Using AI to Predict Drug Targets [Hybrid]

Discover how artificial intelligence is transforming drug discovery.

Two-part, HYBRID class, please read carefully:

You can sign up to take the class virtually or in person at our lab! Please choose the correct ticket type so we can send the zoom details if you sign up to join in virtually.

Saturday, August 23, 3:00PM - 6:00 PM

Sunday, August 24, 3:00PM - 6:00 PM

Drug discovery is a $25 billion industry, and with the rise of AI and big data, it’s only getting bigger. In this hands-on workshop, you’ll step into the world of computational biology and learn how to build your own machine learning model to predict potential drug targets for diseases like breast cancer, Alzheimer’s, and COVID-19.

In particular, we’ll cover:

• Ingesting and processing three single-cell RNA sequencing disease datasets
• Building a supervised algorithm to predict druggable targets from known targets
• Developing a reproducible model pipeline for deeper analysis and next steps

For ease of access, we’ll be working with publicly accessible data from the Chan Zuckerberg Initiative CELLL x GENE Census. To process our single cell data, we will rely on commonly used libraries like scanpy and pandas. This will allow us to do quality control (QC) on the data, identify differentially expressed genes, and scale it appropriately for machine learning. To build, train, test and evaluate our AI model, we will use sklearn. This course assumes beginner experience with Python programming and fundamental Biology knowledge.

Fact-sheet can be found here.

COVID-19 Safety Notice:

If you are feeling unwell, suspect that you have been exposed to COVID-19 or have tested positive in the past 7 days, please do not attend and let us know ASAP (info@genspace.org). If you cancel after our 7-day policy, we cannot refund your ticket, but we can exchange and offer credits toward future classes. If you have signed up for Biohacker Boot Camp, we will automatically transfer your registration to the next month’s dates unless you tell us otherwise.

Meet the Instructor

Aneesa Valentine (she/her) is currently a Genomics Solutions Architect at a software company called TileDB. Being formally trained as a scientist, she has a longstanding career in academic research spanning Microbiology, Immunology and most recently, Computational Genomics. After a brief stint as a PhD student, Aneesa mastered out of her doctoral program to pursue a career in Data Science & AI. She holds an MS in Biomedical Science, and has since held Data Scientist titles before pivoting into the world of Life Sciences software. 

She considers herself a translator and finds joy in enabling and empowering the next generation of scientists. She’s given talks to students and professionals alike: endeavoring to make Computational Biology and Data Science accessible to all.