Bibliographic record
Abstract
Drug discovery is notoriously resource-intensive, prompting interest in computational methods such as virtual screening.Traditional approaches to virtual screening, viz., receptor-based methods (such as molecular docking) and ligand-based methods, face limitations with respect to accuracy and scalability.Recently, integrating artificial intelligence (AI) with molecular docking has emerged as a powerful way to explore vast chemical libraries more efficiently.AI models capture complex ligand-protein interactions but often lack interpretability, whereas molecular docking provides structural insights but struggles with highly flexible or dynamic targets.Appearing in this issue as a Featured Letter, Qian et al. (DOI: 10.1021/acsmedchemlett.5c00433) introduce D2Screen, a hybrid virtual screening pipeline that integrates a pretrained molecular representation model (GEM) with molecular docking, combining the strengths of ligand-and structure-based strategies.In the first stage, GEM, which can be fine-tuned with target-specific bioactivity data, rapidly screens millions of compounds for potential activity.In the second stage, promising candidates are subsequently evaluated by molecular docking, which supplies interpretable binding poses and ranked binding affinity scores.Benchmarking revealed that D2Screen consistently outperformed either AI or docking alone, particularly for challenging targets such as GPCRs and cytochrome P450 enzymes.The approach also proved robust across variations in data set size, activity ratio and scaffold diversity.A case study targeting the SARS-CoV-2 main protease (M pro ) demonstrated D2Screen's practical value.The pipeline identified novel noncovalent inhibitors, including quinolinebased compounds that retained activity against drug-resistant M pro mutants (notably E166 V) known to undermine therapies such as nirmatrelvir.Structural analysis and molecular dynamics confirmed reduced reliance on mutation-prone residues, offering a rational basis for designing resistanceevading inhibitors.Overall, D2Screen represents a scalable, modular and effective framework for AI-driven drug discovery, delivering improved enrichment, improved accuracy and resilience to resistance challenges.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.009 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.005 | 0.006 |
| Insufficient payload (model declined to judge) | 0.110 | 0.053 |
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".