Discover, rate, and discuss biology preprints.

SixPack-AbScan is a web server that computationally screens antibodies for cross-reactivity across species using epitope conservation.

stably (Python) applies error-controlled stability selection to DIA-NN output; its 17-protein pancreatic cancer panel reached held-out AUC 0.93 versus 0.82 for a published two-protein panel rescored on the same data.

ML4SD improves microbial biomanufacturing by combining active learning and high-throughput search to optimize growth-coupled production with fewer design iterations.

This paper compares GANs and VAEs for generating viable antibody sequences, finding GANs outperform VAEs when sampling strategies are optimized.

The paper presents APT, a resource that evaluates proteomics platforms and provides decision tools to select or combine them based on study requirements.

scACORN improves single-cell transcriptomic interpretation by combining specialized small language models with context-engineered agent orchestration, achieving higher accuracy and reducing unsupported gene citations.

FORGE is a configurable Nextflow pipeline for snMultiome analysis that integrates snRNA-seq and snATAC-seq data through latent-variable models and enables regulatory network inference and differential testing.

The paper examines how changes to UniProtKB and taxonomic restrictions affect metaproteomics analysis, finding reduced peptide mapping coverage but stable dominant taxonomic profiles.

CellDot improves spatial transcriptomics by accurately decontaminating transcript assignments using optimal transport, enhancing biological interpretation and spatial pattern recovery.

This paper proposes a joint learning framework for predicting drug combinations and drug-drug interactions using coupled tensor-tensor factorization with side information, achieving strong performance on new-drug prediction.

The paper develops a machine learning model to improve LAMP assay design by identifying key thermodynamic features from primer sets, achieving high classification accuracy.

Ryder normalizes epigenomic bigWig tracks against stable internal reference regions such as invariant CTCF sites, correcting background and signal separately, recovering expected perturbation effects that depth-only normalization obscured.

This study identifies 59 outer membrane β-barrel proteins from B. mallei and constructs a multi-epitope vaccine predicted to induce strong immune responses.

The paper introduces TCRdenoise, a method to denoise TCR-pMHC interaction data by clustering and similarity metrics, improving the quality of training data for predictive models.

The paper proposes using the first 10 Laplace-Beltrami eigenvalues to classify protein structures by surface shape, achieving high accuracy on benchmark datasets.

This paper introduces a new unbiased linkage disequilibrium estimator called Random Probe, which outperforms existing methods in reducing bias, especially in challenging scenarios.

This study uses molecular docking and dynamics simulations to analyze how cyclic boronate inhibitors bind to NDM1, showing they are more stable than carbapenems and their monocyclic counterparts.

The paper develops a foundation model trained on fully human heavy-chain-only antibodies, showing it captures sequence and functional constraints distinct from conventional antibody models.

The paper introduces Xpressor, a framework for cross-scale learning in biology, improving cell-type prediction and embedding quality.

ProteoformTracker models MS signals and evaluates proteoform detectability in top-down and middle-down proteomics for experimental planning.