ArticleNature communications2024
Neural network extrapolation to distant regions of the protein fitness landscape.
Article in Nature communications, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 27 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
27 citing papers in PubMed.
- Functional alignment of protein language models via reinforcement learning.Nature communications · 2026Article
- Breeding 5.0: Artificial intelligence (AI)-decoded germplasm for accelerated crop innovation.Journal of integrative plant biology · 2026Article
- Artificial intelligence and automation in enzyme engineering: evolution, advances, and future perspectives.Bioresources and bioprocessing · 2026Review
- FireProtASR 2.0: evolution-guided Design of Protein Ancestors and Successors with phylogenetics and machine learning.Briefings in bioinformatics · 2026Article
- Scalable and cost-efficient custom gene library assembly from oligopools.Science advances · 2026Article
- Rapid directed evolution guided by protein language models and epistatic interactions.Science (New York, N.Y.) · 2026Article
- Machine learning for evolutionary genetics and molecular evolution.Trends in genetics : TIG · 2026Review
- Physics-based models outperform AI weather forecasts of record-breaking extremes.Science advances · 2026Article
- Descent from a common ancestor restricts exploration of protein sequence space.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Overcoming extrapolation challenges of deep learning by incorporating physics in protein sequence-function modeling.PLoS computational biology · 2026Article
- Efficient, Few-shot Directed Evolution with Energy Rank Alignment.bioRxiv : the preprint server for biology · 2026Article
- Overcoming Extrapolation Challenges of Deep Learning by Incorporating Physics in Protein Sequence-Function Modeling.bioRxiv : the preprint server for biology · 2025Article
- SAGE-prot: scoring-assisted generative exploration for multi-objective protein design.Briefings in bioinformatics · 2025Article
- A protein dynamics-based deep learning model enhances predictions of fitness and epistasis.Proceedings of the National Academy of Sciences of the United States of America · 2025Article
- Identification and understanding of allostery hotspots in proteins: Integration of deep mutational scanning and multi-faceted computational analyses.Journal of molecular biology · 2025Review
- Unexplored regions of the protein sequence-structure map revealed at scale by a library of foldtuned language models.bioRxiv : the preprint server for biology · 2025Article
- Biophysics-based protein language models for protein engineering.Nature methods · 2025Article
- Learning sequence-function relationships with scalable, interpretable Gaussian processes.bioRxiv : the preprint server for biology · 2025Article
- Investigating the determinants of performance in machine learning for protein fitness prediction.Protein science : a publication of the Protein Society · 2025Article
- Designing diverse and high-performance proteins with a large language model in the loop.PLoS computational biology · 2025Article
Corrections and comments
- Update of
Authors and funding
4 authors.
Funding
Abstract
Machine learning (ML) has transformed protein engineering by constructing models of the underlying sequence-function landscape to accelerate the discovery of new biomolecules. ML-guided protein design requires models, trained on local sequence-function information, to accurately predict distant fitness peaks. In this work, we evaluate neural networks' capacity to extrapolate beyond their training data. We perform model-guided design using a panel of neural network architectures trained on protein G (GB1)-Immunoglobulin G (IgG) binding data and experimentally test thousands of GB1 designs to systematically evaluate the models' extrapolation. We find each model architecture infers markedly different landscapes from the same data, which give rise to unique design preferences. We find simpler models excel in local extrapolation to design high fitness proteins, while more sophisticated convolutional models can venture deep into sequence space to design proteins that fold but are no longer functional. We also find that implementing a simple ensemble of convolutional neural networks enables robust design of high-performing variants in the local landscape. Our findings highlight how each architecture's inductive biases prime them to learn different aspects of the protein fitness landscape and how a simple ensembling approach makes protein engineering more robust.
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.