PubMiner AI

Automatic Knowledge Extraction from Scientific Publications

Empower researchers to transform vast amounts of medical data into actionable knowledge through AI-powered insights, graphical representations, and customizable queries. PubMiner AI archives that by:

A scalable, AI-enabled workflow automating the extraction of valuable knowledge from a large body of scientific publications.
An implementation of Retrieval Augmented Generation (RAG) using structured graph knowledge is needed in the retrieval step.
Integrating data from PubMed, SemMedDB, and Ontotext’s LinkedLifeData Inventory powered by GraphDB, for efficient document retrieval.
employing a large language model (LLM) to produce a focused knowledge graph formalizing potentially novel knowledge in the specific domain.
building on the principles of FAIR to provide a knowledge representation that could be directly embedded into downstream information systems.

What to expect

Request a demo

About PubMiner AI

Using PubMiner AI as a blueprint, any skilled data scientist with basic knowledge of semantic technologies (knowledge graphs, RDF, SPARQL, ontologies, and semantic models) could build a targeted workflow that can extract complex relations between biomedical entities from scientific literature.

Request free demo access

Who is PubMiner AI for?

Data scientists

Facilitate researcher’s work and automate data analysis workflows.

Biomedical researchers

Navigate efficiently huge volume and wide range of data about genes, proteins, compounds, diseases, etc.

Pharma Companies

Extend internal knowledge and treat rare and newly identified diseases with information extracted from scientific literature.

How it works

Integrated Data Sources: Combines data from PubMed, SemMedDB, and Ontotext’s LinkedLifeData Inventory powered by GraphDB into a highly scalable biomedical knowledge base.

AI-Powered Knowledge Creation: Uses large language models to analyze cross-referenced biomedical data and generate in-depth insights.

Knowledge Graph Generation: Automatically creates knowledge graphs to visualize and explore relationships between the biomedical entities in scope: diseases and genes.

GraphDB Integration: Leverages GraphDB to enhance data structuring and querying, facilitating more complex insights from interconnected data.

Customizable Data Subsets: Allows users to filter and focus on specific areas of interest for personalized knowledge discovery.

Automated Report Generation: Summarizes research findings and trends into comprehensive, digestible reports.

Enhanced Query Capabilities: Natural language queries enable intuitive, AI-driven exploration of large biomedical datasets.

Biomarker Discovery: Facilitates the mining of scientific literature to identify potentially novel susceptibility genes for disorders of interest.

Request free demo access

What to expect?

Find your Dataset

You will get access to the PubMiner AI notebook and database catalog on the Databricks platform. Since PubMiner AI is based on Ontotext’s LinkedLifeData Inventory, access to the inventory is also provided, along with a demonstration on how to explore datasets such as UMLS, NCBI Gene, MeSH, and many others.

The database catalog consists of a sample dataset of PubMed articles and SemmedDB annotations in relational tables against which to execute the workflow.

Dive Deeper

The notebook presents a sample workflow for knowledge extraction demonstrated through the process of retrieving an answer for a given research question. It also provides a means for visualization and exploration of the results.

Retrieve very targeted subset of documents containing relevant information for the particular use case;
Identify biomedical concepts and the relations between them;
Build a subgraph representing the extracted knowledge normalized to reference data sets.

Request free demo access

Explore PubMiner AI

"Ontotext’s solution does what they need it to do. The willingness of the Ontotext team to adjust the tool based on needs was a critical point. We formed a relationship with them that made a difference - and our ability to handle large data sets, to find and rank choices is now so much better and faster!"

Anonymous

Researcher, Leading US biomedical and genomic research center