I'm a passionate computational chemist with cheminformatics expertise. I am dedicated to utilizing computational methods and tools to solve real-world problems in drug discovery and molecular modeling. I have proven track record in molecular dynamics, quantum mechanics, and structure-based transformations. Skilled in integrating machine learning techniques for rapid compound screening and predictive analytics. I have successfully contributed to developing the ligand-binding and solvation free-energy computational pipepline in a fast-paced start-up environment. Proven experience in developing Python and C++ tools for efficient big data analysis. Adept at harnessing RDKit, Open Babel, and OEChem for advanced cheminformatics applications. Seeking to bring a blend of technical proficiency and analytical expertise to future endeavors.

• Languages: Python, C++
• Cheminformatics Tools: RDKit, Open Babel, OEChem, and Cpptraj
• Databases: PubChem, ChEMBL

A set of tutorial for applying cheminformatics techniques in Virtual Screening, Similarity Search, Conformer generating and High quality figure for presentation.

• 🔍 Molecular Similarity Search with RDKit.
• 🧪 Chemical Descriptor Computation with RDKit.
• 🧬 Clustering Conformers with RDKit

I believe in sharing knowledge. Check out my tutorials on RDKit applications in cheminformatics!

• 🔍 Molecular Similarity Search with RDKit: Unlock the Power of Cheminformatics by Exploring Tanimoto Molecular Similarity!. Molecular similarity plays a pivotal role in cheminformatics, offering insights into various applications such as virtual screening, compound selection, and drug repurposing. In this tutorial, we'll harness the capabilities of RDKit, a comprehensive cheminformatics library, to compute and analyze molecular similarity using fingerprints and the Tanimoto similarity metric.

  The Tanimoto similarity (often referred to as the Jaccard index) between two sets ( A ) and ( B ) is defined as:

$$ \text{Tanimoto}(A, B) = \frac{|A \cap B|}{|A \cup B|} $$

When it comes to molecular fingerprints, this metric essentially computes the ratio of shared bits (features) to the total number of bits set in either of the two molecules.

• 🧪 Chemical Descriptor Computation with RDKit : Transforming Molecular Structures into Meaningful Numerical Descriptors!. Chemical descriptors play a crucial role in cheminformatics by translating molecular structures into numerical values, these descriptors become the foundation for many machine learning and deep learning models. Such models aim to predict chemical properties and facilitate the drug discovery process by efficiently navigating the vast chemical space. The code below uses the RDKit library to compute a series of common chemical descriptors for a given list of molecules represented as SMILES strings.

• 🧬 Clustering Conformers with RDKit: Discover the Power of Conformer Clustering for Molecular Analysis!. Molecular conformers represent different spatial arrangements of atoms in a molecule, arising due to the rotation around single bonds. Clustering these conformers is essential in understanding the conformational landscape of molecules. This tutorial leverages RDKit's capabilities to generate, align, and cluster conformers, providing insights into the structural diversity of a molecule. Such understanding is critical for applications like drug design and molecular simulations.

• LinkedIn: Ajay Khanna
• Email: [email protected]

Feel free to explore my repositories and drop a star ⭐ if you find something interesting!