<aside> 🖖 Hey! I’m a 17 year old passionate about applying computation to drug discovery at the intersection of graph representational learning, natural language processing and molecular property prediction.
</aside>
👨🔬 Incoming computational research intern at Nurix Therapeutics in San Francisco, a public biotech company where I will be working on using large-scale DNA-encoded libraries (DEL's) and high-throughput screening to discover protein degradation drugs for immuno-oncology.
☀️ Mentoring developers as part of Google's Summer of Code for the DeepChem Project!
⛰ Remote-working in Vancouver, British Columbia while hiking and exploring nature with friends this summer.
🏫 Graduating from high school in June of 2021, and currently applying to computer science and engineering programs.
🥼 I work on computational drug discovery and machine learning as a Research Intern in the Aspuru-Guzik Group at the University of Toronto and Vector Institute. One of the projects I help develop there is SELFIES, a 100% robust molecular string representation for machine learning models.
💻 I’m currently working on democratizing deep learning for the life sciences with DeepChem, with the mentorship of Dr. Bharath Ramsundar from Stanford University. There, I work on developing sequence and graph-based models for understanding structural biology and chemistry. In Oct 2020, I published ChemBERTa, a large-scale transformer for molecular property prediction, accepted into the NeurIPS ML for Molecules Workshop.
🔬 My research is supported by the Emergent Ventures Fellowship, selected by Dr. Tyler Cowen at the Mercatus Centre and funded by the Thiel Foundation (Press Release).
🧬 This fall, I helped create Biodojo, a training ground for the next generation of biotechnology innovators in high school and undergrad. We've capped our first cohort at 25 members, around the world from Hong Kong to Toronto.
📈 I worked as an ML intern on the Applied AI team at Integrate.ai, an enterprise software company building a consumer insights platform for Fortune 500 companies.
📊 Data analytics consulting for Fortune 500 companies like Fasken Law (Addressing attorney attrition with automated onboarding systems), Walmart (mapping demand in the supply chain using data wrangling software), and Wealthsimple (increasing engagement with key consumers for the RESP financial product).
🗓️ Organized one of Canada's biggest medical innovation events, donating $6k to SENS + Sick Kids.
🌱 I’m currently learning NLP, geometric learning, and neuroscience. 🧠
⚙️ I use python, tensorflow, pytorch, sklearn, pandas, transformers, and dgl
💬 Ask me about geometric learning, natural language processing and computational chemistry.
🥋 In my free time, I enjoy practicing Taekwon-do, writing, and playing the piano.
👨🏾💻 Check out my Github for more previous work!
Currently looking for new opportunities to grow and provide value.
<aside> <img src="https://www.flaticon.com/svg/static/icons/svg/646/646094.svg" alt="https://www.flaticon.com/svg/static/icons/svg/646/646094.svg" width="40px" /> Email
</aside>
<aside> <img src="https://www.flaticon.com/svg/static/icons/svg/3135/3135683.svg" alt="https://www.flaticon.com/svg/static/icons/svg/3135/3135683.svg" width="40px" /> CV
</aside>
<aside> <img src="https://www.flaticon.com/svg/static/icons/svg/1384/1384088.svg" alt="https://www.flaticon.com/svg/static/icons/svg/1384/1384088.svg" width="40px" /> Linkedin
</aside>
<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/3710635a-94fa-4f6a-b92b-38eb0ada21c3/black-and-white-twitter-logo-transparent_100736.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/3710635a-94fa-4f6a-b92b-38eb0ada21c3/black-and-white-twitter-logo-transparent_100736.png" width="40px" /> Twitter
</aside>
<aside> <img src="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/065fdf9d-eba6-41b8-828c-71189262625a/Youtube-Black-Icon-PNG.png" alt="https://s3-us-west-2.amazonaws.com/secure.notion-static.com/065fdf9d-eba6-41b8-828c-71189262625a/Youtube-Black-Icon-PNG.png" width="40px" /> Youtube
</aside>
Highlighted Publications and Projects
William Lyon Mackenzie Collegiate Institute 2017 - 2021 | Math and Computer Science (MaCS) program | Grade 12 GPA: 4.0
Clubs and Activities: DECA (Finance club executive; Provincial Finalist), HOSA, Mackenzie Science Club (exec), Mackenzie Concert Band, Cabaret Band, Math Club.
Emergent Ventures Fellowship
Recipient of the $15,000 CAD Emergent Ventures research fellowship, supported by the Thiel Foundation. (Press Release)
Tensorflow Research Cloud Fellowship (~$2000 in GPU credits)
Selective research grant offered by Google to use TPU graphics processing units for machine learning research
Re-Work Young Researcher to Watch Delivered talk at Re-Work academic research conference in Montreal in front of over 1000 attendees on independent research in computational. bio + regulatory genomics.
ML Research Intern - University of Toronto 2020 - current | Toronto, Canada (remote) Paid research internship at Prof. Alan-Aspuru Guzik’s Matter Lab and the Vector Institute, focusing on researching machine learning applications at the cutting edge of drug design, chemistry and materials science. Getting to work on many cool things which I hope to share soon :)
Open-source developer - The DeepChem Project 2019 - current | San Francisco, California (Remote)
On the open-source developer team for DeepChem, an organization aimed towards building practical machine tools for chemistry, structural biology, and drug discovery that's accessible for all. Originated Pande Lab at Stanford, now a decentralized research organization across the world. I developed infrastructure + tutorials (ChemBERTa) for transformer and graph-based techniques, receving 250,000 API calls to open-sourced language models.
Machine Learning Engineer (Intern) - Integrate.ai June 2019 - September 2019 | Toronto, Canada Paid internship working on our core product, the Trusted Signals Exchange, on the Machine Learning Science team, developing robust production-ready models with Sklearn, Tensorflow and Spark. Worked with clients across telecom, insurance, fintech, digital gaming, and travel. Led a team of 6 to build an internal ML DevOps compiler, Eunomia, specifically to detect errors in misformatted datasets and training parameters, utilizing JSON schema. The tool was deployed across the entire engineering team of 60 staff.
ChemBERTa - Chithrananda, S., Grand, G., & Ramsundar, B. (2020). ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. (NeurIPS 2020). arXiv:2010.09885. Spotlight presentation, ML for Molecules workshop
SELFIES - Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation. Major developer for v1.0 release. (article)
DeepBind - Implementation of DeepBind algorithm, using Tensorflow, to predict binding for transcription factor proteins on hundreds of genes. (github)
