Life sciences organizations increasingly recognize that graph-driven artificial intelligence (AI) and analytics are essential to accelerate R&D innovation, optimize processes and drive new business growth.
In a recent GlobalData survey, pharmaceutical firms named Big Data and AI as their top two areas of technology investment over the next two years.1
However, implementing graph technology is proving increasingly difficult. The majority of graph tools are struggling to keep up with unprecedented levels of scale and computing power now required for predictive/AI analytics of vast volumes of complex biomedical data spanning a wide array of knowledge sources.
Katana Graph™ offers a breakthrough graph intelligence platform that enables life sciences organizations to reap the huge potential of graph processing and AI, at levels of scale and performance no other data platform can match.
From virtual screening of drugs to managing healthcare providers participating in clinical trials, the Katana Graph platform helps biopharma companies use graph algorithms to discover new opportunities and efficiencies throughout the life sciences value chain.
The Katana Graph intelligence platform interoperates with its own graph database system, providing a single high-performance distributed graph computation platform for life sciences:
|Graph Queries (e.g., virtual screening of ChEMBL database, trial management)
|Graph Analytics (substructure searches, similarity search, fingerprint generation)
|Graph Mining (pattern discovery)
|Graph AI & Deep Machine Learning (patient classification, drug retargeting, precision medicine)
The success of many life sciences use cases lies in the speed and accuracy in which hypotheses can be generated and tested. Katana Graph shines over alternative solutions, providing proven, unrivaled speed and scale — “time to insight” — on a wide array of medical knowledge graphs.
Katana Graph also provides graph AI with graph neural networks (GNN), a new powerful approach for feature learning on graphs. Katana provides easy-to-use and scale-out packages for learning large-scale knowledge graph embeddings, applications such as node classification, link prediction, and recommendation systems essential for bioinformatics and cheminformatics.
The Katana Graph platform can also be extended to run third party algorithms. For example, analytical libraries that have Python interfaces can be run as UDFs (User Defined Functions) on our high performance distributed graph computation platform. Katana Graph can serve as a single integrated platform to fulfill all your data engineering, data mining and graph AI application development needs.
Katana Graph enables life sciences enterprises to accelerate time-sensitive, data-driven business decisions from R&D to clinical trials with an easy-to-use platform. Scientists, analysts, managers and executives alike gain new levels of actionable insight, drawn from high-performance graph algorithms on massive heterogeneous data sets.