CompleteRXN: Toward Completing Open Chemical Reaction Databases
This addresses the problem of incomplete reaction data for chemoinformatics practitioners, but the gap between benchmark and real-world performance indicates incremental progress.
CompleteRXN introduces a benchmark and models for completing missing byproducts, co-reactants, and stoichiometric coefficients in chemical reaction databases. Their Constrained Reaction Balancer achieves 99.20% accuracy on random splits and 91.12% on extreme out-of-distribution splits, but performance drops on uncurated data.
Chemical reaction datasets such as USPTO suffer from substantial incompleteness, frequently missing byproducts, co-reactants, and stoichiometric coefficients. This limits their applicability and reliability in downstream applications. Here, we introduce CompleteRXN, a large-scale supervised benchmark for reaction completion under realistic missing-data conditions. We construct a dataset of aligned incomplete and atom-balanced reactions by mapping USPTO records to curated mechanistic reactions. We evaluate representative baselines, including a novel encoder-decoder reaction completion model with constrained decoding, the Constrained Reaction Balancer (CRB), and a recent algorithmic method, SynRBL. On our CompleteRXN benchmark, the CRB achieves high performance across splits of increasing difficulty, reaching 99.20% equivalence accuracy on the random split and 91.12% on the extreme out-of-distribution split. SynRBL produces many balanced and chemically plausible completions, but with lower accuracy on the benchmark test splits. Across all methods, performance degrades with increasing incompleteness. We observe a substantial drop when evaluating on reactions outside the benchmark (full uncurated USPTO), highlighting the gap between benchmark performance and practical robustness and motivating future work.