Machine Learning

Data 4 COVID19

This document serves as a repository for data collaboratives seeking to address the spread of COVID-19 and its secondary effects. It invites individuals to share projects that show a commitment to privacy protection, data responsibility, and overall user well-being. A project’s inclusion in this living repository does not indicate endorsement by The GovLab or confirmation of its success in meeting these goals. It is updated regularly with new projects and includes initiatives from around the world organized by area. It is curated by GovLab.

Resources

Looking for

Any skill set can be useful, from project management to design to data science.

How to get involved

  • Find a project that interests you and check out their webpage or contribute to the repository.

Project Open Air (Just One Giant Lab)

Project Open Air/Helpful Engineers, hosted within the broader open science group Just One Giant Lab has created a 5,000 strong volunteer organization, with engineers, scientists and doctors around the world who work to organize themselves into teams to design innovative ways to fight the virus. They are quickly trying to design and arrange the production of pragmatic devices to move life-saving air, extend existing tools, or organize volunteers on the ground to bolster medical workers. They have both hardware and software based projects including designing open source, scalable easy to DIY ventilators and O2 concentrators, sentiment analysis for persuasive public health media, diagnostic apps, and more!

Resources

Looking for

MANY different skills sets: app developers, ML researchers, data scientists, data visualization folks, makers, fabricators, designers, organizers, and especially folks who can volunteer time for project management.

How to get involved

  • See this doc and fill out the intake form
  • Join the Slack and introduce yourself in #introductions
  • Email opensourcehumankind@gmail.com
  • If you are a medical professional, additionally fill out this form

Johns Hopkins Mapping nCOV Project

This team has developed an interactive web-based dashboard hosted by the Center for Systems Science and Engineering (CSSE) at Johns Hopkins University, to visualize and track reported cases in real-time. The dashboard illustrates the location and number of confirmed COVID-19 cases, deaths and recoveries for all affected countries. It was developed to provide researchers, public health authorities and the general public with a user-friendly tool to track the outbreak as it unfolds. Additionally, the data (which is verified and updated daily) is available on GitHub. They are interested in conducting additional modeling of the emerging outbreak.

Resources

Looking for

It doesn’t explicitly say on the website, but presumably ML researchers, model-builders, data visualization folks, data scientists.

How to get involved

  • Reach out to the group at COVID19map@jhu.edu or jhusystems@gmail.com
  • Grab the data and build your own project

Folding at Home

Folding at Home uses computer simulations to understand the proteins that viruses use to reproduce and suppress immune systems. This is done by taking the experimental structures as starting points, we can simulate how all the atoms in the protein move. Doing so can help health researchers find and understand new therapeutic opportunities. The calculations involved in these simulations are enormous, and so volunteers can use their existing compute resources to run folding simulations in the background and contribute to the larger F@H database.

Resources

Looking for

Anyone with a computer! Particularly in the areas of

  • Strategic Product Design
  • Gamification
  • Website Enhancement
  • Client Programming (C++, Web dev, JS, vue.js, JSON API)
  • Project Viewer
  • Stats
  • Protein Viewer
  • Github Issue Triage

How to get involved

Follow the instructions on the COVID-19 page Sign up for the dev team at:

Help with COVID-19

A website to connect volunteers with open source projects. Users can sort projects by skill type or project focus. Currently lists over 500 projects ranging from telemedicine to community support apps.

Resources

Looking for

Any skill set can be useful, from project management to design to data science

How to get involved

  • Hop on the webstie and find a project that interests you (or add your own)!

COVID-19 Community

COVID-19 Community is a community effort to build a Neo4j Knowledge Graph (KG) that links heterogenous data about COVID-19 to help fight this outbreak! It serves as a sandbox and incubator project and the best ideas will be incorporated into the Covid-19-Net KG.

Resources

Looking for

Data scientists and machine learning developers, particularly datavisualization pros!

How to get involved

  • Run the current project instance
  • Suggest additional data sets or propose queries
  • Add example Jupyter notebooks or data visualizations

CORD19 Dataset

This open dataset is supported by the White House Office of Science and Technology Policy, The Chan Zuckerberg Initiative, Microsoft Research, The Allen Institute for AI, The NIH Library of Medicine, Georgetown’s Center for Security and Emerging Technology, Cold Spring Harbor Lab, and Kaggle AI. CORD-19 is a resource of over 29,000 scholarly articles, including over 13,000 with full text, about COVID-19, SARS-CoV-2, and related coronaviruses. This freely available dataset is provided to the global research community to apply recent advances in natural language processing and other AI techniques to generate new insights in support of the ongoing fight against this infectious disease. The dataset represents the most extensive machine-readable coronavirus literature collection available for data and text mining to date and is updated as new research is published in peer-reviewed publications and archival services.

Resources

Looking for

Researchers familiar with NLP-based ML and AI methods.

How to get involved

Form a team (or go solo) and submit to the Kaggle Challenge (see Initial Key Questions)

MILA COVID-19 Projects

The primary objective of the Mila AI taskforce is to bring together an interdisciplinary team of researchers in machine learning, bioinformatics, immunology, virology and vaccine design to create open source, data-driven tools that could be deployed in current and future outbreaks. The group has their own set of projects including Peer to Peer AI-based tracing of COVID and Machine Learning for therapuetics discovery. The website also links to other (primarily Canadian) open science projects.

Resources

Looking for

AI researchers, with or without existing COVID related projects.

How to get involved

  • Join the group slack
  • Fill out the request for collaboration form
  • Send an email to covid19research@mila.quebec

COVID-19 Vulnerability Index (CV19 Index)

The CV19 Index is an open source, AI-based predictive model that identifies people who are likely to have a heightened vulnerability to severe complications from COVID-19 (commonly referred to as “The Coronavirus”). The CV19 Index is intended to help hospitals, federal / state / local public health agencies and other healthcare organizations in their work to identify, plan for, respond to, and reduce the impact of COVID-19 in their communities. The CV19 Index is currently deployed in Chicago – Medical Home Network – The largest Medicaid ACO in the country and is undergoing testing in New York and Florida.

Resources

Looking for

You can run the predictive model yourself by following the instructions on the homepage. Unfortunately, the team is not allowed to publicly share the training data set but they are look for volunteers to help out in many areas such as data prep and transformation, developing documentation, and adding more platform support.

How to get involved

Email the team at covid19-info@closedloop.ai

Crowdfight COVID-19

This is an initiative from the scientific community to put all available resources at the service of the fight against COVID-19. It has separate portals for those already doing COVID-19 related research to request resources and for those not yet engaged to volunteer. As of March 21, 2020 this appears to be a (primarily) European initiative.

Resources

Looking for

Almost any skill set, from the ability to transcribe data from text into databases to highly expert. They will try to match people to appropriate projects.

How to get involved

Register on their volunteers page.