Enabling Open Machine Learning of DNA Encoded Library Selections to Accelerate the Discovery of Small Molecule Protein Binders
Bibliographic record
Abstract
Recent advances in DNA-encoded library (DEL) screening have created bioactivity datasets containing billions of molecules, unlocking new opportunities for machine learning (ML) in drug discovery. However, most ultra-large DEL libraries are proprietary, limiting the advancement of ML tools for big chemical data analytics and hindering the democratization of DEL-ML technology. We address this gap by developing an open, end-to-end DEL-ML framework using public datasets, where enriched binders are represented by common chemical fingerprints, ensuring proprietary data protection. We demonstrate that ML models can be built and validated on fingerprinted DEL data and then applied to virtual screening (VS) of billion-sized, publicly accessible chemical libraries. As a proof-of-concept, we screened the human protein WDR91 using the HitGen OpenDEL library (3 billion molecules) and trained ML models, which were used to screen the Enamine REAL Space library (37 billion molecules). Fifty potential binders were identified, 48 of which were tested, and seven were confirmed as novel binders with dissociation constants (KD) from 2.7 to 21 μM that were successfully co-crystalized with WDR91. This fully automated, open-source workflow demonstrates the potential of DEL-ML models in discovering novel binders and promotes the use of open chemical bioactivity datasets and ML to accelerate drug discovery.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".