Loading Video...
NTHRYS
Arrow

Data Quality, Standardization & Chemical Registration | FAIR, Auditable & Reproducible Pipelines

NTHRYS >> Services >> Academic Services >> Training Programs >> Bioinformatics Training >> Cheminformatics, QSAR & ADMET >> Data Quality, Standardization & Chemical Registration | FAIR, Auditable & Reproducible Pipelines

Data Quality, Standardization & Chemical Registration — Hands-on

Create trustworthy, searchable, and compliant chemical datasets. This hands-on module teaches structure standardization (salts/tautomers/protonation/valence) , ID generation (SMILES/InChI) , duplicate detection & merge rules, and registration workflows (business rules, lots/batches, audit trails) that power discovery, QSAR, and regulatory reporting. You will ship reproducible QC/QA pipelines aligned to FAIR principles.

Data Quality, Standardization & Chemical Registration
Help Desk · WhatsApp
Session 1
Fee: Rs 18800
Structure Standardization Foundations
  • Normalization strategies
  • salt/solvent stripping tautomer & charge normalization valence & aromaticity models
  • Stereochemistry & isotopes
  • chiral flags/unspecified centers E/Z normalization mixtures & polymers (basics)
  • Pipelines & configs
  • standardizer rulesets unit tests & golden sets reproducible seeds/versions
Session 2
Fee: Rs 21800
Identifiers, Matching & Dedupe
  • Canonical IDs & encodings
  • SMILES (canonical/isomeric) InChI & InChIKey layers registration-friendly hashes
  • Equivalence & dedup rules
  • tautomer-insensitive matching stereo-sensitive options salts/mixtures handling
  • Ingestion & validation
  • vendor SDF/CSV imports schema checks & CV terms error buckets & fixes
Session 3
Fee: Rs 24800
Registration Workflows, Governance & Audit
  • Registry design & business rules
  • parent/lot/batch hierarchy merges/splits & supersession status & lifecycle states
  • Governance & compliance
  • audit trails & versioning GHS/REACH tags (light) privacy/IP considerations
  • LIMS/ELN integration
  • API/ETL patterns delta loads & snapshots error handling & alerts
Session 4
Fee: Rs 28800
Mini Capstone: QC/QA Pipeline & Mini-Registry
  • Build an ingest → standardize → dedupe pipeline
  • Theory + Practical
  • Register parents/lots, generate IDs & audit entries
  • business rules & merges governance checks QC report export
  • Deliverables
  • QC/QA summary (PDF/HTML) registry sample (CSV/JSON) configs/notebooks for reruns


PDF