Cancer Informatics最新文献

Objectives: For prostate cancer (PCa), hundreds of risk variants have been identified. It remains unknown whether the polygenic risk score (PRS) that combines the effects of these variants is also a sufficiently informative metric with relevance to the molecular mechanisms of carcinogenesis in prostate. We aimed to understand the biological basis of PRS and racial disparities in the cancer.

Methods: We performed a comprehensive analysis of the data generated (deposited in) by several genomic and/or transcriptomic projects (databases), including the GTEx, TCGA, 1000 Genomes, GEO and dbGap. PRS was constructed from 260 PCa risk variants that were identified by a recent trans-ancestry meta-analysis and contained in the GTEx dataset. The dosages of risk variants and the multi-ancestry effects on PCa incidence estimated by the meta-analysis were used in calculating individual PRS values.

Results: The following novel results were obtained from our analyses. (1) In normal prostate samples from healthy European Americans (EAs), the expression levels of 540 genes (termed PRS genes) were associated with the PRS (P < .01). (2) Ubiquitin-proteasome system in high-PRS individuals' prostates was more active than that in low-PRS individuals' prostates. (3) Nine PRS genes play roles in the cancer progression-relevant parts, which are frequently hit by somatic mutations in PCa, of PI3K-Akt/RAS-MAPK/mTOR signaling pathways. (4) The expression profiles of the top significant PRS genes in tumor samples were capable of predicting malignant PCa relapse after prostatectomy. (5) The transcriptomic differences between African American and EA samples were incompatible with the patterns of the aforementioned associations between PRS and gene expression levels.

Conclusions: This study provided unique insights into the relationship between PRS and the molecular mechanisms of carcinogenesis in prostate. The new findings, alongside the moderate but significant heritability of PCa susceptibility contributed by the risk variants, suggest the aptness and inaptness of PRS for explaining PCa and disparities.

Image-based diagnosis has become a crucial tool in the identification and management of various cancers, particularly lung and colon cancer. This review delves into the latest advancements and ongoing challenges in the field, with a focus on deep learning, machine learning, and image processing techniques applied to X-rays, CT scans, and histopathological images. Significant progress has been made in imaging technologies like computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET), which, when combined with machine learning and artificial intelligence (AI) methodologies, have greatly enhanced the accuracy of cancer detection and characterization. These advances have enabled early detection, more precise tumor localization, personalized treatment plans, and overall improved patient outcomes. However, despite these improvements, challenges persist. Variability in image interpretation, the lack of standardized diagnostic protocols, unequal access to advanced imaging technologies, and concerns over data privacy and security within AI-based systems remain major obstacles. Furthermore, integrating imaging data with broader clinical information is crucial to achieving a more comprehensive approach to cancer diagnosis and treatment. This review provides valuable insights into the recent developments and challenges in image-based diagnosis for lung and colon cancers, underscoring both the remarkable progress and the hurdles that still need to be overcome to optimize cancer care.

Objectives: Patients with intermediate or advanced hepatocellular carcinoma (HCC) require repeated disease monitoring, prognosis assessment and treatment planning. In 2018, a novel machine learning methodology "survival path" (SP) was developed to facilitate dynamic prognosis prediction and treatment planning. One year after, a deep learning approach called Dynamic Deephit was developed. The performance of the two state-of-art models in dynamic prognostication have not been compared.

Methods: We trained and tested the SP and Dynamic DeepHit models in a large cohort of 2511 HCC patients using time-series data. The time-series data were converted into data of time slices, with an interval of three months. The time-dependent c-index for OS at given prediction time (t = 1, 6, 12, 18 months) and evaluation time (∆t = 3, 6, 9, 12, 18, 24, 36, 48 months) were compared.

Results: The comparison between SP model and Dynamic DeepHit-HCC model showed the latter had significant better performance at the time of initial admission. The time-dependent c-index of Dynamic DeepHit-HCC model gradually decreased with the extension of time (from 0.756 to 0.639 in the training set; from 0.787 to 0.661 in internal testing set; from 0.725 to 0.668 in multicenter testing set); while the time-dependent c-index of SP model displayed an increased trend (from 0.665 to 0.748 in the training set; from 0.608 to 0.743 in internal testing set; from 0.643 to 0.720 in multicenter testing set). When the prediction time comes to 6 months or later since initial treatment, the survival path model outperformed the dynamic DeepHit model at late evaluation times (∆t > 12 months).

Conclusions: This research highlighted the unique strengths of both models. The SP model had advantage in long term prediction while the Dynamic DeepHit-HCC model had advantages in prediction at near time points. Fine selection of models is needed in dealing with different scenarios.

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.