1197 papers
Bioinformatics sits at the exciting intersection where biology meets data science, using powerful computer tools to decode the vast complexity of living systems. From mapping the human genome to tracking how viruses evolve, this field transforms raw biological information into actionable insights that drive modern medicine and research forward without requiring a supercomputer to understand the basics.
On Gist.Science, we ensure you never miss a breakthrough by processing every new preprint in this category directly from bioRxiv. Our team provides both plain-language explanations and detailed technical summaries for each paper, making cutting-edge discoveries accessible to everyone regardless of their background.
Below are the latest bioinformatics papers added from bioRxiv, ready for you to explore with clarity and depth.
The paper introduces POME, a self-supervised graph-based embedding model designed to generate low-dimensional representations for partially observed mixed-type biomedical data, achieving state-of-the-art imputation performance and enabling effective downstream tasks such as patient subgroup discovery, predictive modeling, and therapy recommendation.
The paper introduces LAMINA, an interpretable deep learning model that accurately predicts peptide-HLA binding by aggregating soft motif interactions, achieving state-of-the-art performance while emergently learning binding energetics and structural features from sequence data alone.
The paper introduces pydreg, a fast and maintainable Python reimplementation of the dREG algorithm for identifying active cis-regulatory elements from nascent transcription, which significantly reduces runtime and memory usage while preserving the original method's accuracy and compatibility with modern computing infrastructure.
By comparing matched full-UDG and non-UDG ancient DNA libraries from medieval Mongolian individuals, this study demonstrates that while various computational damage correction methods (trimming, rescaling, and masking) differentially balance site retention against error reduction, the optimal choice depends on the specific downstream analysis, with corrected data proving essential for accurate kinship inference in non-UDG libraries.
This paper presents a scalable framework integrated into the DMRcaller package that leverages native Oxford Nanopore sequencing to quantify single-molecule DNA methylation heterogeneity and detect co-methylated loci, revealing epigenetic patterns and regulatory interactions obscured by traditional site-level average analyses.
This paper presents a methodology to reconstruct the experimental search space of protein-protein interaction (PPI) screens to infer likely non-interacting protein pairs, thereby enabling better error rate estimation, model calibration, and improved machine learning training for a more accurate and complete mapping of the human interactome.
The paper introduces Inverse FoldDir, a controllable inverse-folding method based on Dirichlet flow matching that generates diverse, experimentally validated protein sequences with user-defined constraints by performing iterative denoising on the amino acid probability simplex, achieving state-of-the-art structural recovery metrics and successful functional redesign of an anti-GFP nanobody.
This study introduces the perturbation-aware Neural ODE (pNODE) framework, which outperforms traditional models by accurately forecasting gut microbiome dynamics and predicting gut-borne bloodstream infections in cancer patients undergoing allogeneic hematopoietic cell transplantation through the integration of microbial abundances and time-resolved antibiotic perturbations.
This study systematically benchmarks small variant calling and haplotype phasing pipelines for long-read RNA sequencing across diverse datasets and technologies, revealing that sequencing quality is the primary performance determinant while identifying Clair3-RNA, DeepVariant, and longcallR as top callers and WhatsHap or HapCUT2 as optimal phasing tools depending on the specific context.
This study demonstrates that while deep-learning classifiers for fungal ITS sequences achieve high accuracy on full-length references, they fail dramatically on the commonly used ITS2 subregion by relying on flanking regions rather than the barcode itself, causing classical baseline methods to significantly outperform them in realistic environmental metabarcoding scenarios.