Indivumed Launches JADBio’s Groundbreaking AI Platform for Multi-omics Data
Analytics Platform Provides Insights into Cancer Biology, Acceleration of Drug and Diagnostic Development
HAMBURG, Germany, Nov. 10, 2020 /PRNewswire/ — Indivumed announced today the launch of its new, AI-integrated Advanced Data Analytics Platform which will accelerate drug targets and diagnostics discoveries. In the past six months, Indivumed has built an ensemble of cutting-edge technologies that allow the company to integrate and automate analytics across the oncology bioinformatics spectrum to unlock the enormous potential of the IndivuType database. Unique and complex datasets contained within the IndivuType database require highly sophisticated data analytics approaches which, until now, have not been available in the required setting.
The platform currently includes five toolboxes (immuno-oncology, clinical data, genomics, expression, and pathway analytics), each containing a number of specific applications. Together with the AI / AutoML based on Gnosis’ JADBIO technology, this constitutes the most powerful analytics platform in oncology today. Additional toolboxes and applications are currently under development.
The engineering of this new software toolbox and its integration into Indivumed’s proprietary multi-omics cancer database, IndivuType, “is a game-changer,” according to Roald Forsberg, VP Oncology Informatics at Indivumed. “It allows us to unlock complex layers of multi-omics data in a streamlined fashion to speed up the discovery and insights of therapeutic targets and biomarkers.” It also provides a deep understanding of cancer biology in individual patients with the ultimate goal of guiding targeted therapies.
“The ability to understand and utilize data has been greatly advanced by recent developments in the fields of AI, machine learning, and systems biology,” said Dr. Jonathan Woodsmith, Director of Advanced Analytics and AI at Indivumed. “In our AI Platform, we have combined key elements from these areas to create a revolutionary new way of generating discoveries and insights in oncology. The performance of the platform has already been proven in a variety of successful target and biomarker discovery projects.”
As the world’s most comprehensive multi-omics database, IndivuType provides a combination of genomics (whole genome sequencing), transcriptomics, proteomics, and phospho-proteomics data of matched tumor-normal pairs, together with clinical and follow up information from patients around the globe. While conventional genomics-only approaches fail to accurately predict tumor progression and response to treatment, the integration of multiple -omics layers provides a clear picture and a better understanding of cancer mechanisms and patient variability in treatment response.
“The development of this unique AI platform by our software engineers and data analysts is a major step to transform Indivumed into a digital biotech company in oncology,” said Dr. Hartmut Juhl, CEO, and Founder of Indivumed. “Based on 18 years of science-guided, standardized tissue collection in a global clinical network, we have established the first multi-omics database. Now, with this AI Platform, we are positioned to fully realize our vision of advancing personalized oncology and are a trusted global partner for drug and diagnostic development.”
About Indivumed
Indivumed is a physician’s-led, integrated global oncology company. Our platform is an enabler for the next generation of precision oncology through our proprietary multi-omics cancer database and customized data analytics, underpinned by our global network of affiliated clinics with gold-standard quality of biospecimens. Through our unique platform, we offer specialized products and services that support our customers in biomarker and target discovery, drug development, clinical trials, individualized therapy, and more. More information at www.indivumed.com
About JADBio
JADBio is an automated machine learning tool, specifically designed for biomedical data, such as multi-omics studies. JADBio’s easy-to-use interface allows biologists, bioinformaticians, clinicians, and non-expert analysts to perform sophisticated analyses with the click of a button. It is fully automatic drastically boosting productivity, even for expert analysts. It tries thousands of combinations of algorithms and tuning parameters to find the optimal model. Novel statistical methods avoid overfitting and overestimation of performance even for low sample sizes. It performs feature selection (biosignature identification) by removing irrelevant, but also redundant features (markers) for prediction. It has been validated on hundreds of public datasets, producing novel scientific results. More information at jadbio.com
Source: PRNewswire
