TRANSLATOR TIDBIT 01
As the pace of scientific research continues to advance, the problem researchers face now is not a lack of information, but pairing the right data with the right question. The vision of Translator is to help researchers more easily see connections across those data, accelerating discovery and getting more treatments to more patients more quickly.
If you have questions about Tidbits, click here to contact us!
NCATS launched the Biomedical Data Translator program to help researchers formulate and refine hypotheses and reduce the time needed to advance discoveries made in the laboratory to clinical application. Ultimately, Translator will accomplish this through an informatics platform that bridges pre-clinical basic research data with clinical data, which will enable exploration of relationships across the full spectrum of data types. Existing biomedical data often remain disconnected, disorganized and mired in disparate jargon from different areas of research. This condition is illustrated below as the “Chasm of Semantic Despair.”
To address the Chasm of Semantic Despair, Translator aims to link previously disparate sources of molecular, cellular, pharmaceutical, patient and other data to form a more complete and comprehensible picture of existing knowledge.
This section will outline the question for Translator to answer.
What is...
Translator?If one data source associates A with B and another source associates B with C, Translator will connect A to C through B because it is mining through both sources. Now amplify this across more than 100 sources and the power of Translator becomes clear. Translator will not only allow users to search across many fields of study but also can retrieve relevant information related to the initial query that the user may not have been aware of, providing possible insight or a “Tidbit” that would not otherwise be easily discoverable. Due to the vast number of data sources that could be mined, Translator needs to be built within a collaborative ecosystem to maximize its effectiveness.
To help prospective users of Translator better understand the variety and complexity of questions it aspires to answer, the consortium developed Tidbits. A Tidbit is a use case that tells a compelling story and demonstrates the unique power of Translator.
Each Tidbit includes:
For additional information, at the end of each Tidbit the reader will find a drop-down box with a more detailed explanation of process details, technical approach and validation. For this Tidbit, the drop-down boxes provide additional insight into Translator as a program.
Issued notice of awards
First face-to-face meeting
Released funds
Architecture meeting
First Translator hackathon
Reasoning tool FOA released
Hackathon
Reasoning tool initial awards issued
Additional hackathons
The conceptual map outlined below is a visual representation of planned and existing connections that Translator can make between data types.
Teams collaborated throughout the feasibility assessment period to create the knowledge graph standard and the reasoner answer standards. To learn more about existing application programming interfaces (APIs) and semantic standards, please refer to the Smart API Registry and the map in BioThings Explorer.
Translator currently utilizes more than 130 data sources, and that number is growing continuously. It would be impossible for any one person to keep up with all of the different kinds of data available, so it is important that Translator can identify and suggest which data are the most useful to a user’s question without the user directing that process. In each Tidbit, we will explain what data were used to answer the question.
Translator continually undergoes validation by subject matter experts from many disciplines evaluating the results it produces for both correctness and completeness.
As the program continues to develop and document compelling Tidbits, we hope that you will explore them with us and see what Translator is capable of.
