NF2 Tumor Genomics Hackathon


On June 23rd, SVAI + + NF2 Project, are kicking off our first AI Genomics hackathon at Google Launchpad in San Francisco! We're also happy to announce the NCBI as a community partner. This event will focus on analyzing Genomic data and research publications using AI and other computational methods. We have a special opportunity to work with patient data from an ongoing medical case, provided by Onno Faber, a serial entrepreneur and NF2 Patient. This event kicks off our first open source medical AI community project and we're super excited for it!



  • Contribute to a real, ongoing patient case.
  • Try to advance our understanding of NF2 mutations.
  • Encourage more AI researchers to pursue healthcare and biology problems.
  • Explore this unique, high definition NF2 Tumor Genomics dataset.
  • Establish an open source community for future Medical AI collaborative hacking.



The main issue with NF2 is that patients develop tumors in the central nervous system, slowly knocking out senses and body functions (hearing for most, facial paralysis and sight/muscles/sensory functions for some). All the ‘tracks’ below are ways to find out why these tumors are there, what makes them grow and most importantly how to stop them.

*We encourage you to analyze the NF2 dataset based on your interests and expertise* 

  1. Drug treatment pathways for existing medications.
  2. Ranking dataset mutations.
  3. Use NLP to mine NF2 research and present novel treatment options.
  4. Create a novel drug intervention with DeepChem (Bharath Ramsundar)

Advanced: NF2 Expanded Problem Tracks and Vision for Ongoing Investigation.



Whole Genome sequence data set for NF2: a genetic condition that causes tumors to grow from Schwann cells. The dataset has a tumor/normal pair and a sibling. All three Whole Genome Sequences were done at 60-90X and available as .bam-files. The dataset was acquired in the context of finding the driver mutations for a particular NF2 patient. For registered participants, we will release the dataset 1-week prior to the start of the hackathon. Get the NF2 Dataset.



  • Learn how to work with Genomic Data.
  • Awesome mentoring sessions on AI and Genomics.
  • Make new friends.
  • Connect with us and our event partners.


All of our In-person event invitation have been sent! You may still apply to participate remotely.

Rules and Genomic Data Usage Agreement



Here's the full schedule for the weekend [PDF].



We created a few slack channels for easy communication during the event Join: #hackathon or #hackathon-remote. 

Join Our Slack Channel.


We will be administering $150,000 in Google Cloud credits to teams over the weekend. Yay! Google Cloud is also the best way to gain access the NF2 dataset. We'll start getting teams set up with credits on Friday night. Sign up on Google Cloud.



Our mentors will float around during the event and check in with teams to help with problems and answer questions. Please feel free to seek them out at the event and say hi! Some of our mentors will also be participating on teams, so we may post specific hours they are available to help. Also: Don't hesitate to ask others at the event for help - everyone participating in this event has extraordinary skill.



The official NF2 AI Genomics Hackathon Hashtag is: #NF2Hack

We will use Twitter for live announcements and updates from the event. Follow us at @SVAIresearch.



Join our FaceBook Group and share some photos of the event (In-person and remote). We plan on periodically live streaming short interviews and broadcasting what people are working on through Facebook. SVAI Facebook.



The opening and closing talks will be live streamed on SVAI's Youtube account.

  • June 23rd 18.40: Opening Talks.
  • June 25th 16.00: Closing Talks and Final Presentations.



We'd like to see submissions follow the same format as an (abbreviated) academic poster. Submissions are not restricted to this format and we encourage you to be as creative as you want. Push to Github.

  1. Introduction
  2. Purpose
  3. Approach
  4. Methods / Algorithms / Models
  5. Results and Discussion 



Each team or individual will have 5 Minutes to present what they worked on. Presentations will be fast! But don't worry, we will link submissions here afterwards so you can get a closer look at what everyone worked on.



Each presentation will be judged on the following criteria weighted in this order:

  1. How well does the solution lead to positive outcomes for NF2 Cancer patient treatment?
  2. How novel is the approach to finding a solution?
  3. Quality and depth of the problem analysis.
  4. Team dynamics, diversity, and intersectionality including cross discipline and specialization collaboration.



We’re giving away three Titan X Pascal boards valued at ~$1,500 a piece, compliments of NVIDIA. Great for local TensorFlow and access with the NVIDIA Deep Learning tool chain etc.  Thanks NVIDIA!


Ben Busby, PhD

Computational Biology Branch, NCBI, NLM, NIH


Ben leads the NIH's efforts to partner with Genomics hackathons. His research interests include generation of clustering algorithms for analysis of large gene families and whole genomes and Phylomic Analysis of Gene Transfer Events. Ben holds a PhD in Biochemistry and Molecular Biology from University of Maryland, Baltimore.


Carlos Uranga

Entrepreneur in Robotics/Genomics/A.I., former Director of Innovation Lab Singularity University


Carlos is founder, developer, and mentor for startups - leveraging robotics to quantify and elucidate patterns in living systems.  Most recently Carlos had the privilege of serving as the Director of the Innovation Lab (iLab) at Singularity University (SU) - empowering leaders and startups to leverage exponential technologies and solve global grand challenges. Carlos has ~ 4 years experience in molecular biology R&D, bioprocess engineering, and over 10 years industry experience in Bioinformatics, Pharmacogenomics, clinical and genomics lab automation.  As an early proponent of preventative medicine using Genomics (and other -omic sciences), he assisted in some of the early designs of novel genetic analysis/ molecular diagnostic tools finding propensity and concurrence of hereditary disease.  Carlos has a Masters in Bioengineering from UCSD and the equivalent of a Masters in Computer Vision and Robotics from INPG/ INRIA in Grenoble, France.  Carlos likes to spend time adventure motorcycle and bicycle riding, and loves to hack 2D & 3D robots for fun - this all while listening to a great audiobook or some rad EDM.



Bharath Ramsundar 175.png

Bharath Ramsundar

Stanford, UC Berkeley, DeepChem Author


Bharath Ramsundar received a BA and BS from UC Berkeley in EECS and Mathematics and was valedictorian of his graduating class in mathematics. He is currently a PhD student in computer science at Stanford University with the Pande group. His research focuses on the application of deep-learning to drug-discovery. In particular, Bharath is the creator and lead-developer of DeepChem, an open source package that aims to democratize the use of deep-learning in drug-discovery and quantum chemistry. He is supported by a Hertz Fellowship, the most selective graduate fellowship in the sciences.

Twitter   LinkedIn

Carolina Garcia Rizo

Roche Molecular Systems, MIT

A global multilingual executive with an MBA and a Ph.D. in Physics/Chemistry, 15+ years of experience in Business Development and Healthcare strategy consulting, leading and executing commercial sales operations in Biotech and Molecular Diagnostics in the area of Immuno and Oncology. Leadership in Precision Medicine, CDx, Genomics, and Bioinformatics. 


Mo Rahman

Bioinformatics & Pharmacogenomics CSO at GeneDrop Inc.


I am a biochemist particularly interested in medicine and novel discovery using genomics, targeted delivery, and computational methodology. Always up for solving relevant problems, as well as close interaction with industry & academia. Specialties: Computational genomics, drug development, pilot scale studies, structural bioinformatics

 Twitter   LinkedIn

Avanti Shrikumar

Stanford, MIT


Avanti is a second-year Ph.D student in the Department of Computer Science at Stanford, advised by Professor Anshul Kundaje. She has develop broadly-applicable methods to make deep learning models interpretable, and has applied these methods to study regulatory genomics. Avanti has a Bachelor's in Computer Science with Molecular Biology from MIT and spent a year working as a developer for the Healthcare team of Palantir Technologies before starting her PhD. Read more at Avanti's Stanford page.

Twitter   LinkedIn


Onno Faber

Entrepreneur, NF2 Patient


*The data we are using for this hackathon is Onno's personal genomic data.*  Onno is the Founder & CEO of Tapstack. He previously founded several companies including; ii studio, Hoppakay, MarketMatchers and Ding Dong. “I have been creating things and solving problems for as long as I can remember. I've studied architecture and got my degree in 2006 ( honors). My interest in the internet and entrepreneuring never left me and ever since grew stronger. Now I'm a full-time entrepreneur, enjoying developing new concepts and products. Above all I value connections to other people."

 Twitter   LinkedIn

Laura Montoya

CEO, Accel.AI


Laura is Founder and CEO of where she teaches AI and Deep Learning workshops. She is also a chapter director for Women Who Code. - I have been described by my team members as a natural and versatile leader with a passion for Artificial Intelligence, Computer Science, Research, and Psychology. Personal interests include growth & empowerment, diversity, and community outreach. I enjoy extending any extra energy and resources into volunteering for human rights organizations. When I am not volunteering in my free time, I enjoy cycling, running, and dancing.

Twitter   LinkedIn

Anita Schjøll Brede


Anita is CEO & Co-Founder of Iris AI, an Artificial Intelligence that will read all of the world's science and help us connect the dots. She attended Singularity University in summer 2015, and is a a Board Member of the Ulstein Group, a 100 years old marine company.

Twitter    LinkedIn

Marco Giovannini, M.D., Ph.D.

Professor and Medical Doctor, UCLA

Marco Giovannini, M.D., Ph.D. is Professor-in- Residence of Head and Neck Surgery at the University of California Los Angeles (UCLA) and Clinical Research Director of the UCLA NF2 Multidisciplinary Clinic. A molecular geneticist by training, Marco Giovannini is a physician-scientist who conducts laboratory and clinical research, and is a world thought leader in the field of Neurofibromatoses. His NIH, Department of Defense and private foundation-supported research laboratory develops models of disease to test new therapeutic options and studies mechanism of action of treatments in patients.

Jane Metcalfe

Founder, Neo.Life and Wired Magazine

Jane Metcalfe is Founder of Neo.Life, a new publication by, for and about the leaders, pioneers and early adopters of the Neo-biological Revolution. We analyze new drugs, tools, research, therapies, exercise, food and "brainfulness." She is also the co-founder, and former president of Wired Ventures, creator and original publisher of the magazine Wired. Prior to that, Metcalfe managed advertising sales for the Amsterdam-based Electric Word magazine.

Twitter   LinkedIn

Berton Earnshaw

Recursion Pharmaceuticals

Berton is Director of Data Science Research at Recursion Pharmaceuticals (, an emerging biotech company combining experimental biology and bioinformatics with artificial intelligence to discover new therapeutic opportunities for rare diseases. At Recursion, data scientists work side-by-side with biologists to harness the potential of deep learning techniques, automation, and biological science to improve the success rate of drug discovery.  Berton leads the data science team in applying deep learning to high-resolution, multi-channel images of cellular disease models in order to help Recursion reach its goal of treating 100 diseases by 2025.

Twitter   LinkedIn

Pete Kane

Director, SVAI, Founder,

Peter has done a lot of work building healthcare and technology communities in Minnesota and the SF Bay Area. His academic background is Chinese Language and Literature.



Patrick Hop

Founder at DeepCrystal

 Patrick studied Math at UC Berkeley and is the Founder of DeepCrystal, a startup doing Deep Learning for Drug Discovery. 

Twitter   LinkedIn


Hane Ryu

Pharmacogenomics, UCSF

I am a PhD candidate in the Pharmacogenomics program at UCSF. My research interests have been mostly focused on identifying and characterizing regions of non-coding DNA that regulate drug response and human development. I've designed multiple projects that have incorporated various types of next-generation sequencing (NGS) and have generated & analyzed my own RNA-seq, ChIP-seq, and DNA-sequencing data. I am familiar with bioinformatics tools such as tophat, bowtie, bedtools, DESeq2, and generally understand how to approach gene/genomic variant data. Feel free to ask me for help if you have a genomics or biology question! 


Keren Gu

Machine Learning at Sift Science, MIT


I am a software engineer on the machine learning team at Sift Science, a real time machine learning startup in San Francisco that helps online merchants detect fraud. Previously, I received my bachelor's in math and computer science in 2014 and master's in computer science in 2015 from MIT. I was a member of the Interactive Robotics Group led by professor Julie Shah at CSAIL. My thesis focuses on building mental models for autonomous agents by drawing intuition from effective human behaviors. While an undergraduate at MIT, I worked on a number of research projects at CSAIL and the Media Lab.

Twitter   LinkedIn

Kevin Haas

Director Bioinformatics at Counsyl,  UC Berkeley

Director of Bioinformatics at Counsyl leading talented team of PhD scientists and innovative software engineers responsible for the clinical analytic pipeline that delivers rigorous next generation genetic screening to hundreds of thousands of patients annually for diseases that can impact men, women and their children.


Jun Axup.png

Jun Axup

Science Director at Indiebio

Jun is an entrepreneurial scientist with a PhD in chemical biology from The Scripps Research Institute. She has worked at several startups in the fields of immuno-oncology, protein engineering, lab automation robotics, CRISPR, and precision medicine. Jun is passionate about using the intersection of biology, technology, and design to increasing human healthspan.

Twitter   LinkedIn

Gaia Andreoletti

Postdoctoral Fellow, UC Berkeley

*Available to mentor online*

Dr Andreoletti conducted her undergraduate studies in Biology (University of Pavia, Italy), MSc in Bioinformatics and System Biology at Birkbeck College, University of London, and obtained her PhD in Genomics at the University of Southampton, UK. Her PhD project focused on the analysis of whole-exome sequencing data in paediatric patients diagnosed with inflammatory bowel disease (IBD), a chronic autoimmune gastrointestinal disorder. Dr Andreoletti is currently a post-doctoral fellow within the group of Prof Steven E Brenner at University California, Berkeley (USA) as the scientific leader of the Critical Assessment of Genome Interpretation (CAGI). 

Aashish Adhikari

Postdoc, UC Berkeley

*Available to mentor online*

Aashish is a postdoctoral researcher at UC Berkeley, where he is developing genome interpretation methods for rare genetic disorders in newborns. Aashish will be available online during the event to help participants navigate genomics problems.

Dan Gailey

CEO, RadBots


Entrepreneur, Hacker, Futurist, and Bot Expert -- Programming all my life, raised by the internet, background in Electrical Engineering (autonomous robotics) and Computational Chemistry. 

Twitter   LinkedIn

Lukasz Kidzinski


Łukasz Kidziński is a researcher in the Mobilize Center at Stanford, working on the intersection of computer science, statistics and biomechanics. Before, he finished his PhD training at Université Libre de Bruxelles in mathematical statistics, working on time series analysis and functional data. He obtained two master degrees, in mathematics and in computer science, from the University of Warsaw. His main interests include machine learning, data mining, big data, time series analysis and applied statistics. He is also interested in dynamics of on-line gaming.

Twitter   LinkedIn

Saurabh Bajaj

Software Engineer, Lyft

Software Engineer at Lyft building machine learning and data infrastructure. Responsible for the architecture, development and scaling of core systems that power Lyft.


Amirhossein Kiani

Director of Product Management at Bina Technologies (Roche), University of Minnesota-Twin Cities

Amir was the first-full time employee of which was acquired by Roche. He has worked on algorithm development (see "SeqAlto aligner"), backend development as well as frontend development for building a scalable genomic data processing and management solution (Bina GMS).  Currently, he leads the Open Innovation Lab group at Roche Sequencing which experiments with state of the art Deep Learning, Augmented Reality and Connectivity technologies to prototype Roche's future products.

Twitter   LinkedIn

Robert Lee, JD, MBA

Stanford, UC Berkeley, Yale

Robert is a CodeX research Fellow at Stanford, Dataist, Aspiring AI Engineer and Published Biomed Researcher. He has worked as an entrepreneur, technology lawyer and Advises companies in machine learning, medical diagnostics, enterprise software, etc.  Robert has his JD/MBA (law and business) from UC Berkeley (where he is also minored in EECS) and his BS/BA (biochemistry and philosophy) from Yale University.



Clinton (Cosmo) Mielke, PhD

UCSF, Mayo Clinic, Infinome

Clinton is the Founder of Infinome, A nonprofit endeavor to save the world with citizen-science genetics experiments. At UCSF and Mayo Clinic, Clinton created projects like: ”Brainman" - a comprehensive web tool for the visualization and analysis of patient cognitive and neuroimaging data, and, a freely-available bioinformatics database. He has Analyzed, developed, and automated computational pipelines to process thousands of raw brain scans from a large population, performed advanced queries and created novel visualizations of imaging, genetic, and demographic data, and done work with supercomputing and gene expression.


Pankaj Kumar 

Cofounder at DataCabinet

Pankaj held engineering positions at AppDynamics and Microsoft. Pankaj graduated from the Indian Institute of Technology, Kharagpur and then went to Purdue University for Masters of Science. He recently completed the Graduate Certificate in Statistical Data Mining and Applications from Stanford university. He is a Deep Learning/Neural Network enthusiast.


Salvatore La Rosa, PhD

Vice President of Research and Development at the Children’s Tumor Foundation

Salvatore La Rosa, PhD, is Vice President of Research and Development at the Children’s Tumor Foundation (CTF) and he is responsible for the implementation of the Foundation’s business strategy into research projects. He manages the foundation’s research activities, providing scientific and knowledgeable review of discovery, preclinical and early development programs in the field of Neurofibromatosis (NF). Dr. La Rosa is responsible for the development and management of novel partnerships and initiatives with academic research groups and biotech/pharma companies which could address unmet needs in the field. Besides the activities of compound scouting and grants management, he is involved in ad-hoc collaborative research programs, CRO selection and management, as well as preclinical testing consortia. Dr. La Rosa’s team acts as project manager for the Synodos program, totaling $9M in three years investment, totaling 5 highly integrated projects, more than 40 Principal Investigators, and 20 different institutions. He has co-authored more than 20 peer-review research articles and served as Group Leader and Project Leader for Siena Biotech (Italy), Nikem Research (Italy) and Evotec (UK). He holds a Ph.D. in Medicinal Chemistry from the University of Strathclyde in Glasgow (Scotland, UK) and MSc in Organic Chemistry from the University of Messina (Italy).




Weekend Hackathon

(Not an overnight event)



Friday Night - June 23rd

18.00: Doors Open, Pizza Served!

18.30: Welcome!

  • Silicon Valley Artificial Intelligence
  • Accel.AI
  • Google
  • Sponsors

19.00: Onno Faber, Entrepreneur

  • NF2 Patient Story 

19:30: Marco Giovannini, MD, PhD

  • Introduction to NF2

20.00: Anita Brede, CEO @

  • Identifying Quality Research Papers

20.30: Berton Earnshaw, Director of Data Science Research @ Recursion Pharmaceuticals

  • AI for Drug Discovery

20.45: Objectives & Team Formation

23.00: Doors Close

Saturday - June 24th

9.00: Doors Open, Breakfast

10.00: Hacking Begins

11.00: DeepChem workshop with Bharath Ramsundar

12.00: Lunch - Bun Mee

13.30: Mo Rahmann, Bioinformatics & Pharmacogenomics CSO @ GeneDrop

  • Genomics Workshop

15.00: Focused Work

17.30: Dinner - Taco Bar

23.00: Doors Close

Sunday - June 25th

9.00: Doors Open, Breakfast

10.00: Hacking Begins

12.00: Lunch - Mediterranean Bistro

13.00: Focused Work

15.30: Final Submissions

16.00: Presentations & Judging

18.00: Sliders & Happy Hour, Celebrate!




It's going to be pretty technical. Our target audience is AI Researchers and Biologists, Genomics Researchers. 




Launchpad Space 

4th floor, 301 Howard, SF



BART: 0.3 miles from Embarcadero Station. Map



Full Food and Drink accommodations provided by Google.

Thank you, in-kind sponsors!

Reach out to learn more about all sponsorship opportunities at



Why are you doing this?

We think it's a good idea to bring together the smartest people in AI / ML, Biology and Genomics to hack on difficult medical cases.

Is this an overnight Hackathon?

Nope. We believe in healthy sleep.

Do I need to provide my own computational power?

No. Google has you covered. We will be issuing Google Cloud credits at the event.

Who is the target Audience?

Computer scientists, AI researchers, Computational Biologists and eager learners around the world.

Can I participate remotely?

Absolutely! Join here.

Will there be opportunities to continue collaborating on this project after the hackathon?

Yes. Please get in touch with us if you'd like to continue working with Onno's dataset.





Standard Event Disclosures

We have a pretty thorough FAQ, please check it out here: FAQ


Our conference is dedicated to providing a harassment-free conference experience for everyone, regardless of gender, gender identity and expression, age, sexual orientation, disability, physical appearance, body size, race, ethnicity, religion (or lack thereof), or technology choices. We do not tolerate harassment of conference participants in any form. Sexual language and imagery is not appropriate for any conference venue, including talks, workshops, parties, Twitter and other online media. Conference participants violating these rules may be sanctioned or expelled from the conference without a refund at the discretion of the conference organizers. For full version, please see:


We take photos at our events. Some of these photos will be used on our website. We seek to respect your privacy and ask that if you do not want your photo to appear on SVAI to please email us.


By signing up for this event, you will automatically be added to future SVAI announcements.


We do not make announcements for non-SVAI events or conferences at our gatherings. Distribution of flyers, printed media or other non SVAI related materials is not allowed at our events. 


This gathering is limited to 150 people. You MUST be pre-registered to attend. Registration must include your First and Last name, and some of our venues require ID for entry. You do not need to print a paper ticket. We will be checking people in the building lobby. Questions or comments? Tweet to us @SVAIresearch.


About   Events   FAQ