SPADE: Faster Drug Discovery by Learning from Sparse Data

2026-05-06

AI Summary

This work addresses the challenge of ligand screening for novel target proteins lacking prior data and facing high experimental costs by proposing SPADE, an algorithm that integrates active learning with an efficient scoring mechanism. SPADE enables highly effective ligand discovery under extremely sparse experimental conditions without requiring large-scale training data. Remarkably, the method identifies ten high-affinity, high-selectivity candidate molecules using only approximately 40 experiments. In zero-prior settings, SPADE significantly outperforms existing approaches, achieving a median improvement in sample efficiency of 7%–32% and accelerating the screening process by an order of magnitude compared to the best-performing competitor, thereby substantially reducing both time and cost in early-stage drug discovery.

Abstract

Drug discovery seeks molecules (ligands) that bind strongly and selectively to a target protein. However, fewer than 5% of candidate ligands pass the bar for even the early stages of drug discovery. Furthermore, we want methods that work for novel proteins for which we have no prior data. Starting from scratch, we have to iteratively select and test candidate ligands such that we find enough ligands of the desired quality in as few tests as possible. Our proposed algorithm, named SPADE, introduces a novel approach to ligand selection that requires only 40 tests on average to find 10 high-quality ligands. In one-vs-one comparisons, SPADE outperforms deep learning and Bayesian optimization methods on more proteins, achieving median improvements of 7%-32% in sample efficiency. SPADE is also 10x faster than its closest competitor at scoring candidate drugs. Dataset and code is available at https://anonymous.4open.science/r/SPADE_Fast_Drug_Discovery_by_Learning_from_Sparse_Data-F028/README.md

Problem

• drug discovery
• ligand selection
• sparse data
• sample efficiency
• novel proteins

Innovation

• SPADE
• sparse data
• drug discovery
• sample efficiency
• ligand selection