[Product Releases]

[Blog]

Most recent post

[News]

Can we trust docking results?
Sept 2010

IBM Systems and Technology Group releases a white paper with eHiTS and Cell
Oct 2008

EPA's ToxCast^TM project will use SimBioSys' eHiTS as docking engine
Nov, 2007

[Events]

240th ACS
Aug 22-26, 2010
Boston, MA, USA
booth #945
see >> more

CLiDE:
Chemical Literature Data Extraction

Features and Benefits

Chemical databases are extremely useful tools for chemists involved in the design of potential drugs. Keeping these databases up to date requires the entry of newly published structures as well as structures found in old publications. In both cases, the information is often available in printed form. Entering this information by redrawing the structure with a computer program is a time consuming and error-prone process. A system capable of reading and understanding chemical drawings and which could extract the information necessary for the database would make the process faster and safer.

CLiDE is such a system.

Extracts chemical structure and text information from printed/scanned pages and stores the information in various forms (ChemDraw, MOL).
Also extracts reaction information. Reaction information can be entered into databases automatically, saving hours of redrawing.
Extracts generic structure informtation from graphics and text. CLiDE will expand condensed generic structures so they can be entered into your database either expanded or condensed.
Recognizes and extracts page layout information. Bibliographical information, such as title, author, etc., is conveniently extracted automatically.

The table below illustrates the features of CLiDE and CLiDE Lite and how they benefit the user:

*Features*	*Benefits*	*CLiDE*	*CLiDE* *Lite*
Extracts chemical structure information from printed/scanned pages and stores the information in various forms (e.g. MOL file, ChemDraw)	Printed structures do not have to be redrawn when cataloging them. Just scan it and recognize it with CLiDE. Makes registering, documenting, or publishing structures easier.
Extracts text from printed/scanned pages	Text does not have to be retyped, just scan it and recognise it with CLIDE.Saves hours of retyping.
Extracts reaction information	Reaction information can be entered into databases automatically. Saves hours of redrawing.
Extracts generic structure information from graphic and text	Expands condenses generic structures so can be entered into DB either expanded or condensed. Saves hours of structure searching.
Recognizes and extracts page layout information information	Bibliographical information (e.g. title, author etc.) is extracted automatically. Saves hours of cataloging.
Batch processing of many pages.	Submit to process many image files in one job. This saves times again.
Customer Support			*