Interpretable AI for drug response prediction (code)
Bibliographic record
Abstract
The code for running each model is divided into individual sub-folders. Two types of model execution can be done: 1) run a pretrained model with specified hyperparameters; 2) run a model from scratch with specified hyperparameters. The former execution can be done by running the run_pretrained.sh script and the latter can be done by running run_model_with_hyp.sh script. Hyperparameter tuning has been performed on the validation set and the best set of hyperparameters for each validation strategy (leave-ccls-out/LCO, leave-drugs-out/LDO, leave-pairs-out /LPO) and each pathway collection (KEGG, PID, Reactome) are provided in sub-folders named best_hyp. All pathway-based models (PathDNN, ConsDeepSignaling, HiDRA, PathDSP) are re-implementations of the original models, with a very small component of code being adaptations (direct usage) of the original code provided by the authors of these pathway-based models. References for such adaptations are included in the comments of the code.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.260 | 0.196 |
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".