About Me


I am a graduate student at IIIT Hyderabad. I finished my Bachelors in Computer Science and currently finishing my Masters by Research in Computational Natural Sciences. I am working under the guidance of Dr. U. Deva Priyakumar. I am affiliated with the Centre for Computational Natural Sciences and Bioinformatics (CCNSB), IIIT Hyderabad.
You can find my resume here

Interests

  • Drug Design & Discovery
  • Deep Learning
  • Reinforcement Learning
  • Graph-based Learning Algorithms
  • Information Retrieval

Education

  • B.Tech in Computer Science and MS by Research in Computational Natural Sciences (2016 - Present)
  • International Institute of Information Technology, Hyderabad
  • Cumulative GPA: 9.18/10

Publications


July, 2020 | ICML'20

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning

Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam M. J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio
37th International Conference on Machine Learning (ICML), 2020.

Paper

Feb, 2020 | AAAI'20

Chemically Interpretable Graph Interaction Network for Prediction of Pharmacokinetic Properties of Drug-like Molecules

Yashaswi Pathak, Siddhartha Laghuvarapu, Sarvesh Mehta, U.Deva Priyaumar
34th AAAI Conference on Artificial Intelligence (AAAI), 2020.

Paper Code

Nov, 2019 | J. Comp. Chem. 2019

BAND NN: A Deep Learning Framework for Energy Prediction and Geometry Optimization of Organic Small Molecules

Siddhartha Laghuvarapu*, Yashaswi Pathak*, U.Deva Priyaumar
Journal of Computational Chemistry, 2019.

Paper Code

Under Review

Deep Learning Enabled Inorganic Material Generator

Yashaswi Pathak, Karandeep Singh Juneja, Girish Varma, Masahiro Ehara, U Priyakumar
Under Review.

Paper Code

Work Experience


99andBeyond

Machine Learning Researcher
Worked on reinforcement learning based agent that can efficiently search for synthesizable drug-like molecules.
Working on developing autonomous platform for drug-design and discovery.

MatSci AI

Research Analyst Intern
Developed Pipeline for various NLP Tasks.
Worked on Database design and efficient data extraction design for a huge data set of Industry materials.

CQBS

Full Stack Developer
Developed complete web app as per client’s need.
Developed analytic tools for the admin to efficiently monitor the work progress of the organization.

Selected Projects


Search Engine

Built a search engine in Python on the Wikipedia data dump. The engine had a variety of capabilities like field queries, exact-match retrieval and best-match retrieval.

Hatespeech Detection

Social media analytics using the twitter dataset was done. Structure based tree-LSTM model and structured self attention based models were used to perform the various tasks.

Compiler Frontend

Developed a compiler frontend for a toy programming language. The compiler includes lexical analysis, syntax analysis, AST generation, interpreter and LLVM code generator.

Molecule GPT

Developing a mini "Generative Pretrained Transformer" GPT for drug like molecules that is able to generate molecules with ~100% accuracy while optimizing for a target property using RL algorithm.

Game Development

Develop a 3D game similar to Legend of Zelda. Incorporated laws of physics(gravity, classical mechanics, etc.) without using any game engine.

Linux Shell

Develop UNIX shell to interact with the kernel using system calls. Implemented features for I/O redirection, piping, background processes.

Contact


Email : yashaswi [dot] pathak [at] research.iiit.ac.in
Phone : +91-9006291343
Address : A3-314, Vindhya, Centre for Computational Natural Sciences and Bioinformatics, IIIT Hyderabad