Data, Machines, and AI (DMAI) Reading Group

Data, Machines, and AI (DMAI) is a reading group to discuss AI theory and methods, with a strong bent towards understanding what AI methods are most suitable for problems in biology and medicine, and how to advance state-of-the-art AI algorithms.

Schedule

Reading group meets every two weeks. We have a speaker for every meeting. The speaker selects a paper and sends it to the group coordinator one week before the presentation. The coordinator shares the information with the group. Everyone is expected to read the paper before the group meeting.

Each meeting lasts for 1 hour and has three parts:

  • Paper presentation (30 minutes): The speaker presents the paper, including background, motivation, key challenges, methods and modeling assumptions, datasets, and experiments. The focus is on algorithms and carefully considering what makes them suitable for biomedical applications and why.
  • Insights (5-10 minutes): The speaker shares their insights with the group. This includes insights related to the merits of the research, possible future directions, how this research can be used in our ongoing projects, any drawbacks and ideas on how to fix them, any related-papers (other approaches to study the same problem), etc.
  • Discussion (20-25 minutes): Q&A and broader debate, brainstorming what biological or medical questions these methods can help us answer, dataset availability, source code implementation, any other topic attendees want to discuss.

These are interactive events; questions and comments are welcome throughout the meeting!

Speakers

Every meeting has a dedicated speaker responsible for selecting a paper and presenting it. We use a rotation system for speakers. Members of the reading group can expect to speak 1-3 times a year.

Paper selection

Papers presented at the reading group are published at various venues over the last two years. Following is a sampling of relevant journals and conferences.

  • Journals:
    • Nature, Science, and Cell family, NEJM, PNAS, Lancet journals, JAMA journals
  • Machine learning and data science:
    • Conferences: ICML, NeurIPS, ICLR, ACL, EMNLP, KDD, ICDM, AAAI, IJCAI, UAI, FAT*, AISTATS, WSDM, SIGIR
    • Bioinformatics conferences: ISMB, RECOMB, PSB
    • Journals: TPAMI, JMLR, TKDD, TKDE, Bioinformatics, JAMIA, PLoS Computational Biology, BMC journals, ACS family

We are generally interested in exciting, intriguing, and thought-provoking papers, no matter their publication venue, including preprints (e.g., arXiv, bioRxiv, and medRxiv).

Time

Every other Thursday at 4:30-5:30pm EST.

Location

Hybrid meetings on Zoom and in-person in Countway Bldg.

Coordinator

Reach out to the reading group coordinator (Zhenglun Kong) with questions and suggestions.

Latest News

Nov 2024:   Ayush Noori Selected as a Rhodes Scholar

Congratulations to Ayush Noori on being named a Rhodes Scholar! Such an incredible achievement!

Nov 2024:   PocketGen in Nature Machine Intelligence

Oct 2024:   Activity Cliffs in Molecular Property Prediction

Oct 2024:   Knowledge Graph Agent for Medical Reasoning

Sep 2024:   Three Papers Accepted to NeurIPS

Exciting projects include a unified multi-task time series model, a flow-matching approach for generating protein pockets using geometric priors, and a tokenization method that produces invariant molecular representations for integration into large language models.

Sep 2024:   TxGNN Published in Nature Medicine

Aug 2024:   Graph AI in Medicine

Excited to share a new perspective on Graph Artificial Intelligence in Medicine in Annual Reviews.

Aug 2024:   How Proteins Behave in Context

Harvard Medicine News on our new AI tool that captures how proteins behave in context. Kempner Institute on how context matters for foundation models in biology.

Jul 2024:   PINNACLE in Nature Methods

PINNACLE contextual AI model is published in Nature Methods. Paper. Research Briefing. Project website.

Jul 2024:   Digital Twins as Global Health and Disease Models of Individuals

Paper on digitial twins outlining strategies to leverage molecular and computational techniques to construct dynamic digital twins on the scale of populations to individuals.

Jul 2024:   Three Papers: TrialBench, 3D Structure Design, LLM Editing

Jun 2024:   TDC-2: Multimodal Foundation for Therapeutics

The Commons 2.0 (TDC-2) is an overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new tasks and benchmarks. Our paper.

May 2024:   Broad MIA: Protein Language Models

Apr 2024:   Biomedical AI Agents

Mar 2024:   Efficient ML Seminar Series

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

Mar 2024:   UniTS - Unified Time Series Model

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

Mar 2024:   Weintraub Graduate Student Award

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

Zitnik Lab  ·  Artificial Intelligence in Medicine and Science  ·  Harvard  ·  Department of Biomedical Informatics