ChemPlot, a Python library for chemical space visualization

Abstract

Visualizing chemical spaces streamlines the analysis of molecular datasets by reducing the information to human perception level, hence it forms an integral piece of molecular engineering, including chemical library design, high-throughput screening, diversity analysis, and outlier detection. We present here ChemPlot, which enables users to visualize the chemical space of molecular datasets in both static and interactive ways. ChemPlot features structural and tailored similarity methods, together with three different dimensionality reduction methods: PCA, t-SNE, and UMAP. ChemPlot is the first visualization software that tackles the activity/property cliff problem by incorporating tailored similarity. With tailored similarity, the chemical space is constructed in a supervised manner considering target properties. Additionally, we propose a metric, the Distance Property Relationship score, to quantify the property difference of similar (i.e. close) molecules in the visualized chemical space. ChemPlot can be installed via Conda or PyPi (pip). Its web application is freely accessible at https://www.amdlab.nl/chemplot/.

Natural Lipid Extracts as an Artificial Membrane for Drug Permeability Assay: In Vitro and In Silico Characterization

“…This result is consistent with the extensive use of these parameters as robust descriptors of in silico models for ADME-T processes such as intestinal absorption [ 27 , 28 ], brain distribution [ 29 ], metabolism [ 25 ], toxicity risk [ 30 ], or hERG inhibition [ 31 ] with similar correlation signs. Moreover, these descriptors are also generally used in such virtual screening tools as an earlier mentioned Ro5 [ 16 ] or other filters (Ghose’s [ 32 ], Veber’s [ 18 ], Egan’s [ 33 ], and Muegge’s [ 34 ]) [ 35 ], which provides further evidence for the internalization of PAMPA models in early drug discovery.…”

“…The t-SNE calculation and the following visualization were carried out using Chemplot library version 1.2.1. [ 18 ]. The compounds were described with their 1,024-bit ECFP4 fingerprint as a structural descriptor.…”