How Big Data is used for our Clinical Trials Database

Since its launch in 2019, the Biotechgate clinical trials registry has grown to house over 725,000 studies from around the world. The data is taken from 20 different registries worldwide, ensuring that Biotechgate users are getting the most recent and most accurate data to power their business development.

The backbone of the clinical trials database is a combination of big data and AI. This was made possible through a two-year project called DISCOVER, involving Venture Valuation, the owner of Biotechgate, Innosuisse, and the Swiss Institute for Information Research.

 At least 90% of the World Wide Web falls under the label of the “deep web”. This refers to parts of the Internet that aren’t indexed by search engines, including areas such as academic databases, government resources, and ontologies. The DISCOVER crawler serves as a way to fulfill the data extraction requirements from areas such as the deep web to garner a wide array of clinical trial data, representing the complete data mining process of data acquisition, extraction, and curation. This allows the Biotechgate clinical trials database to be regularly updated with the latest information, with the crawler also being in place for our licensing agreements and financing round sections.

Further adjustments to this data mining process are made once the information has been acquired. As our database information is retrieved from a variety of sources, we place a particular emphasis on ensuring that the data is well-structured and easily searchable amongst our 1.2 million total entries. This information is then integrated with existing Biotechgate data, with clinical trials being linked to company profiles where applicable to allow for a seamless user experience.

The DISCOVER crawler also analyses the websites of existing organizations in Biotechgate’s records. This includes identifying recently closed license agreements and financing rounds, with this data then being cross-referenced with the extant information. This approach ensures the utmost accuracy for Biotechgate users, allowing them direct access to the most up-to-date data.

While we pride ourselves on our data being up-to-date, we also make a concerted effort to guarantee that it is accurate and relevant, serving as a key resource for investors, business development professionals, and many more organizations who utilize it when conducting their business deals, researching their competition or for a variety of other uses. This combined approach of big data and AI allows us to offer you  a very comprehensive and well connected clinical trial registry.