Generative and Experimental Perspectives for Biomolecular Design

Workshop at the 13th International Conference on Learning Representations

April 27, 2025, Singapore

About

Biomolecular design, through artificial engineering of proteins, molecules, and nucleic acids, holds immense promise in addressing pressing medical, industrial, and environmental challenges. While generative machine learning has shown significant potential in this area, a palpable disconnect exists with experimental biology: many ML research efforts prioritize static benchmark performance, potentially sidelining impactful real-world applications.

The Generative and Experimental perspectives in bioMolecular design (GEM) workshop seeks to bridge this gap by bringing computationalists and experimentalists together. Together, we will explore the strengths and challenges of generative ML in biology, experimental integration of generative ML, and pinpoint biological problems ready for ML.

GEM is collaborating with Nature Biotechnology to allow exceptional submissions to be considered for fast-tracking in their journal. GEM features two tracks of submission: an in-silico generative machine learning track, and an experimental track for any papers that have wet lab results.

Our lineup features renowned scientists as panelists and emerging leaders as speakers, encapsulating a spectrum from high-throughput experimentation and computational biology to generative ML. With a diverse organizing team and backed by industry sponsors, we dedicate the workshop to pushing the boundaries of ML's role in biology.

GEM is an in-person workshop on April 27th in Singapore at ICLR’25.

Join our mailing list today to stay updated.

Logistics of the day

Date and Location:

Our workshop will be held on April 27th 2025 at Hall 4 #4 in the Singapore Expo.

Posters:

We have two poster sessions — one in the morning and another in the afternoon. Session assignments for each poster will be posted shortly. Please put your posters up in the breaks before your session and take them down after your session. The poster assignment will soon be advertised on our website for attendees. Poster dimensions are 24in x 36in in portrait format only.

Schedule:

The schedule can be found on the ICLR workshop page. Thanks to our sponsors, we will provide lunch catering with a set amount of lunchboxes. We also host an after party at Tag Restaurant And Bar starting at 6:30pm.

Openreview:

All accepted submissions have now been made public and viewable unless the authors specifically requested otherwise. Reviews and discussions are not public. https://openreview.net/group?id=ICLR.cc/2025/Workshop/GEM

Call For Papers

GEM has two tracks: a machine learning track, and a biology track.

These topics include but are not limited to the following:

Biology track

Biological problems and data ripe for generative ML and/or employment of ML for biomolecular design with wet lab experimental results.

  • Biological problems apt for ML applications

  • High-throughput data generation methods

  • Adaptive experimental design

  • Benchmarks, datasets, and oracles

ML track

Generative ML advancements for biomolecular design with in silico results.

  • Inverse design of all biomolecules

  • Modelling biomolecular data

  • Model interpretability

We are partnering with Nature Biotechnology from Springer Nature. Authors can opt to have their submissions considered for fast-tracking to Nat. Biotech. See below for details.

Call for Submissions:

GEM workshop welcomes submissions in two formats:

  • Short papers: Both ML and Biology tracks. Up to 5 pages (excluding references & appendix).

  • Extended abstracts: Biology track only. Up to 2 pages, similar to standard biological conferences.

Papers and extended abstract should present novel work that has not been previously accepted at an archival venue at the time of submission.

The submissions, including extended abstracts, need to be anonymized and will be subjected to one round of double blind peer-review.

Short paper submissions must be formatted using the ICLR 2025 main conference template, replacing the style file with the GEM version. We recommend extended abstract submissions to be formatted using either the extended abstract template, or the LaTeX template above. The maximum file size for submissions is 50MB. 

Fast-track opportunity:

GEM will nominate accepted papers to be considered for expedited peer review at Nature Biotechnology. In addition to the GEM reviewers, the Editors of Nat. Biotech., as well as 1-2 additional reviewers will be actively engaged in the expedited review of any accepted papers being considered for publication in Nat. Biotech.

Presentation and Publication:

Accepted papers will be invited to present a poster at the workshop, and the organizers will nominate spotlight talks based on reviewer comments. This workshop is non-archival and does not publish proceedings except for any papers accepted at Nat. Biotech. However, camera ready versions of accepted papers will appear in OpenReview unless the authors specifically request otherwise.

We encourage submissions of:

  • Novel research concurrently in submission.

  • Encouraging work-in-progress results seeking feedback.

  • Forward-looking position papers sparking community discussion.

Submissions will be made through OpenReview.

The workshop will provide travel grants for authors who are from underrepresented groups and/or who need financial assistance. We will release a form in March 2025.

Reviewer self-nomination: If you would like to sign up to be a reviewer for GEM-2025, please fill out this form! If you have reviewed for GEM in 2024, you do not need to sign up again.

Important Dates

Submission Deadline: 10th 13th February 2025, 11:59 PM (AoE, deadline extended)

Notification of Acceptance: 3rd 5th March 2025

Camera-Ready Deadline: 15th April 2025 11:59 PM (AoE)

Workshop Date & Location: 27th April, 2025. Singapore EXPO.

Seed Grants

This year, with the generous support of our sponsors, we are launching small ‘seed grants’ (USD $1,000 each) to catalyze new collaborations between experimental and computational researchers attending the workshop. The goal is to create meaningful, interdisciplinary partnerships between dry and wet lab, and to provide small initial support for promising projects that align with cutting-edge biological challenges and AI-driven solutions.

We will publicize a dedicated a "matchmaking" social event during the main conference, where participants with overlapping research interests can connect and brainstorm potential projects. Following this session, teams (2-4 people, at least 2 different institutions) will be invited to submit concise, half-page proposals and one slide presentations outlining their project idea, collaboration plan, and expected outcomes. The proposals will be pitched to our speakers, panelists, and sponsors during the second poster session. Seed grants will be awarded based on the novelty of the idea, alignment with the workshop's themes, feasibility, and potential for impact. Selected awards will be announced publicly before the closing remarks. Funds will be disbursed after the workshop to the institutions to support project initiation. To further incentivize progress, we plan to invite the awardees back for short talks at the potential 2026 edition of the workshop, where they can share insights, showcase results, and inspire the next wave of AI and biology collaborations. See FAQ for more information.

Invited Speakers & Panelists

Florian Hollfelder

Cambridge University

Kyunghyun Cho

NYU, Prescient Design

Kotaro Tsuboyama

University of Tokyo

Pranav Murugan

Genesis Therapeutics

Michael Bronstein

University of Oxford

Chaok Seok

Seoul National University

Workshop Organizers

Students

Mila, McGill University, Dreamfold

Mila, Université de Montréal, Dreamfold

MIT

Genentech

Caltech

MIT

University of Washington

Duke University

Faculty

Duke University

MIT

MIT

Caltech

Mila, Université de Montréal

Industry

Braidwell

Our Sponsors

Other AI for Science workshops at ICLR 2025 

If you feel that your work is not a good fit for the GEM workshop, consider submitting to one of the other AI for science workshops, such as:

FAQs

We will continue to update this list as we work further details. Please also check the ICLR homepage and ICLR FAQ for general question such as registration and traveling. For any questions not covered in the FAQ, feel free to email us at gembioworkshop@googlegroups.com.