To make informed decisions on pursuing a gene or a protein as a promising drug target, biologists must build a complete picture of the clinical and preclinical landscape surrounding it. Only when they have correlated data on its genes and proteins with existing knowledge on drugs and compounds, can they form hypotheses about if and how the activity of a protein of interest can be modulated in a desirable way. With millions of publications, grants, clinical trials, patents, datasets and policy documents available, analysis can be slow, incomplete and therefore inaccurate. To reduce the risk of efficacy failure and take more drugs to market, Dimensions Life Sciences and Chemistry (Dimensions L&C) has created AI search functionality that not only allows scientists to quickly discover what published data is available, but also helps build new connections to improve research discovery.

Using Dimensions L&C to build a picture of target drug landscape

Unlike research discovery tools which rely on manual curation to index documents and extract key information, Dimensions L&C uses up-to-the-minute semantic, co-occurrence and chemical compound search functions. As one of the world’s largest available databases, it contains ontologies of 40 million concepts with 100 million synonyms including 35M compounds with 85M synonyms; 123K drugs with 230K synonyms; and 850K genes and proteins with 6M synonyms.

Dimensions L&C was built to give scientists evidence-based confidence, as they are able to access a comprehensive landscape view of disease and drug mechanisms, drug targets, chemical compounds and drug combinations.

Watch our video to see how you can easily identify the drug landscape for specific targets.

Identifying potential modulators for target activity through Semantic and Co-occurrence Search

Semantic Co-occurrence Analysis generates insights about a disease of interest including the molecular mechanisms that cause it. For biologists, the increased search functionality allows fast identification of the target across millions of grants, patents, and publications; and thousands of clinical trials and drug labels.

Concepts and terms are organized in an Ontological Tree, and users can easily investigate specific genes and proteins, diseases and many more areas of interest. It can help to identify potential modulators, as well as further therapies that could be used in combinations or sequences with drugs.

Co-occurrence analysis allows for deeper insights into multiple concepts. The system searches instances where concepts of interest are mentioned in close textual proximity, which usually suggests a connection. Biologists can specify a drug, a chemical compound or both, and quickly discover a list of original sources in which they occurred together with a target of interest. Text snippets enable the user  to explore the context, as highlights clearly show where the mentions occur, reducing reading time. Users can also link through to the original source material to investigate in detail.

Empowered with the tools to make confident, data-driven R&D decisions on which drugs or compounds have the potential to hit a target of interest, biologists can avoid and reduce later stage failures in clinical trials and ensure a market share.

To learn more about how Dimensions L&C can quickly map the drug landscape for specific targets, request a consultation today.