Discover, rate, and discuss biology preprints.

The paper integrates glycosylation filtering into a protein design pipeline to improve efficiency and reduce costs in binder design.

The paper develops a computational model for Zika virus sequence and secondary structure analysis using VADR, achieving high validation accuracy and extending the tool to generate structural diagrams and submit new RNA elements.

MutCleaner standardizes mutation datasets for variant effect prediction by cleaning, validating, and organizing mutation records across 16 datasets with over 12.14 million entries.

DELPHI is an open platform for predicting antibody developability from sequence, achieving high AUC scores and enabling residue-level engineering insights.

The paper implements a differentiable AdEx neuron model with surrogate gradients, showing it is faster than traditional methods but gradient-based fitting still struggles with spike mechanisms.

The paper identifies RSX interactors and shows they form phase-separation-prone networks, suggesting convergent evolution of XCI mechanisms through biophysical principles rather than sequence or structure.

The paper evaluates cross-species survival modeling in osteosarcoma, finding that prognostic compatibility does not ensure safe transfer utility due to negative transfer and model-selection bias.

NoroScope uses context-aware machine learning to prioritize amino-acid substitutions in the norovirus capsid protein, achieving high precision in predicting mutation effects with limited data.

miRstring decodes mature miRNA boundaries from precursor context across species and designs artificial miRNAs effectively.

This paper introduces PLABench, a benchmarking framework for protein-ligand binding affinity prediction, revealing that structural input and training scale alone do not ensure cross-target generalization.

The paper addresses volumetric cell segmentation challenges due to limited labelled data by using synthetic 3D objects to generate unlimited training data, achieving accurate segmentations of real biological data.

The paper introduces DYNAM-O, a toolbox for analyzing sleep EEG to identify individualized transient oscillations, finding sex differences in oscillatory activity.

Kmask reduces misclassifications in metagenomics by masking low-complexity regions, improving accuracy in bacterial, archaeal, viral, and fungal classification.

PANDA analyzes targeted bisulfite amplicon sequencing data to assess methylation patterns and heterogeneity at the read level.

RKMR identifies predictive marker panels in spatial omics data using a scalable framework that integrates kernel modeling and spatial dependence.

MIRCID improves drug mechanism modeling by integrating inferred hub miRNAs with gene expression and TF activity, showing better performance than TF activity alone.

The paper identifies the chromatoid body as a dynamic RNA sorting center in spermatogenesis, revealing its role in RNA surveillance and transcript regulation through sequence and structural features.

FourC identifies significant and differential contacts in 4C-seq data using a Bayesian model and Gaussian processes to address duplication and model spatial patterns.

The paper introduces REAL-SWIT, a generative framework for ultra-large virtual screening that efficiently explores chemical space by generating molecules with favorable docking scores.

The paper evaluates multi-view gene representations under a matched contract, showing condition-dependent fusion operator rankings across different view combinations and tasks.