Dakshinamurthy Sivakumar, PhD

Dakshinamurthy Sivakumar, PhD

Drug Discovery with 17years of experience in Cheminformatics
Middle East
English
Academic affiliation

Bioinformatician by training with Postdoctoral studies in Cheminformatics, Drug Design and Quantum Mechanics with good experience in insilico and AI based CROs with diverse clients. Can be an active team player as well as can lead team.

Individual
Company

Skills

Scaffold hopping
Structure-based drug design
Ligand-based drug design
Data mining (ChEMBL, etc.)
AI/ML/NN
Lead optimization
Hit to lead
Fragment based drug discovery
Covalent inhibitor chemistry
Virtual screening
Protein-protein interaction (PPI)

About

A trained computational chemist with strong knowledge and experience in drug design. Practicing structural bioinformatics for more than 17 years with 7+ years post Ph.D. exp. Worked on identifying the crucial determinants of drug binding selectivity for highly similar proteins with profound experience in Molecular dynamics, QSAR, and Pharmacophore. Hands-on working experience in different AI/ML methods (like RL(reinforcement learning), generative models, RNN-LSTM) in drug design and cheminformatics projects. Excellent communication and networking skills, leadership, scientific writing and teamwork skills proved in multifaceted projects and various computational chemistry publications.

Work experience

Postdoctoral Fellow

Company:
Max Planck Institute for Dynamics of Complex Technical Systems – Germany
Duration:
Jan 2019
-
Jun 2020
present

- Structural basis for cysteine proteases OTUB1 and OTUB2 - structural determinants for their catalytic triad stabilization using molecular dynamics simulations - designing selective inhibitors.

- Role of water molecules in enzyme activation and substrate binding.

- Tracking water molecule paths to access the determinants of the enzyme selectivity - highly similar active site architecture and covalent drug discovery.

- Mentored master thesis and handled drug design lab courses for master students.

- Wrote and published peer-reviewed articles concerning findings and highlighted possible applications for findings

Principal Scientist

Company:
PharmCADD
Duration:
Jul 2020
-
Feb 2023
present

- Designing workflow for effective screening of selective inhibitors (From hit identification to candidate selection) from commercial databases.

- Lead optimization - to improve the compound activity with a better pharmacokinetic (ADME/T) profile.

- Drug repurposing - pharmacophore analysis - scaffold hopping - fragment-based approaches – PROTACS/ targeted protein degradation.

- Hit identification – Complex stability of MD simulation – Binding free energy calculations.

- Pipeline design and modifications using KNIME workflows.

Discovery Scientist

Company:
Cresset Software and Discovery
Duration:
Mar 2023
-
present

- Designing novel screening strategies for identification of potential hits for resistant strains.

- Bioisosteric replacement and scaffold hopping to identify novel compounds and lead optimization for different discovery projects.

- Leading the team and direct discussion with clients.

Education

T.N.Dr.MGR.Medical University

Degree:
B.Pharm.
Year of degree awarded:
2003

SASTRA University

Degree:
M.Tech (Bioinformatics)
Year of degree awarded:
2006

SASTRA University

Degree:
PhD
Year of degree awarded:
2016

Publications

Case STUDIES

AI-assisted de novo design approach to design a selective inhibitor

Treating acute myeloid leukemia (AML) by targeting FMS-like tyrosine kinase 3 (FLT-3) is considered an effective treatment strategy. By using AI-assisted hit optimization, we discovered a novel and highly selective compound with desired drug-like properties with which to target the FLT-3 (D835Y) mutant. In this study, an AI-assisted de novo design approach to identify a novel inhibitor of FLT-3 (D835Y). A recurrent neural network containing long short-term memory cells (LSTM) was implemented to generate potential candidates related to our in-house hit compound (PCW-1001). Approximately 10,416 hits were generated from 20 epochs, and the generated hits were further filtered using various toxicity and synthetic feasibility filters. Based on the docking and free energy ranking, the top compound was selected for synthesis and screening. Of these compounds, several fold better active selective inhibitor was identified.