A Needle in a Haystack: Leveraging Machine Learning for Drug-Mechanism of Action Identification across Existing Therapeutics, with Specific Applications for Drug Repurposing for Rare Diseases
Bibliographic record
Abstract
Rare diseases are a prevalent problem within the healthcare sector, primarily due to the multitude of conditions and the limited profiling available for each. Consequently, developing novel therapeutics for rare diseases through traditional pipelines is fraught with risk and cost. The integration of machine learning into bioinformatics has facilitated the growth of in silico drug repurposing, where existing compounds are repositioned based on newly identified molecular targets. This study proposes a multi-class predictive model capable of accurately determining the mechanisms of action for existing compounds. By leveraging even limited rare disease profiles, the model aims to identify candidates for drug repurposing. Four supervised learning algorithms were trained using a combination of Clue and PubChem datasets. The results indicate that the random forest model boasts the best performance with an accuracy of 72.4% – comparable to existing literature. As all the top-performing models in this study were black-box, interpretability features of LIME and OpenAI API were integrated to ensure transparency in the recommendation of drug candidates, preparing the model for clinical integration. This model was then applied to a case study of Infantile Dystonia-Parkinson (IDP), where 105,552 compounds were screened for association with the condition. This study proposes pramipexole, bromocriptine, and ropinirole as candidate compounds for further investigation for IDP treatment. Due to the accuracy of both mechanism prediction and candidate generation, this computational model stands as a suitable approach for rare disease drug repurposing.
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 | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".