GROOT: Effective Design of Biological Sequences with Limited Experimental Data

TL;DR

GROOT introduces a graph-based smoothing method for biological sequence design that effectively leverages limited data to improve optimization, outperforming existing approaches without extensive labeled datasets.

Contribution

GROOT presents a novel graph-based pseudo-labeling and smoothing technique for biological sequence optimization, especially effective with limited labeled data.

Findings

GROOT outperforms existing methods on protein and biological sequence tasks.

It can extrapolate beyond training data while maintaining reliability.

No need for extensive labeled data or black-box access.

Abstract

Latent space optimization (LSO) is a powerful method for designing discrete, high-dimensional biological sequences that maximize expensive black-box functions, such as wet lab experiments. This is accomplished by learning a latent space from available data and using a surrogate model to guide optimization algorithms toward optimal outputs. However, existing methods struggle when labeled data is limited, as training the surrogate model with few labeled data points can lead to subpar outputs, offering no advantage over the training data itself. We address this challenge by introducing GROOT, a Graph-based Latent Smoothing for Biological Sequence Optimization. In particular, GROOT generates pseudo-labels for neighbors sampled around the training latent embeddings. These pseudo-labels are then refined and smoothed by Label Propagation. Additionally, we theoretically and empirically justify our approach, demonstrate GROOT's ability to extrapolate to regions beyond the training set while maintaining reliability within an upper bound of their expected distances from the training regions. We evaluate GROOT on various biological sequence design tasks, including protein optimization (GFP and AAV) and three tasks with exact oracles from Design-Bench. The results demonstrate that GROOT equalizes and surpasses existing methods without requiring access to black-box oracles or vast amounts of labeled data, highlighting its practicality and effectiveness. We release our code at https://anonymous.4open.science/r/GROOT-D554