Chemical Databases & Data Curation — Hands-on

Learn end-to-end chemical data sourcing and curation for drug discovery and QSAR workflows. You will fetch structures and bioactivity metadata from major public repositories, reconcile identifiers, remove duplicates and salts/solvents, and ship clean QSAR-ready datasets with full provenance and licensing compliance.

Chemical Databases & Data Curation (PubChem/ChEMBL/ChEBI)

Help Desk · WhatsApp

Session Index

Session 1 — Public Chemical Repositories & Identifiers Session 2 — Programmatic Access & Bulk Download Session 3 — Standardization, Dedup & QA/QC Session 4 — Mini Capstone: QSAR-Ready Dataset

Session 1

Fee: Rs 10800

Public Chemical Repositories & Identifiers

Landscape & data models

PubChem CID/SID ChEMBL compound/activity ChEBI ontology

Identifiers & cross-refs

SMILES / InChI / InChIKey synonyms & registry IDs provenance & versioning

Licensing & attribution

reuse guidelines citations & metadata compliance checklist

Session 2

Fee: Rs 13800

Programmatic Access & Bulk Download

APIs & clients

PubChem PUG-REST ChEMBL web services FTP/SDF dumps

Query design & filters

substructure/similarity assay/endpoint selection species & units

ETL basics

SDF/CSV to pandas rate limiting & retries caching & checkpoints

Session 3

Fee: Rs 16800

Standardization, Dedup & QA/QC

Structure normalization

salt/solvent stripping tautomer handling charge neutralization

Deduplication & merges

InChIKey-based synonym collapse conflict resolution

QA/QC & audit trails

data dictionaries unit harmonization validation reports

Session 4

Fee: Rs 20800

Mini Capstone: QSAR-Ready Dataset

Assemble endpoint-specific data (e.g., pIC50)

Theory + Practical

Curation pipeline & export

RDKit + pandas SMI/SDF/CSV outputs provenance log

Deliverables

clean dataset + report license & citation file reproducible notebook/script

PDF

Chemical Databases & Data Curation (PubChem/ChEMBL/ChEBI) | Programmatic Access & QSAR-Ready Datasets

Chemical Databases & Data Curation — Hands-on