Are you ready for "in litero" drug discovery?

"Chemistry is, and has been for many years, one of the most information-rich academic disciplines. The very first journal devoted to chemistry was Chemisches Journal, which was published 1778-84 and then, under the name of Chemische Annalen, till 1803. The growth in the chemical literature during the nineteenth century led to a recognition of the need for comprehensive abstracting and indexing services for the chemical sciences."
---Peter Willett


Reverse Informatics provides specialized solution for knowledge generation in drug discovery. We facilitate the integration of chemistry and biology space to address the areas of chemical biology/chemogenomics and tackle target hopping and scaffold morphing challenges.


We analyze the scientific literature for identifying potential links between biological and chemical information to support researchers in satisfying two fundamental needs:


Finding relevant documents that contain information about chemical compounds and biological concepts of interest (information retrieval task). The focus is on the comprehensive identification of biological and chemical entities in the text.

Finding specific information about chemicals that are related to the biological concepts by an explicit relationship from many documents (information extraction task). This deals with the identification and extraction of explicit relationships between chemical and biological entities.


Reverse Informatics has the niche skill set of extracting chemical structural information from the literature. We convert the chemical names and identifiers into appropriate chemical structure representation which is ideal for chemists and organizations to retrieve chemical information.


Molecular biology and genome research profited immensely from the open access to sequence information and annotations. Unlike them, the world of chemistry, particularly the chemistry of bioactive molecules—is much more restricted. Chemical information is generally more proprietary than biological information. Realizing the need of our clients we custom build databases based on their interest!


We follow industry best practices in database development and project management. Our databases have high interconnectivity and interoperability achieved by normalization of data. Our method of building comprehensive guidelines and control vocabulary for a given project combined with quality assurance practices ensure delivery of robust systems.


In-depth, comprehensive, accurate and actionable data is our Offer

Bioactivity Database : Small molecules, big opportunities

Bioactivity databases contain a target module where basic biological data and external identifiers are stored. Targets are categorized as proteins or nucleic acids. A protein target can be an enzyme, a receptor, an ion channel, a transporter, a kinase, protease or any other enzyme. Enzymes can be classified in six major biochemical classes: oxidoreductases, transferases, hydrolases, lyases, isomerases, and ligases; receptors may be categorized as G protein-coupled receptors (GPCRs), nuclear receptors (NRs), integrins, and so on, each with its own subclass hierarchy.


Assignee Centric Database : If only we knew what we know

Every pharmaceutical company's knowledge is stored in millions of pages of scientific literature. In the global scenario of mergers and acquisitions, it is nearly impossible for a scientist in the company to track what research has been done before. In the competitive environment, the decision makers need to keep track of every other individual company's performance in both science and business. We build easily computable and navigable databases focusing on a particular company. Irrespective to the biological targets and disease areas, we build databases from all the patents owned by a particular company including non-patent literature thereby preventing the scientist from committing the most common and costliest error in scientific research which is duplication of research.

Custom Curation : We help you in getting the background knowledge ‘quick and simple’

If you have the idea for a concept, Parthys Reverse Informatics has the process, expertise and resources to envision and co-create a great product. We create products based on your focus like gene variants, pathway curation or ADME information which is curated and customized to your needs, budget and time line. May be you would like to know the list of in force patents on kinase inhibitors, or need to know the list of compounds that are reported to be interacting with GPCRs, or interested in the bioactivity, synthetic methodology, pharmacology and toxicology/metabolism collections generally derived from the primary literature, journals and patents. We make it easier for you to find the information in the context of your work.