Progress of machine learning in the application of small molecule druggability prediction

European Journal of Medicinal Chemistry, Journal Year: 2025, Volume and Issue: 285, P. 117269 - 117269

Published: Jan. 10, 2025

Language: Английский

---

AI-Driven Innovation in Skin Kinetics for Transdermal Drug Delivery: Overcoming Barriers and Enhancing Precision

Pharmaceutics, Journal Year: 2025, Volume and Issue: 17(2), P. 188 - 188

Published: Feb. 2, 2025

Transdermal drug delivery systems (TDDS) offer an alternative to conventional oral and injectable administration by bypassing the gastrointestinal tract liver metabolism, improving bioavailability, minimizing systemic side effects. However, widespread adoption of TDDS is limited challenges such as skin’s permeability barrier, particularly stratum corneum, need for optimized formulations. Factors like skin type, hydration levels, age further complicate development universally effective solutions. Advances in artificial intelligence (AI) address these through predictive modeling personalized medicine approaches. Machine learning models trained on extensive molecular datasets predict accelerate selection suitable candidates. AI-driven algorithms optimize formulations, including penetration enhancers advanced technologies microneedles liposomes, while ensuring safety efficacy. Personalized design tailors individual patient profiles, enhancing therapeutic precision. Innovative systems, sensor-integrated patches, dynamically adjust release based real-time feedback, optimal outcomes. AI also streamlines pharmaceutical process, from disease diagnosis prediction distribution layers, enabling efficient formulation development. This review highlights AI’s transformative role TDDS, applications Deep Neural Networks (DNN), Artificial (ANN), BioSIM, COMSOL, K-Nearest Neighbors (KNN), Set Covering (SVM). These revolutionize both non-skin diseases, demonstrating potential overcome existing barriers improve care innovative

Language: Английский

---

A machine learning assisted designing and chemical space generation of benzophenone based organic semiconductors with low lying LUMO energies

Materials Science and Engineering B, Journal Year: 2025, Volume and Issue: 317, P. 118212 - 118212

Published: March 17, 2025

Language: Английский

---

Predicting UV-Vis Spectra of Benzothio/Dithiophene Polymers for Photodetectors by Machine-Learning-Assisted Computational Studies

Coatings, Journal Year: 2025, Volume and Issue: 15(5), P. 558 - 558

Published: May 7, 2025

The current study represents a machine-learning (ML)-assisted reverse polymer engineering for the rational design of high-performance benzothiophene (BT) benzodithiophene (BDT) polymers photodetector applications. By integrating their 5617 units with various acceptor moieties, total 72,976 unique combinations are generated. optical properties these predicted high accuracy (R2 = 0.86) using Gradient-Boosting Regression (GBR) model. SHAP value-based feature importance analysis indicates that Chi0 is most influential factor in predicting absorption maxima (λmax) polymers, followed by LabuteASA, Chi0V, Chi1, SlogP_VSA12, and other molecular descriptors. robustness employed model further validated through K-Fold cross-validation, highest mean squared error (MSE) observed at 2.02 fold-2 subset. designed exhibit λmax within range 400–750 nm, demonstrating suitability Moreover, Transformer-Assisted Orientation (TAO) approach to optimize design, successfully achieving bandgaps as low 0.42 eV. This facilitates rapid optimization tailored electronic properties, effectively addressing limitations conventional trial-and-error methods. ML-assisted presents promising strategy expediting development photodetectors advanced optoelectronic devices.

Language: Английский

---

Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation

Molecules, Journal Year: 2024, Volume and Issue: 29(20), P. 4894 - 4894

Published: Oct. 16, 2024

Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of systems so numerous that it is impossible to study all them experimentally. To remedy this limitation, solubility landscape selected active pharmaceutical ingredients (APIs) in choline chloride- betaine-based deep was explored using theoretical models based on machine learning. The available data APIs, comprising a total 8014 points, were collected neat solvents, binary solvent mixtures, DESs. This set augmented with new measurements sulfa drugs dry descriptors learning protocol obtained from σ-profiles considered molecules computed within COSMO-RS framework. A combination six sets 36 regressors tested. Taking into account both accuracy generalization, concluded best regressor nuSVR regressor-based predictive trained relative intermolecular interactions twelve-step averaged simplification σ-profiles.

Language: Английский

---

Cocrystal Formation Prediction: Hybrid GIN-Mordred Model Outperforms DFT-Based Methods

Crystal Growth & Design, Journal Year: 2025, Volume and Issue: unknown

Published: March 28, 2025

Language: Английский

---