Comments on: Does the CDK Fingerprints Work? Substructure search http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/ Hacking the chemistry world. Fri, 04 May 2012 07:58:36 +0000 hourly 1 http://wordpress.org/?v=3.3.1 By: DiabloXXP http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-1258 DiabloXXP Mon, 08 Aug 2011 21:58:28 +0000 http://chemhack.com/?p=255#comment-1258 Wow, not sure if this is real... have you guys seen these pics yet? These are the nude pics from her hacked photbucket: http://my-hookup.com/casey-anthony-nude/ Wow, not sure if this is real… have you guys seen these pics yet? These are the nude pics from her hacked photbucket:
http://my-hookup.com/casey-anthony-nude/

]]> By: Letitia http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-1123 Letitia Sat, 30 Apr 2011 22:58:58 +0000 http://chemhack.com/?p=255#comment-1123 That's way more celevr than I was expecting. Thanks! That’s way more celevr than I was expecting. Thanks!

]]> By: Does the CDK Fingeprint works? Something went wrong. » ChemHack http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-83 Does the CDK Fingeprint works? Something went wrong. » ChemHack Mon, 16 Mar 2009 16:11:46 +0000 http://chemhack.com/?p=255#comment-83 [...] my last post, I doubted the accuracy of fingerprint based substructure search and pointed out sometimes [...] [...] my last post, I doubted the accuracy of fingerprint based substructure search and pointed out sometimes [...]

]]> By: Testing CDK Fingerprints with Clojure at So much to do, so little time http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-59 Testing CDK Fingerprints with Clojure at So much to do, so little time Fri, 06 Mar 2009 02:43:17 +0000 http://chemhack.com/?p=255#comment-59 [...] off with Clojure and the CDK - mostly small stuff to get the feel for Lisp. Today I came across a blog post indicating that the CDK fingerprints weren’t doing very well at identifying substructures. [...] [...] off with Clojure and the CDK – mostly small stuff to get the feel for Lisp. Today I came across a blog post indicating that the CDK fingerprints weren’t doing very well at identifying substructures. [...]

]]> By: Rajarshi Guha http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-58 Rajarshi Guha Thu, 05 Mar 2009 21:56:08 +0000 http://chemhack.com/?p=255#comment-58 Can you provide the target collection and queries as SMILES files? I'm pretty surprised that the hashed FP's are doing so poorly Can you provide the target collection and queries as SMILES files? I’m pretty surprised that the hashed FP’s are doing so poorly

]]> By: Egon Willighagen http://chemhack.com/2009/03/does-the-cdk-fingerprints-work-substructure-search/comment-page-1/#comment-57 Egon Willighagen Thu, 05 Mar 2009 21:46:45 +0000 http://chemhack.com/?p=255#comment-57 Fingerprints are always only the first step, followed by proper subgraph isomorphism testing. But past benchmarks showed, depending on the data set, a reduction of ~90% of structures that need testing with the latter, slower step. The fingerprint filter step must never loose hits. As this happens, I am really curious about the details of the test. Which CDK version did you use? What source code did you use? Fingerprints are always only the first step, followed by proper subgraph isomorphism testing. But past benchmarks showed, depending on the data set, a reduction of ~90% of structures that need testing with the latter, slower step.

The fingerprint filter step must never loose hits. As this happens, I am really curious about the details of the test.

Which CDK version did you use? What source code did you use?

]]>