# Efficient Searches in Protein Sequence Space Through AI-Driven Iterative Learning

## TL;DR

AI tools can efficiently find high-performing protein variants and predict viral evolution using only a few hundred experiments.

## Contribution

Demonstrates that AI can rapidly identify high-fitness enzyme variants and predict antibody evasion with minimal experimental data.

## Key findings

- AI models identified high-fitness enzyme variants after training on just a few hundred sequences.
- AI accurately predicted antibody evasion patterns in the SARS-CoV-2 RBD with limited data.
- The approach enables low-throughput, efficient protein engineering and viral evolution analysis.

## Abstract

The protein sequence space is vast. This fact, together with the prevalence of epistasis, hampers the engineering of novel enzymes through library screening and is a major obstacle to any attempt to predict natural protein evolution. Recently, specialized methodologies have been used to determine fitness data on ~260,000 sequences for the gene of the enzyme dihydrofolate reductase and antibody affinity data for all combinations of the mutations present in the receptor-binding domain (RBD) of the Omicron strain of SARS-CoV-2 (~30,000 variants). We show that upon iterative training on a total of just a few hundred variants, various state-of-the-art AI tools (multi-layer perceptron, random forest, and XGBoost algorithms) find very high fitness variants of the enzyme and predict the antibody evasion patterns of the RBD. This work provides a basis for efficient, widely applicable, low-throughput experimental approaches to assess viral protein evolution and to engineer enzymes for biotechnological applications.