Discover, rate, and discuss biology preprints.

This paper introduces Histo3D-MO, a framework for reconstructing 3D spatial multi-omics maps at single-cell resolution, revealing spatial patterns in tumor microenvironments.

The paper calibrates a spatial QSP model using CODEX data to predict TME states and identify biomarkers for HCC immunotherapy response.

The paper introduces improved 3D radial spiral trajectories for MRI that enhance image quality by reducing ringing artifacts and supporting sequential binning.

The paper benchmarks machine learning models for predicting gene expression from epigenomic data using the IHEC EpiATLAS dataset and identifies genes linked to B-cell leukemia.

This paper introduces PeptideCLM-2, a chemical language model for therapeutic peptides, showing strong performance in predicting drug development endpoints.

This paper introduces DeepDETAILS, a method to reconstruct cell-type-specific genomic signals from bulk data, outperforming traditional methods and providing insights into disease mechanisms.

BayesTx identifies causal cancer drug targets by integrating patient and cell line data using Bayesian networks, ranking 47 transcription factors and validating them with survival and drug response data.

This study evaluates if ensembling improves feature attributions from sequence-to-activity models, finding that it enhances downstream applications like motif identification and variant prediction.

TEDlm is a domain-centric protein language model that improves remote-homology detection and Molecular Function prediction by pretraining on structurally-defined domain sequences.

This paper evaluates AlphaFold3's performance across diverse structural biology tasks, finding uneven accuracy and strong dependence on training data.

This study evaluates how model selection, imaging instruments, and color information affect zooplankton classification using CNNs, finding that EfficientNetV2S performs best and color information provides limited benefit.

ORIGAMI improves assessment of multimeric protein complex structures by incorporating orientation-aware geometric features into graph neural networks, achieving better performance than existing methods.

The paper identifies divergent transcriptomic transition programs in Alzheimer's disease between females and males, showing distinct molecular pathways in disease progression.

SSUplex is a tool for extracting and sorting small-subunit rRNA reads by origin, improving accuracy in environmental DNA metabarcoding.

This paper introduces bAIes, a method that improves AlphaFold2 models using Bayesian inference to enhance virtual screening accuracy for drug discovery.

This study identifies sex-dimorphic aging patterns in cardiovascular disease genes using multi-omics data and prioritizes actionable biomarkers with convergent evidence.

The paper introduces CPP2Vec, a Word2Vec-based method for predicting cell-penetrating peptides, and compares it with pre-trained LLM-based models, showing strong predictive performance.

The paper investigates whether structural transfer between natural language and biological foundation models is directional, finding that transfer from language to biology is stronger than the reverse.

The paper introduces amR, an R package suite for predicting antimicrobial resistance in bacterial pathogens using genome data and interpretable machine learning models.

The paper identifies genes near tRNAs in fungal genomes that are enriched in proteasome regulation, ion transport, and rRNA, suggesting local co-regulation of protein synthesis and quality control.