Identifying appropriate clinical trials for cancer patients with specific gene mutations remains a significant challenge, largely due to limitations in current search tools like ClinicalTrials.gov, which at times return irrelevant or misleading results. This diagnostic accuracy study investigates the efficacy of 2 large language models (LLMs), GPT-4.0 and Gemini 2.0, in evaluating the eligibility of patients with specific cancer-related gene mutations for clinical trials. The study prompts GPT 4.0 and Gemini 2.0 with trial details from ClinicalTrials.gov and a particular cancer mutation. We then assess model performance against physician-curated benchmarks across 6 gene mutations (ALK, BRAF, EGFR, ERBB2, KIT, and KRAS). The results demonstrate good F1-scores for both LLMs-averaging 64% for GPT-4.0 and 70% for Gemini 2.0-highlighting their potential to streamline clinical trial matching. Furthermore, decision trees provided interpretability by identifying key textual indicators that LLMs use. This work demonstrates the feasibility of using proprietary LLMs such as GPT 4.0 and Gemini 2.0 "off the shelf" with both limited LLM fine-tuning and limited patient information to evaluate clinical trial eligibility.

Background:The THBS gene family plays key functions in various diseases; however, its specific roles in colorectal cancer (CRC) have not been systematically characterized.Methods:Multi-omics data and online databases were used to analyze the mRNA expression levels of the THBS gene family in CRC and their correlations with clinicopathological features and survival. This analysis identified THBS3 as a potential oncogene closely linked with CRC progression. Then, the relationship between THBS3 expression and the immune landscape was assessed. Single-cell RNA sequencing analyzed THBS3 distribution in CRC subtypes. Additionally, GO, KEGG, and GSEA enrichment analyses investigated the mechanisms of THBS3 in CRC. Molecular docking identified anticancer compounds with high affinity for THBS3. Lastly, in vitro experiments examined THBS3’s function in CRC.Results:THBS3 was significantly upregulated in CRC and correlated with poor prognosis. Elevated THBS3 correlated with increased infiltration of M2 macrophages and regulatory T cells (Treg cells), as well as higher expression of immune checkpoint molecules, suggesting its role in shaping an immunosuppressive microenvironment. THBS3 promoted CRC cell proliferation and metastasis, through activation of the PI3K-AKT and EMT pathways.Conclusion:THBS3 facilitates the progression of CRC and may serve as a novel prognostic biomarker and therapeutic target.

This study systematically reviews and evaluates published research on machine learning models that integrate histopathology whole slide images and high-throughput -omic data to predict overall survival in cancer. A comprehensive search of PubMed, EMBASE, and Cochrane CENTRAL was conducted through August 12, 2024, with citation screening for additional studies. Eligible studies applied machine learning or deep learning methods to multimodal data combining pathology images and -omics. Data extraction followed the CHARMS checklist, and risk of bias was assessed using the PROBAST + AI tool. Narrative synthesis was conducted in line with PRISMA 2020 guidelines. Forty-eight studies published since 2017 met inclusion criteria, spanning 19 cancer types. All relied on The Cancer Genome Atlas dataset. Modelling approaches included regularised Cox regression (n = 4), classical machine learning (n = 13), and deep learning (n = 31). Reported concordance indices ranged from 0.550 to 0.857, with most multimodal models outperforming unimodal counterparts. However, all studies were assessed as having high or unclear risk of bias-most often due to limited external validation, insufficient reporting, and minimal assessment of clinical utility. This review highlights a rapidly evolving yet methodologically underdeveloped field. While model performance is promising, improvements in data standardisation, reporting practices, and real-world contextualisation are critical for clinical translation. This work was funded by the National Pathology Imaging Cooperative (NPIC), supported by UK Research and Innovation (Project no. 104687).

Background and Objectives:Next-generation sequencing (NGS) is transforming clinical diagnostics by enabling the detection of genetic variation with unprecedented precision. However, successful implementation of NGS workflows necessitates stringent quality control. This study introduces Molecular Genetics Dashboard (MGDB), a novel bioinformatics tool designed to enhance quality control in clinical NGS workflows.Methods:Using the Python dash framework for visualizations and MySQL databases, we have developed a novel tool for variant-level monitoring of clinical NGS sequencing runs. MGDB uses a docker-compose containerization for improved portability and can flexibly include or exclude samples from accumulated statistics with notes from interpreters.Results:MGDB facilitates variant-level run-to-run monitoring, ensuring the consistency of variant detection across sequencing cycles. The tool provides an interactive platform for visualizing and assessing variant data, identifying potential inconsistencies or outliers and improving data management and interpretation compared to traditional methods. MGDB was tested using samples sequenced with Oncomine Focus/Comprehensive Plus assays on S5 sequencers and analyzed via IonReporter software.Conclusions:MGDB offers a robust and user-friendly solution for enhancing quality control in clinical NGS workflows, contributing to greater accuracy and reliability in variant detection. The tool is freely available on GitHub: https://github.com/acri-nb/GeneticVariantsDB.

Hepatocellular carcinoma (HCC) is the most common primary liver cancer mainly caused by hepatitis viral infection. Early stage diagnosis is still challenging due to its asymptomatic behavior so there is an urgent need for effective biomarkers. This study aimed to identify effective diagnostic biomarker or therapeutic target for HCC. Label-free quantitative mass spectrometry was performed to analyze protein expression in HCC and control tissues. Protein-protein interaction (PPI) analysis was done using the STRING database and hub proteins were identified by Cytohubba. The survival analysis and expressions profiling of hub proteins were performed by using GEPIA. Functional and pathway enrichment analysis were carried out using Gene Ontology (GO) and Kyoto Encyclopedia of Gene and Genome (KEGG). A total of 1539 proteins were identified, of which 116 were differentially expressed proteins (DEPs). PPI network analysis revealed 10 hub proteins; EGFR, GAPDH, HSP90AA1, MMP9, PTPRC, CD44, ANXA5, PECAM1, MMP2, and CDK1. Among these, GAPDH, MMP9, ANXA5, HSP90AA1, and CDK1 were significantly associated with low survival rate (p ⩽ .05). Moreover, MMP9 and CDK1 were showed significantly increased expression in tumor tissues as compared to control (p ⩽ .05). The GO analysis based on biological process, cellular components and molecular function indicated that DEPs were enriched in stress response, vesicle and extracellular space, protein binding and enzyme activity. The KEGG pathway analysis showed that the thyroid hormone synthesis pathway is the most enriched. The hub proteins GAPDH, HSP90AA1, MMP9, ANXA5, and CDK1 demonstrated significant prognostic potential, could be used as promising theragnostic biomarkers for HCC.

Objectives:Immunogenic cell death (ICD) has been demonstrated to play a critical role in the development and progression of malignant tumors by modulating the anti-tumor immune response. However, its function in cervical cancer (CC) remains largely unexplored. In this study, we aimed to construct an ICD-related gene signature to predict patient prognosis and immune cell infiltration in CC.Methods:The gene expression profiles and clinical data of CC were downloaded from The Cancer Genome Alas (TCGA) and Gene Expression Omnibus (GEO) datasets, serving as the training and testing groups, respectively. An ICD-related gene signature was developed using the LASSO-Cox model. The expression levels of the associated ICD-related genes were evaluated using single-cell data, CC cell lines, and clinical samples in vitro.Results:Two ICD-associated subtypes (cluster 1 and cluster 2) were identified through consensus clustering. Patients classified into cluster 2 demonstrated higher levels of immune cell infiltration and exhibited a more favorable prognosis. Subsequently, an ICD-related gene signature comprising 3 genes (IL1B, IFNG, and FOXP3) was established for CC. Based on the median risk score, patients in both training and testing cohorts were segregated into high-risk and low-risk groups. Further analyses indicated that the estimated risk score functioned as an independent prognostic factor for CC and influenced immune cell abundance within the tumor microenvironment. The up-regulation of the identified ICD-related genes was further validated in CC cell lines and collected clinical samples.Conclusion:In summary, the stratification based on ICD-related genes demonstrated strong efficacy in predicting patient prognosis and immune cell infiltration, which also provides valuable new perspectives for the diagnosis and prognosis of CC.

Objective:Breast cancer is one of the most prominent and deadly diseases in the world, and its prognosis varies widely based on the expression of certain genes. Identification of these genes is important for developing and interpreting clinical prognostic tests as well as furthering our understanding of breast cancer biology. We expand on prior efforts in the field toward identifying prognostic genes, by integrating powerful statistical methods.Methods:To this end, we use an unsupervised random forest model, which allows for robust learning of non-linear gene expression/survival relationships and the ability to identify the most important genes affecting both positive and negative breast cancer prognosis. In total, 1,518 participants were considered from the METABRIC dataset, using 20,387 mRNA expression level variables and 23 clinical variables including HER2 mutation status. The top 250 & bottom 250 expressing genes and 6 clinical features were selected for the unsupervised random forest model.Results:Our research corroborates previous discoveries of 27 important prognostic genes while also identifying 3 genes as potentially novel prognostic factors. Based on gene ontology analysis, we additionally show that these genes have plausible connections to breast cancer biology that should be experimentally investigated.Conclusions:Here, we demonstrate the utility of the unsupervised random forest model over K-means clustering for identifying important genes in breast cancer.

Colorectal cancer (CRC) is a prevalent disease characterized by significant dysregulation of gene expression. Non-invasive tests that utilize microRNAs (miRNAs) have shown promise for early CRC detection. This study aims to determine the association between miRNAs and key genes in CRC. Two datasets (GSE106817 and GSE23878) were extracted from the NCBI Gene Expression Omnibus database. Penalized logistic regression (PLR) and artificial neural networks (ANN) were used to identify relevant miRNAs and evaluate the classification accuracy of the selected miRNAs. The findings were validated through bipartite miRNA-mRNA interactions. Our analysis identified 3 miRNAs: miR-1228, miR-6765-5p, and miR-6787-5p, achieving a total accuracy of over 90%. Based on the results of the mRNA-miRNA interaction network, CDK1 and MAD2L1 were identified as target genes of miR-6787-5p. Our results suggest that the identified miRNAs and target genes could serve as non-invasive biomarkers for diagnosing colorectal cancer, pending laboratory confirmation.

ObjectiveS:This study examined prescription NSAIDs as one of the leading predictors of incident depression and assessed the direction of the association among older cancer survivors with osteoarthritis.Methods:This study used a retrospective cohort (N = 14, 992) of older adults with incident cancer (breast, prostate, colorectal cancers, or non-Hodgkin’s lymphoma) and osteoarthritis. We used the longitudinal data from the linked Surveillance, Epidemiology, and End Results -Medicare data for the study period from 2006 through 2016, with a 12-month baseline and 12-month follow-up period. Cumulative NSAIDs days was assessed during the baseline period and incident depression was assessed during the follow-up period. An eXtreme Gradient Boosting (XGBoost) model was built with 10-fold repeated stratified cross-validation and hyperparameter tuning using the training dataset. The final model selected from the training data demonstrated high performance (Accuracy: 0.82, Recall: 0.75, Precision: 0.75) when applied to the test data. SHapley Additive exPlanations (SHAP) was used to interpret the output from the XGBoost model.Results:Over 50% of the study cohort had at least one prescption of NSAIDs. Nearly 13% of the cohort were diagnosed with incident depression, with the rates ranging between 7.4% for prostate cancer and 17.0% for colorectal cancer. The highest incident depression rate of 25% was observed at 90 and 120 cumulative NSAIDs days thresholds. Cumulative NSAIDs days was the sixth leading predictor of incident depression among older adults with OA and cancer. Age, education, care fragmentation, polypharmacy, and zip code level poverty were the top 5 predictors of incident depression.Conclusion:Overall, 1 in 8 older adults with cancer and OA were diagnosed with incident depression. Cumulative NSAIDs days was the sixth leading predictor with an overall positive association with incident depression. However, the association was complex and varied by the cumulative NSAIDs days.

The present study was the first comprehensive investigation of genetic mutation and expression levels of the p53 signaling genes in cutaneous melanoma through various genetic databases providing large datasets. The mutational landscape of p53 and its signaling genes was higher than expected, with TP53 followed by CDKN2A being the most mutated gene in cutaneous melanoma. Furthermore, the expression analysis showed that TP53, MDM2, CDKN2A, and TP53BP1 were overexpressed, while MDM4 and CDKN2B were under-expressed in cutaneous melanoma. Overall, TCGA data revealed that among all the other p53 signaling proteins, CDKN2A was significantly higher in both sun and non-sun-exposed healthy tissues than in melanoma. Likewise, MDM4 and TP53BP1 expressions were markedly greater in non-sun-exposed healthy tissues compared to other groups. However, CDKN2B expression was higher in the sun-exposed healthy tissues than in other tissues. In addition, various genes were expressed significantly differently among males and females. In addition, CDKN2A was highly expressed in the SK-MEL-30 skin cancer cell line, whereas, Immune cell type expression analysis revealed that the MDM4 was highly expressed in naïve B-cells. Furthermore, all six genes were significantly overexpressed in extraordinarily overweight or obese tumor tissues compared to healthy tissues. MDM2 expression and tumor stage were closely related. There were differences in gene expression across patient age groups and positive nodal status. TP53 showed a positive correlation with B cells, MDM2 with CD8+T cells, macrophages and neutrophils, and MDM4 with neutrophils. CDKN2A/B had a non-significant correlation with all six types of immune cells. However, TP53BP1 was positively correlated with all five types of immune cells except B cells. Only TP53, MDM2, and CDKN2A had a role in cutaneous melanoma-specific tumor immunity. All TP53 and its regulating genes may be predictive for prognosis. The results of the present study need to be validated through future screening, in vivo, and in vitro studies.