Biodata Mining最新文献

{"title":"Automated candidate confounder scoping for adjustment in clinical research: a retrieval-augmented generation approach.","authors":"Jingjing Li, Kesong Wu, Xiao Wang, Ruolin Tao, Yinyao Ma, Hanlin Lv, Xueqian Zhao, Yu Lan, Lei Li, Lei Wang","doi":"10.1186/s13040-026-00562-0","DOIUrl":"10.1186/s13040-026-00562-0","url":null,"abstract":"<p><strong>Background: </strong>Identifying confounding variables is fundamental for robust observational studies, yet the traditional manual process is a time-consuming and subjective barrier for researchers. Recent advances in Retrieval-Augmented Generation (RAG) offer a promising solution, but most existing systems rely on full-text access, cloud-hosted APIs, or manually curated knowledge graphs, raising concerns about privacy, copyright, and computational cost, and making local deployment difficult.</p><p><strong>Objective: </strong>This study developed and evaluated a heuristic tool to scope candidate confounders for adjustment in observational studies. Using a locally deployed, abstract-only RAG architecture, our tool generates a traceable shortlist of candidate confounders from PICO (Population, Intervention, Comparison, Outcome) queries over medical abstracts.</p><p><strong>Methods: </strong>We implemented a three-stage architecture for PICO-based scoping of candidate confounder. The pipeline was deployed on an all-in-one local server and evaluated using 1,000 expert-curated PICO queries spanning 20 clinical specialties. Performance was assessed along four dimensions-internal consistency, output volume, efficiency, and clinical acceptance-by a multi-institutional clinician panel, and was compared with a graph-only SemMedDB baseline.</p><p><strong>Results: </strong>Across repeated runs, the pipeline showed high internal consistency (candidate confounder list consistency 94.6%±8.7%; PMID set consistency 79.4%±23.5%). It suggested a median of 6 candidate confounders (IQR 8) for adjustment and retrieved a median of 33 unique PMIDs (IQR 7) per query. Median processing time was 44.50 s (IQR 31.72). Expert review yielded an overall clinical acceptance rate of 87.12%.</p><p><strong>Conclusions: </strong>In an exploratory capacity, a locally deployed, abstract-only RAG workflow can generate clinically interpretable and traceable candidate confounder suggestions to support early-stage observational study design, particularly in settings with privacy constraints or limited access to full texts and cloud resources.</p><p><strong>Trial registration: </strong>NA.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13295572/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147960472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Coxmos: interpretable survival models for high-dimensional and multi-omic data.","authors":"Pedro Salguero, Anabel Buendía-Galera, Sonia Tarazona","doi":"10.1186/s13040-026-00559-9","DOIUrl":"10.1186/s13040-026-00559-9","url":null,"abstract":"<p><strong>Background: </strong>Survival analysis in high-dimensional (HD) and multi-block (MB) settings, such as omic and multi-omic studies, poses major methodological challenges due to multicollinearity, low events-per-variable ratios, and limited model interpretability. While Cox Proportional Hazards models remain widely used, their applicability is restricted in HD scenarios. Machine learning approaches can handle such complexity but often lack interpretability. Survival models based on Partial Least Squares (PLS) offer an attractive compromise, yet existing implementations provide limited support for model optimization, evaluation, and interpretation.</p><p><strong>Results: </strong>To overcome these limitations, we introduce Coxmos, a CRAN R package that integrates adapted Cox regression models with HD-adapted variable selection, and optimized PLS-based approaches tailored for HD and MB data. Coxmos also provides validation, comparison, interpretation, and visualization tools. Benchmarking on a diverse set of clinical, single-omic, and multi-omic cancer datasets - including breast (BRCA), head and neck (HNSC), and ovarian (HGSOC) cancer - demonstrated that Coxmos outperformed other state-of-the-art machine learning methods, while enhancing interpretability. We illustrated the package's functionalities through two case studies (HGSOC and HNSC), showing how Coxmos facilitates model selection, validation, and biological interpretation in a complex HD and MB survival analysis.</p><p><strong>Conclusions: </strong>Coxmos provides a robust, flexible, and interpretable solution for survival analysis in HD and MB data. By combining optimized PLS-based methodologies with rigorous evaluation and rich visualization tools, Coxmos enables reliable survival prediction and facilitates the identification of relevant risk and protective factors in complex biomedical studies. The package fills an important methodological gap and represents a valuable resource for reproducible and interpretable survival modeling in the big data scenario.</p><p><strong>Availability: </strong>Coxmos is available at CRAN repository: https://cran.r-project.org/web/packages/Coxmos .</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13352765/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147949993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: CancerHubs data Explorer: a web application for investigating mutation-enriched protein interaction hubs in human cancers.","authors":"Ivan Ferrari, Elisa Arsuffi, Stefano Biffo, Nicola Manfrini","doi":"10.1186/s13040-026-00557-x","DOIUrl":"10.1186/s13040-026-00557-x","url":null,"abstract":"","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"19 1","pages":""},"PeriodicalIF":6.1,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13162439/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147876525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive drift-aware multi-stage deep learning framework for EEG-based schizophrenia diagnosis.","authors":"Gran Badshah, Anurag Sinha, Himanshu Bansal, Yash Varshney, Omar Alqahtani, Ayushman Srivastava","doi":"10.1186/s13040-026-00560-2","DOIUrl":"10.1186/s13040-026-00560-2","url":null,"abstract":"<p><p>This study introduces a novel adaptive deep learning framework for EEG-based schizophrenia diagnosis that addresses the limitations of existing static classification models. Traditional approaches often fail to maintain diagnostic reliability when EEG signal distributions shift over time due to patient variability, electrode noise, medication effects, or session-based changes. To overcome these challenges, we propose a drift aware integrating deep feature learning, concept-drift detection, and sliding-window-based sensitivity analysis. The system combines convolutional neural representations with an adaptive drift-monitoring module that continuously evaluates temporal changes in EEG patterns using incremental windows. When drift is detected, the model autonomously updates its parameters, ensuring stable performance during long-term or real-world clinical deployment. A comprehensive SOTA evaluation was conducted using several advanced augmentation and enhancement methods, including SMOTE and data-driven signal transformations. Among the compared models, NEXUS achieved the highest accuracy (98.12%) and best mean rank (1.25), followed by HYPR-A and ZETA-G. The proposed adaptive drift-aware architecture demonstrated superior robustness, lower variance, and stronger generalization under non-stationary EEG conditions compared to conventional deep learning frameworks. These findings confirm that integrating drift-adaptive learning with deep EEG feature extraction significantly enhances diagnostic precision, offering a clinically scalable solution for early and reliable schizophrenia detection.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13170158/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147876445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative models for antimicrobial peptide design: auto-encoders and beyond.","authors":"Lukas Beierle, Julian Hahnfeld, Alexander Goesmann, Reihaneh Mostolizadeh, Franz Cemič","doi":"10.1186/s13040-026-00558-w","DOIUrl":"10.1186/s13040-026-00558-w","url":null,"abstract":"<p><strong>Background: </strong>As the number of multi-resistant pathogens grows rapidly, new strategies to accelerate the development of antimicrobial drugs are urgently needed. A promising candidate class of new antibiotics are antimicrobial peptides, showing a lower tendency to induce antibiotic resistance. High-throughput in silico strategies for candidate mining, such as generative deep learning algorithms, have become increasingly popular over the last few years and offer novel approaches to peptide discovery.</p><p><strong>Methods: </strong>This study presents a comparative analysis of the generative performance of deep learning models for generating novel antimicrobial peptides. The models examined include Variational Auto-Encoders, a Wasserstein Auto-Encoder, a Recurrent Neural Network, and a Language Model. The primary focus of this study is the systematic comparison and evaluation of those models and their sampling options to identify the most suitable model and sampling strategy combination for different use cases.</p><p><strong>Results: </strong>All models generated peptides with physicochemical profiles similar to natural antimicrobial sequences. Auto-encoders performed best overall, with the Wasserstein auto-encoder generating the most diverse and compositionally balanced peptides. In contrast to an unregularized baseline model, embedding-space analyses confirmed that the auto-encoders did not overfit. In addition, evaluating AMP predictors on data biased toward specific peptide properties revealed strong, model-specific preferences. Together, these results underscore the need to tailor models and evaluation metrics to each design objective.</p><p><strong>Conclusion: </strong>The present study investigates the strengths and weaknesses of various generative models for antimicrobial peptides. Practical recommendations for the combination of model type and sampling strategy are provided for individual applications.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13181977/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147864726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Divide-and-conquer analysis reveals hidden immune cell influencers across the placenta in preeclampsia.","authors":"Hyojung Paik, Tae Lyun Ko, Myungsun Park, Jong-Eun Park, Daniel Bunis, Marina Sirota, Byung Soo Lee, Hyoung-Sam Heo, Sung Ki Lee","doi":"10.1186/s13040-026-00556-y","DOIUrl":"10.1186/s13040-026-00556-y","url":null,"abstract":"<p><strong>Background: </strong>Placenta is a focal point of cellular interactions of maternal and fetal immune systems, fostering immune tolerance essential for a successful pregnancy. However, the mechanisms underlying immune dysregulation in disorders such as preeclampsia remain poorly understood.</p><p><strong>Methods: </strong>We constructed a multilayered atlas of the human placenta by performing single-cell RNA sequencing across distinct placental layers from both normal and severe preeclamptic pregnancies. Rather than focusing on specific regions of placenta, such as the villi and decidua, we explore placental architecture by collecting pair-matched tissues from individual pregnancies to suggest appropriate placental-wide immune atlas. To interpret intercellular communication in those unexplored placental layers, we designed two conceptual models: one based on immune interaction frequency (IIF) and another on immune tolerance influencers (IT). We applied machine learning classifiers to identify gene signatures associated with preeclampsia.</p><p><strong>Results: </strong>We observed extensive admixture of semi-allogeneic fetal and maternal cells across all placental layers, regardless of disease status. This contradicts the IIF-based model, which is premised on that such intermixing frequency is a pathologic feature specific to preeclampsia. Instead, analysis under the IT framework revealed key molecular determinants of preeclampsia. Notably, classifier-prioritized genes associated with preeclampsia were enriched for ligands and receptors supporting a role for intercellular immune interactions. Among them, the ligand-receptor pair SPP1-CD44 between fetus and maternal immune cells emerged as peculiarly associated influencers of preeclampsia. Spatial image analysis confirmed co-localization of SPP1-CD44 expression within immune cell populations in preeclamptic placental tissue. Our study provides a comprehensive map of the human placenta and identifies disease-specific immune signaling pathways in preeclampsia using the divide and rule approach. The findings highlight SPP1-CD44 as a putative target of immune dysregulation, offering new insight into the cellular basis of maternal-fetal tolerance and its breakdown in pregnancy-related disorders.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13267352/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147786682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Distinguishing cancer patients' mild and severe symptoms in radiotherapy via zero-shot and few-shot large language model-based probabilistic prompts.","authors":"Matthew W Chen, Yang Yan, Xinglei Shen, Hao Gao, Zhong Chen","doi":"10.1186/s13040-026-00547-z","DOIUrl":"10.1186/s13040-026-00547-z","url":null,"abstract":"<p><p>PURPOSE: Monitoring symptom severity during and after radiotherapy (RT) is critical for cancer patient care, however, existing machine learning and deep learning approaches face high retraining costs and lack clinically acceptable explanations. This study aims to investigate effective prompts for LLM-based reasoning and decision-making, distinguishing cancer patients’ mild and severe status during and after radiotherapy across multiple health symptoms. METHODS: To overcome these limitations, we developed a set of few-shot Large Language Model (LLM)-based predictive models operating under an anomaly detection framework (AD-LLM). Our approach leverages six novel, probabilistically designed prompts tailored for AD-LLM to identify and track patients with mild or severe symptoms, enabling accurate prediction despite limited patient-specific data. RESULTS: Experiments on prostate cancer patients monitoring bowel pain, depression, and sexual dysfunction problems demonstrated AD-LLM’s effectiveness in classifying symptom severity levels using these structured prompts. We evaluate the performance of different prompt strategies using AUC, AUCPR, Precision, Recall, and F1 scores, with confusion matrices and ROC/PR curves visualized to offer insights into LLM reasoning. The reasoning examples of LLMs are also provided to explain and understand their decision-making process. CONCLUSION: This method provides a promising and explainable solution for real-time symptom monitoring in RT settings, potentially improving timely intervention and patient outcomes. </p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13202976/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147693158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Early prediction of longitudinal treatment adherence in obstructive sleep apnea using machine learning approaches.","authors":"Máximo Domínguez-Guerrero, Daniel Álvarez, Verónica Barroso-García, María Fernández-Vaquerizo, Tomás Ruiz-Albi, Roberto Hornero","doi":"10.1186/s13040-026-00554-0","DOIUrl":"10.1186/s13040-026-00554-0","url":null,"abstract":"<p><p>BACKGROUND: Continuous Positive Airway Pressure (CPAP) is the most prescribed treatment for Obstructive Sleep Apnea (OSA), but adherence remains a critical challenge, especially long term. This study aims to predict CPAP adherence at 3, 6, and 12 months based on baseline patient status and usage data from initial 30 days of treatment. RESULTS: A retrospective cohort of 2180 patients was analyzed. Feature selection was performed using the maximum relevance minimum redundancy (mRMR) algorithm with bootstrapping. Three machine learning (ML) models were trained and evaluated: support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP). A core subset of early CPAP usage variables (median nightly use, days of use, and 30-day adherence) emerged as the most relevant features across all timepoints. Each prediction window also revealed exclusive features, suggesting that adherence at different stages may be driven by distinct factors. At 3 months, MLP exhibited the strongest predictive capacity (kappa = 0.823, AUC = 0.910). At 6 months, RF and SVM models yielded the highest results (kappa = 0.727, AUC = 0.863), whereas at 12 months, RF consistently outperformed the other algorithms (kappa = 0.698, AUC = 0.849), underscoring its robustness in forecasting long-term adherence. CONCLUSIONS: Our results suggest that ML algorithms can effectively predict CPAP adherence using very short-term usage data. Accordingly, our models are able to provide efficient early identification of patients at risk of non-adherence in order to support personalized interventions, improve outcomes, and reduce the healthcare burden in OSA management. </p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13202768/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147693188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CRM-TI: an enhanced pipeline for computationally assigning the target genes of cis-regulatory modules by considering comprehensive long-range regulation mechanisms.","authors":"Yu-Huai Yu, Guan-Liang He, Tzu-Hsien Yang","doi":"10.1186/s13040-026-00555-z","DOIUrl":"10.1186/s13040-026-00555-z","url":null,"abstract":"<p><p>BACKGROUND: Metazoan transcriptional regulation is mediated by modular DNA segments termed cis-regulatory modules (CRMs). The precise identification of CRM target genes is essential for understanding cellular functions and disease mechanisms. While reporter assays can validate CRM targets, selecting candidates remains challenging because CRMs often act over long distances, bypassing nearby genes. Simple nearest-gene assignments are therefore unreliable, and methods based on epigenetic correlations are still limited. Enhancer-promoter interaction (EPI) prediction has improved CRM target identification. However, lots of existing EPI tools suffer from overfitting and overlook alternative mechanisms such as non-coding RNAs (ncRNAs) transcribed from CRMs. RESULTS: To address these gaps, we developed CRM-Target Identifier (CRM-TI), a deep learning pipeline that integrates mechanisms of chromatin interactions and CRM ncRNA-transcription-related gene regulation. Using a chromosome-wise partitioning scheme, CRM-TI achieved an unbiased test auROC of 90.0%, outperforming existing methods by at least 10%. Additionally, considering both CRM-gene interactions and ncRNA-transcription-related regulation further improved auROC performance by 21.9% over the model that considers only CRM-gene interactions. CONCLUSIONS: These results demonstrate that combining comprehensive transcriptional regulatory mechanisms on CRMs provides a more complete framework for CRM-target gene assignment. CRM-TI is available at https://github.com/cobisLab/CRM-TI . </p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13203003/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147693201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An efficient hybrid federated learning framework for pneumonia diagnosis with proximal optimization and parameter-efficient adaptation.","authors":"Chhaya Gupta, Rajan Gupta, Nasib Singh Gill, Preeti Gulia, Piyush Kumar Shukla, Ankur Pandey","doi":"10.1186/s13040-026-00543-3","DOIUrl":"10.1186/s13040-026-00543-3","url":null,"abstract":"<p><p>Pneumonia remains a serious worldwide health concern, particularly in low-resource countries, where prompt diagnosis is challenging. Early detection relies on chest radiography; however, data privacy rules and patient data fragmentation make it difficult to build AI models. Federated Learning allows for collaborative model training without sharing patient data, a promising solution. Standard federated learning methods, such as FedAvg, suffer from data heterogeneity and significant communication overhead. To overcome these constraints, this research proposes an upgraded federated framework with FedProx, which mitigates client drift in non-IID contexts by proximal optimization and Low-Rank Adaptation, a parameter-efficient fine-tuning technique that minimizes communication costs. Vision Transformers are utilized as the backbone architecture for chest X-ray categorization because they capture the global visual context more effectively than convolutional models. The proposed technique was validated for a pneumonia classification job utilizing the publicly available Chest X-Ray Images dataset, which was distributed across simulated clients to replicate real-world healthcare organizations. The model’s performance is measured using accuracy, precision, recall, F1-score, AUC, and system-level measures, including communication cost per round and convergence rate. Under conditions of non-IID heterogeneity of data, the proposed FedProx+LoRA framework demonstrated a classification accuracy of 88.5 which was higher compared to the centralized baseline (63.9%) or the standard FedAvg (60.9%), and showed a significant increase in comparison to FedProx itself (78.6%). Furthermore, the framework saved an overhead in communication by 97.4% in comparison to entire fine-tuning.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":" ","pages":""},"PeriodicalIF":6.1,"publicationDate":"2026-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147662847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}