Nature Computational Science
Nature Portfolio · Genomics & Bioinformatics · ISSN 2662-8457
- Impact (2-yr)
- 11.9
- h-index
- 75
- Open access
- 44%
- Works
- 1.1K
- Papers this month
- 14
Rebuilt
Latest in Nat Comput Sci
Newest first · last 60 days
HDOCK-Multimer (HDM) significantly outperforms existing methods in predicting large protein complex structures across multiple benchmarks.
- Open access
Hessian Interatomic Potentials (HIPs) predict molecular Hessians 10 to 100 times faster and more accurately than traditional methods in computational chemistry.
Large language models (LLMs) up to 70 billion parameters consistently fail to learn coordinate information in coordinate-category datasets, despite excelling at category patterns.
- Open access
- 13 cites
Active and geometric deep learning combined in a closed-loop workflow accurately predicts reaction outcomes and regioselectivity in drug discovery, achieving perfect pinpointing on challenging substrates.
- Open access
- 1 cites
INSPIRE achieves in situ photonic neural network training with a relative error of 0.26%, enabling efficient, adaptive optical learning systems.
CellART accurately extracts comprehensive single-cell information from high-resolution spatial transcriptomics data using multimodal integration.
Modulatability of complex oscillators is generally characterized by an equal dimension of parameters and properties, enabling effective property-based modulation.
Large language models can serve as human proxies in four distinct roles, each supporting different scientific claims and requiring unique validity criteria.
MutexaGPT enables translation of enzyme engineering intuition into physics-based models, producing actionable design proposals for two protein engineering tasks.
Physics-transfer learning enables accurate prediction of brain morphogenesis with limited labeled data, achieving strong generalization across complex biological systems.
- Open access
TDiMS descriptor outperforms existing methods by accurately capturing nonlocal intramolecular interactions with 20% higher predictive accuracy in property prediction tasks.
- Open access
PULSE accurately reconstructs metabolomic and proteomic profiles from sparse blood tests, outperforming benchmarks and enabling disease prediction with AUROCs up to 0.83.
A new framework improves out-of-distribution prediction accuracy for Buchwald-Hartwig reactions, achieving reliable results on unseen substrates and conditions.
Algorithmic curation's impact on online content consumption is inconclusive, with human preferences playing a significant role alongside algorithms.
Track Nat Comput Sci in JClub
Browse JClub
Journals this month
- bioRxiv6131
- medRxiv1703
- PNAS447
- Sci Adv354
- JAMA262
- Environ Res230
- BMJ182
- Environ Pollution165
- Nat Commun161
- Science141
- Nature138
- Lancet128
- Cell Rep120
- NEJM119
- mBio107
- Plant Cell Environ107
- Curr Biol106
- J Exp Bot106
Topics moving, week to 23 Oct 2026
- Single-cell and spatial transcriptomics6
- Neuroinflammation and Neurodegeneration Mechanisms5
- Bacteriophages and microbial interactions5
- Gut microbiota and health5
- Genomics and Phylogenetic Studies4
- Cancer Genomics and Diagnostics4
- Cancer Immunotherapy and Biomarkers4
- Alzheimer's disease research and treatments3
- Inflammatory Bowel Disease3
- Influenza Virus Research Studies3