Call for Papers

We invite submissions describing innovative research at the intersection between machine learning and drug discovery. We are specifically interested, but are not limited to, the following areas:

• Genetic & molecular representation learning

• Molecule properties optimization / de novo design

• Protein design

• Virus modeling and forecasting

• Target identification

• Biological experiment design

• Causal inference in drug discovery

• Geometric deep learning

• New datasets & benchmarks for drug discovery

We invite submissions relevant to the workshop and encourage contributions to any of the topics listed above. We will follow the same style formatting instructions as the main ICLR conference. There is no strict limit on the length of your submission, but we expect submissions to fit into 4-8 pages (reviewers are not expected to read beyond the first 8 pages); the references and appendix may have unlimited length. Please upload a single PDF that includes the main paper and any supplementary material. 

If the research has previously appeared in a journal, workshop, or conference, the workshop submission should extend that previous work. Authors should state any overlapping published work at the time of submission. Dual submissions to other conferences are permitted. If accepted, you will have the opportunity to revise your paper before submitting the final version. The workshop will not have any official proceedings, so it is non-archival.

The submission need not be anonymized. You must format your submission using the ICLR 2023 main conference template, replacing the style file with the MLDD version. The maximum file size for submissions is 50MB. Submissions that violate the MLDD style may be rejected without further review.

Submissions to the workshop will be handled via OpenReview.

If you have any questions, please contact us by email (mldd.workshop@gmail.com).