💻 Category

bioinformatics

1178 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.

💻 bioinformatics

Ark-ADMET: endpoint-specific selection of molecular representations and hyperparameters for gradient-boosted ADMET models under the Therapeutics Data Commons benchmark protocol

The Ark-ADMET study demonstrates that tailoring molecular representations and CatBoost hyperparameters to individual ADMET endpoints, rather than applying a uniform architecture across all tasks, yields competitive or superior performance on the Therapeutics Data Commons benchmark without requiring new model architectures.

Shi, Y., Luo, H., Liu, F., Zhao, S.2026-11-03
💻 bioinformatics

A validation approach for RNA structures based on deep-learning 3D-structure predictions

This paper presents an extension of the Conkit-validate tool to RNA, introducing a deep-learning-based, mapless validation method that leverages contact predictions to detect structural errors, such as register misassignments, particularly in cases where traditional map-based approaches are limited by low-resolution experimental data.

Voorspoels, A., Simpkin, A. J., Keegan, R., Chojnowski, G., Rigden, D. J.2026-11-03
💻 bioinformatics

Redesigning the Eterna100 RNA design benchmark for the Vienna 2 folding engine

This study demonstrates that RNA design algorithm performance is intrinsically linked to the thermodynamic models used in folding engines, leading to the creation of a revised Eterna100-V2 benchmark that reveals both the original and updated benchmarks remain unsolved under their intended settings due to prior evaluation errors and engine-specific challenges.

Koodli, R. V., Rudolfs, B., Romano, J., Wayment-Steele, H. K., Dunlap, W. A., Eterna Structure Designers,, Das, R.2026-11-03
💻 bioinformatics

Parameter-Efficient Adaptation of Protein Language Models for Dual-Target Antimicrobial Peptide Discovery Under Strict Homology Constraints

This paper introduces a parameter-efficient multi-task transfer learning framework based on ESM-2 and LoRA that successfully overcomes the limitations of frozen protein language models in predicting both antibacterial potency and hemolytic toxicity under strict homology constraints, enabling the discovery of highly selective antimicrobial peptides with superior therapeutic indices.

Jat, R., Ejaz, S. R.2026-11-03
💻 bioinformatics

SpaceBlocks: an expert-supervised workflow for cohort-level spatial transcriptomics analysis

SpaceBlocks is a reproducible, expert-supervised Snakemake workflow that homogenizes heterogeneous single-cell resolution spatial transcriptomics data across multiple platforms to enable scalable cohort-level analysis, as demonstrated by its ability to identify novel cell types, marker expression patterns, and disease-associated transcriptional differences in diverse biological datasets.

Oterino-Sogo, S., Mechkouri, N., Garcia-Ruano, D., Groppi, A., Rezvani, H.-R., Nikolski, M.2026-11-02
💻 bioinformatics

Bayesian model-based method for clustering gene expression time series with multiple replicates

This paper introduces MMDPGP, a Bayesian model-based method that utilizes Dirichlet process Gaussian processes to cluster gene expression time series with multiple replicates by modeling each replicate separately, thereby achieving superior clustering accuracy and biological insight compared to state-of-the-art approaches.

Nushi, E., Douillard, F. P., Selby, K., Lindström, M., Honkela, A.2026-11-02
💻 bioinformatics

Interpreting graph neural networks reveals microbial association patterns in inflammatory bowel diseases

By interpreting graph neural networks trained on individual-specific microbial association networks, this study reveals that coordinated co-abundance patterns of Bacteroidales species, rather than simple differential abundance, are critical predictive features of inflammatory bowel disease that traditional machine learning models often overlook.

Cunha, A. F., Vidal, E., Barranco-Altirriba, M., Amigo, T., Assis, J. G., Nakaya, H. I., Santos, A.2026-11-01
💻 bioinformatics

Single-cell perturbation prediction near experimental reproducibility with GENESIS

The paper introduces GENESIS, a generative energy-based framework that predicts single-cell perturbation responses with accuracy approaching experimental reproducibility, enabling a complementary strategy of broad, lower-depth measurements augmented by computational inference to overcome the infeasibility of exhaustive experimental atlases.

Conci, R., D'Ascenzo, D., Cultrera di Montesano, S., Raghavan, S., Winter, P. S., Van Allen, E. M., Crawford, L., Lotter (…)2026-11-01