Discover, rate, and discuss biology preprints.

The paper develops a Bayesian method to infer inheritance patterns of allelic imbalance across trios, improving ASE estimation and linking it to chromatin state and causal variants.

IDBSpred predicts IDP-binding sites on structured proteins using ESM-2 embeddings and a multilayer perceptron, achieving an ROC AUC of 0.87.

PaSCient learns patient-level disease representations from scRNA-seq data, enabling disease classification and downstream analyses like dimensionality reduction and patient subgroup discovery.

scTGCL improves scRNA-seq clustering by using a Transformer-based graph contrastive learning framework that handles dropout and noise, achieving high accuracy and efficiency.

BCAR improves barcode-sequence mapping by accurately aligning reads and correcting sequencing errors, outperforming existing methods on simulated and experimental data.

The paper evaluates methods for patient stratification in scRNA-seq cohorts and finds that cell-type composition-based approaches outperform complex methods in stratification performance and computational efficiency.

eSIG-Net predicts how single mutations affect protein interactions using a sequence-based interaction language model, outperforming existing methods.

The paper introduces a method using Krylov subspace trajectories for analyzing biological networks, demonstrating its application in community detection and perturbation analysis on the C. elegans neural network.

This paper introduces a method to identify proteins with identical topology but different conformations from the PDB, enabling the study of large-scale structural dynamics.

This paper introduces a zero-shot framework to predict spatial transcriptomes of mutants using single-cell RNA sequencing data without requiring spatial reference atlases.

ARNy Plotter provides a web-based platform for analyzing and visualizing RNA structural ensembles, offering tools for dynamic analysis and result sharing.

The paper uses stochastic models to analyze clonal data from non-human primates, showing that HSC heterogeneity and quiescence are critical for long-term hematopoiesis.

The paper develops a transformer model to predict codon sequences from amino acids, improving rare codon prediction and linking sequence variation to protein function.

This paper introduces a fast method to predict protein contact maps from sequences, achieving high accuracy in 110 milliseconds.

The paper systematically extracts and catalogs acylcarnitine metabolites from multiple repositories, identifying previously unknown carnitines and providing a resource for further metabolic research.

EnzyGen2 co-designs protein sequences and structures with ligand-guided functionality, outperforming existing methods in in silico benchmarks and generating active enzymes with high novelty.

The paper curates and harmonizes celiac disease gut microbiome sequencing data into a repository to enable large-scale analysis and machine learning applications.

The paper introduces BlueSTARR, a predictive modeling framework trained on whole-genome STARR-seq data to assess variant effects on regulatory functions, revealing purifying selection against loss-of-function and gain-of-function variants.

SLiMMine predicts short linear motifs in the human proteome with high reliability, reducing false positives and discovering novel motifs.