PolyLLM: polypharmacy side effect prediction via LLM-based SMILES encodings
Bibliographic record
Abstract
Polypharmacy, the concurrent use of multiple drugs, is a common approach to treating patients with complex diseases or multiple conditions. Although consuming a combination of drugs can be beneficial in some cases, it can lead to unintended drug-drug interactions (DDI) and increase the risk of adverse side effects. Predicting these adverse side effects using state-of-the-art models like Large Language Models (LLMs) can greatly assist clinicians. In this study, we assess the impact of using different LLMs to predict polypharmacy. First, the chemical structure of drugs is vectorized using several LLMs such as ChemBERTa, GPT, etc., and are then combined to obtain a single representation for each drug pair. The drug pair representation is then fed into two separate models including a Multilayer Perceptron (MLP) and a Graph Neural Network (GNN) to predict the side effects. Our experimental evaluations show that integrating the embeddings of Deepchem ChemBERTa with the GNN architecture yields more effective results than other methods. Additionally, we demonstrated that utilizing complex models like LLMs to predict polypharmacy side effects using only chemical structures of drugs can be highly effective, even without incorporating other entities such as proteins or cell lines, which is particularly advantageous in scenarios where these entities are not available.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".