974 papers
The paper introduces PRISM-G, an interpretable, model-agnostic framework that assesses privacy risks in synthetic human genome data by aggregating proximity, kinship, and trait-linked exposure metrics into a unified 0–100 score, demonstrating that diverse generative models exhibit distinct vulnerability patterns that single similarity metrics fail to capture.
This study utilizes all-atom molecular dynamics simulations to map the electrostatic interaction networks of human CFTR in both apo and ivacaftor-bound states, revealing how dynamic salt bridges, lipid interactions, and specific ion coordination pathways collectively stabilize the channel's architecture and facilitate its conformational transitions and anion conduction.
HEDeST is a robust, weakly supervised framework that integrates histology-derived morphological features with deconvolution-derived spot proportions to achieve single-cell resolution in spatial transcriptomics, outperforming existing methods in both simulated and real cancer datasets.
This paper introduces DVPNet, an interpretable XAI framework that integrates the Nucleotide Transformer with probabilistic circuits to quantify gene importance and uncover biologically significant pathways distinguishing cancer cells from normal cells, revealing insights that transcend traditional statistical analyses.
ADAMIXTURE is a novel, GPU-accelerated optimization framework that integrates the EM algorithm with Adaptive Moment Estimation (Adam) to achieve biobank-scale genetic clustering with significantly faster convergence and comparable accuracy to existing state-of-the-art methods.
This study introduces varTFBridge, a method combining single-molecule deaminase footprinting (FOODIE) with AlphaGenome to identify and mechanistically resolve causal noncoding variants that rewire gene regulatory networks for erythroid traits across hundreds of thousands of UK Biobank genomes.
STRmie-HD is a novel, alignment-free computational framework that enables high-resolution, interruption-aware genotyping and quantitative somatic mosaicism profiling of HTT repeat expansions across multiple sequencing platforms, offering superior sensitivity for characterizing Huntington's disease pathogenesis compared to conventional tools.
EvoRMD is a unified, interpretable deep learning framework that integrates evolutionary RNA language model embeddings with biological metadata to predict competing RNA modification types within a biologically grounded, single-positive, multiple-unlabeled context.
This study presents a fully computational pipeline that successfully designed and atomistically validated a high-affinity VHH nanobody targeting the PI/RuvC interface of SpCas9, establishing a stable, non-inhibitory bivalent hub architecture for recruiting secondary effectors to enhance CRISPR-Cas9 functionality.
This study benchmarks four generative AI tools to design de novo peptides targeting BMPR1A for cartilage regeneration, identifying a top-performing PepMLM candidate through a rigorous multi-metric computational framework and establishing a reproducible pipeline for future experimental validation.
This paper introduces SelectZyme, an embedding-guided framework that leverages protein language models to enable unsupervised, hierarchical navigation of vast enzyme sequence spaces, facilitating scalable discovery and prioritization of biocatalysts without relying on fixed sequence identity thresholds or predefined annotations.
CBIcall is an open-source, configuration-driven framework that ensures reproducible and standardized variant calling across diverse computing environments by validating parameters and dispatching workflows via a single YAML file, as demonstrated in large-scale cohort analyses like the EU HEREDITARY project.
Isopedia introduces an open-source, reference-agnostic framework that leverages population-scale long-read data to distinguish biologically active isoforms from stochastic noise, thereby drastically reducing apparent transcript novelty and enabling systematic interpretation of human RNA diversity for clinical and functional research.
This study demonstrates that in small clinical cohorts, compact longitudinal representations of lifestyle questionnaire data, particularly those capturing temporal changes, significantly outperform static text-derived features for distinguishing ALS patients from controls.
The authors developed ORPHEUS, a novel analytical method that distinguishes between changes in cellular oscillator amplitude and intercellular synchrony, revealing a dramatic loss of circadian synchrony in excitatory neurons of Alzheimer's disease patients that was previously obscured in bulk tissue analyses.
The paper introduces CoMPLip, a training-free method that enhances AlphaFold 3's accuracy in predicting membrane protein structures by explicitly co-folding them with lipid molecules to simulate a realistic membrane environment.
This paper introduces the Duplicate Monophyly Criterion (DMC), an empirical method that calibrates noise levels for parametric bootstrapping in distance-based structural phylogenies by using synthetic taxon duplicates as internal controls to define a conservative resolution limit for assigning confidence to tree topologies.
This study utilizes phylogenomics and genome-wide association studies on Danish epidemic strain isolates to reveal that the emergence and persistence of successful *Achromobacter ruhlandii* lineages are driven by extensive horizontal gene transfer, plasmid integration, and the acquisition of adaptive traits like enhanced iron acquisition and antimicrobial resistance.
This paper introduces Deconomix, a comprehensive Python package and graphical user interface that enables the deconvolution of bulk transcriptomics data to infer cellular compositions, optimize gene weights for resolving small or related cell populations, account for background contributions, and estimate cell-type-specific gene regulation.
This paper presents a machine learning model that successfully learns the principles of non-bonded interactions to predict drug-receptor binding for novel chemical matter, offering a theoretical framework to overcome the limitations of current serendipitous drug discovery methods.