Similarity search in knowledge graphs using meta paths

Relational data in biological systems – such as the cellular interactome, single cell similarity graphs, gene co-expression networks, and patient interaction networks – can be represented by graph structures. Biological networks are often comprised of diverse data modalities; thus, they are poorly modeled by homogenously typed networks. Instead, interconnected objects from various modalities can be represented as a single multigraph with heterogeneous knowledge-informed node and edge types. We develop metapaths, an R software package to implement meta paths and perform meta path-based similarity search in biological knowledge graphs.

Meta paths are a general graph-theoretic approach for flexible similarity search in large networks. While they are widely used in biomedical network analysis, there is currently no package available in R that would offer a wide range of support for meta paths.

Meta paths are sequences of node types that define a walk from the origin node to the destination node. Informative metapaths in knowledge graphs (KGs) are often engineered by hand based on domain knowledge or expertise (e.g., the meta path DRS is clinically meaningful, since it describes associations between a disease and the side effects of its treatments, whereas the meta path PSF would not be). Alternatively, optimal meta paths can be discovered in an unsupervised fashion by feature selection metrics (e.g., maximal spanning tree, Laplacian score, or ranking based on meta path frequency or uniqueness), among other approaches. Once informative meta paths for a given KG have been defined, these meta paths define the semantics of the relationships between nodes in the KG, enabling down-stream machine learning analyses such as link prediction, node classification, and subgraph prediction.

Although various algorithms exist to model meta path-based node simi-larities in a KG, a unifying framework is lacking to compute and compare these similarity scores. We introduce metapaths/ which introduces meta paths in the R ecosystem. The metapaths package enables the computation of meta-path-based similarity search in heterogeneous KGs.

Publication

metapaths: similarity search in heterogene-ous knowledge graphs via meta paths
Ayush Noori, Amelia L.M. Tan, Michelle M. Li, and Marinka Zitnik
In Review 2022 [arXiv]

@article{noori2022metapaths,
  title={Metapaths: similarity search in heterogeneous knowledge graphs via meta paths},
  author={Noori, Ayush and Tan, Amelia L.M. and Li, Michelle M. and Zitnik, Marinka},
  journal={arXiv: 2209.0000},
  volume={},
  number={},
  pages={},
  year={2022},
  publisher={}
}

Code

Implementation in R together with documentation and examples of usage is available in the GitHub repository.

Authors

Latest News

Mar 2023:   New Paper in Nature Machine Intelligence

New paper with NASA in Nature Machine Intelligence on biomonitoring and precision health in deep space supported by artificial intelligence.

Mar 2023:   New Paper in Nature Machine Intelligence

Mar 2023:   TxGNN - Zero-shot prediction of therapeutic use

Mar 2023:   GraphXAI published in Scientific Data

Feb 2023:   Welcoming New Postdoctoral Fellows

A warm welcome to postdoctoral fellows Ruth Johnson and Wanxiang Shen. We are thrilled to have them joining us soon and look forward to working together.

Feb 2023:   New Preprint on Distribution Shifts

Feb 2023:   PrimeKG published in Scientific Data

Jan 2023:   GNNDelete published at ICLR 2023

Jan 2023:   New Network Principle for Molecular Phenotypes

Dec 2022:   Can we shorten rare disease diagnostic odyssey?

New preprint! Geometric deep learning for diagnosing patients with rare genetic diseases. Implications for using deep learning on sparsely-labeled medical datasets. Thankful for this collaboration with Zak Lab. Project website.

Nov 2022:   Can AI transform the way we discover new drugs?

Our conversation with Harvard Medicine News highlights recent developments and new features in Therapeutics Data Commons.

Oct 2022:   New Paper in Nature Biomedical Engineering

New paper on graph representation learning in biomedicine and healthcare published in Nature Biomedical Engineering.

Sep 2022:   New Paper in Nature Chemical Biology

Our paper on artificial intelligence foundation for therapeutic science is published in Nature Chemical Biology.

Sep 2022:   Self-Supervised Pre-Training at NeurIPS 2022

New paper on self-supervised contrastive pre-training accepted at NeurIPS 2022. Project page. Thankful for this collaboration with the Lincoln National Laboratory.

Sep 2022:   Best Paper Honorable Mention Award at IEEE VIS

Our paper on user-centric AI of drug repurposing received the Best Paper Honorable Mention Award at IEEE VIS 2022. Thankful for this collaboration with Gehlenborg Lab.

Sep 2022:   Multimodal Representation Learning with Graphs

Aug 2022:   On Graph AI for Precision Medicine

The recording of our tutorial on using graph AI to advance precision medicine is available. Tune into four hours of interactive lectures about state-of-the-art graph AI methods and applications in precision medicine.

Aug 2022:   Evaluating Explainability for GNNs

New preprint! We introduce a resource for broad evaluation of the quality and reliability of GNN explanations, addressing challenges and providing solutions for GNN explainability. Project website.

Jul 2022:   New Frontiers in Graph Learning at NeurIPS

Excited to organize the New Frontiers in Graph Learning workshop at NeurIPS.

Jul 2022:   AI4Science at NeurIPS

We are excited to host the AI4Science meeting at NeurIPS discussing AI-driven scientific discovery, implementation and verification of AI in science, the influence AI has on the conduct of science, and more.

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