Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • September 15, 2021
  • Article
  • Bioinformatics

Improving Deconvolution Methods in Biology Through Open Innovation Competitions: An Application to the Connectivity Map

By: Andrea Blasco, Ted Natoli, Michael G. Endres, Rinat A. Sergeev, Steven Randazzo, Jin Hyun Paik, N.J. Maximilian Macaluso, Rajiv Narayan, Xiaodong Lu, David Peck, Karim R. Lakhani and Aravind Subramanian
  • Format:Print
ShareBar

Abstract

A recurring problem in biomedical research is how to isolate signals of distinct populations (cell types, tissues, and genes) from composite measures obtained by a single analyte or sensor. Existing computational deconvolution approaches work well in many specific settings, but they might be suboptimal in more general applications. Here, we describe new methods that were obtained via an open innovation competition. The goal of the competition was to characterize the expression of 1,000 genes from 500 composite measurements, which constitutes the approach of a new assay, called L1000, used to scale-up the Connectivity Map (CMap)—a catalog of millions of perturbational gene expression profiles. The competition used a novel dataset of 2,200 profiles and attracted 294 competitors from 20 countries. The top-nine performing methods ranged from machine learning approaches (Convolutional Neural Networks and Random Forests) to more traditional ones (Gaussian Mixtures and k-means). These solutions were faster and more accurate than the benchmark and likely have applications beyond gene expression.

Keywords

Deconvolution; Methods; Open Innovation Competition; Genomics; Research; Innovation and Invention

Citation

Blasco, Andrea, Ted Natoli, Michael G. Endres, Rinat A. Sergeev, Steven Randazzo, Jin Hyun Paik, N.J. Maximilian Macaluso, Rajiv Narayan, Xiaodong Lu, David Peck, Karim R. Lakhani, and Aravind Subramanian. "Improving Deconvolution Methods in Biology Through Open Innovation Competitions: An Application to the Connectivity Map." Bioinformatics 37, no. 18 (September 15, 2021).
  • Find it at Harvard
  • Read Now

About The Author

Karim R. Lakhani

Technology and Operations Management
→More Publications

More from the Authors

    • June 2022
    • Management Science

    Conservatism Gets Funded? A Field Experiment on the Role of Negative Information in Novel Project Evaluation

    By: Jacqueline N. Lane, Misha Teplitskiy, Gary Gray, Hardeep Ranu, Michael Menietti, Eva C. Guinan and Karim R. Lakhani
    • May 2022
    • Faculty Research

    AWS and Amazon SageMaker (C): The Commercialization of Machine Learning Services

    By: Karim R. Lakhani, Shane Greenstein and Kerry Herman
    • May 2022
    • Faculty Research

    AWS and Amazon SageMaker (B): The Commercialization of Machine Learning Services

    By: Karim R. Lakhani, Shane Greenstein and Kerry Herman
More from the Authors
  • Conservatism Gets Funded? A Field Experiment on the Role of Negative Information in Novel Project Evaluation By: Jacqueline N. Lane, Misha Teplitskiy, Gary Gray, Hardeep Ranu, Michael Menietti, Eva C. Guinan and Karim R. Lakhani
  • AWS and Amazon SageMaker (C): The Commercialization of Machine Learning Services By: Karim R. Lakhani, Shane Greenstein and Kerry Herman
  • AWS and Amazon SageMaker (B): The Commercialization of Machine Learning Services By: Karim R. Lakhani, Shane Greenstein and Kerry Herman
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College