This is an overview of the cheminformatics capabilities available in the Datagrok platform. During the interactive sessions, we will do the following:
• import molecules in the SMILES format
• take a closer look at the molecule-specific info panels, including 3D structure, SDF, toxicity prediction, drug likeness, ChEMBL substructure and similarity, identifier conversion, PubChem integration, predictive models, as well as usuing community-produced scripts as context info panels
• sketch new molecules
• retrieve molecules by name, or by other identifiers
• perform in-memory substructure search
• perform similarity and diversity analyses using different metrics and fingerprints
• calculate descriptors
• perform R-Group analysis
• visualize molecules on a scatter plot, bar chart, grid, form, and tile viewer
• learn how to write RDKit-based Python scripts that take molecules as inputs
• search for substructures in a database powered by a chemical cartridge
• reproduce above-mentioned steps by applying recorded macros
00:00 Introduction
01:19 Importing SMILES & Rendering Molecules
03:01 Molecule-Specific Info Panels
06:20 Community-Produced Scripts
09:27 Sketching Molecules
11:07 Substructure Search
12:16 Descriptors
13:44 Converting Molecule Identifiers
15:36 Similarity / Diversity Search
17:09 R-Group Analysis
18:10 Visualizing Molecules on Viewers
19:37 Developing Scripts and Functions
22:24 Searching the ChEMBL Database
Learn more:
datagrok.ai/help/domains/chem/cheminformatics
• Molecular similarity and diversity
コメント