Combining the Power of Attention Models and Many-objective Computational Intelligence Algorithms for Drug Design
Bibliographic record
Abstract
AI-based approaches have been recently applied to in silico drug design. However, existing approaches and protocols consider the absorption, distribution, metabolism, excretion, and toxicity (ADMET) pharmacokinetic properties of drug candidates in a later stage of drug design processes, where failure is most costly. To address this challenge, this research work aims to achieve three objectives. First, it explores the use of Transformer-based models for ADMET prediction based on a hybrid fragment-SMILES tokenization scheme and two training strategies. Second, it evaluates the performance of contrastive Transformer-based latent models for molecular generation. Third, it applies many-objective computational intelligence algorithms in the continuous latent space generated by a Transformer model to generate optimal drug candidates that fulfill ADMET and other essential properties in parallel. The results of this research work demonstrate superiority in the hybrid approach over SMILES in predicting ADMET properties. Furthermore, the system proposed in this study integrates metaheuristics with ADMET prediction and latent Transformer models for solving a drug design problem. A comparative study shows effectiveness of computational intelligence towards a many-objective drug design problem, where 1718 drug-like molecules are obtained after application of a strict filtering criteria.
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 | 0.004 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".