From chemistry-request@www.ccl.net Sun Sep 6 14:25:25 1998 Received: from Lilly.com (inet.d48.lilly.com [40.33.1.1]) by www.ccl.net (8.8.3/8.8.6/OSC/CCL 1.0) with ESMTP id OAA19713 Sun, 6 Sep 1998 14:25:24 -0400 (EDT) Received: from LILLY.COM ([40.59.1.39]) by INET.D48.LILLY.COM (PMDF V5.1-10 #20835) with ESMTP id <01J1HKJJP8DS001G33@INET.D48.LILLY.COM> for chemistry@www.ccl.net; Sun, 6 Sep 1998 13:24:56 EST Received: from aammta1.d51.lilly.com by NEWMAN.D52.LILLY.COM (PMDF V5.1-10 #20835) with SMTP id <01J1HKJJ9QF00077FF@NEWMAN.D52.LILLY.COM> for chemistry@www.ccl.net; Sun, 06 Sep 1998 13:24:55 -0500 (EST) Received: by aammta1.d51.lilly.com(Lotus SMTP MTA Internal build v4.6.2 (651.2 6-10-1998)) id 05256677.006527A2 ; Sun, 06 Sep 1998 13:24:52 -0500 Date: Sun, 06 Sep 1998 13:24:45 -0500 From: David J Cummins Subject: CCL: seeking solubility data for model To: chemistry@www.ccl.net Message-id: <05256677.006525E0.00@aammta1.d51.lilly.com> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-disposition: inline X-Lotus-FromDomain: LILLY Hello, I need to build an aqueous solubility model. The first step is to construct a good training set. I need for the model to be useful for a wide variety of drug-like compounds, and thus my training set must be very heterogeneous. I've seen some data in a recent paper in JCICS vol 38 No. 3, 450-456, and another in the same issue, pages 489-496. I've also seen a training set in an older paper by G. Klopman. These make a fine start for a training set but they are mostly very small molecules. For my purposes I need some larger drugs and drug-like molecules, preferable SMILES and molar aqueous solubility. Does anyone know where I might find such data, or have such data to share? I'll post summaries to the list. Thanks! David J. Cummins Eli Lilly & Company Cummins_DJ@lilly.com