Retro-Rank-In: A Ranking-Based Approach for Inorganic Materials Synthesis Planning

Thorben Prein, Elton Pan, Sami Haddouti, Marco Lorenz, Janik Jehkul, Tymoteusz Wilk, Cansu Moran, Menelaos Panagiotis Fotiadis, Artur P. Toshev, Elsa Olivetti, Jennifer L.M. Rupp

Submission Track: Full Paper

Submission Category: AI-Guided Design + Automated Synthesis

Keywords: Inorganic retrosynthesis, Precursor prediction, Machine learning for materials synthesis, ranking models

TL;DR: Retro-Rank-In reformulates inorganic retrosynthesis as a ranking problem, enabling new precursor discovery and better generalization. It outperforms prior methods, setting a new state-of-the-art for precursor planning in solid-state synthesis.

Abstract: Retrosynthesis strategically plans the synthesis of a chemical target compound from simpler, readily available precursor compounds. This process is critical for synthesizing novel inorganic materials, yet traditional methods in inorganic chemistry continue to rely on trial-and-error experimentation. While emerging machine-learning approaches struggle to generalize to entirely new reactions due to their reliance on known precursors, as they frame retrosynthesis as a multi-label classification task. To address these limitations, we propose Retro-Rank-In, a novel framework reformulating the Retrosynthesis problem by embedding target and precursor materials into a shared latent space and learning a pairwise Ranker on a bipartite graph of Inorganic compounds. We evaluate Retro-Rank-In’s generalizability on challenging retrosynthesis dataset splits designed to mitigate data duplicates and overlaps. For instance, for Cr2AlB2, it correctly predicts the verified precursor pair CrB + Al despite never seeing them in training, a capability absent in prior work. Extensive experiments show that Retro-Rank-In sets a new state-of-the-art, particularly in out-of-distribution generalization and candidate set ranking, offering a powerful tool for accelerating inorganic material synthesis.

Submission Number: 40