LGQMNov 18, 2024

GROOT: Effective Design of Biological Sequences with Limited Experimental Data

arXiv:2411.11265v11 citationsh-index: 11Has CodeKDD
Originality Incremental advance
AI Analysis

This addresses a bottleneck in biological sequence design for researchers, offering a practical solution when data is scarce, though it appears incremental as it builds on latent space optimization methods.

The paper tackles the problem of designing biological sequences with limited experimental data by introducing GROOT, a method that uses graph-based latent smoothing and label propagation to generate pseudo-labels, enabling it to equal or surpass existing methods in tasks like protein optimization without needing vast labeled data or black-box oracles.

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

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes