Discover, rate, and discuss biology preprints.

This paper introduces a hybrid DCNN-WOA framework for brain tumor detection and classification, achieving high accuracy and outperforming existing methods on an MRI dataset.

The paper constructs a spatially resolved APA atlas across 18 human tissues and 76 diseases using SpatialAPA, revealing organ-specific APA patterns and their role in disease progression.

ExplainBind predicts protein-ligand binding likelihood and identifies key residues and non-covalent interactions without structural inputs, outperforming existing methods and enabling drug discovery insights.

This paper introduces a stereochemistry-aware framework for drug-target affinity prediction, showing improved accuracy in distinguishing enantiomer affinities.

This study shows intra-slide calibration technology improves inter-laboratory consistency in immunohistochemical analysis of glioblastoma samples through computational methods.

The scFAIR Consortium develops a unified metadata schema and portal to improve FAIRness of scRNA-seq data through standardized annotations and semantic search.

go3 provides a fast and lightweight Rust-based library for calculating semantic similarity of GO terms and genes, achieving significant speed and memory improvements over existing tools.

DipSkmer improves population genomics by accurately estimating genetic diversity in diploid organisms using low-coverage genome skims, outperforming existing methods.

DDI_single improves multi-domain protein structure prediction by accurately assembling domains using a single sequence and a novel gated cross-attention module.

Chromatix provides a differentiable, GPU-accelerated wave-optics library to enable fast and parallelized optical simulations for computational optics applications.

The paper identifies sex- and brain region-specific pericyte signaling changes in Alzheimer's Disease using single-nucleus RNA sequencing and spatial transcriptomics.

This study develops GLM-Missense, a genomic language model fine-tuned for missense variant impact prediction, showing it captures nucleotide-level effects missed by existing predictors.

PhyloNOW improves phylogenomic analyses by allowing variable window sizes across chromosomes, outperforming fixed-size methods on simulated data and showing size variation in empirical datasets.

This paper generalizes the Gaussian Network Model using spanning-tree thermodynamics to show that KRAS activation is driven by entropy-enthalpy compensation.

The paper introduces HydraMPP, a lightweight Python library for distributed massive parallel processing that addresses limitations of existing frameworks like Ray.

TRACEY updates SNARE protein domain annotation with improved HMMs and expanded sequence coverage, improving domain detection across species.

Metadata Collector is an open-source platform designed to standardize metadata management in multi-centre sequencing projects, ensuring FAIR-aligned and reproducible metadata across distributed research groups.

The paper introduces a multi-LLM consensus framework that improves cell type annotation accuracy for scRNA-seq data by 15% across 50 datasets.

The paper benchmarks model scaling in AI-driven drug discovery, finding that compact models often outperform larger ones across various molecular property and activity prediction tasks.

SO_SCPLOWTACKC_SCPLOW is a foundation model trained on human single-cell data that enables in-context learning for predicting perturbation effects without fine-tuning.