Machine learning-based investigation of the cancer protein secretory pathway

Biomarker Profile of Colorectal Cancer: Current Findings and Future Perspective

OBJECTIVE

Breakthroughs in omics technology have led to a deeper understanding of the fundamental molecular changes that play a critical role in the development and progression of cancer. This review delves into the hidden molecular drivers of colorectal cancer (CRC), offering potential for clinical translation through novel biomarkers and personalized therapies.

METHODS

We summarizes recent studies utilizing various omics approaches, including genomics, transcriptomics, proteomics, epigenomics, metabolomics and data integration with computational algorithms, to investigate CRC.

RESULTS

Integrating multi-omics data in colorectal cancer research unlocks hidden biological insights, revealing new pathways and mechanisms. This powerful approach not only identifies potential biomarkers for personalized prognosis, diagnosis, and treatment, but also predicts patient response to specific therapies, while computational tools illuminate the landscape by deciphering complex datasets.

CONCLUSIONS

Future research should prioritize validating promising biomarkers and seamlessly translating them into clinical practice, ultimately propelling personalized CRC management to new heights.

Identification of secretory pathway-related genes based on Random Forest algorithm to predict the prognosis and immunotherapy response of hepatocellular carcinoma

BACKGROUND

The dysfunction of secretory pathways may represent biomarkers or therapeutic targets of cancer. The hepatocellular carcinoma (HCC) phenotype was studied in relation to the genes in the secretory pathway and to screen for a combination of genes that may be a viable therapeutic target for HCC and connected to the pathophysiological features of the tumor.

METHODS

Using the HCC information from The Cancer Genome Atlas, somatic mutation and prognostic association analysis were performed on the secretory pathway genes. Based on prognostic genes in the secretory pathway, the samples were consensus clustered, and a Random Forest model was built. The clinical characteristics, tumor mutation burden, functional status and potential responses to immunotherapy and tumor suppressor medications of various subtypes and risk groups were discussed.

RESULTS

Of the 84 genes for secretory pathway, 32 were prognostic genes related to HCC, which divided HCC into two categories: C1 and C2. By comparing the two types of HCC samples, it was found that the survival outcome of C1 was inferior, with stronger adaptive and innate immunity, but less sensitive to immunotherapy than C2. The constructed prognostic signature included seven of the 32 prognostic genes in the secretory pathway, which showed significant correlation with the prognosis, somatic mutation, biological pathway status, potential response to immunotherapy and sensitivity of 72 tumor suppressor drugs from different HCC cohorts, and had a feasible prognostic effect for 31 types of cancer and immunotherapy cohorts.

CONCLUSIONS

In this study, HCC was divided into two molecular subtypes according to prognostic genes in the secretory pathway, and seven of them were combined into one signature, which produced significant results in evaluating the prognosis of different HCC cohorts, pan-cancer cohorts and immunotherapy cohorts, and had potential guiding significance for prophylactic immunotherapy in patients with HCC.

Machine learning-based approach for efficient prediction of diagnosis, prognosis and lymph node metastasis of papillary thyroid carcinoma using adhesion signature selection

The association between adhesion function and papillary thyroid carcinoma (PTC) is increasingly recognized; however, the precise role of adhesion function in the pathogenesis and prognosis of PTC remains unclear. In this study, we employed the robust rank aggregation algorithm to identify 64 stable adhesion-related differentially expressed genes (ARDGs). Subsequently, using univariate Cox regression analysis, we identified 16 prognostic ARDGs. To construct PTC survival risk scoring models, we employed Lasso Cox and multivariate + stepwise Cox regression methods. Comparative analysis of these models revealed that the Lasso Cox regression model (LPSRSM) displayed superior performance. Further analyses identified age and LPSRSM as independent prognostic factors for PTC. Notably, patients classified as low-risk by LPSRSM exhibited significantly better prognosis, as demonstrated by Kaplan-Meier survival analyses. Additionally, we investigated the potential impact of adhesion feature on energy metabolism and inflammatory responses. Furthermore, leveraging the CMAP database, we screened 10 drugs that may improve prognosis. Finally, using Lasso regression analysis, we identified four genes for a diagnostic model of lymph node metastasis and three genes for a diagnostic model of tumor. These gene models hold promise for prognosis and disease diagnosis in PTC.

Prostate cancer in omics era

Recent advances in omics technology have prompted extraordinary attempts to define the molecular changes underlying the onset and progression of a variety of complex human diseases, including cancer. Since the advent of sequencing technology, cancer biology has become increasingly reliant on the generation and integration of data generated at these levels. The availability of multi-omic data has transformed medicine and biology by enabling integrated systems-level approaches. Multivariate signatures are expected to play a role in cancer detection, screening, patient classification, assessment of treatment response, and biomarker identification. This review reports current findings and highlights a number of studies that are both novel and groundbreaking in their application of multi Omics to prostate cancer.

A p53 transcriptional signature in primary and metastatic cancers derived using machine learning

The tumor suppressor gene, TP53, has the highest rate of mutation among all genes in human cancer. This transcription factor plays an essential role in the regulation of many cellular processes. Mutations in TP53 result in loss of wild-type p53 function in a dominant negative manner. Although TP53 is a well-studied gene, the transcriptome modifications caused by the mutations in this gene have not yet been explored in a pan-cancer study using both primary and metastatic samples. In this work, we used a random forest model to stratify tumor samples based on TP53 mutational status and detected a p53 transcriptional signature. We hypothesize that the existence of this transcriptional signature is due to the loss of wild-type p53 function and is universal across primary and metastatic tumors as well as different tumor types. Additionally, we showed that the algorithm successfully detected this signature in samples with apparent silent mutations that affect correct mRNA splicing. Furthermore, we observed that most of the highly ranked genes contributing to the classification extracted from the random forest have known associations with p53 within the literature. We suggest that other genes found in this list including GPSM2, OR4N2, CTSL2, SPERT, and RPE65 protein coding genes have yet undiscovered linkages to p53 function. Our analysis of time on different therapies also revealed that this signature is more effective than the recorded TP53 status in detecting patients who can benefit from platinum therapies and taxanes. Our findings delineate a p53 transcriptional signature, expand the knowledge of p53 biology and further identify genes important in p53 related pathways.

Integrative Pan-Cancer Analysis of KIF15 Reveals Its Diagnosis and Prognosis Value in Nasopharyngeal Carcinoma

Background

KIF15 plays a vital role in many biological processes and has been reported to influence the occurrence and development of certain human cancers. However, there are few systematic evaluations on the role of KIF15 in human cancers, and the role of KIF15 in the diagnosis and prognosis of nasopharyngeal carcinoma (NPC) also remains unexplored. Therefore, this study aimed to conduct a pan-cancer analysis of KIF15 and evaluate its diagnostic and prognostic potential in NPC.

Methods

The expression pattern, prognostic value, molecular function, tumor mutation burden, microsatellite instability, and immune cell infiltration of KIF15 were examined based on public databases. Next, the diagnostic value of KIF15 in NPC was analyzed using the Gene Expression Omnibus (GEO) database and immunohistochemistry (IHC). Kaplan–Meier curves, Cox regression analyses, and nomograms were used to evaluate the effects of KIF15 expression on NPC prognosis. Finally, the effect of KIF15 on NPC was explored by in vitro experiments.

Results

The expression of KIF15 was significantly upregulated in 20 out of 33 cancer types compared to adjacent normal tissue. Kyoto Encyclopedia of Genes and Genomes enrichment (KEGG) analysis showed that KIF15 could participate in several cancer-related pathways. The increased expression level of KIF15 was correlated with worse clinical outcomes in many types of human cancers. Additionally, KIF15 expression was related to cancer infiltration of immune cells, tumor mutation burden, and microsatellite instability. In the analysis of NPC, KIF15 was significantly upregulated based on the GEO database and immunohistochemistry. A high expression of KIF15 was negatively associated with the prognosis of patients with NPC. A nomogram model integrating clinical characteristics and KIF15 expression was established, and it showed good predictive ability with an area under the curve value of 0.73. KIF15 knockdown significantly inhibited NPC cell proliferation and migration.

Conclusions

Our findings revealed the important and functional role of KIF15 as an oncogene in pan-cancer. Moreover, high expression of KIF15 was found in NPC tissues, and was correlated with poor prognosis in NPC. KIF15 may serve as a potential therapeutic target in NPC treatment.