Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 38 min ago
PreprintCC BYChemRxiv

Operational insights from the front lines of OpenADMET: lessons from our blind challenges

  • Hugo MacDermott-Opeskin1
  • Maria Castellanos1
  • Jonathan A. Swain1
  • Jenke Scheen1
  • Sean Colby1
  • Georgia Channing2
  • Scott Simpkins3
  • Robert Warneford-Thompson3
  • Galen J. Correy4,5
  • L. Naomi Handly3
  • Sri Kosuri3
  • John Chodera6,7
2 more authors
  • James S. Fraser4,5
  • W. Patrick Walters1
7 affiliations
  1. 1Open Molecular Software Foundation
  2. 2Hugging Face
  3. 3Octant, Inc.
  4. 4Department of Bioengineering and Therapeutic Sciences
  5. 5University of California San Francisco
  6. 6Computational and Systems Biology Program
  7. 7Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center
Open at sourcePDFDOICite

Abstract

The gap between reported machine learning (ML) model performance in drug discovery and the experience of using these models in live discovery projects remains a major hurdle for the field, because the retrospective nature of most benchmarks makes it difficult to objectively assess progress. To address this gap, OpenADMET has hosted a series of blind challenges to benchmark and advance predictive modeling in absorption, distribution, metabolism, excretion, and toxicity (ADMET). In this Perspective, we distill the operational, strategic, and community-level lessons from our first four blind challenges, providing a practical blueprint for designing and running collaborative machine learning competitions in the life sciences. In addition, we open-source our blind challenge infrastructure and data-validation tools to lower the barrier to entry for hosting rigorous, community-driven competitions and to foster a sustainable framework for collective learning in computer-aided drug discovery.

Related

  1. Assessing the state of the art in ADMET prediction: Lessons from the OpenADMET-ExpansionRx community blind challenge
    Maria A. Castellanos, Hugo MacDermott-Opeskin, Jon Ainsley +103
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv
  2. Inside Front Cover: Proximity‐Induced Transfer of a Mass Tag Enables Direct Profiling of Active Matrix Metalloproteases (Angew. Chem. Int. Ed. 24/2026)
    Lomane Berthy, Ugo Pasco, Mylene Sejalon-Cipolla +18
    Angewandte Chemie International EditionPeer-reviewedLicence not statedFull textPhysical chemistryHAL
  3. Subsonic phase front propagation in martensitic transitions of 1,2,4,5-tetrabromobenzene single crystals
    Ken Takazawa, Jun-ichi Inoue
    Communications ChemistryPeer-reviewedCC BY-NC-ND 4.0Full textMaterials & polymersPMC
  4. Circumventing Inner Filter Effects in Ultrafast Near-Infrared II (NIR-II) Up-Conversion Spectroscopy Using Front-Face Optical Configuration.
    Tse-Hua Hsu, Hao-Chun Huang, Yen-Chang Chen +4
    Analytical chemistryPeer-reviewedCC BYFull textPhysical chemistryEurope PMC
  5. Organic vehicle engineering for high-aspect-ratio front-side fine-line silver paste in TOPCon solar cells
    Jing Liu, Chaoqun Niu
    PLOS OnePeer-reviewedCC BY 4.0Full textMaterials & polymersPLOS

Cite

BibTeXRIS
BibTeX
@misc{macdermottopeskin2026operational,
  title = {{Operational insights from the front lines of OpenADMET: lessons from our blind challenges}},
  author = {Hugo MacDermott-Opeskin and Maria Castellanos and Jonathan A. Swain and Jenke Scheen and Sean Colby and Georgia Channing and Scott Simpkins and Robert Warneford-Thompson and Galen J. Correy and L. Naomi Handly and Sri Kosuri and John Chodera and James S. Fraser and W. Patrick Walters},
  howpublished = {ChemRxiv},
  year = {2026},
  month = sep,
  doi = {10.26434/chemrxiv.15009105/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009105/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Operational insights from the front lines of OpenADMET: lessons from our blind challenges
AU  - Hugo MacDermott-Opeskin
AU  - Maria Castellanos
AU  - Jonathan A. Swain
AU  - Jenke Scheen
AU  - Sean Colby
AU  - Georgia Channing
AU  - Scott Simpkins
AU  - Robert Warneford-Thompson
AU  - Galen J. Correy
AU  - L. Naomi Handly
AU  - Sri Kosuri
AU  - John Chodera
AU  - James S. Fraser
AU  - W. Patrick Walters
PY  - 2026
DA  - 2026/09/20
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15009105/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15009105/v1
AB  - The gap between reported machine learning (ML) model performance in drug discovery and the experience of using these models in live discovery projects remains a major hurdle for the field, because the retrospective nature of most benchmarks makes it difficult to objectively assess progress. To address this gap, OpenADMET has hosted a series of blind challenges to benchmark and advance predictive modeling in absorption, distribution, metabolism, excretion, and toxicity (ADMET). In this Perspective, we distill the operational, strategic, and community-level lessons from our first four blind challenges, providing a practical blueprint for designing and running collaborative machine learning competitions in the life sciences. In addition, we open-source our blind challenge infrastructure and data-validation tools to lower the barrier to entry for hosting rigorous, community-driven competitions and to foster a sustainable framework for collective learning in computer-aided drug discovery.
ER  -