BioData Mining

Rare diseases are individually uncommon but collectively prevalent. Their primary clinical challenge lies not in treatment but in diagnosis. In the early stages of clinical management, it is frequently unclear whether the observed phenotypes are associated with a rare disease. Leveraging machine learning methods to mine latent associations between these phenotypes and rare diseases for early diagnosis offers a viable strategy to alleviate this diagnostic dilemma. In the present study, we demonstrated that machine learning can effectively discriminate rare disease cases from their controls using observed and excluded phenotypes as features. Among them, the Random Forest model achieved the best classification performance with a certain degree of generalizability. Based on further analysis of the feature selection results, we conclude that the two factors, specificity and occurrence count, are important for phenotype selection in rare disease discrimination, and comparable importance should be attached to both observed and excluded phenotypes, during feature construction.

In this work, we present a machine learning model for identifying pathogenic DNA variants. The model was learned from the analysis of normal and pathogenic sequences extracted from the ClinVar database (supported by NCBI). This analysis was based on a conceptual semantic model of DNA sequences converted to peptide sequences (amino acid sequences) governed by a well-defined grammar, which allowed us to apply NLP techniques, specifically Part of Speech tagging (POS tagging). Our predictive model was built by combining two techniques: CRF (from the Markov model family), which performs the sequencing, and BiLSTM (a deep learning model) which captures the past and future content of the sequences. The training space was created with the sequences of 105 genes associated with approximately 27,000 pathogenic variants. The model was evaluated using the metrics precision, P-R and ROC curves, AUC, and confusion matrices. Its performance was also compared against five known methods for predicting pathogenic variants. The results show exceptional performance that exceeds expectations and places this new method at the state of the art for predicting pathogenic DNA sequences.

Background: Genetic conditions are common in congenital heart disease (CHD) and affect care, but are often missed or diagnosed late. We asked whether routine clinical data can shortlist the most likely genetic conditions. Methods: Retrospective single-center cohort of children with CHD and an echocardiogram who had either a confirmed genetic diagnosis or negative cytogenetic testing and CHD gene sequencing. Echocardiogram images and serial medical record data were added as model inputs in the order they become clinically available. Class balanced logistic regression (LR) and a multimodal deep learning fusion network were fitted to the same inputs at each step. The primary metric was balanced top-3 accuracy (correct diagnosis among the top three, averaged across conditions), with bootstrap intervals. Results: The cohort included 1,720 children (988 with common CHD-associated genetic conditions, 231 rare diagnoses, 501 negative testing). Using only inputs generated at the echocardiogram visit, LR reached a balanced top-3 accuracy 0.758 (chance 0.429). Serial records, radiology notes and ICD-10 codes, raised this to 0.809. Multimodal fusion performed similarly at each stage. With a genetic condition withheld from training, the fusion embedding placed affected children nearest to others sharing a gene group in 0.37 of cases versus 0.10 without the embedding (+0.268 [95% CI +0.242, +0.295]). Conclusions: Routine clinical data available at first echocardiogram can help identify likely genetic diagnoses, and later coded inputs ceiling. Multimodal fusion added no accuracy over LR, but places children sharing a genetic cause near one another, making nearest-neighbor retrieval informative for undiagnosed children.

In recent years, the issue of reproducibility in scientific studies has been at the forefront of scientific discussion. Many of these issues arise due to poor employment of statistical methods, making it crucial to address these knowledge gaps for frequently used methods. Elastic net regression (ENET) is one such algorithm used frequently in biology and public health due to its ability to select important predictors (also known as "features") from large data sets. However, ENET struggles with consistent feature selection and hyperparameter choice in these applications due to low observation counts and noisy data. This limitation hinders ENET's effectiveness in biological research due to low model reproducibility and predictor interpretability. We propose the Instability Quotient Criterion (IQC) as a metric to quantify the consistency of selected features for feature selection models such as ENET, with a specific emphasis on biological applications. IQC leverages ensemble modeling and Shannon's entropy in order to determine the stability of selected features derived from ENET models. We demonstrate IQC's robustness via simulation studies, showing that IQC is capable of detecting significant decreases in model stability with lower observation counts, higher dimensionality, and higher proportions of noisy signal. We additionally utilize simulation to provide a naive threshold for low versus high stability. Finally, we applied IQC to a case study to illustrate how our method can be integrated into a larger analysis pipeline when looking at microarray gene expression data. IQC indicated stability issues for differentially-expressed genes when classifying acute leukemia subtypes in spite of high classification success. Lastly, we discuss how model instability impedes interpretation of biologically significant genes for discerning cancer subtypes. Overall, we present IQC as a robust evaluation metric that can easily be incorporated into high-dimensional biological analyses.

Manual extraction of high-fidelity gene-disease-phenotype information from human genetics literature is a labor-intensive task that requires trained human genetics researchers to read through many primary research papers. This presents a major challenge for maintaining up-to-date human disease genetic databases. Recent exploration into large language models (LLMs) opens new directions in automating this manual process. However, most approaches depend on pre-training, finetuning, or specialized generative artificial intelligence (GenAI) tools, but there is a lack of empirical evidence to show whether commercially-available LLMs can be directly used to reliably extract gene-disease-phenotype for human genetic diseases. Herein, we perform a benchmark of the use of three zero-shot prompted LLMs, namely GPT-4, DeepSeek and Claude, without task-specific fine-tuning, to extract human genetic information directly from full text of scientific papers. Using known congenital heart diseases (CHD) genes found in the open access CHDgene database (https://chdgene.victorchang.edu.au/) as the benchmark data set, GPT-4o achieved overall 88.8% extraction accuracy across 23 gene entries containing over 57 references, with 100% accuracy in gene name, 78.3% and 76.7% in disease and phenotype fields respectively. This work introduces a lightweight, easy-to-deploy, and yet robust LLM-based agent named GeneAgent, analyze sources of disagreement, and highlight the feasibility of integrating powerful LLM into genetic evidence synthesis workflows. Highlight- First systematic benchmark of LLMs for extracting human gene-disease-phenotype relationships from full-text biomedical articles - GeneAgent: a lightweight, highly accurate prompt-only LLM agent - New domain task-specific evaluation framework

Logistic regression remains a widely used classification method due to its interpretability and computational efficiency, but its direct application to high-dimensional biomedical data is limited when the number of features greatly exceeds the number of samples. In this paper, we propose a reformulated logistic regression framework designed for feature selection and classification in complex high-dimensional settings. The method is evaluated on three biomedical datasets, including scenarios with tens of thousands of attributes and substantially fewer samples. Across these datasets, the proposed approach achieved clear separation between control and disease groups while selecting a compact set of features. Several selected features were consistent with previously reported disease-associated markers, supporting the biological plausibility of the model, while additional selected features suggest potential novel candidates for further investigation. These results indicate that the proposed framework may provide an interpretable and computationally efficient alternative for feature selection in high-dimensional computational biology applications.

Adverse event report (AER) data are a key source of signal for post marketing drug surveillance. The standard methodology to analyze AER data applies disproportionality metrics, which estimate the strength of drug/side-effect associations from discrete counts of their occurrence at report level. However, in other domains, improvements in predictive modeling accuracy have been obtained through representation learning, where discrete features are replaced by distributed representations learned from unlabeled data. This paper describes aer2vec, a novel representational approach for AER data in which concept embeddings emerge from neural networks trained to predict drug/side-effect co-occurrence. Trained models are evaluated for their utility in identifying drug/side-effect relationships, with improvements over disproportionality metrics in most cases. In addition, we evaluate the utility of an otherwise-untapped resource in the Food and Drug Administration (FDA) AER system - reporter designations of suspected causality - and find that incorporating this information enhances performance of all models evaluated.

BackgroundAdverse drug-drug interactions (DDIs) cause preventable hospitalizations, but exhaustive experimental screening of all drug pairs is infeasible. Many computational predictors rely on SMILES or other molecular representations, limiting their direct applicability to biologics and other non-small-molecule therapeutics. We present a structure-agnostic framework that combines semantic representations derived from Medical Subject Headings (MeSH) with graph-derived topology from a Drug-Target-Protein knowledge graph constructed from DrugBank and UniProt. We further investigate how variation in MeSH annotation depth affects predictive performance. ResultsDrugs are grouped according to their deepest MeSH annotation level (Low, Mid, or Deep), and performance is evaluated across the resulting interaction categories in transductive and inductive settings. The Intermediate ontology scope (Low+Mid) provides the most stable performance, while adding Deep-level terms offers limited and inconsistent benefit. Lightweight topological descriptors are integrated with MeSH features through instance-wise, dimension-specific latent-space gating, using curated reliable-negative pairs for supervision. Fusion improves mean performance over the MeSH-only baseline across all six categories in the transductive setting. Under induction, the clearest gains occur for Low-Low interactions ({Delta}AUROC = 0.056;{Delta} F1 = 0.137) and Low-Mid interactions ({Delta}AUROC = 0.077;{Delta} F1 = 0.114). ConclusionsMeSH annotation depth is associated with systematic variation in DDI prediction performance that aggregate evaluation can obscure. Graph-derived topology is particularly beneficial when ontology annotations are shallow. The framework provides a common, structure-agnostic representation compatible with both small-molecule and biologic therapeutics and supports first-pass DDI prioritization for subsequent expert assessment.

Background: Extrauterine growth restriction (EUGR) is a common and clinically significant complication among preterm infants, contributing to adverse neurodevelopmental and metabolic outcomes. Early and individualized risk prediction remains challenging. This study aimed to develop and validate an interpretable machine learning model for early prediction of EUGR using routinely available clinical variables, and to implement a user-friendly web-based calculator for clinical use. Methods: We retrospectively analyzed 1,431 preterm infants admitted within 24 hours after birth to our hospital between May 2020 and March 2025. Infants from the Yangpu campus (n=863) formed the training set, and those from the Huangpu campus (n=568) formed the validation set. Early clinical variables available within 48-72 hours were screened using the Boruta algorithm. Logistic regression, XGBoost, random forest, decision tree, and support vector machine models were developed and compared. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, F1 score, and Brier score. SHapley Additive exPlanations (SHAP) were applied to assess global and individual feature contributions, nonlinear effects, and interactions. A web-based calculator was constructed based on the optimal model. Results: Nine variables were identified as important predictors: birth weight, small for gestational age status, gestational age, breastfeeding, multiple gestation, neonatal respiratory distress syndrome, patent ductus arteriosus, maternal hypertension, and maternal group B Streptococcus infection. Among the five models, XGBoost achieved the best performance in the validation set (AUC 0.922, accuracy 0.849, Brier score 0.108). SHAP analysis showed that low birth weight, small for gestational age, maternal group B Streptococcus infection, and patent ductus arteriosus were major risk factors, while breastfeeding was protective. Notable nonlinear and interactive effects were observed, particularly between birth weight and gestational age and between breastfeeding and patent ductus arteriosus. The web-based calculator provides real-time individualized risk estimation and visualized interpretation. Conclusions: An interpretable XGBoost-based model and web calculator were successfully developed and validated for early prediction of EUGR in preterm infants. This tool may support clinicians in identifying high-risk infants and guiding individualized nutritional and clinical management.

Drug repurposing presents a potential solution for finding new therapies for rare and orphan diseases. The limited number of patients affected by rare diseases, combined with scarce research and the financial burden of clinical trials, creates a significant barrier to developing new drugs. Drug repurposing utilizes the known safety profile and effectiveness of existing medications to fast-track the development of life-saving therapies. Recently drug repurposing has focused on utilizing biomedical knowledge graphs to uncover hidden connections between diseases and drugs, revealing promising candidates for repurposing. Because most knowledge graphs in biomedical domain are made by text-mining scientific literature we decided to compare the amount of knowledge contained in open access and controlled (subscription only) access literature. Elsevier and Every Cure make logical partners and allowed the project to use Elseviers ability to access both controlled and open access publications and its proprietary Elsevier AI technology to construct the knowledge graph. Notwithstanding the fact that more than 50% of relationships in drug repurposing for rare diseases can be found in open access content, 45% of relationships remain only in controlled access. We argue that this is due to the large number of edges supported by single reference in the entire biomedical knowledge graph and does not reflect an intrinsic difference between open and controlled access.

Large Language Models (LLMs) have emerged as promising tools for assisting researchers in automating and accelerating the synthesis of literature reviews. However, their reliability is a significant concern due to issues like factual inaccuracies and hallucinations. The key question is whether LLMs can reliably provide comprehensive, up-to-date overviews and analyses. This study evaluates the performance of three leading LLMs (OpenAI's ChatGPT, Google's Gemini, and DeepSeek) on the complex task of generating a comprehensive survey paper on deep learning for cancer Drug Response Prediction (DRP). By testing both standard and Deep Research (DR) / Deep Think (DT) modes of LLMs with prompts of varying detail, this paper assesses key academic dimensions, including reference management, content quality, and analytical depth. Key findings reveal that while DR modes of LLMs significantly improve reliability by eliminating hallucinations, performance variations exist across models and prompts. A trade-off between reference quantity and integration quality was observed, and even the best-performing models lacked the analytical depth of human experts, often requiring extensive human supervision. The study concludes that LLMs currently serve as powerful assistive tools but still cannot replace the critical validation and synthesis provided by human researchers. Choosing the best LLM to use depends on the task in hand, while several strategies can be implemented to improve the produced output.

Manual clinical DNA variant classification is the bottleneck of every clinical and research rare disease workflow. The process typically requires a curator to assemble evidence from numerous databases, weigh 28 criteria, reconcile competing evidence, and produce a defensible case for the final classification. Additionally, the framework used to assess variants is not static and successive addenda have revised individual criteria. The most complete and current evidence aggregators available are commercial platforms, which can limit researcher access. We present HeartVar, an open-source web tool that automates the evidence-gathering and interpretation steps of variant classification associated with cardiovascular disease. Given a gene, a variant, and clinical context, HeartVar queries 20 public databases in parallel and assigns ACMG/AMP criteria through a hybrid rule-based/large language model (LLM) approach. Criteria that can be resolved from structured data are computed programmatically, and only those requiring interpretation of unstructured evidence are passed to the LLM. HeartVar returns a classification, point score, per-criterion breakdown, clinical-narrative summary, and database annotations. Benchmarking of 106 expert-curated ClinGen variants showed HeartVar outperformed other curation tools, assigning the correct ACMG tier in 72% of cases. HeartVar demonstrates that an LLM constrained by a domain-specific prompt and grounded in structured evidence can produce variant interpretations of first-pass quality for a cardiovascular disease cohort; however, it is not intended to replace manual assessment by a qualified variant curator. The tool is freely available to use and hosted at www.heartvar.victorchang.edu.au.

ObjectiveTo develop and evaluate a personalized literature review system that efficiently processes and summarizes biomedical literature to provide timely, relevant insights for researchers. MethodsThe system integrates ontology-aware keyword extraction (MeSH/ACM constrained TF-IDF from CV/Research Statement), citation-informed retrieval (PubMed and NIH iCite API), and dual-model large language model (LLM) summarization (Google Gemini 2.0 flash, OpenAI GPT-4o-mini). These LLMs leverage advanced Transformer architectures, building on foundations such as BERT, BART, and BioBERT. A two-stage ranking algorithm combines Relative Citation Ratio (RCR) with cosine similarity. Summary quality was evaluated using ROGUE-1/2/L and BERTScore. The system is deployed as a Streamlit web application. ResultsAcross 20 biomedical queries, the system demonstrated strong average performance (BERT-F1{approx} 0.86), with cosine similarity strongly correlating with summary quality. Human evaluation involving 10 users yielded average scores above 4.5/5 across summary fidelity and keyword relevance. ConclusionHybrid ranking and ensemble LLM summarization significantly accelerate scientific sense-making. These findings suggest broad applicability to various domains beyond biomedicine.

Incorporating realistic sets of patient-associated covariates, i.e., virtual populations, in pharmacometric simulation workflows is essential to obtain realistic model predictions. Current covariate simulation strategies often omit or simplify dependency structures between covariates. Copula models are multivariate distribution functions suitable to capture dependency structures between covariates with improved performance compared to standard approaches. We aimed to develop and evaluate a copula model for generation of adult virtual populations for 12 patient-associated covariates commonly used in pharmacometric simulations, using the publicly available NHANES database, including sex, race-ethnicity, body weight, albumin, and several biochemical variables related to organ function. A multivariate (vine) copula was constructed from bivariate relationships in a stepwise fashion. Covariate distributions were well captured for the overall and subgroup populations. Based on the developed copula model, a web application was developed. The developed copula model and associated web application can be used to generate realistic adult virtual populations, ultimately to support model-based clinical trial design or dose optimization strategies.

Background: Several omics studies have been completed in recent years, with the goal of identifying biomarkers of complex multifactorial diseases, such as bronchopulmonary dysplasia (BPD). Objective: To evaluate the performance of 3 distinct omics platforms, using a machine learning pipeline with integration of sparse, reliable and adaptive biomarker identification (Stabl). Methods: Using a well-characterized birth cohort, cord blood metabolomics, proteomics and adductomics data were integrated with Least Absolute Shrinkage and Selection Operator (LASSO) regression and Stabl, to evaluate predictive performance for BPD. Results: Sparse multivariable modeling of 45,000 features measured in 217 infants (52 term, 165 extremely preterm <28 weeks; 82 with BPD and 35 with severe BPD/death) identified a perfect signature for preterm birth with both LASSO and Stabl (AUROC=1.0; p<0.001). Analysis of the preterm group yielded excellent predictive power for severe BPD (AUROC=0.83; p=0.005). Stabl identified a set of 12 biomarkers (2 adducts, 3 proteins and 7 metabolites) with good performance for predicting grade III BPD (AUROC=0.76; P=0.03). Biomarkers across the 3 omics platforms revealed dysregulated pathways of innate/adaptive immune responses, metabolic programming and oxidative stress. Conclusions: The sparse machine learning pipeline is a complementary approach for identifying novel pathways and biomarkers of multifactorial BPD and its endotypes.

BackgroundThis study addresses limitations of traditional medication adherence assessment tools by developing a machine learning model to evaluate post-discharge medication compliance in patients using drugs. The research was conducted at Nanjing Drum Tower Hospital from February 2024 to December 2024. MethodsWe collected clinical data from 240 patients through questionnaires and developed a multi-class machine learning model. Feature selection employed manual screening and polynomial logistic regression. Six ML models were evaluated, with the Random Forest Classifier (RFC) demonstrating optimal performance (bad_AUC = 0.979, fine_AUC = 0.973, good_AUC = 0.917). SHAP analysis was used to explain the best-performing model. ResultsThe RFC model showed superior predictive capability across all adherence levels. Model interpretation revealed key clinical factors influencing adherence patterns. The tool enables early identification of non-compliance and supports intervention strategies. ConclusionsThis RFC-based model represents a significant advancement in medication adherence assessment, offering clinicians a practical tool for monitoring compliance. The approach shows particular promise for enhancing mental health management in this patient population by fostering better medication awareness and establishing scientific medication habits during early treatment stages.

Acute myeloid leukemia (AML) is an aggressive hematopoietic malignancy defined by aberrant clonal expansion of abnormal myeloid progenitor cells. Characterized by morphological, molecular, and genetic alterations, AML encompasses multiple distinct subtypes that would exhibit subtype-specific responses to treatment and prognosis, underscoring the critical need of accurately identifying AML subtypes for effective clinical management and tailored therapeutic approaches. Traditional wet lab approaches such as immunophenotyping, cytogenetic analysis, morphological analysis, or molecular profiling to identify AML subtypes are labor-intensive, costly, and time-consuming. To address these challenges, we propose AttentionAML, a novel attention-based deep learning framework for accurately categorizing AML subtypes based on transcriptomic profiling only. Benchmarking tests based on 1,661 AML patients suggested that AttentionAML outperformed state-of-the-art methods across all evaluated metrics (accuracy: 0.96, precision: 0.96, recall of 0.96, F1-score: 0.96, and Matthews correlation coefficient: 0.96). Furthermore, we also demonstrated the superiority of AttentionAML over conventional approaches in terms of AML patient clustering visualization and subtype-specific gene marker characterization. We believe AttentionAML will bring remarkable positive impacts on downstream AML risk stratification and personalized treatment design. To enhance its impact, a user-friendly Python package implementing AttentionAML is publicly available at https://github.com/wan-mlab/AttentionAML.

Diet plays a critical role in human health, with growing evidence linking dietary habits to disease outcomes. However, extracting structured dietary knowledge from biomedical literature remains challenging due to the lack of dedicated relation extraction datasets. To address this gap, we introduce RECoDe, a novel relation extraction (RE) dataset designed specifically for diet, disease, and related biomedical entities. RECoDe captures a diverse set of relation types, including a broad spectrum of positive association patterns and explicit negative examples, with over 5,000 human-annotated instances validated by up to five independent annotators. Furthermore, we benchmark various natural language processing (NLP) RE models, including BERT-based architectures and enhanced prompting techniques with locally deployed large language models (LLMs) to improve classification performance on underrepresented relation types. The best performing model gpt-oss-20B, a local LLM, achieved an F1-score of 64% for multi-class classification and 92% for binary classification using a hierarchical prompting strategy with a separate reflection step built in. To demonstrate the practical utility of RECoDe, we introduce the Contextual Co-occurrence Summarisation (Co-CoS) framework, which aggregates sentence-level relation extractions into document-level summaries and further integrates evidence across multiple documents. Co-CoS produces effect estimates consistent with established dietary knowledge, demonstrating its validity as a general framework for systematic evidence synthesis. AvailabilityThe code, models, and data will be made freely available upon acceptance.

Interpretation of a given variants pathogenicity is one of the most profound challenges to realizing the promise of genomic medicine. A large amount of information about associations between variants and diseases used by curators and researchers for interpreting variant pathogenicity is buried in biomedical literature. The development of text-mining tools that can extract relevant information from the literature will speed up and assist the variant interpretation curation process. In this work, we present a text-mining tool, MACE2k that extracts evidence sentences containing associations between variants and diseases from full-length PMC Open Access articles. We use different machine learning models (classical and deep learning) to identify evidence sentences with variant-disease associations. Evaluation shows promising results with the best F1-score of 82.9% and AUC-ROC of 73.9%. Classical ML models had a better recall (96.6% for Random Forest) compared to deep learning models. The deep learning model, Convolutional Neural Network had the best precision (75.6%), which is essential for any curation task.

Acute myocardial infarction (AMI) is one of the leading cardiovascular diseases worldwide and remains a major cause of mortality. Early risk prediction can help clinicians identify high risk patients shortly after admission and support timely monitoring and individualized treatment. Previous AMI risk assessment approaches predominantly rely on a single model structure or fixed feature representation, which may limit their ability to capture diverse risk related patterns and reduce predictive performance. To address these challenges, we propose MetaAMI, a random projection based meta-learning framework for AMI outcome prediction. Specifically, patients were selected based on ICD-9 and ICD-10 diagnostic codes for AMI from the Medical Information Mart for Intensive Care IV (MIMIC-IV) v3.1 database. Features were transformed through multiple random projections, with each random projection generating a distinct lower dimensional feature representation. Subsequently, baseline classifiers were trained on each lower dimension representation to predict in-hospital mortality among AMI patients. The predictions were aggregated to construct an integrated feature representation, which was used as input to a meta-learner architecture. By effectively integrating complementary information from diverse baseline models, the meta-learner refined the decision boundary and enhanced overall predictive performance. Survival analysis and SHapley Additive exPlanations (SHAP) analysis were further performed to evaluate clinical utility and interpret the model predictions. Benchmarking results based on MIMIC-IV dataset suggested that our MetaAMI consistently outperformed all the baseline classifiers across seven evaluation metrics including Accuracy, Area Under the Curve (AUC), F1 Score, G-Measure, Jaccard Index, Youden J, and Matthews Correlation Coefficient (MCC). In addition, feature importance analysis showed clinically relevant predictors of in-hospital mortality. In summary, MetaAMI provides an effective and robust solution for machine learning based AMI risk prediction. We anticipate that the application of MetaAMI will have a positive impact on clinical risk stratification and personalized treatment strategies for AMI.