Artificial Intelligence & Machine Learning Methods


Our GitHub Spaces

KGARevion

Knowledge Graph Based Agent for Complex, Knowledge-Intensive QA in Medicine

View KGARevion KGARevion Website

PocketFlow

Generalized Protein Pocket Generation with Prior-Informed Flow Matching

View PocketFlow PocketFlow Website

Therapeutics Data Commons 2.0

Multimodal Foundation for Therapeutic Science

View TDC-2 TDC-2 Website

SPECTRA

Evaluating Generalizability of Artificial Intelligence Models for Molecular Datasets

View SPECTRA SPECTRA Website

PocketGen

Efficient Generation of Protein Pockets with PocketGen

View PocketGen PocketGen Website

UniTS

A Unified Multi-Task Time Series Model

View UniTS UniTS Website

PDGrapher

Combinatorial Prediction of Therapeutic Perturbations Using Causally-Inspired Neural Networks

View PDGrapher PDGrapher Website

FAIR

Full-Atom Protein Pocket Design via Iterative Refinement

View FAIR FAIR paper

TxGNN

A Foundation Model for Clinician Centered Drug Repurposing

View TxGNN TxGNN Website TxGNN Explorer

PINNACLE

Contextual AI Models for Single-Cell Protein Biology

View PINNACLE PINNACLE Website

TimeX

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

View TimeX TimeX Website

Raincoat

Domain Adaptation for Time Series Under Feature and Label Shifts

View Raincoat Raincoat Website

SHEPHERD

Deep Learning for Diagnosing Patients with Rare Genetic Diseases

View SHEPHERD SHEPHERD Website

GNNDelete

General Strategy for Unlearning in Graph Neural Networks

View GNNDelete GNNDelete Website

TF-C

Self-Supervised Contrastive Pre-Training For Time Series

View TF-C TF-C Website

metapaths

Similarity Search in Heterogeneous Knowledge Graphs via Meta Paths

View metapaths metapaths Website metapaths Package

Mutual Interactors

Phenotype Discovery in Molecular Interaction Networks

View Mutual Interactors Mutual Interactors Website

Raindrop

Graph-Guided Network for Irregularly Sampled Multivariate Time Series

View Raindrop Raindrop Website

SIPT

Structure Inducing Pre-Training

View SIPT SIPT Website

REMAP

Multimodal Learning on Graphs for Disease Relation Extraction

View REMAP REMAP Website

Therapeutics Data Commons

Machine Learning Datasets and Tasks for Drug Discovery and Development

View TDC TDC Documentation TDC Website

GraphXAI

Evaluating Explainability for Graph Neural Networks

View GraphXAI GraphXAI Website

NIFTY

Unified Framework for Fair and Stable Graph Representation Learning

View NIFTY NIFTY Website

G-Meta

Graph meta learning via local subgraphs

View G-Meta G-Meta Website

SubGNN

Subgraph Neural Networks

View SubGNN SubGNN Website

GNNGuard

Defending graph neural networks against adversarial attacks

View GNNGuard GNNGuard Website

Graph ML Tutorials

Tutorials on machine learning for graphs

View Graph ML Tutorials

Nimfa

Python module for fast non-negative matrix factorization

View Nimfa Nimfa Website

Decagon

Graph neural networks for multirelational link prediction

View Decagon

DeepPurpose

Deep learning library for drug-target interaction prediction and applications to drug repurposing and virtual screening

View DeepPurpose

SkipGNN

Skip-graph networks for molecular interaction prediction

View SkipGNN

scikit-fusion

Data fusion via collective latent factor models

View Scikit-fusion

Network Enhancement

Method for denoising biological networks

View NE

CRank

Method for prioritizing network communities

View CRank

OhmNet

Representation learning for multi-layer graphs

View OhmNet

Mambo

Tool for construction, representation, and analysis of large multi-modal networks

View Mambo

GNNExplainer

Method for generating explanations for graph neural networks

View GNNExplainer

GraphWave

Method for learning structural node embeddings

View GraphWave

Graph Query Embeddings

Method for embedding logical queries on knowledge graphs

View Graph Query Embeddings

Collage

Method for gene prioritization by compressive data fusion and chaining

View Collage

Network-Guided Matrix Completion

Method for probabilistic prediction and imputation of interactions using prior knowledge

View NGMC

fast-NMTF

Fast methods for non-negative matrix tri-factorization

View Fast-NMTF

Multi-BioNER

Deep multi-task learning for cross-type biomedical named entity recognition

View Multi-BioNER

CROW

Scalable multi-GPU and multi-CPU methods for non-negative matrix tri-factorization

View CROW

Latest News

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

Graph foundation model for drug repurposing published in Nature Medicine. [Harvard Gazette] [Harvard Medicine News] [Forbes] [NVIDIA]

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!

Mar 2024:   PocketGen - Generating Full-Atom Ligand-Binding Protein Pockets

PocketGen is a deep generative model that generates residue sequence and full-atom structure of protein pockets, maximizing binding to ligands. Project website.

Feb 2024:   SPECTRA - Generalizability of Molecular AI

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