Abstract Motivation Identifying transcriptomic factors with potential causal effects on breast cancer progression is important for understanding disease mechanisms and prioritizing therapeutic targets. However, causal-effect estimation from high-dimensional gene-expression data remains challenging because of the large number of variables and potential unmeasured confounding. Results We propose CICIV, a causal inference framework that integrates PC-simple-based causal feature selection with conditional instrumental variable (CIV) representation learning. PC-simple first reduces the dimensionality of transcriptomic data by identifying candidate parent genes, after which CIV estimates and ranks their absolute causal effects. Applied to TCGA-BRCA, CICIV prioritized 40 breast cancer-related candidate genes and identified signals that were not captured by conventional correlation-based analyses. External validation using the independent METABRIC cohort showed consistent effect directions for 21 of the 40 genes, with four genes overlapping in the Top 10 and nine in the Top 20 rankings. Pathway enrichment and literature-based analyses further supported the biological relevance of the prioritized genes. Availability and Implementation The CICIV benchmarking framework and source code are freely available at https://github.com/Zaiwen/CICIV. The software version and test data used in this study are archived at Zenodo (DOI: 10.5281/zenodo.22143976).
MOTIVATION:Predicting and deciphering the regulatory logic of enhancers remains a significant challenge due to their complex sequence features and the absence of consistent genetic or epigenetic signatures that distinguish them from other genomic regions. Existing machine learning methods capture nucleotide composition but often fail to model sequence context effectively. RESULTS:We present DNABERT-Enhancer, a novel enhancer prediction method, by applying DNABERT pre-trained language model on the human genome. Using ENCODE registry of candidate cis-regulatory elements (cCREs), we curated a benchmark dataset, consisting of 21,926 enhancers of 201 bp length and 46,159 enhancers of 350 bp length, as positive instances. The best fine-tuned model achieved 88.05% accuracy and a Matthews correlation coefficient of 76% on an independent dataset. Genome-wide application identified 1,684,595 enhancer regions covering 26.65% of the human genome. By performing integrative analyses with DNABERT-based transcription factor models, we identify 2,681 statistically significant loss-of-function and 1,917 gain-of-function enhancer variants, which respectively alter the function of 1,623 and 1,247 ENCODE-cCRE enhancers. Similarly, we identify 4,057 candidate de novo enhancers, created by 5,464 gain-of-function variants. These genome-wide enhancer annotations and candidate genetic variants predicted by DNABERT-Enhancer provide valuable resources for genome interpretation in functional and clinical genomics studies. AVAILABILITY:DNABERT-Enhancer is freely available at https://github.com/DavuluriLab/DNABERT-Enhancer; Trained model predictions can be explored interactively via the web application at https://dnabert-enhancer-datarepo.streamlit.app/. The fine-tuned models are archived and citable through Zenodo (https://doi.org/10.5281/zenodo.19157566). SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
Abstract Motivation Hypergraph-based models for brain disorder prediction mainly adopt imaging-derived hypergraphs as propagation backbones. However, the entanglement of topology construction and feature propagation leaves regional representations weakly constrained by underlying biological organization, making them vulnerable to subject-specific variation and noise, particularly in heterogeneous multimodal settings. Results We present BriGHT, a Brain transcriptome-reGularized Hypergraph framework for mulTimodal disorder prediction. BriGHT employs a transcriptome-derived structural reference as a soft anchoring prior to regularize neuroimaging ROI embeddings, stabilizing representation geometry while preserving disease-relevant subject-specific variation. BriGHT further incorporates a reliability-aware fusion module to estimate subject-specific modality reliability from prediction confidence, cross-modal consistency, and decision certainty, enabling adaptive integration under heterogeneous modality quality. Experiments on three neuroimaging cohorts (ADNI, ADHD-200, REST-meta-MDD) and four modalities (VBM, fMRI, FDG, AV45) demonstrate that BriGHT consistently outperforms competing graph/hypergraph learning methods across six brain disorder prediction tasks. Perturbation analyses show that BriGHT benefits from the spatial correspondence between transcriptomic modules and imaging ROIs, rather than from arbitrary hypergraph regularization alone. Ablation and meta-analytic interpretability analyses support the contribution of transcriptomic anchoring and adaptive fusion to robust and biologically meaningful brain disorder prediction. Availability The software is publicly available at: https://github.com/Yaolab-fantastic/BriGHT.
MOTIVATION:Accurate prediction of antibody-antigen binding affinity is essential for therapeutic antibody design. Existing methods often model the dissociation constant (KD) and Gibbs free energy (ΔG) independently, overlooking their thermodynamic relationship and complex paratope-epitope spatial interactions. RESULTS:We introduce Phys-AbGAT, a physics-informed multi-task graph attention network that represents the antibody-antigen interface as a spatial graph. It integrates ESM2 evolutionary embeddings with radial basis functions and employs a thermodynamically motivated auxiliary loss to encourage coupling between log10(KD) and ΔG. On an independent 42-complex benchmark, Phys-AbGAT achieved Pearson correlation coefficients of 0.569 for log10(KD) and 0.573 for ΔG. In matched-set comparisons, Phys-AbGAT achieved numerically lower RMSE and higher PCC than four baseline methods. The differences remained significant after Holm correction for MVSF-AB and PPA-Pred2, but not for AREA-AFFINITY or CSM-AB. Higher attention scores were assigned to several aromatic paratope residues, providing model-level hypotheses for structural inspection. These results support Phys-AbGAT as an interpretable multi-task geometric framework for joint prediction of two affinity-related quantities. AVAILABILITY AND IMPLEMENTATION:Code and data are available at https://github.com/cliffgao/Phys-AbGAT . SUPPLEMENTARY INFORMATION:Supplementary data are available at Bioinformatics online.
MOTIVATION:Designing mRNA coding sequences that simultaneously optimize RNA accessibility in the translation initiation region and codon adaptation while preserving the encoded protein requires navigating a vast discrete combinatorial space. The inherently discrete nature of codon choices prevents direct application of gradient-based optimization, despite the availability of accurate deep learning predictors such as DeepRaccess for RNA accessibility prediction. RESULTS:We present the Input Data Differentiable Designer (ID3), a unified framework for mRNA codon optimization. ID3 treats trained models as fixed differentiable functions and optimizes input data through continuous probability distributions while preserving the encoded amino acid sequence through three constraint mechanisms. The framework shows strong performance in both accessibility optimization and joint accessibility-CAI optimization across diverse protein targets. We also provide convergence analyses from the perspective of trained model input optimization. AVAILABILITY AND IMPLEMENTATION:Code, datasets, and reproduction scripts are available at https://github.com/Li-Hongmin/ID3.git and archived on Zenodo (DOI: 10.5281/zenodo.18917770).
