open access publication

Article, 2024

A data science roadmap for open science organizations engaged in early-stage drug discovery

Nature Communications, ISSN 2041-1723, Volume 15, 1, Page 5640, 10.1038/s41467-024-49777-x

Contributors

Edfeldt, Kristina 0000-0002-0550-1133 [1] Edwards, Aled Morgan 0000-0002-4782-6016 [2] Engkvist, Ola 0000-0003-4970-6461 [3] Günther, Judith [4] Hartley, Matthew [5] Hulcoop, David G 0000-0003-1323-1759 [6] [7] Leach, Andrew R 0000-0001-8178-0253 [5] Marsden, Brian D. [8] Menge, Amelie 0000-0002-0423-6593 [9] Misquitta, Leonie [10] Müller, Susanne [9] Owen, Dafydd R [11] Schütt, Kristof T 0000-0001-8342-0964 [12] Skelton, Nicholas J [13] Steffen, Andreas [12] Tropsha, Alexander 0000-0003-3802-8896 [14] Vernet, Erik 0000-0002-4175-1244 [15] Wang, Yanli [10] Wellnitz, James 0000-0002-9181-3431 [14] Willson, Timothy Mark 0000-0003-4181-8223 [14] Clevert, Djork-Arné 0000-0003-4191-2156 (Corresponding author) [12] Haibe-Kains, Benjamin 0000-0002-7684-0079 (Corresponding author) [2] [16] [17] Schiavone, Lovisa Holmberg (Corresponding author) [3] Schapira, Matthieu 0000-0002-1047-3309 (Corresponding author) [2]

Affiliations

  1. [1] Karolinska Institutet
    2. [NORA names: Sweden; Europe, EU; Nordic; OECD];
  2. [2] University of Toronto
    3. [NORA names: Canada; America, North; OECD];
  3. [3] AstraZeneca (Sweden)
    4. [NORA names: Sweden; Europe, EU; Nordic; OECD];
  4. [4] Bayer (Germany)
    5. [NORA names: Germany; Europe, EU; OECD];
  5. [5] European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, UK
    6. [NORA names: United Kingdom; Europe, Non-EU; OECD];

Abstract

The Structural Genomics Consortium is an international open science research organization with a focus on accelerating early-stage drug discovery, namely hit discovery and optimization. We, as many others, believe that artificial intelligence (AI) is poised to be a main accelerator in the field. The question is then how to best benefit from recent advances in AI and how to generate, format and disseminate data to enable future breakthroughs in AI-guided drug discovery. We present here the recommendations of a working group composed of experts from both the public and private sectors. Robust data management requires precise ontologies and standardized vocabulary while a centralized database architecture across laboratories facilitates data integration into high-value datasets. Lab automation and opening electronic lab notebooks to data mining push the boundaries of data sharing and data modeling. Important considerations for building robust machine-learning models include transparent and reproducible data processing, choosing the most relevant data representation, defining the right training and test sets, and estimating prediction uncertainty. Beyond data-sharing, cloud-based computing can be harnessed to build and disseminate machine-learning models. Important vectors of acceleration for hit and chemical probe discovery will be (1) the real-time integration of experimental data generation and modeling workflows within design-make-test-analyze (DMTA) cycles openly, and at scale and (2) the adoption of a mindset where data scientists and experimentalists work as a unified team, and where data science is incorporated into the experimental design.

Keywords

Genomics Consortium, Structural Genomics Consortium, Working Group, acceleration, adoption, architecture, artificial intelligence, automation, benefits, boundaries, breakthrough, centralized database architecture, chemical, chemical probe discovery, cloud-based computing, computer, considerations, consortium, data, data generation, data integration, data management, data mining, data model, data processing, data representation, data science, data scientists, data sharing, data-sharing, database architecture, dataset, design, discovery, disseminate data, drug discovery, early-stage drug discovery, electronics lab, estimate prediction uncertainty, experimental data generation, experimental design, experimentalists, experts, field, formation, generation, group, important vector, integration, intelligence, lab, lab automation, laboratory, machine-learning models, management, mindset, mining, model, modeling workflow, ontology, optimization, organization, prediction uncertainty, private sector, probe discovery, process, questions, real-time integration, recommendations, representation, research organizations, right training, roadmap, robust data management, science, science organizations, scientists, sector, sets, sharing, standard vocabularies, structure, team, test, test set, training, uncertainty, vector of acceleration, vocabulary, work, workflow

Funders

  • United States National Library of Medicine
  • Takeda (United States)
  • Bayer (United States)
  • Ontario Genomics
  • Merck (Germany)
  • Natural Sciences and Engineering Research Council
  • Boehringer Ingelheim (United States)
  • Deutsche Forschungsgemeinschaft
  • Bristol-Myers Squibb (United States)
  • Genome Canada
  • National Institute of General Medical Sciences
  • Pfizer (United States)
  • Canadian Institutes of Health Research
  • European Commission
  • Ontario Institute for Cancer Research

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+