Application of Machine Learning and Deep Learning Approaches Cheminformatic for Drug Discovery
Bibliographic record
Abstract
Artificial Intelligence driven Molecular properties prediction (MPP) is pivotal in drug discovery and drug repositioning.Deep learning models for MPP extract pertinent molecular features from varied molecule representations.Accurate prediction of drug molecules' physical properties and bioactivity depends on effective molecular representation.A diverse array of molecular descriptors has been developed to establish quantitative structure-activity relationships (QSAR), tailored for specific applications with distinct encoding preferences.This study assessed MPP and model performance using Morgan fingerprints employing both machine learning (ML) and deep learning (DL) methodologies, encompassing Random Forest, XGBoost, and SVM.Results indicate that the Morgan fingerprints presented enhanced predictive performance.DL methods in this research utilized BERT and LSTM.BERT, a pre-trained bi-directional encoder, extracts semantic representations through selfsupervised learning.The LSTM approach employs the mol2vec function for vectorizing compound structures and executing a single-layer LSTM model.An innovative hybrid model combining seq2seq LSTM with XGBoost proves highly effective in predicting molecular properties, leveraging neural networks' nonlinear generalization capabilities.This study introduces a novel methodology integrating diverse elements, including seq2seq LSTM and the XGBoost classifier, establishing a nonlinear network.The proposed approaches achieve 97% prediction accuracy for active and inactive compounds across various ML and DL classifications in MPP.F-1 scores attained with Random Forest, XGBoost, and SVM are 96%, 97%, and 96%, respectively, which proclaim robust and reliable model performance.
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 | 0.002 |
| 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) | 0.002 | 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".