OC Processor
Transform unstructured data into actionable intelligence
Speed your time to market and increase your output with an annotated library of data
Help your science teams extract new knowledge from their chemical and life sciences research with a database of ontology-driven annotation of any documentation held by your organization.
The OC Processor is a powerful text and data mining tool designed to perform advanced annotations within text documents and process images, enabling named entity recognition for complex content such as chemical compounds and reactions.
It applies data normalization based on large domain-specific ontologies, providing named entity recognition and data extraction through a combination of semantic algorithms and machine learning.
It can be accessed and explored by anyone within your organization and compared with external databases using the SciWalker Semantic Search Engine, helping to find documents and new relationships, drive innovation and accelerate your time to market.
How does the OC Processor work?
Once your documentation has been fed into the OC Processor, you can then interrogate the database to determine new relationships between your data.
All cartridges you selected will be used for annotation, meaning the annotator detects domain-specific terms (eg. chemical terms, diseases or proteins) within the texts and marks them for later use.
In the context of life sciences, it enables your teams to establish the relationship between a drug and a disease, whether they interact, or if anyone has reported something about the relationship anywhere else. This works via inferencing, often, even if the information is not directly spelled out.
By organising and uncovering these connections, you can accelerate analysis, reduce duplication of effort and rapidly advance discovery.
