ArticleChemical science2022
Model agnostic generation of counterfactual explanations for molecules.
Article in Chemical science, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 46 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
46 citing papers in PubMed.
- Language of Toxicity: An eXplainable Artificial Intelligence Approach.Journal of chemical information and modeling · 2026Article
- Chemical language models for early-stage drug discovery: applications, pitfalls, and future directions.Journal of computer-aided molecular design · 2026Review
- Censoring chemical data to mitigate dual use risk.Digital discovery · 2026Article
- Interpreting the Black Box: Interpretable Machine Learning and Systems Pharmacology in Small-Molecule Therapeutics.Pharmaceutics · 2026Review
- Motif-Level Graph Learning Enables Interpretable Prediction of Drug-Induced QT Prolongation via Cooperative Substructural Determinants.International journal of molecular sciences · 2026Article
- Multiscale-Aware Graph Embedding Approach Uncovers LC-61, a Potent Anti-Journal of chemical information and modeling · 2026Article
- Boosting Computational Catalysis and Chemical Reactivity with Artificial Intelligence.Journal of the American Chemical Society · 2026Review
- General-Purpose Models for the Chemical Sciences: LLMs and Beyond.Chemical reviews · 2026Review
- Interpretable machine learning rationalizes carbonic anhydrase inhibition via conformal and counterfactual prediction.Scientific reports · 2026Article
- Explainable artificial intelligence for molecular design in pharmaceutical research.Chemical science · 2026Review
- Explainable artificial intelligence for materials discovery: application to catalysts for the HER and ORR.Chemical science · 2026Article
- Establishment of an Integrated Model for Predicting Compound Mutagenicity with a Feature Importance Analysis.Journal of chemical information and modeling · 2025Article
- Contrastive explanations for machine learning predictions in chemistry.Journal of cheminformatics · 2025Article
- ACES-GNN: can graph neural network learn to explain activity cliffs?Digital discovery · 2025Article
- Studying Noncovalent Interactions in Molecular Systems with Machine Learning.Chemical reviews · 2025Review
- Machine Learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the Real World.Chemical research in toxicology · 2025Review
- Chemical space as a unifying theme for chemistry.Journal of cheminformatics · 2025Article
- Human interpretable structure-property relationships in chemistry using explainable machine learning and large language models.Communications chemistry · 2025Article
- Recent advances in AI-based toxicity prediction for drug discovery.Frontiers in chemistry · 2025Review
- Integrating Model-Informed Drug Development With AI: A Synergistic Approach to Accelerating Pharmaceutical Innovation.Clinical and translational science · 2025Review
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
Abstract
An outstanding challenge in deep learning in chemistry is its lack of interpretability. The inability of explaining why a neural network makes a prediction is a major barrier to deployment of AI models. This not only dissuades chemists from using deep learning predictions, but also has led to neural networks learning spurious correlations that are difficult to notice. Counterfactuals are a category of explanations that provide a rationale behind a model prediction with satisfying properties like providing chemical structure insights. Yet, counterfactuals have been previously limited to specific model architectures or required reinforcement learning as a separate process. In this work, we show a universal model-agnostic approach that can explain any black-box model prediction. We demonstrate this method on random forest models, sequence models, and graph neural networks in both classification and regression.
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.