Cancer Informatics最新文献

Objectives: The primary goal of this research is to develop treatment-related genomic predictive markers for non-small cell lung cancer by integrating various machine learning algorithms that recommends near-optimal individualized patient treatment for chemotherapy in an effort to maximize efficacy or minimize treatment-related toxicity. This research can contribute toward developing a more refined, accurate and effective therapy accounting for specific patient needs.

Methods: To accomplish our research goal, we implement ensemble learning algorithms, bagging with regularized Cox regression models and nonparametric tree-based models via Random Survival Forests. A comprehensive meta-database was compiled from the NCBI Gene Expression Omnibus data repository for lung cancer patients to capture and utilize complex genomic patterns that can predict treatment outcomes more accurately.

Results: The developed novel prediction algorithm demonstrates the ability to support complex clinical decision-making processes in the treatment of NSCLC. It effectively addresses patient heterogeneity, offering predictions that are both refined and personalized in improving the precision of chemotherapy regimens prescribed to the eligible patients.

Conclusion: This research should contribute substantial advancement of cancer treatments by improving the accuracy and efficacy of chemotherapy treatments for a targeted group of patients who need the right treatment. The integration of complex machine learning techniques with genomic data holds substantial potential to transform current cancer treatment paradigms by providing robust support in clinical decision-making.

Objectives: Under the classification of multicategory survival outcomes of cancer patients, it is crucial to identify biomarkers that affect specific outcome categories. The classification of multicategory survival outcomes from transcriptomic data has been thoroughly investigated in computational biology. Nevertheless, several challenges must be addressed, including the ultra-high-dimensional feature space, feature contamination, and data imbalance, all of which contribute to the instability of the diagnostic model. Furthermore, although most methods achieve accurate predicted performance for binary classification with high-dimensional transcriptomic data, their extension to multi-class classification is not straightforward.

Methods: We employ the One-versus-One strategy to transform multi-class classification into multiple binary classification, and utilize the overlapping group screening procedure with binary logistic regression to include pathway information for identifying important genes and gene-gene interactions for multicategory survival outcomes.

Results: A series of simulation studies are conducted to compare the classification accuracy of our proposed approach with some existing machine learning methods. In practical data applications, we utilize the random oversampling procedure to tackle class imbalance issues. We then apply the proposed method to analyze transcriptomic data from various cancers in The Cancer Genome Atlas, such as kidney renal papillary cell carcinoma, lung adenocarcinoma, and head and neck squamous cell carcinoma. Our aim is to establish an accurate microarray-based multicategory cancer diagnosis model. The numerical results illustrate that the new proposal effectively enhances cancer diagnosis compared to approaches that neglect pathway information.

Conclusions: We showcase the effectiveness of the proposed method in terms of class prediction accuracy through evaluations on simulated synthetic datasets as well as real dataset applications. We also identified the cancer-related gene-gene interaction biomarkers and reported the corresponding network structure. According to the identified major genes and gene-gene interactions, we can predict for each patient the probabilities that he/she belongs to each of the survival outcome classes.

This narrative review explores the burgeoning field of Artificial Intelligence (AI)-driven Breast Cancer (BC) survival prediction, emphasizing the transformative impact on patient care. From machine learning to deep neural networks, diverse models demonstrate the potential to refine prognosis accuracy and tailor treatment strategies. The literature underscores the need for clinician integration and addresses challenges of model generalizability and ethical considerations. Crucially, AI's promise extends to Low- and Middle-Income Countries (LMICs), presenting an opportunity to bridge healthcare disparities. Collaborative efforts in research, technology transfer, and education are essential to empower healthcare professionals in LMICs. As we navigate this frontier, AI emerges not only as a technological advancement but as a guiding light toward personalized, accessible BC care, marking a significant stride in the global fight against this formidable disease.

Objectives: Captopril is a commonly used therapeutic agent in the management of renovascular hypertension (high blood pressure), congestive heart failure, left ventricular dysfunction following myocardial infarction, and nephropathy. Captopril has been found to interact with proteins that are significantly associated with bladder cancer (BLCA), suggesting that it could be a potential medication for BLCA patients with concurrent hypertension.

Methods: DrugBank 5.0 was utilized to identify the direct protein targets (DPTs) of captopril. STRING was used to analyze the multiple protein interactions. TNMPlot was used for comparing gene expression in normal, tumor, and metastatic tissue. Then, docking with target proteins was done using Autodock. Molecular dynamics simulations were applied for estimate the diffusion coefficients and mean-square displacements in materials.

Results: Among all these proteins, MMP9 is observed to be an overexpressed gene in BLCA and its increased expression is linked to reduced survival in patients. Our findings indicate that captopril effectively inhibits both the wild type and common mutated forms of MMP9 in BLCA. Furthermore, the LCN2 gene, which is also overexpressed in BLCA, interacts with captopril-associated proteins. The overexpression of LCN2 is similarly associated with reduced survival in BLCA. Through molecular docking analysis, we have identified specific amino acid residues (Tyr179, Pro421, Tyr423, and Lys603) at the active pocket of MMP9, as well as Tyr78, Tyr106, Phe145, Lys147, and Lys156 at the active pocket of LCN2, with which captopril interacts. Thus, our data provide compelling evidence for the inhibitory potential of captopril against human proteins MMP9 and LCN2, both of which play crucial roles in BLCA.

Conclusion: These discoveries present promising prospects for conducting subsequent validation studies both in vitro and in vivo, with the aim of assessing the suitability of captopril for treating BLCA patients, irrespective of their hypertension status, who exhibit elevated levels of MMP9 and LCN2 expression.

Objectives: Aim of this study was to explore the immune-related lncRNAs having prognostic role and establishing risk score model for better prognosis and immunotherapeutic coherence for esophageal cancer (EC) patients.

Methods: To determine the role of immune-related lncRNAs in EC, we analyzed the RNA-seq expression data of 162 EC patients and 11 non-cancerous individuals and their clinically relevant information from the cancer genome atlas (TCGA) database. Bioinformatic and statistical analysis such as Differential expression analysis, co-expression analysis, Kaplan Meier survival analysis, Cox proportional hazards model, ROC analysis of risk model was employed.

Results: Utilizing a cutoff criterion (log2FC > 1 + log2FC < -1 and FDR < 0.01), we identified 3737 RNAs were significantly differentially expressed in EC patients. Among these, 2222 genes were classified as significantly differentially expressed mRNAs (demRNAs), and 966 were significantly differentially expressed lncRNAs (delncRNA). Through Pearson correlation analysis between differentially expressed lncRNAs and immune related-mRNAs, we identified 12 immune-related lncRNAs as prognostic signatures for EC. Notably, through Kaplan-Meier analysis on these lncRNAs, we found the low-risk group patients showed significantly improved survival compared to the high-risk group. Moreover, this prognostic signature has consistent performance across training, testing and entire validation cohort sets. Using ESTIMATE and CIBERSORT algorithm we further observed significant enriched infiltration of naive B cells, regulatory T cells resting CD4+ memory T cells, and, plasma cells in the low-risk group compared to high-risk EC patients group. On the contrary, tumor-associated M2 macrophages were highly enriched in high-risk patients. Additionally, we confirmed immune-related biological functions and pathways such as inflammatory, cytokines, chemokines response and natural killer cell-mediated cytotoxicity, toll-like receptor signaling pathways, JAK-STAT signaling pathways, chemokine signaling pathways significantly associated with identified IRlncRNA signature and their co-expressed immune genes. Furthermore, we assessed the predictive potential of the lncRNA signature in immune checkpoint inhibitors; we found that programed cell death ligand 1 (PD-L1; P-value = .048), programed cell death ligand 2 (PD-L2; P-value = .002), and T cell immunoglobulin and mucin-domain containing-3 (TIM-3; P-value = .045) expression levels were significantly higher in low-risk patients compared to high-risk patients.

Conclusion: We believe this study will contribute to better prognosis prediction and targeted treatment of EC in the future.

Background: Lysophosphatidic acid receptor 1 (LPAR1) has been identified as a biomarker in various cancer types. However, its biological function in papillary thyroid carcinoma (PTC) remains unknown.

Methods: LPAR1 was identified as a key regulator of epithelial-mesenchymal transition (EMT) in PTC cells through bioinformatics analysis of TCGA and GEO datasets. PPI analysis and correlation with immune infiltrates were also conducted. LPAR1 expression was evaluated using Gepia2 and GTEx, and miRNA target gene prediction was done with multiMiR. To assess the expression of LPAR1, we extracted total RNA from both the BCPAP cell line and the normal human thyroid epithelial cell line Nthy-ori 3-1. The levels of LPAR1 expression were then measured using quantitative real-time polymerase chain reaction (qRT-PCR) in the BCPAP cell line, with a comparison to the Nthy-ori 3-1 cell line.

Results: 1081 genes were upregulated, and 544 were downregulated compared to normal tissue. LPAR1 was identified as a key candidate by analyzing the TCGA and GEO datasets. PPI data analysis showed interactions with metastasis-related proteins. Functional enrichment analysis indicated involvement in signaling pathways like phospholipase D and actin cytoskeleton regulation. LPAR1 expression correlated positively with immune infiltrates such as CD4⁺ T cells, macrophages, neutrophils, and myeloid dendritic cells but negatively with B cells. Additionally, miR-221-5p was predicted to target LPAR1 in PTC. Furthermore, our experimental data demonstrated that LPAR1 was under-expressed in the PTC cell line compared to the nonmalignant one (P < .01).

Conclusion: LPAR1 suppresses metastasis and is linked to EMT, as evidenced by the decreased LPAR1 expression and increased miR-221-5p in PTC. This suggests its potential as a biomarker for diagnosis and prognosis and as a therapeutic target for EMT.

Background: Transcriptomics can reveal much about cellular activity, and cancer transcriptomics have been useful in investigating tumor cell behaviors. Patterns in transcriptome-wide gene expression can be used to investigate biological mechanisms and pathways that can explain the variability in patient response to cancer therapies.

Methods: We identified gene expression patterns related to patient drug response by clustering tumor gene expression data and selecting from the resulting gene clusters those where expression of cluster genes was related to patient survival on specific drugs. We then investigated these gene clusters for biological meaning using several approaches, including identifying common genomic locations and transcription factors whose targets were enriched in these clusters and performing survival analyses to support these candidate transcription factor-drug relationships.

Results: We identified gene clusters related to drug-specific survival, and through these, we were able to associate observed variations in patient drug response to specific known biological phenomena. Specifically, our analysis implicated 2 stem cell-related transcription factors, HOXB4 and SALL4, in poor response to temozolomide in brain cancers. In addition, expression of SNRNP70 and its targets were implicated in cetuximab response by 3 different analyses, although the mechanism remains unclear. We also found evidence that 2 cancer-related chromosomal structural changes may impact drug efficacy.

Conclusion: In this study, we present the gene clusters identified and the results of our systematic analysis linking drug efficacy to specific transcription factors, which are rich sources of potential mechanistic relationships impacting patient outcomes. We also highlight the most promising of these results, which were supported by multiple analyses and by previous research. We report these findings as promising avenues for independent validation and further research into cancer treatments and patient response.

Objectives: This study aims to introduce a prediction model based on a machine learning approach as an efficient solution for prediction purposes to better prognosis and increase CRC survival.

Methods: In the current retrospective study, we used the data of 1062 CRC cases to analyse and establish a prediction model for the 5-year CRC survival. The machine learning algorithms were used to develop prediction models, including random Forest, XG-Boost, bagging, logistic regression, support vector machine, artificial neural network, decision tree, and K-nearest neighbours.

Results: The current study revealed that the XG-Boost with AU-ROC of 0.906 and 0.813 for internal and external conditions gave us better insight into predictability and generalizability than other algorithms.

Conclusion: XG-Boost can be utilised as a knowledge source for implementing intelligent systems as an assistive tool for clinical decision-making in healthcare settings to improve prognosis and increase CRC survival through various clinical solutions that doctors can achieve.

Background: Ovarian cancer has brought serious threats to female health. CCAAT/enhancer binding proteins (C/EBPs) are key transcription factors involved in ovarian cancer. Therefore, comprehensive profiling C/EBPs in ovarian cancer is needed.

Methods: A comprehensive analysis concerning C/EBPs in ovarian cancer was performed. Firstly, detailed expression of C/EBP family members was integrally retrieved and then confirmed using immunohistochemistry. The regulatory effects and transcription regulatory functions of C/EBPs were studied by using regulatory network analysis and enrichment analysis. Using survival analysis, receiver operating characteristic curve analysis, and target-disease association analysis, the predictive prognostic value of C/EBPs on survival and drug responsiveness was systematically evaluated. The effects of C/EBPs on tumor immune infiltration were also assessed.

Results: Ovarian cancer tissues expressed increased CEBPA, CEBPB, and CEBPG but decreased CEBPD when compared with normal control tissues. The overall alteration frequency of C/EBPs in ovarian cancer was approaching 30%. C/EBP family members formed a reciprocal regulatory network involving carcinogenesis and had pivotal transcription regulatory functions. C/EBPs could affect survival of ovarian cancer and correlated with poor survival outcomes (OS: HR = 1.40, P = .0053 and PFS: HR = 1.41, P = .0036). Besides, expression of CEBPA, CEBPB, CEBPD, and CEBPE could predict platinum and taxane responsiveness of ovarian cancer. C/EBPs also affected immune infiltration of ovarian cancer.

Conclusions: C/EBPs were closely involved in ovarian cancer and exerted multiple biological functions. C/EBPs could be exploited as prognostic and predictive biomarkers in ovarian cancer.

Objective: Host immunogenetics (Human Leukocyte Antigen, HLA) play a critical role in the human immune response to melanoma, influencing both melanoma prevalence and immunotherapy outcomes. Beneficial outcomes hinge on the successful binding of epitopes of melanoma antigens to HLA Class I molecules for an effective engagement of cytotoxic CD8+ lymphocytes and subsequent elimination of the cancerous cell. This study evaluated the binding affinity and immunogenicity of HLA Class I to melanoma tumor antigens to identify alleles best suited to facilitate elimination of melanoma antigens.

Methods: In this study, we used freely available software tools to determine in silico the binding affinity and immunogenicity of 2462 reported HLA Class I alleles to all linear nonamer epitopes of 11 known antigens expressed in melanoma tumors (TRP2, S100, Tyrosinase, TRP1, PMEL(17), MAGE1, MAGE4, CTA, BAGE, GAGE/SSX2, Melan).

Results: We identified the following 9 HLA Class I alleles with very high immunogenicity and binding affinity against all 11 melanoma antigens: A*02:14, B*07:10, B*35:10, B*40:10, B*40:12, B*44:10, C*07:11, and C*07:13, and C*07:14.

Conclusion: These 9 HLA alleles possess the potential to aid in the elimination of melanoma both by themselves and by enhancing the beneficial effect of immune checkpoint inhibitors.