Pi-OmniKG: Making Sense of Biomedical Data

Enable actionable insights with a ready-to-go, Google-backed Knowledge Graph framework.

Solution overview

Persistent partnered with Google Cloud Platform (GCP) to create Pi-OmniKG, a biomedical data-specific Knowledge Graph (KG) framework that integrates data across sources, formats, types, and modalities. This solution accelerates time-to-value with faster, explainable insights, combining Google’s scalable infrastructure with Persistent’s three decades of data engineering expertise.

Pi-OmniKG deconstructs the complexity of Knowledge Graphs into three operational steps:

Consolidating the knowledge base

Pi-OmniKG seamlessly integrates large biomedical databases from public or proprietary scientific literature and authentic sources. Leveraging GCP’s storage, structured and unstructured data can be stored in vectors and graphs, with the option of integrating it with other data sources based on events or triggers.

Designing the relational schema to create KG

Depending on the use case, Pi-OmniKG adopts a pre-defined schema to intake data and create a KG. Machine learning (ML) models scan through the KG to understand inherent relationships and anticipate hidden ones, which can be gleaned as insights via natural language processing (NLP).

Actionable insights using KG

Generative AI (GenAI), backed by large language models (LLMs) trained on the KG, helps users with queries or retrieving information faster through virtual assistants. GenAI also aids in analysis with quality control metrics.

Benefits

Pivot to evidence-based insights

Make sense of large volumes of unstructured and structured data while ensuring insights are explainable with underlying data connections. This leads to evidence-based insights, critical for regulatory approvals or designing scientific R&D projects.

Increase efficiency

Streamline access, utilization, and monetization across the data landscape, grounding decisions in evidence-backed knowledge that reduces chances of failure. This significantly removes guesswork and outliers, reinforcing simplified protocols.

Halve data mining and analytics costs

Provide precursors to advanced AI applications, specifically GenAI, which automates insights gleaning through an interactive user interface. This significantly reduces time to insights and opens data to users other than data analysts, creating richer, highly contextualized insights that reduce costs by as much as 50%.