Papers › A Bayesian Flow Network Framework for Chemistry Tasks

A Bayesian Flow Network Framework for Chemistry Tasks

28 Jul 2024arXiv:2407.20294archive 2025-07-28

Nianze Tao, Minori Abe

In this work, we introduce ChemBFN, a language model that handles chemistry tasks based on Bayesian flow networks working on discrete data. A new accuracy schedule is proposed to improve the sampling quality by significantly reducing the reconstruction loss. We show evidence that our method is appropriate for generating molecules with satisfied diversity even when a smaller number of sampling steps is used. A classifier-free guidance method is adapted for conditional generation. It is also worthwhile to point out that after generative training, our model can be fine-tuned on regression and classification tasks with the state-of-the-art performance, which opens the gate of building all-in-one models in a single module style. Our model has been open sourced at https://github.com/Augus1999/bayesian-flow-network-for-chemistry.

PaperPDFCode

Code

Augus1999/bayesian-flow-network-for-chemistry officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityLanguage ModelingLanguage ModellingMolecular Property PredictionText-based de novo Molecule Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Molecular Property Prediction BACE ChemBFN ROC-AUC 73.56 #15 of 20 Archive leaderboard report
Molecular Property Prediction BBBP ChemBFN ROC-AUC 95.74 #2 of 29 Archive leaderboard report
Molecular Property Prediction ESOL ChemBFN RMSE 0.884 #17 of 20 Archive leaderboard report
Molecular Property Prediction FreeSolv ChemBFN RMSE 1.418 #11 of 22 Archive leaderboard report
Molecular Property Prediction HIV ChemBFN ROC-AUC 79.37 #3 of 4 Archive leaderboard report
Molecular Property Prediction HIV dataset ChemBFN AUC 0.794 #3 of 11 Archive leaderboard report
Molecular Property Prediction Lipophilicity ChemBFN RMSE 0.746 #7 of 13 Archive leaderboard report
Molecular Property Prediction clintox ChemBFN ROC-AUC 99.18 #2 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections