Discover, rate, and discuss biology preprints.

This paper quantifies how Evo2 likelihood scores calibrate with fitness across five E. coli datasets, showing context-dependent calibration that varies by selection regime and sequence divergence.

The paper investigates the location dependence of protein intrinsic disorder in Drosophila melanogaster, finding that disorder is more common at terminals and linked to specific functions like protein-binding.

The paper identifies RNA editing signatures associated with AML disease stage and risk, showing their potential for peripheral blood-based disease assessment.

ClonoTrace integrates BCR sequences with transcriptomics to improve trajectory inference in B cell development and disease, identifying novel pathways in autoimmunity and aging.

This paper introduces FastBindRank, a distillation-based framework for high-fidelity virtual screening of large chemical libraries, achieving higher hit rates and discovery yields than traditional methods.

RD-OMICS integrates and structures rare disease omics data from GEO into a knowledge graph to support research and drug repurposing.

This paper introduces AMPHORA, a pathogen-conditioned generator of antimicrobial peptides, showing that incorporating pathogen-specific features improves peptide design and potency.

This paper uses pre-trained LLMs to enhance Bayesian optimization for selecting superior genotypes from germplasm collections, improving efficiency with passport data and genomic information.

ProLoc localizes protein functional regions using text guidance, outperforming existing methods on a new benchmark.

StructureSAFE is a chemical language model that combines protein structure and evolutionary information with molecular representations to improve hit identification and lead optimization, achieving state-of-the-art performance in chemical plausibility and binding affinity prediction.

The paper develops a Cell Size Score (CSS) to predict cell size from gene expression and validates its utility in disease and physiological contexts.

ProteoDUDes improves taxonomic profiling in metaproteomics by reducing false positives, achieving higher accuracy in identifying active organisms in complex samples.

The paper investigates late diploidization after three polyploidies by analyzing gene tree discordance using the POInT tool.

WattmaMod detects multiple RNA modifications from nanopore sequencing data using deep learning, achieving high accuracy and extending to low-resource modifications.

GAZE predicts metabolite concentrations from gene expression using a physics-informed graph neural network, achieving better performance than existing methods in zero-shot scenarios.

This paper introduces PhyloTrajectory, a method that uses TCR clonotype frequencies and scRNA-seq to infer T cell differentiation trajectories.

The paper evaluates pocket detection methods across molecular dynamics simulations to identify conserved and transient druggable sites in proteins.

This paper improves the minimum flow decomposition algorithm for bioinformatics tasks by jointly modeling equations in flow networks, achieving faster and more accurate results.

BacNeMu reconstructs bacterial neutral mutation spectra using phylogenetic analysis and open databases, matching mutation accumulation experiments with less time.

SpaGRD models cell-cell communication using graph reaction-diffusion systems, revealing spatially resolved signaling patterns in spatial transcriptomics data.