ArticleDigital discovery2022
Limitations of machine learning models when predicting compounds with completely new chemistries: possible improvements applied to the discovery of new non-fullerene acceptors.
Article in Digital discovery, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 11 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
11 citing papers in PubMed.
- Validation design and experimental provenance shape apparent machine-learning transferability in legacy Mössbauer spectroscopy.RSC advances · 2026Article
- Artificial intelligence and ultra-high performance computing methods and experiments for drug discovery: virtual screening, deep learning, molecular dynamics simulations, ADMET modelling, and experimental validation.Molecular biomedicine · 2026Review
- Explainable Artificial Intelligence Assisted Modeling of Malachite Green Adsorption onto SBA-15-Zn-Fe Composite.Molecules (Basel, Switzerland) · 2026Article
- An End-User Audit of Reproducibility, Data Leakage, and Overfitting of the Top-Ranked ADMET Prediction Models in TDC Leaderboards.Journal of chemical information and modeling · 2026Article
- From Quantum Mechanics to Coarse-Grained Models: Bridging the Gap toward Polymer Rational Design.Journal of chemical theory and computation · 2026Article
- Best Practices and Considerations for Applying Multiple Linear Regression in Organic Chemistry Research.The Journal of organic chemistry · 2026Review
- Integration of Machine Learning With PBPK and QSAR Modeling Approaches to Facilitate Drug Discovery and Development.CPT: pharmacometrics & systems pharmacology · 2026Review
- The Predictive Power of Chemical Bonding Analysis in Materials: A Perspective on Optoelectronic Properties.Journal of the American Chemical Society · 2025Review
- High-Throughput Screening of Molecule/Polymer Photocatalysts for the Hydrogen Evolution Reaction.ACS catalysis · 2025Article
- Predicting cardiac resynchronization therapy response: development and validation of a single photon emission computed tomography-based nomogram.Quantitative imaging in medicine and surgery · 2025Article
- Augmenting large language models with chemistry tools.Nature machine intelligence · 2024Article
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
We try to determine if machine learning (ML) methods, applied to the discovery of new materials on the basis of existing data sets, have the power to predict completely new classes of compounds (extrapolating) or perform well only when interpolating between known materials. We introduce the leave-one-group-out cross-validation, in which the ML model is trained to explicitly perform extrapolations of unseen chemical families. This approach can be used across materials science and chemistry problems to improve the added value of ML predictions, instead of using extrapolative ML models that were trained with a regular cross-validation. We consider as a case study the problem of the discovery of non-fullerene acceptors because novel classes of acceptors are naturally classified into distinct chemical families. We show that conventional ML methods are not useful in practice when attempting to predict the efficiency of a completely novel class of materials. The approach proposed in this work increases the accuracy of the predictions to enable at least the categorization of materials with a performance above and below the median value.
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.