Aevidence

Aevidence is a biological intelligence platform developed by datavisyn, designed to advance data-driven drug discovery by providing interactive access to biomedical evidence. It is built for drug discovery teams who need to consolidate and explore foundational pre-discovery research — replacing fragmented spreadsheets and siloed data sources with a unified, continuously updated framework for gathering, organizing, and sharing scientific evidence.

The platform comprises 10 specialized discovery apps that enable researchers to investigate potential biological targets (including receptors, enzymes, proteins, genes, and molecular structures), leverage competitive intelligence on companies, approved medicines, clinical trials, and market potential, and inform experimental design throughout early discovery efforts. When paired with Ordino and the visyn Knowledgebase, Aevidence delivers a comprehensive visual analytics suite with immediate access to a wealth of public and internal scientific data.

Core Workflow

1. Search for Entities: Access an exhaustive biological knowledgebase to retrieve detailed information on genes, diseases, compounds, companies, and other entities — individually or in combination — without leaving the datavisyn workspace.
2. Retrieve Query Results Instantly: Build easy queries to explore different types of biological evidence across specialized discovery apps, each designed to best fit the data type being mined, whether genetic sequences, protein structures, or known drug interactions. Save searches for entities and their combinations to retrieve updated results in seconds.
3. Explore Biomedical Evidence in Context: Drill down into data to identify key insights about the role of entities of interest. Upload and integrate in-house research data to enrich the knowledgebase and tailor evidence exploration to a specific drug program.

Key Capabilities and Specialized Apps

• Disease Biology: Mine the visyn Knowledgebase of regularly updated biomedical intelligence to strengthen understanding of disease pathophysiology and rigorously assess potential targets and therapeutic modalities.
• Bioactivity: Investigate comparative human, mouse, and rat bioactivity data from ChEMBL and PROTAC-DB, including drug-like molecules and PROTACs. Define target and off-target filters as well as structural constraints such as substructures or reference structures for similarity filtering.
• Protein Structure: Visualize 3D structures and explore underlying sequences of experimentally-determined and computed proteins from the RCSB Protein Data Bank, critical for understanding the role of macromolecules in health, disease, and therapeutics.
• Protein Sequence Analysis: Retrieve protein sequence alignments between human and animal species used in preclinical toxicology studies. View human gene orthologs from NCBI orthologs and OrthoDB, run multiple sequence alignments on homolog proteins using UniProt data, and narrow comparisons to specific protein domains of interest.
• General Information: Retrieve concise summaries of genes or diseases of interest, including subcellular location and topology of mature proteins, with interactive cell diagram highlighting.
• GWAS and PheWAS Studies: Access summary statistics from genome-wide association (GWAS) and phenome-wide association (PheWAS) studies, with links to PubMed publications. Drill down to regional association plots of trait associations within a given genomic range.
• Oncology: Access a visual overview of genomic alterations from The Cancer Genome Atlas (TCGA), including alteration prevalence by cancer type, gene expression distribution in tumor and normal samples, missense mutation hotspots, DepMap CRISPR knock-out gene effect scores, and survival analyses for selected patient cohorts.
• Expression Analysis: Compare expression of one or multiple genes using integrated data from GTEx, TCGA, and the Cancer Cell Line Encyclopedia (CCLE). Visualize expression in the context of tissue type, disease status, or other factors, and define cohorts using genomic markers such as mutations, copy number alterations, or expression ranges.
• Custom App Development: Work with the datavisyn team to create new portals tailored to specific research requirements and discovery data landscapes.

The visyn Knowledgebase

• Integrates public data from more than 70 sources and repositories, including UniProt, GTEx, ChEMBL, Reactome, cBioPortal for Cancer Genomics, Cancer Dependency Map Project (DepMap), and The Cancer Genome Atlas (TCGA).
• Covers over 80,000 recognized biological entities and is regularly curated and updated to ensure access to the most current publicly available biological evidence.
• Includes universal data import tools enabling any team member to integrate in-house experimental and internal research data into the knowledgebase.
• Continuously evolves through close collaboration with customers and partners to prioritize new biological data resources for future updates.

Aevidence supports go/no-go decision making at every stage of preclinical drug discovery and development. The platform is available for licensing and deployment, and the datavisyn team works closely with customers to tailor the solution to their specific research focus and data landscape.