Machine learning based dynamic consensus model for predicting blood-brain barrier permeability

TL;DR: This review comprehensively explores artificial intelligence applications in pharmacology research, including drug discovery, pharmacokinetic prediction, and clinical pharmacology, highlighting strengths, limitations, and future directions of AI models in the field.

TL;DR: MPDS-CL is an open-source structure-based classification of molecules based on their atom composition and fingerprints. It contains nearly 150 million unique compounds classified into 56 structurally well-defined classes and 625 clusters.

TL;DR: This study develops a predictive model of Blood-Brain Barrier penetration using an Artificial Neural Network optimized by the Sine Cosine Algorithm, achieving an accuracy of 0.89 and F1-score of 0.75, offering a reliable in silico alternative to in vivo methods.

TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.

TL;DR: This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost.

TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.

TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.