Unveiling Tahoe Deep Dive Hackathon

‍

We created and released Tahoe-100M to start a movement and a community.

Our Tahoe Deep Dive Hackathon with Hugging Face was the first occasion for this community to get together physically and build. I am excited to announce the winning teams; selected by Richard Socher, Alexandra Pettet, Theofanis Karaletsos and Matthew T. Chang who judged the submissions on novelty, impact, and clarity.

Our hackathon weekend was a great success! The ideas and projects the teams came up with and executed on within two days was impressive. 10 multidisciplinary teams were formed during the hack weekend, detailed below are the first, second and third place winners.

First place: ClinOracle 🥇

Including Emma Dann, Kevin Hoffer-Hawlik, Meer Mustafa, Ross M Giglio, and Tony Zeng.

This team worked on building models that can predict clinical success from large-scale transcriptional datasets such as Tahoe-100M.

Second place: DAWO 🥈

Including Tiange (Alex) Cui, PhD, Danila Bredikhin, Jaanak Prashar, Mikaela Koutrouli, Sheng-Yong Niu and Yuhan Hao.

They built a specialized Variational Autoencoder (VAE) and leveraged multimodal representation learning to predict drug responses in cancer cell lines by integrating gene expression data with drug and cell line features.

Third place: SigSpace 🥉

Including Yanay Rosen, Giovanni Palla, Ishita Mangla, Kuan Pang, rohit khurana, Siddhant Sanghi, Yasha Ektefaie.

They developed an AI agent that accesses the Tahoe-100M dataset along with publicly available and novel datasets. This agent works to refine and expand the mechanisms of action (MOA) and drug signatures of the perturbations within the Tahoe-100M dataset.

These models and all the other models developed by the participants are all available open source on Hugging Face.

Congratulations to the winners!

Thanks to the energetic and creative participants. Thanks to our mentors and judges, and thanks to Hugging Face, Lambda, NVIDIA, and Amazon Web Services (AWS) for helping organize this fantastic event.

We are just getting started.