Skip to main navigation Skip to search Skip to main content

MoleNovo: A Casanovo-Based De Novo Molecular Generation Framework

  • Jun Gao
  • , Haifeng Zhao
  • , Guohao Zong
  • , Shunxiang Gao
  • , Yan Zhang
  • , Lan Du

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

Mass spectrometry (MS) is a powerful tool for analyzing small molecules in complex samples, yet accurate structure elucidation from spectral data remains challenging. We present a Transformer-based model for de novo molecular generation, named MoleNovo, which directly predicts SMILES strings from MS spectra. MoleNovo employs a tailored embedding strategy for both mass-to-charge ratio (m/z) and intensity values within a sequence-to-sequence architecture. Evaluated on the NIST20 dataset, MoleNovo outperforms existing models such as Spec2Mol and MS2Mol across multiple metrics, including BLEU score, Levenshtein distance, fingerprint similarity, and chemical validity. These results underscore the potential of Transformer architectures for scalable, automated compound identification in metabolomics and drug discovery.

Original languageEnglish
Title of host publicationAdvanced Data Mining and Applications - 21st International Conference, ADMA 2025, Proceedings
EditorsMasatoshi Yoshikawa, Xiaofeng Meng, Yang Cao, Chuan Xiao, Weitong Chen, Yanda Wang
Place of PublicationSingapore Singapore
PublisherSpringer
Pages97-111
Number of pages15
ISBN (Electronic)9789819534593
ISBN (Print)9789819534586
DOIs
Publication statusPublished - 2026
EventInternational Conference on Advanced Data Mining and Applications 2025 - Kyoto, Japan
Duration: 22 Oct 2025 → 24 Oct 2025
Conference number: 21st
https://link.springer.com/book/10.1007/978-981-95-3456-2 (Proceedings)
https://adma2025.github.io/ (Website)

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume16199
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceInternational Conference on Advanced Data Mining and Applications 2025
Abbreviated titleADMA 2025
Country/TerritoryJapan
CityKyoto
Period22/10/25 → 24/10/25
Internet address

Keywords

  • De Novo Molecular Generation
  • Mass Spectrometry
  • SMILES
  • Transformer

Cite this