Graph tech Expert insights Engineering AI

Using Memgraph for Knowledge-Driven AutoML in Alzheimer’s Research at Cedars-Sinai

By Memgraph

10 min readOctober 28, 2024

Alzheimer’s research depends on connecting patient data, genomics, clinical studies, and drug information without losing the relationships between them. In a recent community call, Jason H. Moore, Chair of the Department of Computational Biomedicine at Cedars-Sinai Medical Center, explained how his team uses Memgraph to build a knowledge graph that supports explainable AutoML and graph-powered biomedical discovery.

This post summarizes the main takeaways from that session, including how Moore’s team structures biomedical data, where KRAGEN and ESCARGOT fit, and why connected graph context improves predictive modeling and drug discovery in Alzheimer’s disease.

Watch the full webinar recording here: Cedars-Sinai: Using Graph Databases for Knowledge-Aware Automated Machine Learning.

Here’s a quick rundown of the key insights from the session.

AutoML for Alzheimer’s Research

Jason H. Moore highlighted how AutoML (Automated Machine Learning) is central to his team’s work on disease-risk prediction and drug discovery. AutoML automates key parts of the machine learning pipeline, including model selection and hyperparameter tuning, but it still depends on high-quality, structured data.

Memgraph provides the graph layer for a knowledge base that connects complex biomedical data sources, including patient health records, genetic data, and clinical trial results. Those connected data points give the team a stronger foundation for training AutoML models, improving disease-progression predictions and helping identify potential drug therapies.

Alzheimer’s research is data-heavy and relies on large datasets to extract meaningful insights. Memgraph’s ability to work with connected data at this scale makes it a practical fit for the AutoML pipeline.

Structuring Biomedical Data with KRAGEN and ESCARGOT

Biomedical data is often siloed and difficult to integrate across sources. Memgraph supports the team’s knowledge graph-enhanced RAG (Retrieval-Augmented Generation) workflow for biomedical problem-solving with LLMs, alongside tools like KRAGEN and ESCARGOT.

KRAGEN (Knowledge-Rich AI for Genomics and Environmental Networks) and ESCARGOT are pivotal to how Jason H. Moore’s team structures data within Memgraph. With KRAGEN, the team integrates diverse data sources like genomic data, clinical trial results, and electronic health records (EHRs) into a cohesive knowledge graph, allowing retrieval and exploration of relationships among biological entities—genes, proteins, symptoms, and more. This approach, powered by Memgraph, supports the Graph of Thoughts (GoT), a technique that layers contextual knowledge for LLM-driven biomedical insights, enabling researchers to ask complex queries that would be prohibitively time-consuming in traditional relational databases.

With Memgraph, KRAGEN, and ESCARGOT working together, Moore’s team can visualize and explore relationships in the data quickly. That helps researchers test new hypotheses around disease progression and intervention strategies without stitching together disconnected datasets by hand.

querying-alzkb-using-llms-with-context-learning-cedars-sinai

How Knowledge Graphs Improve AutoML

One of the key advantages of using a graph database like Memgraph is that it gives the AutoML pipeline contextualized data. The knowledge graph built with Memgraph includes interconnected data that adds context to individual data points, improving the quality and interpretability of machine learning models.

For example, when predicting disease risk, the system can incorporate not just patient demographics and genetic factors but also historical medical conditions, drug interactions, and lifestyle factors—all linked through the graph. This extra layer of contextual information allows the AutoML system to deliver more precise and explainable predictions, which is essential in biomedical research, where understanding why a model makes a specific prediction is critical.

Knowledge graphs also enhance the adaptability of AutoML models, allowing researchers to refine models as new data is continuously integrated.

TPOT and Memgraph in the AutoML Pipeline

TPOT, a Python-based tool for AutoML, is used with Memgraph to streamline the machine learning process further. TPOT automates model selection and hyperparameter tuning, which can be time-consuming when done manually.

Memgraph complements TPOT by ensuring the data feeding into the AutoML process is well-structured and connected. This reduces the time spent on data wrangling and preprocessing, enabling researchers to focus on model optimization and evaluation.

This integration allows for faster experimentation and quicker drug discovery insights in Alzheimer’s research, accelerating the identification of promising therapeutic candidates.

Scaling the Research Graph

Scalability is a major requirement in Alzheimer’s research, where datasets grow continuously as new patients are enrolled, new biomarkers are discovered, and new therapies are tested. Memgraph offers the scalability needed to support this ongoing research.

The knowledge graph is constantly updated with the latest findings from clinical trials, genomic research, and patient outcomes, ensuring that models use the most up-to-date data. Memgraph’s ability to handle large, complex datasets makes it a strong foundation for scaling both the knowledge base and the machine learning models built on top of it.

As the research expands, Memgraph helps the team add new data sources and continue optimizing AutoML models without disrupting risk-prediction and drug-discovery workflows.

Wrapping Up

Use Memgraph for workflows like this when your ML or GraphRAG system depends on connected biomedical context rather than isolated tables or vector search alone. A graph database is especially useful when researchers need to trace relationships across genes, drugs, symptoms, trials, and patient records while keeping those links queryable and explainable.

If you want to build a similar graph-backed workflow, start with the Memgraph getting started guide and then watch the full webinar for the Cedars-Sinai-specific implementation details.