Keeping pace with the explosive growth of chemical libraries with structure‐based virtual screening
Bibliographic record
Abstract
Abstract Recent efforts to synthetically expand drug‐like chemical libraries have led to the emergence of unprecedently large virtual databases. This surge of make‐on‐demand molecular datasets has been received enthusiastically across the drug discovery community as a new paradigm. In several recent studies, virtual screening (VS) of larger make‐on‐demand collections resulted in the identification of novel molecules with higher potency and specificity compared to more conventional VS campaigns relying on smaller in‐stock libraries. These results inspired ultra‐large VS against various clinically relevant targets, including key proteins of the SARS‐CoV‐2 virus. As library sizes rapidly surpassed the billion compounds mark, new computational screening strategies emerged, shifting from conventional docking to fragment‐based and machine learning‐accelerated methods. These approaches significantly reduce computational demands of ultra‐large screenings by lowering the number of molecules explicitly docked onto a target. Such strategies already demonstrated promise in evaluating libraries of tens of billions of molecules at relatively low computational cost. Herein, we review recent advancements in structure‐based methods for ultra‐large virtual screening that drug discovery practitioners have adopted to explore the ever‐expanding chemical universe. This article is categorized under: Data Science > Databases and Expert Systems Data Science > Artificial Intelligence/Machine Learning Molecular and Statistical Mechanics > Molecular Mechanics
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".