
BERG (BPGbio)
Pioneering hypothesis-free drug discovery through the Interrogative Biology® platform and Causal AI.

Systematic drug target identification and prioritization through large-scale genomic and clinical data integration.

Open Targets is a pre-competitive public-private partnership that provides a comprehensive platform for systematic drug target identification and prioritization. As of 2026, it remains the global benchmark for integrating human genetics, genomics, and clinical data to bridge the gap between biomedical research and pharmaceutical R&D. The technical architecture relies on a robust ETL pipeline that harmonizes data from over 20 primary sources, including GWAS Catalog, ClinVar, UniProt, and ChEMBL. It utilizes a sophisticated Evidence-to-Target (E2T) and Locus-to-Gene (L2G) machine learning framework to assign confidence scores to target-disease associations. By 2026, the platform has expanded its NLP-driven literature mining capabilities and integrated massive-scale single-cell transcriptomics and CRISPR screening data. It offers a highly performant GraphQL API for real-time data retrieval and hosts multi-terabyte datasets on Google BigQuery for batch-processing and deep-learning model training. Its market position is unique as it serves as the foundational data layer for both academic researchers and major pharmaceutical conglomerates, facilitating a 'fail-early' strategy in drug development by identifying safety and efficacy signals at the earliest possible stage.
Open Targets is a pre-competitive public-private partnership that provides a comprehensive platform for systematic drug target identification and prioritization.
Explore all tools that specialize in identify drug targets. This domain focus ensures Open Targets delivers optimized results for this specific requirement.
Explore all tools that specialize in target-disease association scoring. This domain focus ensures Open Targets delivers optimized results for this specific requirement.
A gradient-boosting machine learning model that prioritizes the most likely causal genes at a given GWAS locus using features like distance, eQTL, and chromatin interaction.
A flexible API layer allowing nested queries across targets, diseases, drugs, and evidence sources in a single request.
Integration of non-clinical safety data, including known target-related toxicities and expression in vital organs.
Maps genetic variants to drug response phenotypes, identifying how individual genetic makeup affects drug efficacy and safety.
A specialized tool for fine-mapping and colocalisation analysis of GWAS and molecular QTL data.
A configurable scoring algorithm that weights different types of evidence (e.g., Genetic vs. Literature) to calculate a global confidence score.
Data is mirrored to public cloud instances for massive SQL-based analysis without managing local infrastructure.
Navigate to the Open Targets Platform or Genetics portal.
Perform a global search for a target (e.g., BRCA2) or disease (e.g., Alzheimer's).
Analyze the overall Association Score, which aggregates evidence from genetics, somatic mutations, and expression.
Drill down into specific evidence strings to verify the provenance of data.
Use the Target Safety section to assess potential toxicological risks.
Consult the 'Tractability' widget to evaluate drug-ability (Small molecule vs Antibody).
Access the GraphQL Playground to construct custom queries for specific data fields.
Download filtered data in TSV or JSON format for local analysis.
For large-scale analysis, connect to the Open Targets public dataset in Google BigQuery.
Integrate the data into internal R&D workflows using the Open Targets PySpark pipeline code from GitHub.
All Set
Ready to go
Verified feedback from other users.
"Highly praised for its data transparency and the rigorous L2G model. Academic and industry users consider it an essential daily tool."
Post questions, share tips, and help other users.

Pioneering hypothesis-free drug discovery through the Interrogative Biology® platform and Causal AI.

Unifying life sciences data into an actionable knowledge graph for accelerated drug discovery.

Accelerate drug discovery workflows with AI-driven evidence synthesis and biological insight.

Gamified Protein Folding: Harnessing human intuition to solve complex biochemical puzzles for drug discovery.

The industry-standard engine for high-throughput genomic variant discovery and clinical-grade sequencing analysis.

Advanced gene function prediction and association network integration for precision genomics.

The premier open-source genomic workflow system for reproducible scientific research and advanced omics analysis.
The Human Protein Atlas is an open-access resource that maps all human proteins in cells, tissues, and organs.