Genetic Engineering Attribution Challenge Hosted By altLabs

competition
complete
$60,000

Woohoo! This competition has come to a close!

Many thanks to the participants for all of their hard work and commitment to using data for good!

Working with lab samples

Overview

Your goal is to create an algorithm that identifies the most likely lab-of-origin for genetically engineered DNA.

Applications for genetic engineering are rapidly diversifying. Researchers across the world are using powerful new techniques in synthetic biology to solve some of the world’s most pressing challenges in medicine, agriculture, manufacturing and more. At the same time, increasingly powerful genetically engineered systems could yield unintended consequences for people, food crops, livestock, and industry. These incredible advances in capability demand tools that support accountable innovation.

Genetic engineering attribution is the process of identifying the source of a genetically engineered piece of DNA. This ability ensures that scientists who have spent countless hours developing breakthrough technology get their due credit, intellectual property is protected, and responsible innovation is promoted. By connecting a genetically engineered system with its designers, society can examine the policies, processes, and decisions that led to its creation. As has been observed in other disciplines, reducing anonymity encourages more prudent behavior within scientific and entrepreneurial communities—without stifling innovation.

Development of attribution capabilities is critical for the maturation of genetic engineering as a field, protecting the significant benefits it promises society while promoting accountability, responsibility, and dialog. In this competition, we challenge you to advance the state-of-the-art in this exciting new domain!


This competition will include two tracks:

  • The Prediction Track is an open machine learning competition, where participants will compete to attribute each DNA sample to its lab-of-origin with the highest possible accuracy. The top 4 finalists will be determined by the private leaderboard.
  • The Innovation Track will reward models that excel in domains other than raw accuracy, as assessed by a multidisciplinary panel of expert judges. Competitors that beat our BLAST benchmark in the Prediction Track will be invited to compete in the Innovation Track.

For more on each, see the Problem Description and Innovation Track.

Note on solution IP: As described in the Competition Rules, prize-winning algorithms will be assigned to the competition sponsor. Public sharing of code or IP is prohibited in order to be eligible for a prize. After the competition, altLabs will seek input from various stakeholders – including prizewinning teams – on how best to use these results to promote responsible innovation. altLabs is a non-profit organization, and will never sell or otherwise monetize prize-winning submissions. The IP for submissions that do not win prizes will remain with their respective teams.

Note on external data: External data for any use is strictly prohibited. In this challenge you may only use the data provided through the contest website. Code from prize-eligible solutions will be collected and run against an out-of-sample verification set to ensure that models can perform comparably on unseen data.


Oct. 19, 2020, 11:59 p.m. UTC

Submissions close.

Place Prize Amount
1st $15,000
2nd $7,500
3rd $5,000
4th $2,500

Prediction Track

Predictions evaluated using top-10 classification accuracy. Top 4 finalists determined based on the private leaderboard and verified using out-of-sample verification set.

Prize Amount
1st $15,000
2nd $7,500
3rd $5,000
4th $2,500

Innovation Track

Evaluated on reports describing the real-world merits of modeling approaches. Competitors that beat a benchmark score in the Prediction Competition will have the opportunity to submit reports. Final winners will be selected by a judging panel.

altLabs and partner employees are not eligible for prizes.


Sponsored by altLabs:

In partnership with:

The Johns Hopkins Center for Health Security
The Johns Hopkins University Applied Physics Laboratory
iGEM Safety and Security Program


Image courtesy of altLabs.