Molecular Representations — SMILES, InChI & Fingerprints — Hands-on

Understand how real molecules are converted into machine-usable objects for QSAR, virtual screening and molecular ML. This module covers chemical graph concepts, SMILES and InChI encodings, and practical use of fingerprints for similarity, clustering and basic library analytics using open-source toolkits.

Molecular Representations — SMILES InChI Fingerprints

Help Desk · WhatsApp

Session Index

Session 1 — Atoms, Bonds & Molecular Graphs Session 2 — SMILES & InChI Encodings Session 3 — Fingerprints for Similarity & QSAR Session 4 — Mini Capstone: Similarity Search & Clustering

Session 1

Fee: Rs 8800

Atoms, Bonds & Molecular Graphs

Chemical graphs and internal representation of molecules

atoms, bonds, adjacency valence & formal charge aromaticity flags

Isomerism, tautomers and stereocenters at representation level

constitutional isomers E/Z and R/S centers tautomer handling

From drawings to data structures

sketchers & structure editors file import and sanitization basic quality checks

Session 2

Fee: Rs 11800

SMILES & InChI Encodings

SMILES basics and writing rules

atoms and branches rings and aromaticity isomeric SMILES

Canonicalization, stereochemistry and charges in SMILES

canonical vs input SMILES stereo flags charged species handling

InChI and InChIKey layers

connectivity layer stereo and charge layers linking databases with InChIKey

Session 3

Fee: Rs 14800

Fingerprints for Similarity & QSAR

Structural keys and substructure fingerprints

MACCS keys PubChem style keys substructure presence flags

Circular and path based fingerprints

ECFP style circular encoding radius and bit length choices hashing and collisions

Similarity metrics and distance notions

Tanimoto and Dice cosine and Hamming thresholds for hits

Session 4

Fee: Rs 18800

Mini Capstone: Similarity Search & Clustering

Building a fingerprint matrix from a small library

Theory + Practical

Running simple similarity search and enrichment checks

query by example hit lists and cutoffs basic scaffold overview

Clustering and simple visualization of chemical space

hierarchical or k means clustering heatmaps and similarity maps deliverables for later QSAR modules

PDF

Molecular Representations — SMILES InChI Fingerprints Training | Encoding Molecules for QSAR & Screening

Molecular Representations — SMILES, InChI & Fingerprints — Hands-on