Leap: molecular synthesisability scoring with intermediates

TL;DR

Leap is a novel GPT-2 based model that dynamically scores molecular synthesisability by incorporating key intermediates, outperforming existing methods in identifying synthesizable compounds in drug discovery.

Contribution

The paper introduces Leap, a GPT-2 model that conditions synthesisability scores on intermediates, enabling dynamic assessment and surpassing existing scoring methods.

Findings

Leap achieves at least 5% higher AUC scores than existing methods.

Leap can adapt scores based on available intermediates.

Leap effectively incorporates intermediate information at inference time.

Abstract

Assessing whether a molecule can be synthesised is a primary task in drug discovery. It enables computational chemists to filter for viable compounds or bias molecular generative models. The notion of synthesisability is dynamic as it evolves depending on the availability of key compounds. A common approach in drug discovery involves exploring the chemical space surrounding synthetically-accessible intermediates. This strategy improves the synthesisability of the derived molecules due to the availability of key intermediates. Existing synthesisability scoring methods such as SAScore, SCScore and RAScore, cannot condition on intermediates dynamically. Our approach, Leap, is a GPT-2 model trained on the depth, or longest linear path, of predicted synthesis routes that allows information on the availability of key intermediates to be included at inference time. We show that Leap surpasses all other scoring methods by at least 5% on AUC score when identifying synthesisable molecules, and can successfully adapt predicted scores when presented with a relevant intermediate compound.