BEST: a web application for comprehensive biomarker exploration on large-scale data in solid tumors

Journal Of Big Data, Journal Year: 2023, Volume and Issue: 10(1)

Published: Nov. 1, 2023

Abstract Data mining from RNA-seq or microarray data has become an essential part of cancer biomarker exploration. Certain existing web servers are valuable and broadly utilized, but the meta-analysis multiple datasets is absent. Most only contain tumor samples TCGA database with one cohort for each type, which also means that analysis results mainly derived a single thin unstable. Indeed, consistent performance across independent cohorts foundation excellent biomarker. Moreover, deeper exploration specific biomarkers on underlying mechanisms, microenvironment, drug indications missing in tools. Thus, we introduce BEST (Biomarker Exploration Solid Tumors), application comprehensive large-scale solid tumors. To ensure comparability genes between different sequencing technologies legibility clinical traits, re-annotated transcriptome unified nomenclature traits. delivers fast customizable functions, including association, survival analysis, enrichment cell infiltration, immunomodulator, immunotherapy, candidate agents, genomic alteration. Together, our server provides cleaned-up diverse functionalities, helping unleash value current resources. It freely available at https://rookieutopia.com/ .

Language: Английский

---

Integrated machine learning survival framework develops a prognostic model based on inter-crosstalk definition of mitochondrial function and cell death patterns in a large multicenter cohort for lower-grade glioma

Journal of Translational Medicine, Journal Year: 2023, Volume and Issue: 21(1)

Published: Sept. 2, 2023

Abstract Background Lower-grade glioma (LGG) is a highly heterogeneous disease that presents challenges in accurately predicting patient prognosis. Mitochondria play central role the energy metabolism of eukaryotic cells and can influence cell death mechanisms, which are critical tumorigenesis progression. However, prognostic significance interplay between mitochondrial function LGG requires further investigation. Methods We employed robust computational framework to investigate relationship 18 patterns cohort 1467 patients from six multicenter cohorts worldwide. A total 10 commonly used machine learning algorithms were collected subsequently combined into 101 unique combinations. Ultimately, we devised mitochondria-associated programmed index (mtPCDI) using models exhibited optimal performance. Results The mtPCDI, generated by combining influential genes, demonstrated strong predictive performance for prognosis patients. Biologically, mtPCDI significant correlation with immune metabolic signatures. high group enriched pathways heightened activity profile. Of particular importance, our maintains its status as most potent indicator even following adjustment potential confounding factors, surpassing established clinical strength. Conclusion Our utilization highlights providing personalized risk assessment tailored recommendations immunotherapy interventions individuals diagnosed LGG. significance, signature features genes present prospects future investigations PCD within function.

Language: Английский

---

Integrated multiomics analysis and machine learning refine molecular subtypes and prognosis for muscle-invasive urothelial cancer

Molecular Therapy — Nucleic Acids, Journal Year: 2023, Volume and Issue: 33, P. 110 - 126

Published: June 5, 2023

Muscle-invasive urothelial cancer (MUC), characterized by high aggressiveness and significant heterogeneity, is currently lacking highly precise individualized treatment options. We used a computational pipeline to synthesize multiomics data from MUC patients using 10 clustering algorithms, which were then combined with machine learning algorithms identify molecular subgroups of resolution develop robust consensus learning-driven signature (CMLS). Through clustering, we identified three subtypes (CSs) that are related prognosis, CS2 exhibiting the most favorable prognostic outcome. Subsequent screening enabled identification 12 hub genes constitute CMLS predictive power for prognosis. The low-CMLS group exhibited more prognosis greater responsiveness immunotherapy was likely exhibit "hot tumor" phenotype. high-CMLS had poor lower likelihood benefitting immunotherapy, but dasatinib romidepsin may serve as promising treatments them. Comprehensive analysis can offer important insights further refine classification MUC. Identification represents valuable tool early prediction patient potential candidates benefit broad implications clinical practice.

Language: Английский

---

Leveraging mitochondrial-programmed cell death dynamics to enhance prognostic accuracy and immunotherapy efficacy in lung adenocarcinoma

Journal for ImmunoTherapy of Cancer, Journal Year: 2024, Volume and Issue: 12(10), P. e010008 - e010008

Published: Oct. 1, 2024

Lung adenocarcinoma (LUAD) is a highly heterogeneous disease, posing significant challenges to accurate prognosis prediction. Mitochondria play central role in the energy metabolism of eukaryotic cells and can influence programmed cell death (PCD) mechanisms, which are critical tumorigenesis cancer progression. However, prognostic significance interplay between mitochondrial function PCD LUAD requires further investigation.

Language: Английский

---

Comprehensive machine-learning survival framework develops a consensus model in large-scale multicenter cohorts for pancreatic cancer

eLife, Journal Year: 2022, Volume and Issue: 11

Published: Oct. 25, 2022

As the most aggressive tumor, outcome of pancreatic cancer (PACA) has not improved observably over last decade. Anatomy-based TNM staging does exactly identify treatment-sensitive patients, and an ideal biomarker is urgently needed for precision medicine. Based on expression files 1280 patients from 10 multicenter cohorts, we screened 32 consensus prognostic genes. Ten machine-learning algorithms were transformed into 76 combinations, which selected optimal algorithm to construct artificial intelligence-derived signature (AIDPS) according average C-index in nine testing cohorts. The results training cohort, Meta-Cohort, three external validation cohorts (290 patients) consistently indicated that AIDPS could accurately predict prognosis PACA. After incorporating several vital clinicopathological features 86 published signatures, exhibited robust dramatically superior predictive capability. Moreover, other prevalent digestive system tumors, nine-gene still stratify prognosis. Of note, our had important clinical implications PACA, with low owned a dismal prognosis, higher genomic alterations, denser immune cell infiltrates as well more sensitive immunotherapy. Meanwhile, high group possessed prolonged survival, panobinostat may be potential agent AIDPS. Overall, study provides attractive tool further guide management individualized treatment

Language: Английский

---

Stemness Refines the Classification of Colorectal Cancer With Stratified Prognosis, Multi-Omics Landscape, Potential Mechanisms, and Treatment Options

Frontiers in Immunology, Journal Year: 2022, Volume and Issue: 13

Published: Jan. 27, 2022

Stemness refers to the capacities of self-renewal and repopulation, which contributes progression, relapse, drug resistance colorectal cancer (CRC). Mounting evidence has established links between stemness intratumoral heterogeneity across cancer. Currently, intertumoral remains elusive in CRC.This study enrolled four CRC datasets, two immunotherapy a clinical in-house cohort. Non-negative matrix factorization (NMF) was performed decipher stemness. Multiple machine learning algorithms were applied develop nine-gene cluster predictor. The outcomes, multi-omics landscape, potential mechanisms, immune features clusters further explored.Based on 26 published signatures derived by alternative approaches, we heterogeneous clusters, low 1 (C1) high 2 (C2). C2 possessed higher proportion advanced tumors displayed worse overall survival relapse-free compared with C1. MSI-H CMS1 tended enrich C1, mesenchymal subtype CMS4 prevalent C2. Subsequently, developed predictor, robustly validated reproduced our three independent datasets an C1 also generally superior mutational burden, burden copy number deletion. Further investigations suggested that enriched numerous proliferation-related biological processes abundant infiltration, while significantly associated mesenchyme development differentiation. Given results from immunotherapeutic cohorts, observed could benefit more immunotherapy. For patients C2, constructed ridge regression model identified nine latent therapeutic agents, might improve their outcomes.This proposed stratified prognosis, treatment options. Current work not only provided new insights into stemness, but shed light optimizing decision-making chemotherapy.

Language: Английский

---

Necroptosis-related lncRNA signature predicts prognosis and immune response for cervical squamous cell carcinoma and endocervical adenocarcinomas

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Sept. 29, 2022

Necroptosis, a programmed form of necrotic cell death, plays critical regulatory roles in the progression and metastatic spread cancers such as cervical squamous carcinoma endocervical adenocarcinoma (CESC). However, there are few articles systematically analyzing necroptosis-related long non-coding RNAs (NRlncRNAs) correlated with CESC patients. Both RNA-sequencing clinical data patients downloaded from TCGA database this study. Pearson correlation analysis, least absolute shrinkage, operator algorithm selection Cox regression model employed to screen create risk score eleven-NRlncRNAs (MIR100HG, LINC00996, SNHG30, LINC02688, HCG15, TUBA3FP, MIAT, DBH-AS1, ERICH6-AS1SCAT1, LINC01702) prognostic. Thereafter, series tests carried out sequence evaluate for independent prognostic value. Gene set enrichment analytic paper, Ontology Kyoto Encyclopedia Genes Genomes pathway paper make it clear that immune-related signaling pathways very rich high-risk subgroup. Additionally, is immune infiltration, potential checkpoint, function, micro-environmental m6A-related gene. Mutation frequency mutated genes survival probability trend higher low-risk subgroup most test cases when compared This study constructs renewed eleven-NRlncRNAs, which may some contribution accurately predicting prognosis response patients, improve recognition optimize customized treatment regimens extent.

Language: Английский

---

Integrated analysis of multi-omics data for the discovery of biomarkers and therapeutic targets for colorectal cancer

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 155, P. 106639 - 106639

Published: Feb. 11, 2023

Language: Английский

---

Artificial Intelligence Applications in the Treatment of Colorectal Cancer: A Narrative Review

Clinical Medicine Insights Oncology, Journal Year: 2024, Volume and Issue: 18

Published: Jan. 1, 2024

Colorectal cancer is the third most prevalent worldwide, and its treatment has been a demanding clinical problem. Beyond traditional surgical therapy chemotherapy, newly revealed molecular mechanisms diversify therapeutic approaches for colorectal cancer. However, selection of personalized among multiple options become another challenge in era precision medicine. Artificial intelligence recently increasingly investigated This narrative review mainly discusses applications artificial patients. A comprehensive literature search was conducted MEDLINE, EMBASE, Web Science to identify relevant papers, resulting 49 articles being included. The results showed that, based on different categories data, can predict outcomes essential guidance information novel therapies, thus enabling individualized strategy Some frequently implemented machine learning algorithms deep frameworks have also employed long-term prognosis prediction patients with Overall, shows encouraging evaluation

Language: Английский

---

Identification of a 9-gene signature to enhance biochemical recurrence prediction in primary prostate cancer: A benchmarking study using ten machine learning methods and twelve patient cohorts

Cancer Letters, Journal Year: 2024, Volume and Issue: 588, P. 216739 - 216739

Published: Feb. 22, 2024

Language: Английский

---