Exploiting Ligand Additivity for Transferable Machine Learning of Multireference Character Across Known Transition Metal Complex Ligands

TL;DR

This paper introduces a ligand additivity approach for predicting the multi-reference character of transition metal complexes, enabling transferable machine learning models that improve virtual screening accuracy across diverse ligands.

Contribution

The study demonstrates that ligand additivity of MR character allows for the development of transferable ML models predicting TMC properties from ligand features.

Findings

MR character correlates linearly with inverse bond order.

Ligand additivity of MR character holds in TMCs.

ML models show high accuracy and transferability.

Abstract

Accurate virtual high-throughput screening (VHTS) of transition metal complexes (TMCs) remains challenging due to the possibility of high multi-reference (MR) character that complicates property evaluation. We compute MR diagnostics for over 5,000 ligands present in previously synthesized transition metal complexes in the Cambridge Structural Database (CSD). To accomplish this task, we introduce an iterative approach for consistent ligand charge assignment for ligands in the CSD. Across this set, we observe that MR character correlates linearly with the inverse value of the averaged bond order over all bonds in the molecule. We then demonstrate that ligand additivity of MR character holds in TMCs, which suggests that the TMC MR character can be inferred from the sum of the MR character of the ligands. Encouraged by this observation, we leverage ligand additivity and develop a ligand-derived machine learning representation to train neural networks to predict the MR character of TMCs from properties of the constituent ligands. This approach yields models with excellent performance and superior transferability to unseen ligand chemistry and compositions.