LGMLJan 28, 2022

Biases in In Silico Evaluation of Molecular Optimization Methods and Bias-Reduced Evaluation Methodology

arXiv:2201.12163v11 citations
Originality Incremental advance
AI Analysis

This work addresses evaluation biases in molecular optimization, which is crucial for reliable method development in computational chemistry and drug discovery, though it is incremental as it builds on existing evaluation practices.

The paper identifies two biases in the in silico evaluation of molecular optimization methods: predictor misspecification and sample reuse, and proposes bias reduction methods to address them, demonstrating their effectiveness empirically.

We are interested in in silico evaluation methodology for molecular optimization methods. Given a sample of molecules and their properties of our interest, we wish not only to train an agent that can find molecules optimized with respect to the target property but also to evaluate its performance. A common practice is to train a predictor of the target property on the sample and use it for both training and evaluating the agent. We show that this evaluator potentially suffers from two biases; one is due to misspecification of the predictor and the other to reusing the same sample for training and evaluation. We discuss bias reduction methods for each of the biases comprehensively, and empirically investigate their effectiveness.

Foundations

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

Your Notes