visyn Knowledgebase

visyn Knowledgebase, developed by datavisyn, is a curated biological intelligence platform designed to enrich drug discovery workflows. Built to address the challenge of integrating vast amounts of public biological data with in-house experimental results and clinical knowledge, it provides discovery teams with a unified, continuously updated foundation of biological evidence. The platform is purpose-built to support datavisyn's Aevidence and Ordino applications, enabling researchers to explore, compare, and verify biological findings without the burden of manual data wrangling across dozens of disparate sources.

Together with pharma partners, datavisyn has identified, compiled, curated, and integrated a core set of public data from more than 70 bioinformatics databases and disease-specific resources. The result is a knowledgebase covering over 80,000 recognized entities across 10 distinct data types, giving discovery teams immediate access to the biological intelligence needed to drive strategic decisions.

Key Scale and Coverage

• More than 70 data sources integrated into a single curated knowledgebase
• Over 80,000 recognized biological entities
• 10 distinct data types spanning genomics, chemical biology, clinical data, and more
• Regularly updated to ensure access to the most current publicly available biological evidence

Featured Data Sources

• Cancer Genomics: Includes AACR Project GENIE (large-scale international cancer genomics data sharing), DepMap/Cancer Dependency Map (essential gene identification across 2,000+ cancer cell line models), cBioPortal (exploration of genetic mutations and clinical outcomes across cancer types), and TCGA (comprehensive genomic, epigenomic, transcriptomic, and clinical cancer data)
• Chemical Biology: Includes miRWalk (microRNA target predictions with experimentally validated and predicted miRNA-target interactions), data from systematic protein turnover analyses in primary cells, and high-throughput profiling of reactive cysteines for electrophile library screening
• Clinical Data: FDA UNII (Unique Ingredient Identifier system for substances used in pharmaceuticals, biologics, food, and cosmetics)
• Drug and Compound Data: ChEMBL (manually curated database of bioactive molecules with drug-like properties integrating chemical, bioactivity, and genomic data) and Protac-DB (comprehensive information on PROTACs, including structures, target proteins, and mechanisms of action)
• Additional sources include UniProt, GTEx, Reactome, and many more across the full catalogue of 73+ listed entries

Core Capabilities

• Eliminates time-consuming manual searches across multiple databases by consolidating biological evidence in one place
• Provides universal tools that simplify import and integration functions, allowing teams to further refine and customise the knowledgebase to their specific research focus
• Seamlessly integrates with the Ordino and Aevidence platforms for exploration, drill-down analysis, and advanced discovery workflows
• Supports verification of biological meanings underlying patterns and findings in data visualisations

visyn Knowledgebase is available with flexible licensing and deployment options. It integrates directly into the datavisyn platform ecosystem, and teams can explore its capabilities through the Aevidence and Ordino applications. For further information, datavisyn can be contacted directly to discuss deployment and integration requirements.