Large Language Models in Drug Discovery: A Comprehensive Analysis of Drug-Target Interaction Prediction
Bibliographic record
Abstract
Large Language Models have successfully caught the eyes of the pharmaceutical industry and provided aid in several tasks, such as de novo drug design, drug repurposing, molecular optimization, activity prediction, and Drug-Target Interaction (DTI) prediction. In this survey, we delved deep into these models, among their various applications, techniques, performance metrics, and the datasets they utilized. Additionally, we gave special attention to DTI predictive models due to the crucial rule of DTI prediction in the Drug Discovery (DD) process, which aims to enhance the efficiency of finding suitable drug-like candidates while lowering time and costs. Furthermore, we presented some of the successful models that have reached the market and showed some tangible success. While aiming to highlight the potential of LLMs and acknowledging their challenges that need to be overcome for broader adoption, we focused on some key areas, such as their clinical and financial aspects, generalizability, computational cost, interpretability, and hybrid models. Moreover, eXplainable Artificial Intelligence (XAI) was emphasized and we underscored its potential and need in the field of DD to further validate the trust-worthiness of such models.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.003 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".