ArticleCommunications chemistry2024
The Goldilocks paradigm: comparing classical machine learning, large language models, and few-shot learning for drug discovery applications.
Article in Communications chemistry, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 15 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
15 citing papers in PubMed.
- Organic Chemistry as a Catalyst for AI Innovation: Challenges, Methods, and Emerging Paradigms.Chemical reviews · 2026Review
- Nature meets machine: the AI renaissance in natural product drug discovery.Natural products and bioprospecting · 2026Review
- Application and Prospects of Large Language Models in Small-Molecule Drug Discovery.Analytical chemistry · 2025Review
- Assessing and optimizing Team-Based Learning in undergraduate cosmetic dermatology education: an empirical study using interpretable machine learning.BMC medical education · 2025Article
- MegaEye: Applying multiple machine learning approaches to identify oral compounds with ocular bioactivity.Artificial intelligence in the life sciences · 2025Article
- From NMR to AI: FusingJournal of chemical information and modeling · 2025Article
- Experimental and computational approaches for evaluating molecule interactions with equilibrative nucleoside transporters 1 and 2.The Journal of pharmacology and experimental therapeutics · 2025Article
- DDI-CYP: Metabolism ensemble models for drug-drug interaction predictions.Drug metabolism and disposition: the biological fate of chemicals · 2025Article
- Adjusted imbalance ratio leads to effective AI-based drug discovery against infectious disease.Scientific reports · 2025Article
- Machine Learning and Large Language Models for Modeling Complex Toxicity Pathways and Predicting Steroidogenesis.Environmental science & technology · 2025Article
- Adverse Outcome Pathway and Machine Learning to Predict Drug Induced Seizure Liability.ACS chemical neuroscience · 2025Article
- Comparative analysis of the performance of the large language models ChatGPT-3.5, ChatGPT-4 and Open AI-o1 in the field of Programmed Cell Death in myeloma.Discover oncology · 2025Article
- MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery.Journal of chemical information and modeling · 2025Article
- A meta-learning approach for selectivity prediction in asymmetric catalysis.Nature communications · 2025Article
- Predicting the Hallucinogenic Potential of Molecules Using Artificial Intelligence.ACS chemical neuroscience · 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
9 authors.
Funding
Abstract
Recent advances in machine learning (ML) have led to newer model architectures including transformers (large language models, LLMs) showing state of the art results in text generation and image analysis as well as few-shot learning (FSLC) models which offer predictive power with extremely small datasets. These new architectures may offer promise, yet the 'no-free lunch' theorem suggests that no single model algorithm can outperform at all possible tasks. Here, we explore the capabilities of classical (SVR), FSLC, and transformer models (MolBART) over a range of dataset tasks and show a 'goldilocks zone' for each model type, in which dataset size and feature distribution (i.e. dataset "diversity") determines the optimal algorithm strategy. When datasets are small ( < 50 molecules), FSLC tend to outperform both classical ML and transformers. When datasets are small-to-medium sized (50-240 molecules) and diverse, transformers outperform both classical models and few-shot learning. Finally, when datasets are of larger and of sufficient size, classical models then perform the best, suggesting that the optimal model to choose likely depends on the dataset available, its size and diversity. These findings may help to answer the perennial question of which ML algorithm is to be used when faced with a new dataset.
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.