Neural network extrapolation to distant regions of the protein fitness landscape
Fahlberg, S. A.; Freschlin, C. R.; Heinzelman, P.; Romero, P. A.
Show 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. Our findings highlight how each architectures inductive biases prime them to learn different aspects of the protein fitness landscape.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Meta Learning Improves Robustness and Performance in Machine Learning-Guided Protein Engineering 96%
- Rugged fitness landscapes minimize promiscuity in the evolution of transcriptional repressors 95%
- FlowDesign: Improved Design of Antibody CDRs Through Flow Matching and Better Prior Distributions 95%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.