Standardize and analyze molecular structures with RDKit for cheminformatics workflows.
npx skills add https://github.com/dralkh/seerai --skill datamol-dralkh
Please help me install this Agent Skill. Skill: datamol Source: https://github.com/dralkh/seerai/tree/main/skills/datamol Command: npx skills add https://github.com/dralkh/seerai --skill datamol-dralkh
Datamol removes the friction from cheminformatics by giving researchers a Pythonic, RDKit-compatible workflow for turning raw molecular inputs into standardized, analysis-ready data.
Ask the datamol skill to load your molecular file, standardize the structures, compute key descriptors, and return a clean research-ready summary.
High-intent search queries and answers about installing and using this skill.
To convert SMILES to RDKit Mol objects for cheminformatics analysis, you standardize molecular structures by loading SMILES, InChI, or SELFIES inputs. This sanitizes and cleans the structures, outputting native RDKit molecules required for downstream descriptor calculation and clustering workflows.
Clustering molecules by similarity for drug discovery involves computing molecular fingerprints and similarity matrices. Applying parallel batch processing to these fingerprints efficiently groups large compound libraries into clusters for screening and scaffold analysis.
Calculating molecular descriptors from a compound library in Python requires native RDKit molecule objects. You load your molecular file, standardize the structures, and use parallel batch processing to compute key descriptors for drug-likeness scoring.
Yes, this cheminformatics workflow supports reading and writing SDF files, alongside CSV and Excel molecular files. It handles molecular file I/O with optional fsspec-backed local or remote data access, enabling reproducible, high-throughput computation for research analysis.
Yes, you can generate 3D conformers and apply reaction SMARTS for library design. The workflow supports 3D conformer generation for standardized molecules and applies reaction SMARTS directly to native RDKit objects for virtual screening and compound library expansion.
Yes, you need RDKit installed to compute fingerprints and molecular scaffolds. The workflow requires native RDKit molecule objects to perform parallel batch processing for descriptor calculation, fragmentation, and publication-ready visualization.
ovachieverConvert SMILES or RDKit molecules into ML-ready numerical representations.
lijiandaoGenerate publication-ready charts from CSV or Excel data for PNG or PDF.
SciMate-AIProvide a Pythonic RDKit interface for molecular parsing, descriptors, and conformer generation.
Estrella-231Compute cheminformatics descriptors, fingerprints, and SMARTS substructure matches from SMILES/SDF/MOL inputs.
