974 papers
This study identifies distinct serum metabolic signatures, including specific acylcarnitines, diet-derived compounds like piperine and lutein, and altered drug metabolism, that serve as molecular predictors of exceptional cognitive resilience in a longitudinal aging cohort.
This study demonstrates that supervised machine learning models, specifically Random Forest and k-Nearest Neighbors, can accurately predict the geographic origin of samples using bee-collected pollen DNA metabarcoding data, proving that raw sequence abundance is sufficient for reliable geolocation without time-consuming taxonomic assignment.
The paper introduces BulkMonSTR, a computational framework that combines STR-specific error modeling with machine learning to accurately detect and distinguish genuine mosaic short tandem repeat mutations from sequencing noise and germline variants in bulk sequencing data, outperforming existing methods across diverse sample types.
The authors present VicMAG, an open-source visualization tool designed to comprehensively display circular metagenome-assembled genomes (cMAGs) with annotations for virulence factors, antimicrobial resistance genes, and mobile genetic elements, thereby facilitating holistic surveillance of bacterial pathogen spread in clinical and environmental settings.
This study systematically benchmarks protein language models against BLAST for enzyme commission number prediction, demonstrating that while simple MLP classifiers match BLAST's performance on in-distribution proteins, they significantly outperform it for evolutionarily distant organisms, establishing that smaller PLMs with lightweight classifiers are both efficient and superior for remote homology detection.
The paper introduces PSALM, a novel protein domain annotation method that integrates a pretrained protein language model (ESM-2) with a structured probabilistic decoder to achieve domain detection sensitivity and specificity comparable to traditional HMMER tools while offering improved coverage at relaxed confidence thresholds.
This study introduces "AA substitutomics," a novel proteomic pipeline using the PIPI-C tool to identify widespread post-translational amino acid substitutions in cancer that are largely absent from genomic databases, thereby revealing critical biological implications and mechanisms of drug resistance and immune escape.
This bioinformatic study demonstrates that the upregulation of ITGB1 across multiple cancer types is significantly associated with poor prognosis and therapeutic resistance, highlighting its potential as a critical biomarker and therapeutic target for overcoming treatment evasion.
This systematic review examines the application of deep representation learning, particularly Variational Autoencoders, in cancer omics, highlighting their current dominance in subtyping and prognosis while identifying the scarcity of longitudinal data as a major barrier to modeling cancer's temporal dynamics and proposing the use of VAEs as generative models to advance time-based cancer staging.
EnzyGen2 is a 730-million-parameter protein foundation model that enables the rapid, simultaneous co-design of sequence and structure for functional de novo enzymes by leveraging multi-task learning on protein-ligand pairs, achieving superior performance and experimental validation across multiple enzyme families compared to state-of-the-art methods.
The paper introduces Flipper, a robust framework that adapts the DESeq2 statistical model to overcome limitations in current tools by integrating input controls and hierarchical normalization, thereby enabling more accurate and sensitive identification of differential RNA binding behavior in eCLIP data.
CCIDeconv is a hierarchical machine learning model that leverages subcellular spatial transcriptomics data to train a robust framework for deconvolving cell-cell interactions into specific subcellular regions (nucleus and cytoplasm) within standard non-spatial single-cell RNA sequencing datasets.
By integrating single-cell RNA sequencing with variational autoencoder modeling and agentic AI simulations, this study quantifies the transcriptional hysteresis and irreversible structural collapse in severe periodontitis, introducing a Regenerative Permission Index (RPI) that predicts the failure of biomaterial interventions in advanced disease states.
This paper introduces BlueSTARR, a retrainable deep learning framework that leverages whole-genome STARR-seq data to predict the regulatory effects of noncoding variants, revealing global signatures of purifying selection and demonstrating the model's ability to capture distance- and treatment-dependent transcription factor binding patterns.
IDBSpred is a novel sequence-based machine learning method that utilizes ESM-2 protein language model embeddings to accurately predict residue-level binding sites of intrinsically disordered proteins on structured partners, achieving high performance and providing a practical framework for studying IDP-mediated interfaces.
The paper introduces WayFindR, an R package that converts pathway data from WikiPathways and KEGG into graph structures to reveal that negative feedback loops are significantly underrepresented in current biological databases, highlighting the need for improved data curation to better understand regulatory dynamics.
The paper introduces MoCoO, a modular framework combining Variational Autoencoders, Neural ODEs, and Momentum Contrast with Phase-2 Flow Matching refinement, which systematically outperforms existing methods in capturing both discrete cell-type identities and continuous developmental trajectories across 20 scRNA-seq datasets.
This paper introduces a novel pooled experimental design and a Bayesian statistical model for whole-genome population-scale STARR-seq, enabling the high-accuracy detection and effect size estimation of rare regulatory mutations that was previously unattainable.
This study demonstrates that simple, interpretable cell-type composition metrics, particularly centered log-ratio-transformed proportions, outperform complex computational methods for unsupervised patient stratification in single-cell RNA-seq cohorts by capturing clinically relevant variation driven by cellular heterogeneity, and introduces the open-source R package scECODA to facilitate this approach.
This study introduces protein language model-based decoys for proteomics target-decoy competition and benchmarks them against classical methods, finding that while they offer superior sequence-level indistinguishability and diagnostic value, they currently do not outperform traditional reverse decoys in overall search performance.