AI Protein Design & Structure Prediction
AlphaFold and successors, diffusion-based protein design, inverse folding and de novo binders and enzymes.
Most influential
- Highly accurate protein structure prediction with AlphaFold
Abstract Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort 1–4 , the structures of around 100,000 unique proteins have been determined 5 , but this represents a small fraction of the billions of known protein sequences 6,7 . Structural covera…
Abstract excerpt by John Jumper et al., CC-BY, https://doi.org/10.1038/s41586-021-03819-2; truncated.
Article43,700 citationsdoi:10.1038/s41586-021-03819-2 - Accurate structure prediction of biomolecular interactions with AlphaFold 3
Abstract The introduction of AlphaFold 2 1 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design 2–6 . Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of com…
Abstract excerpt by Josh Abramson et al., CC-BY, https://doi.org/10.1038/s41586-024-07487-w; truncated.
Article15,805 citationsdoi:10.1038/s41586-024-07487-w - UniProt: the Universal Protein Knowledgebase in 2023
The aim of the UniProt Knowledgebase is to provide users with a comprehensive, high-quality and freely accessible set of protein sequences annotated with functional information. In this publication we describe enhancements made to our data processing pipeline and to our website to adapt to an ever-increasing information content. The number of sequences in Un…
Abstract excerpt by the authors, CC-BY, https://doi.org/10.1093/nar/gkac1052; truncated.
Article6,891 citationsdoi:10.1093/nar/gkac1052 - AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models
The AlphaFold Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) is an openly accessible, extensive database of high-accuracy protein-structure predictions. Powered by AlphaFold v2.0 of DeepMind, it has enabled an unprecedented expansion of the structural coverage of the known protein-sequence space. AlphaFold DB provides programmatic acc…
Abstract excerpt by Mihály Váradi et al., CC-BY, https://doi.org/10.1093/nar/gkab1061; truncated.
Article7,841 citationsdoi:10.1093/nar/gkab1061 - Protein complex prediction with AlphaFold-MultimerArticle3,795 citationsdoi:10.1101/2021.10.04.463034
- InterPro: the protein sequence classification resource in 2025
InterPro (https://www.ebi.ac.uk/interpro) is a freely accessible resource for the classification of protein sequences into families. It integrates predictive models, known as signatures, from multiple member databases to classify sequences into families and predict the presence of domains and significant sites. The InterPro database provides annotations for …
Abstract excerpt by Blum M et al., CC-BY, https://doi.org/10.1093/nar/gkae1082; truncated.
Article1,063 citationsdoi:10.1093/nar/gkae1082 - AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences
The AlphaFold Database Protein Structure Database (AlphaFold DB, https://alphafold.ebi.ac.uk) has significantly impacted structural biology by amassing over 214 million predicted protein structures, expanding from the initial 300k structures released in 2021. Enabled by the groundbreaking AlphaFold2 artificial intelligence (AI) system, the predictions archiv…
Abstract excerpt by Mihály Váradi et al., CC-BY, https://doi.org/10.1093/nar/gkad1011; truncated.
Article2,049 citationsdoi:10.1093/nar/gkad1011 - De novo design of protein structure and function with RFdiffusion
There has been considerable recent progress in designing new proteins using deep-learning methods 1-9 . Despite this progress, a general deep-learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher-order symmetric architectures, has yet to be described. Diffusion m…
Abstract excerpt by Watson JL et al., CC-BY, https://doi.org/10.1038/s41586-023-06415-8; truncated.
Article1,906 citationsdoi:10.1038/s41586-023-06415-8 - Improved protein structure prediction using potentials from deep learningArticle3,381 citationsdoi:10.1038/s41586-019-1923-7
- Highly accurate protein structure prediction for the human proteome
Abstract Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure 1 . Here we markedly …
Abstract excerpt by Kathryn Tunyasuvunakool et al., CC-BY, https://doi.org/10.1038/s41586-021-03828-1; truncated.
Article3,023 citationsdoi:10.1038/s41586-021-03828-1 - Robust deep learning–based protein sequence design using ProteinMPNN
Although deep learning has revolutionized protein structure prediction, almost all experimentally characterized de novo protein designs have been generated using physically based approaches such as Rosetta. Here, we describe a deep learning-based protein sequence design method, ProteinMPNN, that has outstanding performance in both in silico and experimental …
Abstract excerpt by Justas Dauparas et al., CC-BY, https://doi.org/10.1126/science.add2187; truncated.
Article2,102 citationsdoi:10.1126/science.add2187 - Ensembl 2023
Ensembl (https://www.ensembl.org) has produced high-quality genomic resources for vertebrates and model organisms for more than twenty years. During that time, our resources, services and tools have continually evolved in line with both the publicly available genome data and the downstream research and applications that utilise the Ensembl platform. In recen…
Abstract excerpt by Fergal J. Martin et al., CC-BY, https://doi.org/10.1093/nar/gkac958; truncated.
Article1,028 citationsdoi:10.1093/nar/gkac958 - ProtGPT2 is a deep unsupervised language model for protein design
Abstract Protein design aims to build new proteins from scratch thereby holding the potential to tackle many environmental and biomedical problems. Recent progress in the field of natural language processing (NLP) has enabled the implementation of ever-growing language models capable of understanding and generating text with human-like capabilities. Given th…
Abstract excerpt by Noelia Ferruz et al., CC-BY, https://doi.org/10.1038/s41467-022-32007-7; truncated.
Article795 citationsdoi:10.1038/s41467-022-32007-7 - Dali server: structural unification of protein families
Protein structure is key to understanding biological function. Structure comparison deciphers deep phylogenies, providing insight into functional conservation and functional shifts during evolution. Until recently, structural coverage of the protein universe was limited by the cost and labour involved in experimental structure determination. Recent breakthro…
Abstract excerpt by Holm L, CC-BY, https://doi.org/10.1093/nar/gkac387; truncated.
Article890 citationsdoi:10.1093/nar/gkac387 - The Pfam protein families database: embracing AI/ML
The Pfam protein families database is a comprehensive collection of protein domains and families used for genome annotation and protein structure and function analysis (https://www.ebi.ac.uk/interpro/). This update describes major developments in Pfam since 2020, including decommissioning the Pfam website and integration with InterPro, harmonization with the…
Abstract excerpt by Typhaine Paysan‐Lafosse et al., CC-BY, https://doi.org/10.1093/nar/gkae997; truncated.
Article362 citationsdoi:10.1093/nar/gkae997
Newest work
- Accurate structural modelling of protein-glycan recognition with GlycoWeavePreprintarXiv:2610.37410
- Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson LoopsPreprintarXiv:2610.37656
- Computational De Novo Design of Miniprotein Candidate Neutralizers Targeting the IL-23 Cytokine Subunit p19PreprintarXiv:2610.32779
- Agent-guided epitope excision enables economical de novo binder designPreprintarXiv:2610.33195
- Challenges in AI-based structural modeling of host-pathogen protein interactionsReviewdoi:10.1016/j.coviro.2026.101587
- ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and ModelPreprintarXiv:2610.26009
- The Effectiveness and Durability of Pretraining Data Filtering in Protein Language ModelsPreprintarXiv:2610.26651
- recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language ModelsPreprintarXiv:2610.26747
- PDKE-G: A Bio-Inspired Contributory Group Authenticated Key Exchange Grounded in Per-Member AlphaFold2 Protein GeometryArticledoi:10.3390/biomimetics11100753
- Generative Retrieval for Reverse Target Fishing with a Proteome-Scale BenchmarkPreprintarXiv:2610.24458