Chemoinformatics has evolved over the last few decades into an important scientific discipline. Molecular Connections from its inception has been working with key industry players on critical aspects of Chemoinformatics – such as chemical structure representation, chemical reaction representation, property prediction, data analysis and mining, and synthesis design.
Chemical information extraction has also gained momentum as a parallel drug discovery process. Given that Lead identification  and optimization are major bottle necks in identifying new chemical entities. More than 40% of candidates in development fail due to insufficiency in ADMET profiles. It is difficult to conceive drug discovery programs that are independent of Chemical Information management. Molecular Connections has emerged as a key service provider to Pharma-Biotech industry in extracting vital information on structure activity relationship and ADMET to support their drug discovery research programs.
Molecular Connections Cheminformatics services include:
  • Annotation and development of novelty of the molecules/processes/chemical reactions with respect to the prior art from Patents
  • Chemical Structure Indexing from scientific literature (journals as well as patents) including 2D chemical structure and stereo chemical attributes
  • Technical abstract writing from Patents to enable customers to make critical decisions pertaining to their area of research and innovation
  • Automated extraction of Chemical terminologies from OCR process and manual review and corrections due to inaccuracies in the extraction process
  • We also provide expertise in handling of scientific literature from different languages including – Deutsch, French, Japanese, Chinese, Korean
  • Redrawing/creating abstract files of reaction information from published journal articles, patent documents and books along with the reaction scheme, reaction conditions, yields and catalysts
Molecular Connections Cheminformatics literature curation services for drug discovery include:
  • Annotation focussed on profiling compounds for SAR and ADME – Tox properties covering chemical structure, IUPAC name, Bio Assay, Target protein and Kinetic values
  • Annotation of Chemical compound with associated gene and protein and out linking it to the public domain databases
  • Annotating drug adverse effects from drug labels to build a knowledgebase adverse effects of drugs and other compounds

Select Case Studies

  • We custom built a reaction database for one of our clients with extracting information from journals and patent publications to enable researchers to plan and execute their experiments. Curation of non-English chemical patent publications is challenging, during the project we developed a workflow to maintain high quality levels in terms of content accuracy and contextual relevance, which is impossible with just machine translation although translation technology is constantly evolving.

Case Studies