Tacit

TAckling Chemistry through ImpliciT negative learning

Nick Wierich*, Niklas Dobberstein*, Frank Glorius†

Organisch-Chemisches-Institut, Universität Münster, 48149 Münster, Germany

* These authors contributed equally.  ·  † Corresponding author.

Positive reaction data is abundant, negative data is limited. TACIT predicts negative outcomes by implicit learning from positive-only data.

Abstract

Machine learning models for reaction product prediction have largely been trained and evaluated on datasets of successful reactions. While this setting allows reaching high accuracy scores, these models generally struggle to discriminate between successful and unsuccessful transformations due to the lack of negative training data. This critically limits their practical use, as reliably recognizing unproductive substrate combinations in silico is required to accelerate experimental campaigns and save resources in the laboratory.

While the availability of negative reaction data remains limited to date, we show that even purely positive datasets implicitly contain a significant amount of information about cases in which no reaction occurs. To exploit this, we introduce TACIT (TAckling Chemistry through ImpliciT negative learning). While trained on positive-only data, TACIT learns to distinguish between productive and unproductive transformations. On two published high-throughput experimentation datasets, it outperforms all evaluated reaction outcome prediction models in separating successful from failed reactions.

Crucially, TACIT’s accuracy on the popular USPTO-MIT benchmark remains competitive, despite its added ability to predict negative reaction outcomes.

Results

ModelUSPTO-MITChemlexAIChemEco
Top-1 [%]ROC-AUCPR-AUCROC-AUCPR-AUC
TACIT77.80.800.560.610.69
MEGANa80.50.690.380.470.56
FlowERb42.80.500.260.510.60
Molecular Transformera,d81.70.680.420.510.61
LocalTransforma,d80.40.640.370.510.59
ReactionT5a,c,d95.1e0.690.410.470.58

USPTO-MIT: all 40,000 test reactions. HTE datasets: all 11,669 (Chemlex) and 47,015 (AIChemEco) wells. A well is positive if its conversion or yield is at least 20%, and negative otherwise.

  1. a Retrained on the blockspace-filtered USPTO-MIT training set used for TACIT.
  2. b Published checkpoint. Not retrained, since a mechanistic dataset is required for training.
  3. c Pretrained on the Open Reaction Database.
  4. d No stop action. The confidence of the top-1 prediction is used as the score.
  5. e 34,552 of the 40,000 test reactions (86.4%) are contained in the ORD pretraining data. The top-1 accuracy is 97.5% on these and 80.4% on the remaining 5,448 reactions.

BibTeX

@article{tacit,
  title   = {Implicit Learning: Reaction Outcome Prediction from Positive-Only Data},
  author  = {Wierich, Nick and Dobberstein, Niklas and Glorius, Frank},
  journal = {ChemRxiv},
  year    = {2026},
  doi     = {10.26434/chemrxiv.15011216/v1},
  note    = {TACIT: TAckling Chemistry through ImpliciT negative learning}
}