Genestack’s new module helps biologists interrogate Life Science Data
Answering basic questions about drug targets requires having all transcriptLife Science Data in one place, properly annotated by curators, processed and visualised by bioinformaticians. This is costly to set up and maintain; not doing it delays decision making and puts unnecessary strain on computational biology resources.
Misha Kapushesky, PhD, CEO of the Cambridge-based bioinformatics software company, explains that “by enabling biologists to quickly look up where genes of interest are active, or what genes are active in a targeted tissue or cell type, speeds up target discovery and validation decision making.”
“Expression Data Miner was developed for biologists – by giving them a tool for investigating genes of interest on their own we hope to make the lives of bioinformaticians simpler. We worked with bioinformaticians who develop pipelines to build a mechanism to aggregate outputs into a system accessible to bench researchers. Computational biologists in the meantime can spend more time on developing new methods and performing novel analyses, and do fewer repetitive tasks to unblock their biologist colleagues.”
“The advantages don’t stop there either. The data and metadata management functionality of the Genestack platform combined with an intuitive search supports all discovery scientists. They can find and access all the data available to them, public and private across the entire R&D organisation. Scientists can also share views and receive notifications when new studies of interest become available. Expression Data Miner makes use of provenance tracking features of the underlying Genestack Platform, supporting robust reproducibility and good data governance practices. These capabilities really unlock the full potential of the new app.”
Imad Yassin, VP of Marketing and Sales added “people are now looking to AI and machine learning techniques to improve the drug discovery process, often overlooking the fundamental first step of better data and metadata management. This is what Genestack is all about, simple modular software solutions that can improve the workflow without changing your architecture. This not only supports organisations right now but in the upcoming AI revolution.”
The Expression Data Miner module, although specifically for transcriptLife Science Data, continues to demonstrate Genestack’s flexible approach to its services and software solutions. By itself, it enables the use of public dictionaries and ontologies as well as importing your own. But it is part of a much larger vision. When combined with the Genestack ODM app it allows data managers to load, curate and process large volumes of public and private Life Science Datasets with easy-to-use tools or by opening APIs to curation partners.
Genestack’s mission is to help scientists make decisions. Its Life Science Data platform, with its new modules, is set to free discovery scientists and bioinformaticians to concentrate on the challenges that will bring the greatest value to their organisations. Expression Data Miner is out now, with Genestack ODM scheduled for release in Spring 2019.
Genestack CEO, Dr Misha Kapushesky, will be discussing what is holding back pharmaceutical organisations from making the most of their AI initiatives, in the Pharmaceutical IT Track of the 16th Annual Pharmaceutical IT Congress 2018 on Thursday 20th September at 12:50 am. Genestack is also on stand 10 showcasing its new Expression Data Miner module.