Computational and structural biotechnology journal最新文献

{"title":"Machine learning and gene network integration reveal prognostic subnetworks and biomarkers in pancreatic cancer.","authors":"Rana Salihoglu, Jesus Nieves, Gudrun Dandekar, Regina Ebert, Maximilian Rudert, Thomas Dandekar, Elena Bencurova","doi":"10.1016/j.csbj.2025.09.028","DOIUrl":"10.1016/j.csbj.2025.09.028","url":null,"abstract":"<p><strong>Background: </strong>Pancreatic cancer has a high mortality rate and lacks early detection markers. Advanced methods, such as machine learning (ML) and network analysis, identify central cancer networks with potential diagnostic and prognostic biomarkers, leading to improved tumor targeting strategies<b>.</b></p><p><strong>Methods: </strong>We systematically collected pancreatic cancer transcriptome datasets from the databases TCGA, GTEx, and GEO. Weighted gene co-expression network analysis (WGCNA) identified gene modules associated with clinical traits. Multiple machine learning-based feature selection methods (Random Forest, Support Vector Machine, LASSO, ReliefF) and differential gene expression (DGE) analysis prioritized candidate genes. Functional enrichment (Gene Ontology and KEGG pathway database) examined biological processes involved in tumor progression and immune evasion. Survival analyses evaluated prognostic significance.</p><p><strong>Results: </strong>WGCNA identified pancreatic cancer networks from key gene modules strongly associated with cancer stage and survival. Common biomarkers, including transcripts from genes <i>ANLN</i>, <i>GPRC5A</i>, <i>KLF6</i>, <i>MUC1</i>, and <i>PHF20</i>, demonstrated significant diagnostic and prognostic potential as shown by ML, WGCNA, DGE, and survival analyzes. <i>In vitro</i> validation was performed for proteins mucin1 and CD44 in patient samples and tissue models.</p><p><strong>Conclusion: </strong>This study identified novel regulatory cancer networks and associated biomarkers for pancreatic cancer prognosis and diagnosis by integrating WGCNA with ML, DGE, pathway, and survival analyses. An interactive web portal to explore the full results and visualizations is available at pc-biomarkers.de. Future work will further validate these biomarkers to improve early detection, prognosis, and treatment strategies.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4151-4162"},"PeriodicalIF":4.1,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12495057/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DrugForm-DTA: Towards real-world drug-target binding affinity model.","authors":"Ivan Khokhlov, Anna Tashchilova, Nikolai Bugaev-Makarovskiy, Olga Glushkova, Vladimir Yudin, Anton Keskinov, Sergey Yudin, Dmitry Svetlichnyy, Veronika Skvortsova","doi":"10.1016/j.csbj.2025.09.023","DOIUrl":"10.1016/j.csbj.2025.09.023","url":null,"abstract":"<p><p>Drug-target affinity (DTA) prediction is a fundamental challenge in drug discovery. Computational methods for predicting DTA can greatly assist drug design by narrowing the search space and reducing the number of protein-ligand complexes with low affinity. Currently DTA approaches often do not require three-dimensional (3D) structural information of proteins, which is frequently unavailable. In this study we present the DrugForm-DTA model, which uses only structure-less representations of ligand and protein. It is a Transformer-based neural network with protein encoding based on ESM-2, and small molecule ligand encoding obtained with Chemformer. We evaluated the model on the standard benchmarks Davis and KIBA, and revealed superior performance of DrugForm-DTA with the best result for KIBA. Moreover, we developed a ready-to-use model trained on the BindingDB dataset which was subjected to high-quality filtering and transformation. Overall, our method predicts drug-target affinity values with a confidence level comparable to that of a single <i>in vitro</i> experiment. Also, we compared DrugForm-DTA against molecular modeling methods and revealed higher efficacy of the developed model for drug-target affinity predictions. Our investigation provides a high accuracy neural network model with performance comparable to that of experimental measurements, a filtered.and reassessed BindingDB dataset for further usage, and demonstrates the outstanding applicability of the proposed method for DTA prediction.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4106-4120"},"PeriodicalIF":4.1,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12495441/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A miRNA signature linked to high lipoprotein (a) and coronary calcification in familial hypercholesterolaemia.","authors":"Rafael Escate, Juan F Sánchez Muñoz-Torrero, Marta Mauri, Pedro Mata, Lina Badimon, Teresa Padro","doi":"10.1016/j.csbj.2025.09.026","DOIUrl":"10.1016/j.csbj.2025.09.026","url":null,"abstract":"<p><strong>Background: </strong>High lipoprotein(a) [Lp(a)] levels are associated with increased coronary artery calcification (CAC) in familial hypercholesterolaemia (FH) patients. However, mechanisms linking high Lp(a) with CAC remain poorly understood. In this study, we have performed a bioinformatics and system biology analysis to identify miRNAs and their target genes involved in Lp(a)-associated atherosclerotic lesion and coronary calcification in FH patients.</p><p><strong>Methods: </strong>Patients with a genetic diagnosis of FH (<i>n</i> = 24) from the SAFEHEART were included in the study. Plasma miRNA signature was obtained using Affymetrix miRNA microarrays from patients with FH grouped using an Lp(a) cut-off of (>50 mg/dL) and presence or absence of coronary artery calcification [CCS(+) or CCS(-)]. <i>In silico</i> analyses were performed to identify potential miRNA target genes.</p><p><strong>Results: </strong>Forty-two miRNAs had > 1.5-fold difference in their detection levels when grouped by Lp(a) [FH-Lp(a)> 50 (<i>n</i> = 9) <i>vs</i> FH-Lp(a)< 50 (<i>n</i> = 15)]. Among these, 9 miRNAs were associated with CCS(+) (miR-1228-5p, miR-3940-5p, miR-1237-5p, miR-3196, miR-6765-5p, miR-6786-5p, miR-4486, miR-6821-5p and miR-1908-5p). <i>In silico</i> analysis, identified 68 target genes of these 9 miRNAs in lipid and atherosclerosis pathways (KEGG code: hsa05417). Network analysis revealed seven target genes (AKT3, APAF1, BCL2L1, TRAF6, MYD88, STAT3, and CASP9) with stronger interactions and higher binding probability for the nine-miRNA signature, mainly linked to lipid metabolism, inflammation and calcification processes.</p><p><strong>Conclusion: </strong>Our results identify a miRNA signature that regulates atherosclerotic processes associated with high Lp(a) levels and CAC in asymptomatic FH patients. These findings offer new insights into the underlying mechanisms and highlight potential therapeutic targets.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4096-4105"},"PeriodicalIF":4.1,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481025/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145205648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ASOG: AntiSense Oligonucleotide Generator.","authors":"Jonah Kimi, Patricia Korczak, Brune Vialet, Eric Roubin, Philippe Barthélémy, Sébastien Campagne, Florian Malard","doi":"10.1016/j.csbj.2025.09.022","DOIUrl":"10.1016/j.csbj.2025.09.022","url":null,"abstract":"<p><p>Antisense oligonucleotides (ASOs) are used in both fundamental research and clinical applications to modulate gene expression by targeting the RNA transcript of specific genes. Historically, ASOs were designed manually, a time-consuming process that limited exhaustive searches through the ASO space. More recently, resources have been developed based on traditional or deep learning approaches to facilitate ASO design, each with their specific use cases and limitations. In this context, we propose an original and generalistic pipeline for ASO design, based on explicit criteria, original algorithms, and third-party software, encapsulated in a web application we named AntiSense Oligonucleotide Generator (ASOG). The ASOG pipeline requires only a target gene sequence as input, and it proceeds with ASO generation, predicts the structural properties of target subsequences, predicts splice site masking, detects off-target effects, and computes thermodynamic hybridization parameters, taking into account some of the most common RNA modifications. ASOG is designed to enable users to quickly navigate the ASO space, assisting them in making informed decisions. The ASOG webserver is available at asog.iecb.u-bordeaux.fr.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4145-4150"},"PeriodicalIF":4.1,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12493213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231476","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cyanobacteriochrome-like GAF folds in phages revealed via AlphaFold proteomic modelling.","authors":"Isaac Meza-Padilla, Andrew C Doxey, Jozef I Nissimov","doi":"10.1016/j.csbj.2025.09.020","DOIUrl":"10.1016/j.csbj.2025.09.020","url":null,"abstract":"<p><p>Accurate protein structure prediction followed by structural homology detection enable the functional annotation of otherwise obscure viral protein-coding genes. Here we employ AlphaFold proteomic modelling and structural homology searches on the genome of CrV-01T, a representative freshwater cyanophage, to reveal previously unknown structural homologs. One of these cryptic viral proteins is found to be a cyanobacteriochrome-like GAF fold (CGF) protein. Cyanobacteriochromes (CBCRs) are known to regulate phototaxis, cyclic nucleotide metabolism and optimization of light harvesting in cyanobacteria. Phylogenetic analyses indicate that the CGF protein of CrV-01T was probably acquired from a cyanobacterial host. We then use experimentally determined CBCR structures to query the Big Fantastic Virus Database and discover that CGFs are present among many different bacteriophages. The GAF domain sequence, which is a hallmark of CBCRs, can still be detected in some of these divergent viral proteins. Remarkably, viral CGF proteins harbor an N-terminal extension that in most cases is predicted to contain a transmembrane α-helix, indicating that they may bind the host membrane after being synthesized in the virocell. The presence of CGF protein-coding genes in cyanophage genomes suggests novel ways in which viruses may manipulate the metabolism of cyanobacteria, the most abundant oxygenic phototrophs on Earth. Overall, the findings reported here emphasize the importance of applying structural homology detection methods when annotating viral genomes and highlight the potential of AlphaFold for exploring the dark matter of the aquatic virosphere.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4089-4095"},"PeriodicalIF":4.1,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481020/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145205623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"iComBat: An incremental framework for batch effect correction in DNA methylation array data.","authors":"Yui Tomo, Ryo Nakaki","doi":"10.1016/j.csbj.2025.09.014","DOIUrl":"10.1016/j.csbj.2025.09.014","url":null,"abstract":"<p><p>DNA methylation is associated with various diseases and aging; thus, longitudinal and repeated assessments of methylation patterns are crucial for revealing the mechanisms of disease onset and identifying factors associated with aging. The presence of batch effects influences the analysis of DNA methylation array data. As existing methods for correcting batch effects are designed to correct all samples simultaneously, when data are incrementally measured and included, the correction of newly added data affects previous data. Therefore, we propose an incremental framework for batch-effect correction based on ComBat, a location/scale adjustment approach using a Bayesian hierarchical model, and empirical Bayes estimation. Using numerical experiments and application to actual data, we demonstrate that the proposed method can correct newly included data without re-correcting the old data. The proposed method is expected to be useful for studies involving repeated measurements of DNA methylation, such as clinical trials of anti-aging interventions.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4121-4131"},"PeriodicalIF":4.1,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12495439/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discovery of diverse chimeric peptides in a eukaryotic proteome sets the stage for experimental validation of the mosaic translation hypothesis.","authors":"Umut Çakır, Noujoud Gabed, Yunus Emre Köroğlu, Selen Kaya, Senjuti Sinharoy, Vagner A Benedito, Marie Brunet, Xavier Roucou, Igor S Kryvoruchko","doi":"10.1016/j.csbj.2025.09.019","DOIUrl":"10.1016/j.csbj.2025.09.019","url":null,"abstract":"<p><p>The high complexity of eukaryotic organisms enabled their evolutionary success, driven by the diversification of their proteomes. Various mechanisms contributed to this process. Alternative splicing had the largest known impact among these mechanisms. Earlier, we hypothesized that along with alternative splicing, a different but conceptually similar mechanism creates novel versions of existing proteins in all eukaryotes. However, this mechanism operates at the level of translation, where amino acid sequence novelty arises through multiple programmed ribosomal frameshifting events occurring within the same transcript. This mechanism, which is termed mosaic translation, is very difficult to demonstrate even with the most up-to-date molecular tools. Thus, it remained unnoticed so far. Using a subset of mass spectrometry proteomic data from various organs of the model plant <i>Medicago truncatula</i>, we took the first step toward experimental validation of this hypothesis. Our original <i>in silico</i> approach resulted in the discovery of two candidates for mosaic proteins (homologs of EF1α and RuBisCo) and 154 candidates for chimeric peptides. Chimeric peptides and polypeptides are produced in the course of one ribosomal frameshifting event and may correspond to parts of mosaic proteins. In addition, our analysis reveals the possibility of translation of chimeric peptides from five ribosomal RNA transcripts, ten long non-coding RNA transcripts, and one transfer RNA transcript. These findings are novel and will form the basis for future experimental validation. We also present multiple lines of indirect evidence supporting the validity of our <i>in silico</i> data.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4048-4064"},"PeriodicalIF":4.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481079/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145205640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DrugDomain 2.0: Comprehensive database of protein domains-ligands/drugs interactions across the whole Protein Data Bank.","authors":"Kirill E Medvedev, R Dustin Schaeffer, Nick V Grishin","doi":"10.1016/j.csbj.2025.09.018","DOIUrl":"10.1016/j.csbj.2025.09.018","url":null,"abstract":"<p><p>Proteins carry out essential cellular functions - signaling, metabolism, transport - through the specific interaction of small molecules and drugs within their three-dimensional structural domains. Protein domains are conserved folding units that, when combined, drive evolutionary progress. The Evolutionary Classification Of protein Domains (ECOD) places domains into a hierarchy explicitly built around distant evolutionary relationships, enabling the detection of remote homologs across the proteomes. Yet no single resource has systematically mapped domain-ligand interactions at the structural level. To fill this gap, we introduce DrugDomain v2.0, an updated comprehensive resource, that extends earlier releases by linking evolutionary domain classifications (ECOD) to ligand binding events across the entire Protein Data Bank. We also leverage AI-driven predictions from AlphaFold to extend domain-ligand annotations to human drug targets lacking experimental structures. DrugDomain v2.0 catalogs interactions with over 37,000 PDB ligands and 7560 DrugBank molecules, integrates more than 6000 small-molecule-associated post-translational modifications, and provides context for 14,000 + PTM-modified human protein models featuring docked ligands. The database encompasses 43,023 unique UniProt accessions and 174,545 PDB structures. The DrugDomain data is available online: https://drugdomain.cs.ucf.edu/ and https://github.com/kirmedvedev/DrugDomain.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4040-4047"},"PeriodicalIF":4.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12475577/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145184821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational epitope profiling and AI-driven protein engineering enable rational design of multi-epitope vaccines against <i>Mycobacterium tuberculosis</i>.","authors":"Xinfeng Li, Xinyu Tao, Mingyue Zhong, Yiyao Wang, Heng Xue, Binda T Andongma, Shan-Ho Chou, Hongping Wei, Jin He, Hang Yang","doi":"10.1016/j.csbj.2025.09.015","DOIUrl":"10.1016/j.csbj.2025.09.015","url":null,"abstract":"<p><p>Tuberculosis (TB), caused by <i>Mycobacterium tuberculosis</i> (Mtb), remains a major global health threat, accounting for approximately 1.5 million deaths annually. The rise of antibiotic-resistant strains further complicates treatment efforts. While vaccination is a cornerstone of disease control, the only licensed TB vaccine, Bacille Calmette-Guérin (BCG), shows limited efficacy in adults. There is thus a critical need for more effective vaccines. Multi-epitope vaccines, which incorporate key epitopes from multiple antigens, offer a promising strategy by eliciting both humoral and cellular immunity. Here, we employed a comparative epitopomics approach to identify immunodominant epitopes from eight major Mtb antigens and selected 17 potent epitopes for the design of a multi-epitope antigen. Using AI-driven protein design, we systematically optimized epitope arrangement and flanking sequences to generate a stable, structurally integrated antigen-MtbEpi-17. Computational analyses suggest that MtbEpi-17 can effectively interact with TLR2 and TLR4, potentially stimulating robust innate and adaptive immune responses. Our study provides a rational design framework for multi-epitope vaccines, and proposes MtbEpi-17 as a strong candidate for further preclinical and clinical evaluation.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4065-4077"},"PeriodicalIF":4.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481023/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145205712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"<i>In-silico</i> assessment of dynamic symbiotic microbial interactions in a reduced microbiota related to the autism spectrum disorder symptoms.","authors":"Juan Manuel Olaguez-Gonzalez, Isaac Chairez, Luz Breton-Deval, Mariel Alfaro-Ponce","doi":"10.1016/j.csbj.2025.09.006","DOIUrl":"10.1016/j.csbj.2025.09.006","url":null,"abstract":"<p><p>The gut microbiota plays a crucial role in human health, with growing evidence linking its composition to the development of Autism Spectrum Disorder. However, inconsistencies in previous studies have hindered the identification of a definitive microbial signature associated with Autism Spectrum Disorder. Machine learning models have emerged as powerful tools for analyzing microbiome data, yet their interpretability remains limited. In this study, we integrate <i>in silico</i> simulations with machine learning predictions to explore microbial interactions under different dietary conditions and provide biological context to features of the intestinal microbiota that are linked to Autism Spectrum Disorder. This study employs constraint-based modeling to simulate metabolic exchanges among key bacterial taxa in order to assess their ecological relationships. Findings reveal that high-fiber diets foster mutualistic and balanced interactions, whereas Western-style diets promote competitive and parasitic dynamics, potentially contributing to gut dysbiosis in Autism Spectrum Disorder. In addition, the presence of oxygen (a factor associated with colonocyte permeability, a pathological condition of the colon) significantly alters microbial interactions, influencing metabolic dependencies and the overall structure of the community. This integrative approach enhances the interpretability of machine learning-based Autism Spectrum Disorder classifiers, bridging computational predictions with mechanistic insights. By identifying diet-dependent microbial interactions, our study highlights potential dietary interventions to modulate the composition of the gut microbiota in Autism Spectrum Disorder. These findings underscore the value of combining <i>in silico</i> modeling and machine learning for unraveling complex microbiome-host relationships and improving Autism Spectrum Disorder biomarker identification.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4078-4088"},"PeriodicalIF":4.1,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12481116/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145205688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}