Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning

TL;DR

This paper introduces Sequence Completion Ranking (SCR), a novel margin-based classifier calibration method that significantly improves property-guided synthesis planning by expanding the set of reachable, property-satisfying reaction sequences.

Contribution

The paper proposes SCR, a contrastive, margin-based calibration technique for classifiers, enhancing guided retrosynthesis by better discriminating reaction continuations during decoding.

Findings

SCR improves multi-step solve rates from 16.8% to over 78% and 95% with different guidance.

Unlocks valid routes for 33 previously unsolvable targets.

Closes the diversity gap between template-free and template-based methods.

Abstract

Synthesis planning seeks an efficient sequence of chemical reactions that produce a target molecule. Typically, a pretrained single-step (autoregressive) retrosynthesis model is repeatedly invoked to generate such a sequence. Classifier guidance can, in principle, help steer the output of single-step model toward reactions that satisfy specific constraints or accommodate chemist's preferences during inference without having to retrain the autoregressive generator. We expose the insufficiency of auxiliary classifiers trained with cross-entropy loss to override the unconditional token-level distributions learned from typical sparse single-disconnection reaction datasets. We overcome this issue with a novel method called Sequence Completion Ranking (SCR), which employs contrastive argumentation and a margin-based loss to calibrate the classifier so that it can meaningfully discriminate between continuations during decoding. We formally establish that margin-calibrated classifiers can expand the set of property-satisfying sequences reachable under guided beam search. Empirically, on USPTO-190, given chemist-specified guidance targets, SCR substantially improves multi-step solve rates from $16.8\%$ (unguided generator) to $78.4\%$ with reaction-type guidance and $95.3\%$ with Tanimoto guidance, unlocking valid routes for 33 targets ($17.4\%$) previously unsolvable with baselines. Our method also effectively closes the long-standing diversity gap between template-free and template-based methods.