CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions

TL;DR

CoRe-Gen advances molecular structure prediction from MS/MS spectra by robustly handling noisy fingerprint predictions, achieving state-of-the-art accuracy while maintaining efficiency.

Contribution

It introduces a comprehensive approach combining synthetic-spectrum pretraining, frequency-aware fingerprint corruption, and structure-aware autoregressive decoding to improve robustness.

Findings

Achieves 19.54% Top-1 accuracy on NPLIB1 benchmark.

Outperforms previous methods on standard benchmarks.

Maintains efficiency of autoregressive decoding.

Abstract

Molecular structure elucidation from tandem mass spectra (MS/MS) remains challenging, particularly for de novo generation beyond database coverage. A common approach decomposes the task into spectrum-to-fingerprint prediction followed by fingerprint-to-structure decoding, enabling the use of large-scale molecular corpora. However, at deployment, the decoder relies on predicted rather than oracle fingerprints, introducing structured errors that propagate into generation. This results in a fundamental condition mismatch, where models trained on clean inputs must operate under noisy, biased predictions, especially for long-tail substructures. We present CoRe-Gen that explicitly addresses this gap. CoRe-Gen improves the intermediate condition via synthetic-spectrum pretraining of the encoder, matches deployment-time noise through frequency-aware fingerprint corruption during decoder training, and mitigates residual errors using structure-aware autoregressive decoding with compositional SELFIES representations, auxiliary structural supervision, and lightweight chemical constraints. Experiments on standard benchmarks show that CoRe-Gen establishes a new state of the art on NPLIB1, achieving 19.54\% Top-1 and 29.92\% Top-10 exact-match accuracy, while remaining competitive on the more challenging MassSpecGym benchmark. Importantly, CoRe-Gen preserves the efficiency advantages of autoregressive decoding, providing a practical and scalable solution for robust spectrum-to-structure generation under realistic conditions.