Aigenpulse’s new pharmaceutical discovery and development platform is designed to harness artificial intelligence (AI) and machine learning to deliver advanced analytics necessary for informed decision making.
The data-agnostic platform enables users to import, integrate, process, link, visualize and brake down information from multiple sources and bring it into a common frame of reference. According to the company, the platform enables users to leverage diverse data assets to arrive at new insigts, build predictive foresight and easily share findings with stakeholders.
Outsourcing-Pharma recently discussed the platform with an Aigenpulse spokesperson, who told us life-science professionals struggle with use of different systems across locations, and translating that information into one common format.
“We are providing the ability to interact with and exchange data across systems, sources, and software,” they said. “We also recognize the significant regulatory requirements of life science organisations, and developed an automated system to collect, template and store the evidence required for any configuration of the platform."
Aigenpuse told us that researchers can use the platform to process hundreds of datasets simultaneously and at scale, freeing them up for higher value tasks. The platform can be integrated easily integrate with ELNs and LIMSs, in-house data lakes, for a single-point-of-truth for sample/experiment meta-data, and public data sources, such as TRON,TCGA, and GTeX.
Steve Yemm, Aigenpulse chief commercial officer, said, “The need to deliver innovative therapeutics more cost-effectively and generate profitable growth means that drug developers need to embrace disruptive technologies. Being able to fail faster, design streamlined, targeted and efficient clinical trials, and accelerate the discovery and approval of new therapeutics, whilst reducing cost, is all achievable with the Aigenpulse platform.”
“We have designed the platform to help digitalise the entire research process, by logically storing and securing biological data from diverse sources and applying advanced analytics to aid data integration,” Yemm added. “We thereby provide a framework by which governance, regulatory and security policies can be applied and powerful insights can be generated in real-time. Ultimately, we combine machine learning and human expertise to facilitate the efficient creation of better drugs.”
The platform reportedly is configurable and modular and can be tailored to cater for various data types and business needs. Its experiment suites, which solve specific challenges and are focused on one type of scientific data, are mapped to organisation-wide sets of samples, vocabularies and ontologies, enabling a centralised, accessible, auditable repository of data (raw, processed and analysed), analysis, machine-learning models and reports.