# Tango*: constrained synthesis planning using chemically informed value functions

## TL;DR

This paper introduces Tango*, a new method for computer-aided synthesis planning that efficiently finds chemical pathways using specific starting materials.

## Contribution

Tango* improves synthesis planning by using a guided search with a computed node cost function, outperforming existing methods.

## Key findings

- Tango* outperforms existing methods in efficiency and solve rate by optimizing a single hyperparameter.
- The computed node cost function effectively guides synthesis pathways toward desired starting materials.
- Tango* achieves superior performance compared to neural network approaches in constrained synthesis planning.

## Abstract

Computer-aided synthesis planning (CASP) has made significant strides in generating retrosynthetic pathways for simple molecules in a non-constrained fashion. Recent work has introduced specialized bidirectional search algorithms to find synthesis pathways that incorporate pre-selected starting materials, tackling a specific formulation of the starting material-constrained problem. In this work, we introduce a simple guided search—Tango*-which allows solving the starting material-constrained synthesis planning problem using an existing unidirectional search algorithm, Retro*. We show that by optimising a single hyperparameter, Tango* outperforms existing methods in terms of efficiency and solve rate. We also highlight the effectiveness of our computed node cost function in steering synthesis pathways.

TANGO* enables starting material constrained synthesis planning using computed molecular similarity to guide retrosynthetic search toward specific starting materials, achieving superior performance to neural network approaches.