Discover, rate, and verify biology preprints.

DUET: a sequence-only ensemble for RNA-small molecule binding-site prediction

DUET is a sequence-only ensemble model for RNA-small molecule binding-site prediction that outperforms existing methods on benchmark datasets.

Genomic heterogeneity inflates the performance of variant pathogenicity predictions

The paper evaluates AI models for predicting pathogenic variants, finding that performance is inflated by genomic heterogeneity in pathogenic variant prevalence.

Fox: Predicting rates of host-symbiont co-evolution events with association-aware attention

Fox predicts host-symbiont co-evolution event rates directly from sequence alignments without tree reconstruction, achieving high accuracy and speed compared to existing methods.

Representation learning of somatic missense mutation landscapes across cancer types

This paper introduces MMRL, a framework for learning representations of somatic missense mutations across cancer types, showing improved prognostic discrimination and identification of mutation subtypes.

Protein co-scientist aided simulations of the structural and functional impact of O-GlcNAc Transferase TPR domain deletions and amino acid substitutions associated with X-Linked Intellectual Disability

The paper uses computational methods to model structural and functional impacts of TPR domain deletions and amino acid substitutions in OGT linked to X-Linked Intellectual Disability.

RankMap: Rank-based reference mapping for fast and robust cell type annotation in spatial and single-cell transcriptomics

RankMap improves cell type annotation in spatial and single-cell transcriptomics by using rank-based representations and multinomial regression, achieving competitive accuracy and faster runtime.

SiSaNA: A Python-based command line interface for Single-Sample Network Analysis

SiSaNA provides a command line interface for single-sample regulatory network analysis without requiring programming experience.

Carrier-Limited Release Risk in Electrospun Nanofibers for Regenerative Endodontics: Constraint Discovery from 25 Formulations

The paper evaluates 25 electrospun PVP fiber formulations for regenerative endodontics, using machine learning to identify constraints and release risks, finding carrier-limited release and recommending further testing.

Negative sampling shapes benchmark discrimination and experimental retrieval in synthetic-lethality prediction

The paper evaluates how negative sampling affects synthetic-lethality prediction models, showing that benchmark performance does not reliably predict experimental retrieval success.

Kontext: Kernel-based method bridging spatial domain identification and cell-cell communication

Kontext identifies spatial domains and cell-cell communication by integrating ligand-receptor interactions, outperforming existing methods in spatial transcriptomics.

PatHoST: weakly supervised reconstruction of pathogen spatial distributions from host transcriptomes

PatHoST reconstructs pathogen spatial distributions from host transcriptomes using weakly supervised learning, showing improved detection in both experimental and human SARS-CoV-2 data.

VoroTIDE: Protein domain segmentation through independent hierarchical searches using Voronoi tessellation and physical self-containment

VoroTIDE segments protein domains using Voronoi contact areas and self-containment scores, achieving strong performance on benchmark datasets.

Multiscale Transcriptomic Architecture of the ALS Motor Cortex

The paper identifies seven subtypes of ALS motor cortex with distinct molecular programs and shows they are organized by genetic and clinical factors rather than disease duration.

Mechanistic gene-regulation-based trajectory inference with bowside

The paper introduces bowside, a neural model for trajectory inference and gene regulatory network reconstruction in single-cell RNA sequencing data, showing it recovers known regulatory motifs in hematopoiesis and reprogramming.

smoothclust: Spatial smoothing and boundary-density summaries for spatial transcriptomics

smoothclust provides a framework for spatial domain analysis in spatial transcriptomics, including a clustering workflow and a boundary density metric to summarize tissue architecture.

mock-fastq-generator: A synthetic FASTQ generator

mock-fastq-generator creates synthetic FASTQ files for testing bioinformatics pipelines without using biological data.

Identification of environmental factors and growth stages in the prediction of fibre yield and fibre quality traits in rain-grown cotton

The paper identifies environmental factors and growth stages affecting fibre yield and quality in rain-grown cotton using statistical models and field data.

Network analysis reveals converging molecular mechanisms in genetic epilepsies

The paper identifies converging molecular pathways in genetic epilepsies through network analysis of epilepsy-associated genes and highlights potential therapeutic targets.

Alignment-Free k-mer Analysis Reveals Age-Associated k-mer Signals in Canine Buccal DNA and Cell-Free DNA

This study identifies age-associated k-mer signals in canine buccal and cell-free DNA using alignment-free k-mer analysis and ridge regression models.

Assembly of minimally fragmented metagenomic pangenome graphs

The paper introduces PANIMaSTA, a method to construct minimally fragmented metagenomic pangenome graphs for highly diverse viral genomes, improving graph topology for comparative analysis.