Retrieval-Augmented Foundation Models for Matched Molecular Pair Transformations to Recapitulate Medicinal Chemistry Intuition

TL;DR

This paper introduces a large-scale, controllable, retrieval-augmented foundation model for generating matched molecular pair transformations, enhancing diversity, novelty, and practical applicability in medicinal chemistry design.

Contribution

It presents a variable-to-variable analog generation framework trained on extensive MMP data, with prompting and retrieval mechanisms for improved control and generalization.

Findings

Enhanced diversity and novelty in generated analogs

Effective control over transformation patterns via prompting

Successful application to patent-specific datasets

Abstract

Matched molecular pairs (MMPs) capture the local chemical edits that medicinal chemists routinely use to design analogs, but existing ML approaches either operate at the whole-molecule level with limited edit controllability or learn MMP-style edits from restricted settings and small models. We propose a variable-to-variable formulation of analog generation and train a foundation model on large-scale MMP transformations (MMPTs) to generate diverse variables conditioned on an input variable. To enable practical control, we develop prompting mechanisms that let the users specify preferred transformation patterns during generation. We further introduce MMPT-RAG, a retrieval-augmented framework that uses external reference analogs as contextual guidance to steer generation and generalize from project-specific series. Experiments on general chemical corpora and patent-specific datasets demonstrate improved diversity, novelty, and controllability, and show that our method recovers realistic analog structures in practical discovery scenarios.