An approach combining deep learning and molecule docking for drug discovery of cathepsin L
Bibliographic record
Abstract
Cathepsin L (CTSL) is a promising therapeutic target for metabolic disorders and COVID-19. However, there are still no clinically available CTSL inhibitors. Our objective is to develop an approach for the discovery of potential reversible covalent CTSL inhibitors. The authors combined Chemprop, a deep learning-based strategy, and the Schrödinger CovDock algorithm to identify potential CTSL inhibitors. First, they used Chemprop to train a deep learning model capable of predicting whether a molecule would inhibit the activity of CTSL and performed predictions on ZINC20 in-stock librarie (~9.2 million molecules). Then, they selected the top-200 predicted molecules and performed the Schrödinger covalent docking algorithm to explore the binding patterns to CTSL (PDB: 5MQY). The authors then calculated the binding energies using Prime MM/GBSA and examined the stability between the best two molecules and CTSL using 100ns molecular dynamics simulations. The authors found five molecules that showed better docking results than the well-known cathepsin inhibitor odanacatib. Notably, two of these molecules, ZINC-35287427 and ZINC-1857528743, showed better docking results with CTSL compared to other cathepsins. Our approach enables drug discovery from large-scale databases with little computational consumption, which will save the cost and time required for 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 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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| 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".