ArticleNature communications2021
Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias.
Article in Nature communications, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 29 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
29 citing papers in PubMed.
- Bayesian optimization- and high-throughput-guided synthesis of monofluoroalkenesChemical science · 2026Article
- Syndirella: synthesis-directed fragment elaboration enables extensive and cost-effective binding site exploration beyond catalog compounds.Chemical science · 2026Article
- Automation of Rietveld refinement through machine learning.Journal of applied crystallography · 2026Article
- Collision-free morgan fingerprints: a principled approach to enhance machine learning performance and interpretability in chemistry.Journal of cheminformatics · 2026Article
- Hybrid 2-Quinolone-1,2,3-triazole Compounds: Rational Design, In Silico Optimization, Synthesis, Characterization, and Antibacterial Evaluation.Antibiotics (Basel, Switzerland) · 2025Article
- Transfer Learning for Heterocycle Retrosynthesis.Journal of chemical information and modeling · 2025Article
- Challenging Reaction Prediction Models to Generalize to Novel Chemistry.ACS central science · 2025Article
- Computational tools for the prediction of site- and regioselectivity of organic reactions.Chemical science · 2025Review
- Graph-Theory Algorithm for Prediction of Electrolyte Degradation Reactions in Lithium- and Sodium-Ion Batteries.Materials (Basel, Switzerland) · 2025Article
- DrugGym: A testbed for the economics of autonomous drug discovery.bioRxiv : the preprint server for biology · 2024Article
- Generalizability Improvement of Interpretable Symbolic Regression Models for Quantitative Structure-Activity Relationships.ACS omega · 2024Article
- Accelerated chemical science with AI.Digital discovery · 2024Review
- BUSClean: Open-source software for breast ultrasound image pre-processing and knowledge extraction for medical AI.PloS one · 2024Article
- Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks.Nature communications · 2023Article
- Review
- Characterizing Uncertainty in Machine Learning for Chemistry.Journal of chemical information and modeling · 2023Article
- Quantum chemical data generation as fill-in for reliability enhancement of machine-learning reaction and retrosynthesis planning.Digital discovery · 2023Article
- RetroRanker: leveraging reaction changes to improve retrosynthesis prediction through re-ranking.Journal of cheminformatics · 2023Article
- Retrosynthesis prediction using an end-to-end graph generative architecture for molecular graph editing.Nature communications · 2023Article
- Global reactivity models are impactful in industrial synthesis applications.Journal of cheminformatics · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Organic synthesis remains a major challenge in drug discovery. Although a plethora of machine learning models have been proposed as solutions in the literature, they suffer from being opaque black-boxes. It is neither clear if the models are making correct predictions because they inferred the salient chemistry, nor is it clear which training data they are relying on to reach a prediction. This opaqueness hinders both model developers and users. In this paper, we quantitatively interpret the Molecular Transformer, the state-of-the-art model for reaction prediction. We develop a framework to attribute predicted reaction outcomes both to specific parts of reactants, and to reactions in the training set. Furthermore, we demonstrate how to retrieve evidence for predicted reaction outcomes, and understand counterintuitive predictions by scrutinising the data. Additionally, we identify Clever Hans predictions where the correct prediction is reached for the wrong reason due to dataset bias. We present a new debiased dataset that provides a more realistic assessment of model performance, which we propose as the new standard benchmark for comparing reaction prediction models.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.