Computational biology and bioinformatics articles from across Nature Portfolio

Computational biology and bioinformatics is an interdisciplinary field that develops and applies computational methods to analyse large collections of biological data, such as genetic sequences, cell populations or protein samples, to make new predictions or discover new biology. The computational methods used include analytical methods, mathematical modelling and simulation.

Featured

Machine learning for accelerating discovery from single-molecule data

Manual analysis of single-molecule time traces is slow and subjective. Now, a transformer-based foundation model — META-SiM —automates key analysis tasks across diverse datasets and enables rapid, systematic discovery of subtle single-molecule behaviors. Application of this approach reveals a previously undetected pre-mRNA splicing intermediate, highlighting its potential to streamline biological discovery.

News & Views02 Oct 2025 Nature Methods
P: 1-2
AI uses medical records to accurately predict onset of disease 20 years into the future

An artificial-intelligence model trained on health-care records uses a person’s medical history to estimate whether and when any of more than 1,200 diseases might arise.
- Yonghui Wu
News & Views30 Sept 2025 Nature
What does a language model know about proteins?

A new approach sheds light on the biological features learned by protein language models, promising greater interpretability for unsupervised sequence learning.
- Jeffrey A. Ruffolo
News & Views29 Sept 2025 Nature Methods
P: 1-3

Related Subjects

Latest Research and Reviews

HALO: hierarchical causal modeling for single cell multi-omics data

Chromatin accessibility dynamics causally influence changes in gene expression levels, but these fluctuations may not be directly coupled over time. Here, authors develop computational causal framework HALO, examining epigenetic plasticity and gene regulation dynamics in single-cell multi-omic data.
- Haiyi Mao
- Minxue Jia
- Panayiotis V. Benos
ResearchOpen Access07 Oct 2025 Nature Communications
Volume: 16, P: 8892
Genotyping short tandem repeats across copy number alterations, aneuploidies, and polyploid organisms

ConSTRain is a short tandem repeat caller allowing for the investigation of tumour heterogeneity and clonal lineage tracing in cancer, even in closely related samples.
- Max A. Verbiest
- Elena Grassi
- Maria Anisimova
ResearchOpen Access07 Oct 2025 Communications Biology
Volume: 8, P: 1437
A histomorphological atlas of resected mesothelioma discovered by self-supervised learning from 3446 whole-slide images

Mesothelioma is a highly lethal cancer that remains challenging to diagnose. Here, the authors curate a histomorphological atlas of resected mesothelioma and map it using self-supervised AI endorsed by human pathological assessment, revealing patterns that generate highly interpretable predictions.
- Farzaneh Seyedshahi
- Kai Rakovic
- John Le Quesne
ResearchOpen Access07 Oct 2025 Nature Communications
Volume: 16, P: 8891
Scalable long-read nanopore HPV16 amplicon-based whole-genome sequencing
- Maina K. Titus
- David Giesbrecht
- Jeffrey A. Bailey
ResearchOpen Access07 Oct 2025 Scientific Reports
Volume: 15, P: 34892
HCS-3DX, a next-generation AI-driven automated 3D-oid high-content screening system

Standardisation of working with 3D cell cultures in high-content screening (HCS) approaches remains difficult. Here, the authors propose HCS-3DX, a system for HCS of 3D tumour models at single-cell resolution by combining micromanipulation, custom multi-well plates, advanced imaging and AI-based analysis.
- Akos Diosdi
- Timea Toth
- Peter Horvath
ResearchOpen Access07 Oct 2025 Nature Communications
Volume: 16, P: 8897
Synergistic enhancement of detection-tracking framework for zebrafish shoaling behavior analysis
- Chen Chen
- Natalia Binti Ali
- Youquan Zhao
ResearchOpen Access07 Oct 2025 Scientific Reports
Volume: 15, P: 34945

All Research & Reviews

News and Comment

Customizable AI systems that anyone can adapt bring big opportunities — and even bigger risks

Open and adaptable artificial-intelligence models are crucial for scientific progress, but robust safeguards against their misuse are still nascent.
- Yarin Gal
- Stephen Casper
Comments & Opinion07 Oct 2025 Nature
Volume: 646, P: 286-287
Will AI ever win its own Nobel? Some predict a prize-worthy science discovery soon

Other researchers question whether autonomous AI scientists are possible or even desirable.
- Jenna Ahart
News06 Oct 2025 Nature
Volume: 646, P: 276-278
How AI agents will change research: a scientist’s guide

Researchers are increasingly turning to artificial-intelligence tools that can handle complex, multi-step processes.
- Elizabeth Gibney
News03 Oct 2025 Nature
AI has designed thousands of potential antibiotics. Will any work?

Machine learning can speed up the discovery of potential antibiotics, but challenges remain.
- Rachel Fieldhouse
News03 Oct 2025 Nature
Machine learning for accelerating discovery from single-molecule data

Manual analysis of single-molecule time traces is slow and subjective. Now, a transformer-based foundation model — META-SiM —automates key analysis tasks across diverse datasets and enables rapid, systematic discovery of subtle single-molecule behaviors. Application of this approach reveals a previously undetected pre-mRNA splicing intermediate, highlighting its potential to streamline biological discovery.

News & Views02 Oct 2025 Nature Methods
P: 1-2
AI is dreaming up millions of new materials. Are they any good?

Critics slammed attempts by Google, Microsoft and Meta to speed up materials discovery. But behind the hype, there is progress.
- Mark Peplow
News01 Oct 2025 Nature
Volume: 646, P: 22-25