15 Years Building the Biomedical Knowledge Infrastructure Behind Drug Discovery and Precision Medicine​

Biomedical data is vast, fragmented, and inconsistent — spread across millions of publications, clinical databases, genomic repositories, and regulatory submissions. The teams that win in drug discovery and precision medicine are not the ones with the most data. They are the ones who can reason over it: connecting genes to diseases, variants to clinical outcomes, and molecular mechanisms to therapeutic hypotheses.

That is the problem MedBioInformatics was built to solve. We design and build knowledge infrastructure that transforms dispersed biomedical evidence into structured, semantically integrated, provenance-tracked systems that discovery and AI teams can trust and build on.​

DISGENET™: Where It Started​

In 2010, a research team at IMIM and Pompeu Fabra University in Barcelona set out to answer a question that was reshaping drug development: what does the human genome tell us about disease, and how can we make that knowledge actionable at scale?

The result was DISGENET™ — a systematically curated, evidence-scored network of gene-disease and variant-disease associations, built from the ground up with semantic structure, full provenance tracking, and scientific rigor at its core. Today it is the most cited gene-disease knowledge platform in the world, with 8,500+ citations and adoption by leading pharma companies, AI organizations, and clinical research institutions globally.

21,000+

researchers and teams rely on DISGENET™ worldwide

8,500+

citations across pharma, biotech and clinical research

Active since 2010

Continuously updated and expanded

MedBioInformatics: From Platform to Full Knowledge Infrastructure Company

As DISGENET™’s scientific impact translated into commercial demand, it became clear that pharma, biotech, and AI organizations needed more than access to a platform — they needed partners who could design, build, and integrate biomedical knowledge infrastructure into their specific workflows.

MedBioInformatics Solutions was incorporated in 2020 to meet that need. Drawing on the same expertise in NLP, semantic integration, and knowledge graph construction that powers DISGENET™, we work with organizations across drug discovery, chemical safety, and precision medicine to deliver:

  • Target identification and prioritization — evidence-ranked gene-disease associations that connect genomic data to therapeutic hypotheses
  • Drug safety and chemical risk assessment — AI-powered tools for anticipating adverse effects and supporting regulatory submissions
  • Drug repurposing intelligence — knowledge graph analysis that surfaces new indications for existing compounds
  • Biomarker and variant interpretation — structured genomic evidence for precision medicine and clinical decision support
  • Custom NLP and knowledge graph solutions — bespoke pipelines built on our core infrastructure for any biomedical data challenge

Whether you need to integrate DISGENET™ into your discovery pipeline, build a custom knowledge graph from your proprietary data, or extract structured intelligence from scientific literature — our team brings 15 years of biomedical knowledge engineering to your challenge.

Let’s talk about what you’re building.

Leadership team

From target identification to safety assessment, we build the biomedical knowledge infrastructure your teams can trust and build on. Let’s talk about your challenge.