GISAID is a global science initiative and primary source that provides access to genomic data of influenza viruses and the coronavirus responsible for the COVID-19 pandemic.
We developed tool for GISAID’s internal team so that they can have the access to the largest database of COVID-19. API was used to develop this tool to pull data from across the world.
The main goal of developing such a tool for GISAID is that the scientists and their internal employees can use it for further research and make their research & implementation on such viruses impactful.
Expertise
Design, Interaction and Development
Platform
Web and API
Deliverables
Concept and Development
Technology
Python, ReactJS, NLP, BioPython, BLAST
Challenges
While developing this health tech tool, the main challenge we faced was that creating such functionalities could help pull the data from trustable sources. Once pulled, they are compared. And, if the data is the same and available in GISAID’S database, it ignores it. But if it is unique, it will be stored in GISAID’s main database.
Apart from that, our developers added this basic yet important functionality. Scientists who have access to this tool can easily edit the information such as source, virus name, originating lab/submitting lab, authors, collection date.
7 Algorithm where developed which would help System to have artificial intelligence to compare records with each other which includes NLP, Sequence Matching (BioPython), Date of Record, Type of Disease, Author Records, Origin of Virus.
BLAST was used to further do matching with 20 Millions records of GISAID.
We created best-in-class dashboard in this tool so that users can have easy access to total records pulled, rejected, accepted and final submitted.
Solutions
With the help of this tool, logs can be imported. Plus, users of this tool can edit it and put it in the draft. If they want to reject it, they can. But if it is finally submitted, these logs will be added to the main database of GISAID universally.