ArticleScience (New York, N.Y.)2024
Unsupervised evolution of protein and antibody complexes with a structure-informed language model.
Article in Science (New York, N.Y.), 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 77 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
77 citing papers in PubMed.
- Prediction of antibody non-specificity using protein language models and biophysical parameters.mAbs · 2026Article
- Machine learning-assisted directed evolution of plant Rubisco.Science advances · 2026Article
- Graph-based representations in modern protein science.The Biochemical journal · 2026Review
- Multiobjective VScience advances · 2026Article
- Aligning protein-generative models to experimental fitness with ProteinDPO.Nature methods · 2026Article
- R1-32-like public antibodies acquire tolerance to SARS-CoV-2 antigenic drift through somatic hypermutation.PLoS biology · 2026Article
- Enhancing Enzyme Activity With Mutation Combinations Guided by Few-Shot Learning and Causal Inference.Angewandte Chemie (International ed. in English) · 2026Article
- Evolutionary profiles for protein fitness prediction.Bioinformatics (Oxford, England) · 2026Article
- Multi-objective antibody design and optimization using machine learning.Nature reviews bioengineering · 2026Article
- PreFold-dG: estimating binding affinity of protein-protein interaction from intermediate representations of protein folding model.Bioinformatics (Oxford, England) · 2026Article
- Article
- Structure and evolution-guided design of minimal RNA-guided nucleases.Science (New York, N.Y.) · 2026Article
- Artificial intelligence in biologic drug discovery: A review of methodological evolution and therapeutic applications.Acta pharmaceutica Sinica. B · 2026Review
- Efficient generation of epitope-targeted antibodies with Germinal.Nature biotechnology · 2026Article
- Sequence redesign of glycosyltransferases for enhanced heterologous expression and glycosylation efficiency in Escherichia coli.Nature communications · 2026Article
- Protein design and RNA design: Perspectives.Quantitative biology (Beijing, China) · 2026Article
- Generalist biological artificial intelligence in modeling the language of life.Nature biotechnology · 2026Review
- A tri-modal contrastive learning framework for protein representation learning.Cell reports methods · 2026Article
- Rapid directed evolution guided by protein language models and epistatic interactions.Science (New York, N.Y.) · 2026Article
- pLM-Repeat: Exploiting the sequence representations of protein language models for sensitive repeat detection.Protein science : a publication of the Protein Society · 2026Article
17 more citing papers are in PubMed but not listed here.
Corrections and comments
- Commented on by
- Update of
Authors and funding
4 authors.
Funding
Abstract
Large language models trained on sequence information alone can learn high-level principles of protein design. However, beyond sequence, the three-dimensional structures of proteins determine their specific function, activity, and evolvability. Here, we show that a general protein language model augmented with protein structure backbone coordinates can guide evolution for diverse proteins without the need to model individual functional tasks. We also demonstrate that ESM-IF1, which was only trained on single-chain structures, can be extended to engineer protein complexes. Using this approach, we screened about 30 variants of two therapeutic clinical antibodies used to treat severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. We achieved up to 25-fold improvement in neutralization and 37-fold improvement in affinity against antibody-escaped viral variants of concern BQ.1.1 and XBB.1.5, respectively. These findings highlight the advantage of integrating structural information to identify efficient protein evolution trajectories without requiring any task-specific training data.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.