Machine Learning for Genomics Explorations (MLGenX)


Our limited understanding of the biological mechanisms underlying diseases remains a critical bottleneck in drug discovery. As a result, we often lack insights into why patients develop specific conditions, leading to the failure of many drug candidates in clinical trials. Recent advancements in genomics platforms and the emergence of diverse omics datasets have sparked increasing interest in this field. The primary objective of this workshop is to bridge the gap between machine learning and genomics, emphasizing target identification and emerging drug modalities such as gene and cell therapies and RNA-based drugs. By fostering interdisciplinary collaboration, we aim to advance the integration of these disciplines and accelerate innovation in drug discovery.




Call for Papers

This year, the workshop will feature three distinct tracks designed to welcome a diverse array of researchers in the field of machine learning and biology: the Main Track including application and ML topics, the Special Track on LLMs and Agentic AI, and the Tiny Papers Track. Papers in the main and the special tracks must be prepared and submitted as a single file: 8 pages for the paper, with unlimited pages for references, the impact statement, and appendices.

Both contributions introducing new ML methods to existing problems and those that highlighting and explaining open problems are welcome. We also encourage submissions related to application of molecular biology, including but not limited to, single-cell RNA analysis, bulk RNA studies, proteomics, and microscopy imaging of cells and/or tissues.

We consider a broad range of subject areas including but not limited to the following topics.

Main Track:

  • Foundation models for genomics
  • Biological sequence design
  • Interpretability and Generalizability in genomics
  • Causal representation learning
  • Perturbation biology
  • Modeling long-range dependencies in sequences, single-cell and spatial omics
  • Integrating multimodal perturbation readouts
  • Active learning in genomics
  • Generative models in Biology
  • Multimodal representation learning
  • Uncertainty quantification
  • Optimal transport
  • Experimental design for Biology
  • Graph neural network and knowledge graph
  • New datasets and benchmarks for genomics explorations

Special Track on LLMs and Agentic AI:

  • Pre-training multi-omics models
  • Synthetic data generation and data quality for pre-training, fine-tuning and instruction tuning
  • Fine-tuning (SFT, RLHF, RL with lab feedback, ...) on novel tasks
  • In-context learning with large-context models
  • Reasoning through prompt engineering or architectural design
  • Interpretability and uncertainty quantification
  • Knowledge retrieval (RAG, knowledge graph, ...)
  • Efficient interactive system designs (agents, humans, and biological tools)
  • Training/fine-tuning LLM-powered design and planning engine

Tiny Papers Track:

This year, ICLR is discontinuing the separate “Tiny Papers” track, and is instead requiring each workshop to accept short (3-4 pages in ICLR format) paper submissions, with an eye towards inclusion; see ​​https://iclr.cc/Conferences/2025/CallForTinyPapers for more details. Authors of these papers will be earmarked for potential funding from ICLR, but need to submit a separate application for Financial Assistance that evaluates their eligibility. This application for Financial Assistance to attend ICLR 2025 will become available on https://iclr.cc/Conferences/2025/ at the beginning of February and close on March 2nd.

Submission Instructions

Similar to the main ICLR conference, submissions will be double blind. We use OpenReview to host papers. There will be a strict upper limit of 8 pages for the main text of the submission in the main and special tracks, and 4 pages for the main text of the submission in the tiny paper track, with unlimited additional pages for citations and appendices. To prepare your submission, please use the ICLR template style.

Submissions that are identical to versions that have been previously published, or accepted to the main ICLR conference are not allowed. However, papers that cite previous related work by the authors and papers that have appeared on non-peer reviewed websites (like arXiv) do not violate the policy. Submission of the paper to archival repositories such as arXiv is allowed during the review period.

Note: Authors are permitted to submit works that are currently under review by other venues. Additionally, accepted papers are not considered archival and can be subsequently published in other conferences or journals.

We plan to offer Best Paper Award(s), and exceptional submissions will be chosen for oral presentations. Please note that while our workshop is not archival, accepted papers will be featured on the workshop website.

Note: Official reviews are anonymous, and unlike the main conference, the papers and reviews are not made public until acceptance!

Important Dates

All deadlines are 11:59 pm UTC -12h ("Anywhere on Earth"). All authors must have an OpenReview profile when submitting.

  • Submission Deadline (all tracks): February 12, 2025
  • Acceptance Notification: March 5, 2025
  • Camera-Ready Deadline: April 24, 2025


Tentative Speakers & Panelists

Marinka Zitnik

Marinka Zitnik

Harvard University
Jure Leskovec

Jure Leskovec

Stanford University
Shekoofeh Azizi

Shekoofeh Azizi

Google DeepMind
Mihaela van der Schaar

Mihaela van der Schaar

University of Cambridge
Yun S. Song

Yun S. Song

UC Berkeley
Djork-Arne Clevert

Djork-Arne Clevert

Pfizer
Max Welling

Max Welling

CuspAI, UvA
Limsoon Wong

Limsoon Wong

National University of Singapore
Jakob Nikolas Kather

Jakob Nikolas Kather

NCT, TDU

Organizers

Ehsan Hajiramezanali
Ehsan Hajiramezanali
Aviv Regev
Aviv Regev
Fabian Theis
Fabian Theis
Arman Hasanzadeh
Arman Hasanzadeh
Mengdi Wang
Mengdi Wang
Tommaso Biancalani
Tommaso Biancalani
Sara Mostafavi
Sara Mostafavi
Aïcha Bentaieb
Aïcha Bentaieb
Gabriele Scalia
Gabriele Scalia