from randomization, stratified by preoperative chemotherapy, metastatic organs, number of metastases, lenght of previous systemic treatment, response to previous chemotherapy. Secondary outcomes will include overall survival (OS), 1-year,2-year,3-year survival rate and adverse reactions.

As a potentially effective treatment, low-dose capecitabine metronomic chemotherapy has been explored in clinical practice. The results of this trial will provide evidence on the efficacy and safety of capecitabine metronomic chemotherapy for patients with mCRC who have reached NED status.

Chinese Clinical Trial Registry (ChiCTR2100047149, protocol version number F2.0).

Precision medicine has brought revolutionary changes to the diagnosis and treatment of cancer patients, and is currently a hot and challenging research topic. Currently, the treatment regimens for most colorectal cancer (CRC) patients are mainly determined by several biomakers, including Microsatellite Instability (MSI), RAS, and BRAF. However, the roles of promising biomarkers such as HER-2, consensus molecular subtypes (CMS), and circulating tumor DNA (ctDNA) in CRC are not yet fully clear. Therefore, it is urgent to explore the potential of these emerging biomarkers in the diagnosis and treatment of CRC patients. In this paper, we discuss recent advances in CRC biomarkers, especially clinical data, and focus on the roles of biomarkers in prognosis, prediction, treatment strategies, and the intrinsic connections with clinical pathological features, hoping to promote better precision medicine for colorectal cancer.

Tumor mutations and the composition of the tumor microenvironment have prognostic and therapeutic significance in colorectal cancer (CRC). However, immunotherapy remains a challenge for patients with proficient mismatch repair (pMMR) CRC. In this paper, the association between tumor-infiltrating lymphocytes (TILs) and tumor mutations on survival outcomes in patients with localized pMMR CRC was examined.

A systematic review of the literature and a meta-analysis were conducted in accordance with the PRISMA guidelines. The literature search was conducted in PubMed, Embase, Cochrane Library, and Web of Science. The outcomes of interest were overall survival, disease-free survival, and cancer-specific survival. The risk of bias was assessed through the Newcastle-Ottawa Scale and the quality of the cumulative evidence was evaluated through the modified GRADE approach.

In total, 8498 articles were screened for eligibility and 44 articles were included in the meta-analysis with 33,704 patients in total. Patients with high infiltration of any TILs showed significantly improved overall survival (HR = 0.57, 95 % CI: 0.49-0.67, I2: 0 %), especially for the subgroup of CD3 + (HR = 0.52, 95 % CI: 0.38-0.71, I2: 0 %) and CD8 + (HR = 0.60, 95 % CI: 0.37-0.99, I2: 10 %) TILs. Patients with BRAF mutation (HR = 2.68, 95 % CI: 1.47-4.89, I2: 83 %) and KRAS mutation (HR = 1.25, 95 % CI: 1.18-1.33, I2: 0 %) showed decreased overall survival.

High infiltration of TILs, especially CD3 + and CD8 + , was associated with significantly improved survival, while BRAF and KRAS mutations were correlated with worse survival outcomes for patients with non-metastatic pMMR CRC.

Colorectal cancer (CRC) is one of the major cancers threatening human health, with high mortality, tumor drug resistance and metastasis. Due to its advantages of non-invasive, strongly targeted and limited side effects, Photodynamic therapy (PDT) has become a promising treatment for CRC. Remarkably, PDT has been shown to activate T cell-adaptive immune response and induce immunogenic cell death (ICD). Used in combination with other treatment techniques, PDT has considerable promise in the management of colorectal cancer. In particular, the combination of PDT and tumor immunotherapy, the systemic anti-tumor immune response was enhanced more significantly. This strategy is expected to achieve a synergistic anti-tumor effect by inducing tumor cell apoptosis, regulating tumor immune microenvironment and effectively activating anti-tumor immunity during treatment process. This review focuses on the research of PDT combined with immunotherapy to improve the treatment of CRC. In most studies, a positive effect was observed for combination therapy, experimentally indicating new therapeutic opportunities for CRC.

Lymph node metastasis is a crucial determinant of prognosis in colorectal cancer (CRC), significantly impacting survival outcomes and treatment decision-making. This study aims to evaluate the prognostic value of tumor infiltration proportion within lymph nodes (TIPLN) in N1 CRC patients and to develop a TIPLN-based nomogram to predict prognosis.

A total of 416 N1 CRC patients who underwent radical resection were enrolled and divided into training and validation cohorts. Whole-slide images of lymph nodes were annotated to assess the TIPLN. Univariable and multivariable Cox regression analyses were conducted to identify independent prognostic factors and to develop a nomogram for predicting patient outcomes. The precision and discrimination of the nomogram were evaluated using the area under the receiver operating characteristic curve (AUC), concordance index (C-index), and calibration curve. Decision curve analysis (DCA) was performed to compare the net benefit of the nomogram at different threshold probabilities. Additionally, net reclassification index (NRI) and integrated discrimination improvement (IDI) were used to evaluate the nomogram's clinical utility.

High TIPLN levels were significantly associated with poorer overall survival (OS). Five variables, including TIPLN, were selected to construct the nomogram. The C-index in OS prediction was 0.739 and 0.753 for the training and validation cohorts, respectively. Additionally, strong precision and discrimination were demonstrated through AUC and calibration curves. The NRI (training cohort: 0.191 for 3-year and 0.436 for 5-year OS prediction; validation cohort: 0.180 for 3-year and 0.439 for 5-year OS prediction) and IDI (training cohort: 0.079 for 3-year and 0.094 for 5-year OS prediction; validation cohort: 0.078 for 3-year and 0.098 for 5-year OS prediction) suggest that the TIPLN-based nomogram significantly outperformed the clinicopathological nomogram. Furthermore, DCA demonstrated the high clinical applicability of the TIPLN-based nomogram for predicting OS.

TIPLN could serve as a prognostic predictor for N1 CRC patients. The TIPLN-based nomogram enhances survival prediction accuracy and facilitates more informed, individualized clinical decision-making.

Background/Objective: Studies have shown an association between colorectal cancer (CRC) sidedness and gene mutations that may affect CRC clinical behavior. This study examined the association between specific KRAS, NRAS, and BRAF hot-spot mutations and primary CRC sidedness. Methods: We performed a retrospective cohort analysis of 722 patients diagnosed with primary CRC and tested for KRAS, NRAS, and BRAF hot-spot mutations at the University of Texas Medical Branch (UTMB) from January 2016 through July 2023. Multivariable logistic regressions analyses were conducted. Results:KRAS, NRAS, and BRAF hot-spot mutations rates were 37.8%, 4.6%, and 6.1%, respectively. Right-sided primary CRC had the highest prevalence of mutated tumors (64%). KRAS and BRAF hot-spot mutations were significantly different according to tumor sidedness. KRAS p.Gly12Asp, p.Gly12Val, and p.Gly13Asp showed a significantly increased likelihood of right-sided primary CRC compared to KRAS wildtype, 128%, 134%, and 221% higher, respectively. Conversely, KRAS p.Gly12Val and p.Gly13Asp mutations were associated with decreased likelihood of rectal cancer (53% lower) and left-sided tumors (56% lower), respectively. BRAF p.Val600Glu mutation, as opposed to BRAF wildtype, was associated with a 278% higher likelihood of right-sided CRC. No significant associations were observed between NRAS mutations and primary CRC sidedness. Conclusions: In primary CRC, specific mutations in KRAS (p.Gly12Asp, p.Gly12Val, and p.Gly13Asp) and BRAF p.Val600Glu were associated with increased likelihood of right-sided tumors. KRAS p.Gly12Val and p.Gly13Asp mutations were associated with decreased likelihood of rectal cancer and left-sided tumors, respectively. These findings suggest that tumorigenesis and mutational processes differ based on tumor sidedness. Further studies are needed to substantiate these findings.

Colorectal cancer (CRC) is characterized by high heterogeneity, aggressiveness, and high morbidity and mortality rates. With machine learning (ML) algorithms, patient, tumor, and treatment features can be used to develop and validate models for predicting survival. In addition, important variables can be screened and different applications can be provided that could serve as vital references when making clinical decisions and potentially improving patient outcomes in clinical settings.

To construct prognostic prediction models and screen important variables for patients with stage I to III CRC.

More than 1000 postoperative CRC patients were grouped according to survival time (with cutoff values of 3 years and 5 years) and assigned to training and testing cohorts (7:3). For each 3-category survival time, predictions were made by 4 ML algorithms (all-variable and important variable-only datasets), each of which was validated via 5-fold cross-validation and bootstrap validation. Important variables were screened with multivariable regression methods. Model performance was evaluated and compared before and after variable screening with the area under the curve (AUC). SHapley Additive exPlanations (SHAP) further demonstrated the impact of important variables on model decision-making. Nomograms were constructed for practical model application.

Our ML models performed well; the model performance before and after important parameter identification was consistent, and variable screening was effective. The highest pre- and postscreening model AUCs 95% confidence intervals in the testing set were 0.87 (0.81-0.92) and 0.89 (0.84-0.93) for overall survival, 0.75 (0.69-0.82) and 0.73 (0.64-0.81) for disease-free survival, 0.95 (0.88-1.00) and 0.88 (0.75-0.97) for recurrence-free survival, and 0.76 (0.47-0.95) and 0.80 (0.53-0.94) for distant metastasis-free survival. Repeated cross-validation and bootstrap validation were performed in both the training and testing datasets. The SHAP values of the important variables were consistent with the clinicopathological characteristics of patients with tumors. The nomograms were created.

We constructed a comprehensive, high-accuracy, important variable-based ML architecture for predicting the 3-category survival times. This architecture could serve as a vital reference for managing CRC patients.

Agaricus blazei murill (ABM) mainly exerts its antitumor effect via modulation of the immune system. However, the immunomodulatory role of the ABM polysaccharide (ABMP) in mice with subcutaneously and intraperitoneally implanted MC38 tumor remains to be explored. This study aimed to define the progression effect of inhibiting tumor of ABMP in subcutaneous and intraperitoneal models and its effect on tumor microenvironment (TME) metabolism. In vitro experiments showed that ABMP could significantly promote the activity of CD8+ T immune cells in the co-culture system and promoted their colorectal cancer killing function (p < 0.05). In vivo animal exploration further showed that ABMP could inhibit the growth of intraperitoneal but not subcutaneous tumors. MCR-ALS analysis revealed a significant reduction in the signal of lipid-related spectral components in the TME of peritoneal tumors after ABMP intervention. In addition, preventive intervention with ABMP increased ω-3 polyunsaturated fatty acids content in intraperitoneal TME, revealing that ABMP shifted the metabolic landscape of the TME to promote T cell function and achieved immune regulation. These results suggest that the inhibitory effect of ABMP on colon cancer may be tumor stage-dependent, and that remodeling of fatty acid composition may be an important determinant of its action at any given stage.

Chemo-immunotherapy is standard of care for women with recurrent or advanced mismatch repair deficient endometrial carcinoma. However, it is uncertain whether patients with mismatch repair deficient advanced or recurrent endometrial carcinoma derive less benefit from chemotherapy than those with mismatch repair proficient endometrial carcinoma.

We performed a meta-analysis of randomized controlled trials (RCTs) in advanced or recurrent endometrial carcinoma to determine the difference in the benefit of chemotherapy in mismatch repair deficient vs mismatch repair proficient endometrial carcinoma. Data on chemotherapy outcomes including objective response rate, progression-free survival (PFS), and overall survival were retrieved. We pooled these data using the inverse variance method and examined subgroup difference by mismatch repair status. We also compared differences in PFS and overall survival outcomes by creating individual patient data from the Kaplan-Meier curves of trial publications for sensitivity analyses.

A total of 5 RCTs with 1137 participants (mismatch repair deficient, 26%; mismatch repair proficient, 74%) were included. All participants were treated with carboplatin-based chemotherapy. There was no difference between the mismatch repair deficient and mismatch repair proficient subgroups for objective response rate (66.5% vs 64.0%; P = .20 for subgroup difference), PFS (hazard ratio [HR] = 0.93, 95% confidence interval [CI] = 0.77 to 1.12; P = .44; median PFS = 7.6 vs 9.5 months) or overall survival (HR = 1.03, 95% CI = 0.73 to 1.44; P = .88; median overall survival = not reached vs 28.6 months).

Objective response rate, PFS, and overall survival were similar among those with mismatch repair deficient vs mismatch repair proficient endometrial cancer treated with front-line, platinum-doublet chemotherapy in RCTs. These findings reinforce the importance of combining chemotherapy together with immune checkpoint inhibitors until the results of trials comparing immune checkpoint therapy alone with combination therapy are available.

This study aimed to investigate the characteristics of patients with colorectal mucinous adenocarcinoma (MAC) who benefit from postoperative chemotherapy (POCT) and to develop effective postoperative survival nomograms for predicting overall survival (OS) in colorectal MAC patients.

Data of colorectal MAC patients who underwent surgery from the Surveillance, Epidemiology, and End Results (SEER) database between 2010 and 2020 were collected. Patients were grouped based on POCT, and intergroup analysis was performed using 1:1 propensity score matching (PSM). Kaplan-Meier (K-M) curves were used to compare the prognosis between the 2 groups. Cox analysis was employed to identify factors associated with OS in patients with colorectal MAC who underwent POCT. The variance inflation factor (VIF) and bilateral stepwise regression were used to determine factors included in the model. Additionally, a nomogram was constructed to predict postoperative survival outcomes for patients. The discriminative ability of the nomograms was evaluated using the C-index and calibration curve analysis, the decision curve analysis (DCA) assessed the clinical utility of the nomogram, and the receiver operating characteristic (ROC) curve evaluated the nomograms' performance.

This study encompassed 6829 patients with colorectal MAC, among whom 2258 received POCT, and 4571 did not. Whether pre or post PSM, patients in the POCT group consistently exhibited a superior median OS compared to those in the postoperative non-chemotherapy group (P < .0001). For colorectal MAC patients undergoing POCT, OS was correlated with factors such as patient age, carcinoembryonic antigen levels, tumor deposits, perineural invasion (PNI), lymph node examination count, T staging, and Grade staging. Notably, a significant chemotherapy advantage was observed in patients without perineural invasion, those with lymph node examination counts exceeding 12, and patients with moderately differentiated tumors. The overall colorectal MAC patient postoperative OS predictive nomogram demonstrated a C-index of .74, with a calibration curve near the diagonal and a DCA curve indicating positive net benefits. In comparison to TNM staging, the ROC curves of the nomogram at 1 year, 3 years, and 5 years demonstrated superior predictive capabilities (AUC: .80 vs .71, .78 vs .71, .77 vs .70).

This study revealed the characteristics of colorectal MAC patients who benefit from POCT and established effective prognostic nomograms, which can aid clinicians in designing personalized treatment plans for individual patients and promote precision medicine.

Introduction: Lung cancer remains a significant global health burden, with non-small cell lung cancer (NSCLC) being the predominant subtype. Despite advancements in treatment, the prognosis for patients with advanced NSCLC remains unsatisfactory, underscoring the imperative for precise prognostic assessment models. This study aimed to develop and validate a survival prediction model specifically tailored for patients diagnosed with NSCLC.

A total of 523 patients were randomly divided into a training dataset (n=313) and a validation dataset (n=210). We conducted initial variable selection using three analytical methods: univariate Cox regression, LASSO regression, and random survival forest (RSF) analysis. Multivariate Cox regression was then performed on the variables selected by each method to construct the final predictive models. The optimal model was selected based on the highest bootstrap C-index observed in the validation dataset. Additionally, the predictive performance of the model was evaluated using time-dependent receiver operating characteristic (Time-ROC) curves, calibration plots, and decision curve analysis (DCA).

The LASSO regression model, which included N stage, neutrophil-lymphocyte ratio (NLR), D-dimer, neuron-specific enolase (NSE), squamous cell carcinoma antigen (SCC), driver alterations, and first-line treatment, achieved a bootstrap C-index of 0.668 (95% CI: 0.626-0.722) in the validation dataset, the highest among the three models tested. The model demonstrated good discrimination in the validation dataset, with area under the ROC curve (AUC) values of 0.707 (95% CI: 0.633-0.781) for 1-year survival, 0.691 (95% CI: 0.616-0.765) for 2-year survival, and 0.696 (95% CI: 0.611-0.781) for 3-year survival predictions, respectively. Calibration plots indicated good agreement between predicted and observed survival probabilities. Decision curve analysis demonstrated that the model provides clinical benefit at a range of decision thresholds.

The LASSO regression model exhibited robust performance in the validation dataset, predicting survival outcomes for patients with advanced NSCLC effectively. This model can assist clinicians in making more informed treatment decisions and provide a valuable tool for patient risk stratification and personalized management.

Drug resistance poses a significant challenge in cancer treatment despite the clinical efficacy of cisplatin. Identifying and targeting biomarkers open new ways to improve therapeutic outcomes. In this study, comprehensive bioinformatic analyses were employed, including a comparative analysis of multiple datasets, to evaluate overall survival and mutation hotspots in 27 base excision repair (BER) genes of more than 7,500 tumors across 23 cancer types. By using various parameters influencing patient survival, revealing that the overexpression of 15 distinct BER genes, particularly PARP3, NEIL3, and TDG, consistently correlated with poorer survival across multiple factors such as race, gender, and metastasis. Single nucleotide polymorphism (SNP) analyses within protein-coding regions highlighted the potential deleterious effects of mutations on protein structure and function. The investigation of mutation hotspots in BER proteins identified PARP3 due to its high mutation frequency. Moving from bioinformatics to wet lab experiments, cytotoxic experiments demonstrated that the absence of PARP3 by CRISPR/Cas9-mediated knockdown in MDA-MB-231 breast cancer cells increased drug activity towards cisplatin, carboplatin, and doxorubicin. Pathway analyses indicated the impact of PARP3 absence on the platelet-derived growth factor (PDGF) and G-coupled signal pathways on cisplatin exposure. PDGF, a critical regulator of various cellular functions, was downregulated in the absence of PARP3, suggesting a role in cancer progression. Moreover, the influence of PARP3 knockdown on G protein-coupled receptors (GPCRs) affects their function in the presence of cisplatin. In conclusion, the study demonstrated a synthetic lethal interaction between GPCRs, PDGF signaling pathways, and PARP3 gene silencing. PARP3 emerged as a promising target.

RAS, BRAF, and mismatch repair (MMR)/microsatellite instability (MSI) are crucial biomarkers recommended by clinical practice guidelines for colorectal cancer (CRC). However, their characteristics and influencing factors in Chinese patients have not been thoroughly described.

To analyze the clinicopathological features of KRAS, NRAS, BRAF, and PIK3CA mutations and the DNA MMR status in CRC.

We enrolled 2271 Chinese CRC patients at the China-Japan Friendship Hospital. MMR proteins were tested using immunohistochemical analysis, and the KRAS/NRAS/BRAF/PIK3CA mutations were determined using quantitative polymerase chain reaction. Microsatellite status was determined using an MSI detection kit. Statistical analyses were conducted using SPSS software and logistic regression.

The KRAS, NRAS, BRAF, and PIK3CA mutations were detected in 44.6%, 3.4%, 3.7%, and 3.9% of CRC patients, respectively. KRAS mutations were more likely to occur in patients with moderate-to-high differentiation. BRAF mutations were more likely to occur in patients with right-sided CRC, poorly differentiated, or no perineural invasion. Deficient MMR (dMMR) was detected in 7.9% of all patients and 16.8% of those with mucinous adenocarcinomas. KRAS, NRAS, BRAF, and PIK3CA mutations were detected in 29.6%, 1.1%, 8.1%, and 22.3% of patients with dMMR, respectively. The dMMR was more likely to occur in patients with a family history of CRC, aged < 50 years, right-sided CRC, poorly differentiated histology, no perineural invasion, and with carcinoma in situ, stage I, or stage II tumors.

This study analyzed the molecular profiles of KRAS, NRAS, BRAF, PIK3CA, and MMR/MSI in CRC, identifying key influencing factors, with implications for clinical management of CRC.

Stage II colon cancer (CC) encompasses a heterogeneous group of patients with diverse survival experiences: 87% to 58% 5-year relative survival rates for stages IIA and IIC, respectively. While stage IIA patients are usually spared the adjuvant chemotherapy, some of them relapse and may benefit from it; thus, their timely identification is crucial. Current gene expression signatures did not specifically target this group nor did they find their place in clinical practice. Since processes at invasion front have also been linked to tumor progression, we hypothesize that aside from bulk tumor features, focusing on the invasion front may provide additional clues for this stratification. A retrospective matched case-control collection of 39 stage IIA microsatellite-stable (MSS) untreated CCs was analyzed to identify prognostic gene expression-based signatures. The endpoint was defined as relapse within 5 years vs. no relapse for at least 6 years. From the same tumors, three different classifiers (bulk tumor, invasion front, and constrained baseline on bulk tumor) were developed and their performance estimated. The baseline classifier, while the weakest, was validated in two independent data sets. The best performing signature was based on invasion front profiles [area under the receiver operating curve (AUC) = 0.931 (0.815-1.0)] and contained genes associated with KRAS pathway activation, apical junction complex, and heme metabolism. Its combination with bulk tumor classifier further improved the accuracy of the predictions.

Primary tumor sidedness (PTS) is an independent prognostic factor in patients with metastatic colorectal cancer (CRC), with a worse prognosis for right-sided tumors. There are limited data on the prognostic impact of PTS in stage III CRC. The main objective of this study was to analyze the prognostic impact of PTS in stage III CRC.

A retrospective and uni-institutional cohort study was performed in an oncology reference center. Patients with stage III CRC treated with a 5-fluorouracil and oxaliplatin-based chemotherapy regimen (mFLOX regimen) from October 2007 to February 2013 were included. The primary outcome was the probability of overall survival (OS) at 5 years stratified by PTS. Secondary outcomes were the probability of disease-free survival (DFS) at 5 years and an analysis of the prognostic impact of clinical and molecular biomarkers. Kaplan‒Meier curves were used, and Cox models were used to evaluate prognostic factors associated with OS and DFS.

Overall, 265 patients were evaluated. Transverse colon tumors, multicentric tumors, and undetermined primary subsites were excluded, resulting in 234 patients classified according to PTS: 95 with right sidedness (40.6%) and 139 with left sidedness (59.4%). The median follow-up time was 66 months [interquartile range (IQR): 39-81]. The 5-year OS probabilities for right-sided and left-sided tumors were 67% (95% CI: 58%-77%) and 82% (75%-89%), respectively [hazard ratio (HR): 2.02, 95% CI: 1.18-3.46; P = .010]. The 5-year probabilities of DFS for right-sided and left-sided tumors were 58% (49%-69%) and 65% (58%-74%), respectively (HR: 1.29, 0.84-1.97; P = 0.248).

These data suggest that there may be a worse prognosis (inferior OS at 5 years) for resected right-sided stage III CRC patients treated in the real world. However, these data need to be confirmed by prospective studies with a larger number of participants.

Colorectal cancer (CRC) is the third most commonly diagnosed cancer worldwide and a public health problem. Several clinical studies have shown that copper (Cu) is involved in carcinogenesis, possibly via cuproptosis, a new form of programmed cell death, but the conclusions from published reports are inconsistent. This study aimed at evaluating the potential of Cu dysregulation as a CRC susceptibility factor.

In this systematic review and meta-analysis, we searched Cochrane Library, EBSCOhost, EMBASE, ProQuest, PubMed/MEDLINE, Scopus, and Web of Science for studies reporting serum Cu concentrations in CRC patients and controls from articles published till June 2023. The studies included reported measurements of serum/plasma/blood Cu levels. Meta-analyses were performed as well as study quality, heterogeneity, and small study effects were assessed. Based on a random effects model, summary standardized mean differences (SMDs) and the corresponding 95% confidence intervals (95% CIs) were applied to compare the levels of Cu between CRC patients and controls.

26 studies with a pooled total of9628 participants and 2578 CRC cases were included. The pooled SMD was equal to 0.85 (95% CIs -0.44; 2.14) showing that the CRC patients had higher mean Cu levels than the control subjects, but the difference was not significant (p = 0.185) and the heterogeneity was very high, I2 = 97.9% (95% CIs: 97.5-98.3%; p < 0.001).

The pooled results were inconclusive, likely due to discordant results and inaccuracy in reporting data of some studies; further research is needed to establish whether Cu dysregulation might contribute to the CRC risk and whether it might reflect different CRC grades.

To investigate the correlation between doublecortin and CaM kinase-like-1 (DCAMKL-1) protein expression, K-ras gene mutation, and their impact on patient prognosis in colorectal cancer (CRC).

Immunohistochemistry was used to detect the expression of DCAMKL-1 protein in 60 cases of colorectal adenoma, 82 cases of CRC (including 65 cases of lymph node metastasis) and paraffin-embedded paracancerous intestinal mucosal tissue. K-ras gene mutations in primary CRC lesions were detected using an amplification-refractory mutation system and fluorescent polymerase chain reaction. The relationship between DCAMKL-1 protein expression and K-ras gene mutations with the clinicopathological characteristics of patients with CRC was analyzed. Univariate Kaplan‒Meier survival analysis and multivariate Cox regression analysis were performed using follow-up data.

The mutation rate of the K-ras gene in 82 cases of CRC was 48.8% (40/82). The positivity rate for the presence of DCAMKL-1 protein in CRC was 70.7% (58/82), significantly higher than that for colorectal adenomas (53.3%; 32/60) and paracancerous intestinal mucosa (0%; 0/82) (P<0.05). The positive expression rate for the presence of DCAMKL-1 protein in 65 patients with lymph node metastasis was higher in the primary lesions (69.2%; 45/65) than in the lymph node metastases (52.3%; 34/65) (χ2=12.087, P=0.001). The K-ras gene mutation status was positively correlated with DCAMKL-1 protein expression (r=0.252, P=0.022).

In this study, a potential positive correlation between K-ras gene mutation and DCAMKL-1 protein expression was identified in CRC tissues. The assessment of K-ras gene mutation status and DCAMKL-1 protein expression holds promise for augmenting early diagnosis and prognosis evaluation in CRC. This approach may improve the overall prognosis and survival outcomes for CRC patients.

Colorectal cancer (CRC) is one of the most frequent types of cancer, with high incidence rates and mortality globally. The extended timeframe for developing CRC allows for the potential screening and early identification of the disease. Furthermore, studies have shown that survival rates for patients with cancer are increased when diagnoses are made at earlier stages. Recent research suggests that the development of CRC, including its precancerous lesion, is influenced not only by genetic factors but also by epigenetic variables. Studies suggest epigenetics plays a significant role in cancer development, particularly CRC. While this approach is still in its early stages and faces challenges due to the variability of CRC, it shows promise as a potential method for understanding and addressing the disease. This review examined the current evidence supporting genetic and epigenetic biomarkers for screening and diagnosis. In addition, we also discussed the feasibility of translating these methodologies into clinical settings. Several markers show promising potential, including the methylation of vimentin (VIM), syndecan-2 (SDC2), and septin 9 (SEPT9). However, their application as screening and diagnostic tools, particularly for early-stage CRC, has not been fully optimized, and their effectiveness needs validation in large, multi-center patient populations. Extensive trials and further investigation are required to translate genetic and epigenetic biomarkers into practical clinical use. biomarkers, diagnostic biomarkers.

The PKHD1 (Polycystic Kidney and Hepatic Disease 1) gene is essential for producing fibrocystin or polyductin, which is crucial in various cellular functions. Mutations in PKHD1 have been found to be involved in the development and progression of colorectal cancer (CRC). Along with APC, TP53, and KRAS, PKHD1 is one of the most frequently mutated genes in CRC. PKHD1 expression is governed by the Wnt/PCP pathway, often dysregulated in CRC. Targeting this pathway, crucial for CRC progression, could unveil potential therapeutic strategies for colon cancer treatment.

This study examined an in-house dataset of 3702 colon cancer samples, analyzing mutation landscapes, clinical features, tumor mutational burden (TMB), microsatellite instability (MSI), and chromosomal instability (CIN) score. For the survival analysis of PKHD1 patients, survival data of 436 colon adenocarcinoma samples were obtained from TCGA dataset. Additionally, 433 samples from TCGA with RNA-seq data were used for the assessment of immune cell infiltration and gene set enrichment analysis.

Polycystic Kidney and Hepatic Disease 1 mutation was detected in 424 colon cancer patients from our in-house cohort and was associated with increased TMB, higher MSI, and lower CIN score. Importantly, within the TCGA dataset, PKHD1 mutations were identified as an independent prognostic factor, not merely correlated with established prognostic biomarkers, and were associated with poorer overall survival outcomes. In terms of immune response, these mutations correlated with increased enrichment scores for 12 immune cell types, including B cell plasma, macrophages, and naive CD4+ T cells. Additionally, interferon alpha and interferon-gamma gene sets were significantly down-regulated in patients with PKHD1 mutations (FDA q-value < 0.1).

Overall, these findings suggest that PKHD1 may be a potential biomarker for the prognosis of colon cancer and provide some insight for personalized immunotherapy.

Colorectal cancer (CRC) is one of the most common malignant cancers worldwide and seriously threatens human health. The clustered regulatory interspaced short palindromic repeat/CRISPR-associate nuclease 9 (CRISPR/Cas9) system is an adaptive immune system of bacteria or archaea. Since its introduction, research into various aspects of treatment approaches for CRC has been accelerated, including investigation of the oncogenes, tumor suppressor genes (TSGs), drug resistance genes, target genes, mouse model construction, and especially in genome-wide library screening. Furthermore, the CRISPR/Cas9 system can be utilized for gene therapy for CRC, specifically involving in the molecular targeted drug delivery or targeted knockout in vivo. In this review, we elucidate the mechanism of the CRISPR/Cas9 system and its comprehensive applications in CRC. Additionally, we discussed the issue of off-target effects associated with CRISPR/Cas9, which serves to restrict its practical application. Future research on CRC should in-depth and systematically utilize the CRISPR/Cas9 system thereby achieving clinical practice.

Background Colorectal cancer (CRC) is a global health concern with rising incidence. This study analyzed demographic and clinicopathological factors influencing overall survival (OS) and disease-free survival (DFS) in Jordanian CRC patients. Methodology This retrospective, single-center study collected data from CRC patients at the Royal Medical Services, Jordan, from January 2018 to June 2020. Patient variables included disease stage, stage risk, tumor location, history of chemotherapy, and metastasis status. OS and DFS were defined as the time from surgery to death, last follow-up, or metastasis confirmation. Kaplan-Meier curves and Cox models were used for survival analysis. Results Of 127 CRC patients, 33.3% died during the follow-up period. Most patients were males (55.1%), diagnosed with stage III (55.9%), and classified as high risk (59.2%). Metastasis occurred in 24.4%, and 65.4% received chemotherapy. OS at one, two, and end of the follow-up years was 85.2%, 75.6%, and 66.9%, respectively. Metastasis-free rates were 85%, 78.5%, and 71%, respectively. Multivariate analysis showed that stage III (hazard ratio (HR) = 2.968) and high-risk stage (HR = 2.966) were associated with shorter OS and increased metastasis risk. Right-sided tumors (HR = 2.183) had shorter OS, while chemotherapy recipients (HR = 0.430) had longer OS. Stage III and high-risk stages were strong predictors of mortality, while only stage III and high-risk stages were robust predictors of metastasis. Demographic variables (sex and age) showed no significant associations with survival outcomes. Conclusions Our findings highlight the prognostic significance of disease stage, stage risk, tumor location, and chemotherapy in CRC survival among Jordanian patients. Understanding these factors can guide tailored treatment and improve outcomes.

Loss-of-function mutations in the adenomatous polyposis coli (APC) gene are common in metastatic colorectal cancer (mCRC). However, the characteristic of APC specific mutations in mCRC is poorly understood. Here, we explored the clinical and molecular characteristics of N-terminal and C-terminal side APC mutations in Chinese patients with mCRC.

Hybrid capture-based next-generation sequencing was performed on tumor tissues from 275 mCRC pati-ents to detect mutations in 639 tumor-associated genes. The prognostic value and gene-pathway difference between APC specific mutations in mCRC patients were analyzed.

APC mutations were highly clustered, accounting for 73% of all mCRC patients, and most of them were truncating mutations. The tumor mutation burden of the N-terminal side APC mutations group (n=76) was significantly lower than that of the C-terminal side group (n=123) (p < 0.001), further confirmed by the public database. Survival analysis showed that mCRC patients with N-terminus side APC mutations had longer overall survival than C-terminus side. Tumor gene pathway analysis showed that gene mutations in the RTK/RAS, Wnt and transforming growth factor β signaling pathways of the C-terminal group were significantly higher than those of the N-terminal group (p < 0.05). Additionally, KRAS, AMER1, TGFBR2, and ARID1A driver mutations were more common in patients with C-terminal side APC mutations.

APC specific mutations have potential function as mCRC prognostic biomarkers. There are obvious differences in the gene mutation patterns between the C-terminus and N-terminus APC mutations group, which may have certain guiding significance for the subsequent precise treatment of mCRC.

The Immunoscore can categorize patients into high- and low-risk groups for prognostication in colorectal cancer (CRC). Collagen plays an important role in immunomodulatory functions in the tumor microenvironment (TME). However, the correlation between collagen and the Immunoscore in the TME is unclear. This study aimed to construct a collagen signature to illuminate the relationship between collagen structure and Immunoscore.

A total of 327 consecutive patients with stage I-III stage CRC were included in a training cohort. The fully quantitative collagen features were extracted at the tumor center and invasive margin of the specimens using multiphoton imaging. LASSO regression was applied to construct the collagen signature. The association of the collagen signature with Immunoscore was assessed. A collagen nomogram was developed by incorporating the collagen signature and clinicopathological predictors after multivariable logistic regression. The performance of the collagen nomogram was evaluated via calibration, discrimination, and clinical usefulness and then tested in an independent validation cohort. The prognostic values of the collagen nomogram were assessed using Cox regression and the Kaplan-Meier method.

The collagen signature was constructed based on 16 collagen features, which included 6 collagen features from the tumor center and 10 collagen features from the invasive margin. Patients with a high collagen signature were more likely to show a low Immunoscore (Lo IS) in both cohorts (P<0.001). A collagen nomogram integrating the collagen signature and clinicopathological predictors was developed. The collagen nomogram yielded satisfactory discrimination and calibration, with an AUC of 0.925 (95% CI: 0.895-0.956) in the training cohort and 0.911 (95% CI: 0.872-0.949) in the validation cohort. Decision curve analysis confirmed that the collagen nomogram was clinically useful. Furthermore, the collagen nomogram-predicted subgroup was significantly associated with prognosis. Moreover, patients with a low-probability Lo IS, rather than a high-probability Lo IS, could benefit from chemotherapy in high-risk stage II and stage III CRC patients.

The collagen signature is significantly associated with the Immunoscore in the TME, and the collagen nomogram has the potential to individualize the prediction of the Immunoscore and identify CRC patients who could benefit from adjuvant chemotherapy.

The wide adoption of electronic health records (EHRs) offers immense potential as a source of support for clinical research. However, previous studies focused on extracting only a limited set of medical concepts to support information extraction in the cancer domain for the Spanish language. Building on the success of deep learning for processing natural language texts, this paper proposes a transformer-based approach to extract named entities from breast cancer clinical notes written in Spanish and compares several language models. To facilitate this approach, a schema for annotating clinical notes with breast cancer concepts is presented, and a corpus for breast cancer is developed. Results indicate that both BERT-based and RoBERTa-based language models demonstrate competitive performance in clinical Named Entity Recognition (NER). Specifically, BETO and multilingual BERT achieve F-scores of 93.71% and 94.63%, respectively. Additionally, RoBERTa Biomedical attains an F-score of 95.01%, while RoBERTa BNE achieves an F-score of 94.54%. The findings suggest that transformers can feasibly extract information in the clinical domain in the Spanish language, with the use of models trained on biomedical texts contributing to enhanced results. The proposed approach takes advantage of transfer learning techniques by fine-tuning language models to automatically represent text features and avoiding the time-consuming feature engineering process.

Background: Colorectal cancer (CRC) is one of the most prevalent cancer types globally. A survival paradox exists due to the inherent heterogeneity in stage II/III CRC tumor biology. Ferroptosis is closely related to the progression of tumors, and ferroptosis-related genes can be used as a novel biomarker in predicting cancer prognosis. Methods: Ferroptosis-related genes were retrieved from the FerrDb and KEGG databases. A total of 1,397 samples were enrolled in our study from nine independent datasets, four of which were integrated as the training dataset to train and construct the model, and validated in the remaining datasets. We developed a machine learning framework with 83 combinations of 10 algorithms based on 10-fold cross-validation (CV) or bootstrap resampling algorithm to identify the most robust and stable model. C-indice and ROC analysis were performed to gauge its predictive accuracy and discrimination capabilities. Survival analysis was conducted followed by univariate and multivariate Cox regression analyses to evaluate the performance of identified signature. Results: The ferroptosis-related gene (FRG) signature was identified by the combination of Lasso and plsRcox and composed of 23 genes. The FRG signature presented better performance than common clinicopathological features (e.g., age and stage), molecular characteristics (e.g., BRAF mutation and microsatellite instability) and several published signatures in predicting the prognosis of the CRC. The signature was further stratified into a high-risk group and low-risk subgroup, where a high FRG signature indicated poor prognosis among all collected datasets. Sensitivity analysis showed the FRG signature remained a significant prognostic factor. Finally, we have developed a nomogram and a decision tree to enhance prognosis evaluation. Conclusion: The FRG signature enabled the accurate selection of high-risk stage II/III CRC population and helped optimize precision treatment to improve their clinical outcomes.

It is common for elderly patients to be underrepresented in clinical trials for cancer, which can result in a lack of efficacy data and unclear criteria to guide treatment decisions for clinical doctors. Therefore, one of the common challenges in oncology treatment is determining the extent to which patients aged 75 and older have benefited from postoperative chemotherapy.

The study aimed to explore the effect of adjuvant chemotherapy (AC) on 3-year recurrence-free survival (RFS) after curative resection in patients aged 75 years and older with stage II-III colorectal cancer (CRC).

The retrospective cohort analysis was performed on patients with stage II-III CRC who received curative resection at three cancer centers in China between 2008 and 2017. Kaplan-Meier curves and Multivariable Cox regression models were used to analyze the impact of AC on RFS in patients. Finally, propensity-score matching was used to reduce selection bias and confounding factors in patients aged 75 years and older with stage II-III CRC.

A total of 2885 patients were included (1729 (59.9%) male; 1312 (61.5%) received AC). The pre-matching cohort was comprised of 151 patients aged 75 years and older (median age (IQR)77.00 (76.00, 79.00); 97 (64.2%) male, 51 (72.9%) received AC). Age (P=0.001), postoperative carcinoembryonic antigen (CEA)(P=0.02) level were associated with prognosis. But AC was not associated with 3-year RFS (HR, 1.27; 95% CI, 0.80-2.0; log-rank P=0.37). After a predisposition 1: 1 match (with or without AC, n = 42), AC remains uncorrelated with 3-year RFS (HR, 1.39; 95% CI, 0.52-3.70; log-rank P=0.66).

Patients over the age of 75 with stage II-III CRC who receive AC or do not face the same risk of postoperative recurrence. As a result, patients with stage II-III postoperative adjuvant chemotherapy can make an informed decision regarding whether they want to undergo chemotherapy based on their age and reduce the unnecessary side effects of chemotherapy.

Tertiary lymphoid structures (TLS) are the lymphocyte aggregates that play a key role in the vast majority of solid tumors including colon cancer, displaying an antitumor effect under most circumstances. The heterogeneity between left- and right-sided colon cancer (LCC and RCC) encompasses various aspects, such as clinical manifestations, pathological features, and immune responses. However, the function and prognostic significance of TLS within LCC and RCC have yet to be fully understood.

A retrospective analysis was performed on 2612 patients who underwent radical resection for LCC or RCC without distant metastasis in multiple medical centers. Utilizing propensity score matching, 121 patients with LCC and 121 patients with RCC were selected for the training set. An external validation set including 64 patients with LCC and 64 patients with RCC were also employed. Hematoxylin-eosin and immunohistochemical staining were used to assess TLS and the proportion of various immune cells. Clinical characteristics and prognostic values of TLS in patients with LCC and RCC were analyzed. Nomograms were constructed for LCC and RCC to predict 3-year and 5-year overall survival (OS), respectively.

For LCC and RCC patients, TLS was located in the interstitial region or outside the tumor tissue and mainly consisted of B cells and T cells. The TLS quantity and density in RCC were higher than those of LCC. In multivariate Cox regression analysis, TLS density ( P =0.014), vascular invasion ( P =0.019), and AJCC stage ( P =0.026) were independent prognostic factors for 5-year OS of RCC. For LCC patients, AJCC stage ( P =0.024), tumor differentiation ( P =0.001), and tumor budding ( P =0.040) emerged as independent prognostic factors for 5-year OS. Similar results were obtained in the external verification set. Separate nomograms for RCC and LCC were developed, displaying improved prediction performance compared to the AJCC 8th edition TNM staging system.

Differences in TLS quantity and density were observed between LCC and RCC, suggesting that a nomogram based on TLS density could more effectively predict survival for RCC patients. Furthermore, a nomogram based on tumor budding was recommended for better prediction of LCC patient survival. Taken together, these results suggested that the immune and clinical characteristics of colon cancer at left and right side were substantially different, which may lead to the use of different prediction model and the development of individual treatment strategy.

Colorectal cancer (CRC) is a significant global health issue characterized by a high prevalence of KRAS gene mutations. The RAS/MAPK pathway, involving KRAS, plays a crucial role in CRC progression. Although some RAS inhibitors have been approved, their efficacy in CRC is limited. To overcome these limitations, pan-RAF inhibitors targeting A-Raf, B-Raf, and C-Raf have emerged as promising therapeutic strategies. However, resistance to RAF inhibition and the presence of an immunosuppressive tumor microenvironment (TME) pose additional obstacles to effective therapy. Here, we evaluated the potential of a novel pan-RAF inhibitor, SJ-C1044, for targeting mutant KRAS-mediated signaling and inhibiting CRC cell proliferation. Notably, SJ-C1044 also exhibited inhibitory effects on immunokinases, specifically, CSF1R, VEGFR2, and TIE2, which play crucial roles in immune suppression. SJ-C1044 demonstrated potent antitumor activity in xenograft models of CRC harboring KRAS or BRAF mutations. Importantly, treatment with SJ-C1044 resulted in increased infiltration of T cells and reduced presence of tumor-associated macrophages and regulatory T cells within the TME. Thus, SJ-C1044 shows immunomodulatory potential and the ability to enhance antitumor responses. The study underscores the therapeutic potential of SJ-C1044 as a novel pan-RAF inhibitor capable of targeting oncogenic signaling pathways and overcoming immune suppression in CRC.

The current tumor-node-metastasis staging system does not provide sufficient prognostic prediction or adjuvant chemotherapy benefit information for stage II-III colon cancer (CC) patients. Collagen in the tumor microenvironment affects the biological behaviors and chemotherapy response of cancer cells. Hence, in this study, we proposed a collagen deep learning (collagenDL) classifier based on the 50-layer residual network model for predicting disease-free survival (DFS) and overall survival (OS). The collagenDL classifier was significantly associated with DFS and OS (P < 0.001). The collagenDL nomogram, integrating the collagenDL classifier and three clinicopathologic predictors, improved the prediction performance, which showed satisfactory discrimination and calibration. These results were independently validated in the internal and external validation cohorts. In addition, high-risk stage II and III CC patients with high-collagenDL classifier, rather than low-collagenDL classifier, exhibited a favorable response to adjuvant chemotherapy. In conclusion, the collagenDL classifier could predict prognosis and adjuvant chemotherapy benefits in stage II-III CC patients.

Evidence reveals that gastric cancer (GC) is the fifth most common malignancy in humans, and about 770,000 people die from this cancer yearly. It has been reported that new cases and deaths from GC are more common in men than women. Therapeutic approaches, such as surgery, chemotherapy, and radiotherapy, have been common for treating GC. Nevertheless, due to the complications and limitations of these methods, researchers use novel approaches, such as immunotherapeutic or target therapies, to evaluate the effectiveness of treatment in patients with metastatic GC. Studies have shown that monotherapy is usually associated with unpromising outcomes, and combination therapy can be a more practical option for treating metastatic GC. Therefore, to clarify different aspects of chemotherapy and immunotherapy in patients with metastatic GC, this review discussed the achievements and challenges of combining immunotherapeutic methods with chemotherapeutic agents.

FBXL8 is a conserved F-box protein, belonging to the ubiquitin ligase complex, which promotes the development and progression of tumours. However, the regulation function and mechanism of FBXL8's involvement in colorectal cancer (CRC) remain unclear.

RT-PCR is used to detect gene expression levels. Protein levels were determined by western blotting and flow cytometry. The bindings of FBXL8 and p53 and ubiquitination levels were detected by cell transfection and immunoprecipitation. The transwell assay was used to measure the ability of cells to migrate and invade. Animal studies were used to verify the function of FBXL8 in vivo.

The expression of FBXL8 was up-regulated in CRC tissues, and its overexpression was associated with poor prognosis in CRC patients. The up-regulation of FBXL8 promoted the proliferation, invasion and migration of CRC tumour cells and maintained the stem-cell characteristics of colorectal tumour cells. Further analysis demonstrated that FBXL8 targeted p53 and reduced its stability through ubiquitination. Knockout of FBXL8 down-regulated the proliferation, migration and stem-like properties of tumour cells. CRC mouse xenograft tumour model confirmed that FBXL8 gene knockout inhibited tumour formation and liver metastasis.

FBXL8 was highly expressed in CRC. Mechanism studies have shown that FBXL8 degraded tumour suppressor gene p53 by ubiquitination. FBXL8 knockout inhibited the proliferation and stem characteristics of CRC cells, so SCF-FBXL8-TP53 has potential to be used as a therapeutic target for CRC in subsequent studies.

F-box and WD repeat domain containing 10 (FBXW10) is a member of the FBXW subgroup that contains the WD40 domain. FBXW10 has been rarely reported in colorectal cancer (CRC) and its mechanism is unclear. To investigate the role of FBXW10 in CRC, we conducted in vitro and in vivo experiments. Through the database and our clinical samples, we found that FBXW10 expression was up-regulated in CRC, and it was positively correlated with CD31 expression. CRC patients with high FBXW10 expression levels had a poor prognosis. Overexpression of FBXW10 up-regulated cell proliferation, migration and vascular formation, while knockdown of FBXW10 had the opposite effects. Studies on the mechanism of FBXW10 in CRC showed that FBXW10 could ubiquitinate large tumor suppressor kinase 2 (LATS2) and promote its degradation with the Fbox region of FBXW10 played an essential role in this process. In vivo studies demonstrated that knockout of FBXW10 inhibited tumor proliferation and reduced liver metastasis. In conclusion, our study proved that FBXW10 was significantly overexpressed in CRC and was involved in the pathogenesis of CRC by affecting angiogenesis and liver metastasis. Mechanistically, FBXW10 degraded LATS2 through ubiquitination. Therefore, FBXW10-LATS2 can be used as a therapeutic target for CRC in subsequent studies.

Microsatellite instability (MSI) due to mismatch repair (MMR) defects accounts for 15-20% of colon cancers (CC). MSI testing is currently standard of care in CC with immunohistochemistry of the four MMR proteins representing the gold standard. Instead, label-free quantum cascade laser (QCL) based infrared (IR) imaging combined with artificial intelligence (AI) may classify MSI/microsatellite stability (MSS) in unstained tissue sections user-independently and tissue preserving.

Paraffin-embedded unstained tissue sections of early CC from patients participating in the multicentre AIO ColoPredict Plus (CPP) 2.0 registry were analysed after dividing into three groups (training, test, and validation). IR images of tissue sections using QCL-IR microscopes were classified by AI (convolutional neural networks [CNN]) using a two-step approach. The first CNN (modified U-Net) detected areas of cancer while the second CNN (VGG-Net) classified MSI/MSS. End-points were area under receiver operating characteristic (AUROC) and area under precision recall curve (AUPRC).

The cancer detection in the first step was based on 629 patients (train n = 273, test n = 138, and validation n = 218). Resulting classification AUROC was 1.0 for the validation dataset. The second step classifying MSI/MSS was performed on 547 patients (train n = 331, test n = 69, and validation n = 147) reaching AUROC and AUPRC of 0.9 and 0.74, respectively, for the validation cohort.

Our novel label-free digital pathology approach accurately and rapidly classifies MSI vs. MSS. The tissue sections analysed were not processed leaving the sample unmodified for subsequent analyses. Our approach demonstrates an AI-based decision support tool potentially driving improved patient stratification and precision oncology in the future.

The interaction between genetic variables is one of the major barriers to characterizing the genetic architecture of complex traits. To consider epistasis, network science approaches are increasingly being used in research to elucidate the genetic architecture of complex diseases. Network science approaches associate genetic variables' disease susceptibility to their topological importance in the network. However, this network only represents genetic interactions and does not describe how these interactions attribute to disease association at the subject-scale. We propose the Network-based Subject Portrait Approach (NSPA) and an accompanying feature transformation method to determine the collective risk impact of multiple genetic interactions for each subject.

The feature transformation method converts genetic variants of subjects into new values that capture how genetic variables interact with others to attribute to a subject's disease association. We apply this approach to synthetic and genetic datasets and learn that (1) the disease association can be captured using multiple disjoint sets of genetic interactions and (2) the feature transformation method based on NSPA improves predictive performance comparing with using the original genetic variables. Our findings confirm the role of genetic interaction in complex disease and provide a novel approach for gene-disease association studies to identify genetic architecture in the context of epistasis.

The codes of NSPA are now available in: https://github.com/MIB-Lab/Network-based-Subject-Portrait-Approach.

ting.hu@queensu.ca.

Supplementary data are available at Bioinformatics Advances online.