Relationships between scientific entities (such as genes or drugs) are often hidden in the biomedical literature.
Based on TERMite, TExpress is a semantic regular expression engine that identifies and extracts semantic patterns of biomedical entities, classes of an entity (e.g., kinase receptors), and biomedical verbs within sentences.
TExpress finds potential relationships in unstructured text and delivers valuable scientific insight.
We have curated a specific vocabulary of scientific verbs for TExpress, these can also be augmented/edited or replaced with your own collected as required.
Documents are first passed through TERMite, which identifies the individual entities in the text. Once marked up, they are then passed to TExpress to match semantic patterns defined in the search, as in the example below.
The patterns can be as broad or narrow as needed depending on the specificity of the entities used.
Get in touch with the team to learn more, or download the TExpress datasheet.
Key product highlights
-
Make Connections
Create simple patterns to find genes causing a disease, or phenotypes associated with pathways
-
Combine Patterns
Encapsulate multiple related patterns and business logic into bundles which can be run across the same data simultaneously
-
Flexible
Incorporate your own bespoke patterns and export outputs in a range of formats including JSON, RDF, XML, HTML and TSV
Want to learn more about TExpress?
Get in touch with us to find out how we can transform your data
Contact usUse cases
Comprehensive competitive intelligence monitoring in real time [Use case]
Most pharmaceutical companies struggle to maintain an up-to-date awareness of the latest biomedical research relevant to their own therapeutic programmes. Competitor intelligence monitoring typically involves a manual approach involving the time consuming, piecemeal review of a small range of data sources.
However, the exponentially growing amount of literature and increasingly diverse range of sources make it almost impossible to maintain a comprehensive and up-to-date understanding. The result is that the legacy approach to literature scanning is no longer practical.
SciBite’s resource-effective solution uses semantic analytics to reduce both the time and uncertainty involved in evaluating the vast body of research and news to track trends, gain early insight into potentially ground-breaking scientific advances.
Biomarker discovery in literature
[Use Case]
The identification and application of biomarkers in basic and clinical research is almost a mandatory process in any productive pipeline of a pharmaceutical organisation. Validated biomarkers play a crucial role in the prediction of clinical outcome and support the translation from candidate discovery to successful clinical treatment.
A wealth of valuable biomarker-related information is available in the biomedical literature. However, the process of discovering and validating new biomarkers depends on the ability to extract insight from this resource effectively.
SciBite uses semantic enrichment to unlock the value of unstructured text and simplify the identification of new potential biomarker leads from scientific text.
