From chemistry-request@server.ccl.net  Tue Mar 21 10:32:56 2000
Received: from mcdc-us-smtp4.cdc.gov (mcdc-us-smtp4.cdc.gov [198.246.96.75])
	by server.ccl.net (8.8.7/8.8.7) with ESMTP id KAA10103
	for <chemistry@ccl.net>; Tue, 21 Mar 2000 10:32:56 -0500
Received: from mcdc-us-bis.cdc.gov (mcdc-us-bisgate.cdc.gov [198.246.96.18]) by mcdc-us-smtp4.cdc.gov with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2650.10)
	id HLVG7NRY; Tue, 21 Mar 2000 10:30:38 -0500
Received: by mcdc-us-bis.cdc.gov with Internet Mail Service (5.5.2650.10)
	id <HMAX2ZV8>; Tue, 21 Mar 2000 10:30:52 -0500
Message-ID: <CF5EBE47968BD111BEB70000F840E60C044A3051@mcdc-mtn-1.cdc.gov>
From: "Poda, Gennady" <gep4@cdc.gov>
To: "'chemistry@ccl.net'" <chemistry@ccl.net>
Subject: CCL: QSAR software
Date: Tue, 21 Mar 2000 10:30:22 -0500
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.5.2650.10)
Content-Type: text/plain;
	charset="iso-8859-1"


Dear CCLers,

I am trying to collect information about QSAR software alternative to
well-known suites of Tripos and Oxford Molecular (mainly chemometrics,
freeware or for a reasonable price). 

So I would appreciate if you could site any competitive program (web site?)
which can do good QSAR work (NNs, GAs, PLS, GOLPE, etc.) with a good
descriptor set, variable selection/pruning/data preprocessing and model
validation (LOO, cross-validation, etc.). Any hints will be highly
appreciated. 

I will post a summary.

Thanks a lot for your participation.

Gennady Poda

NIOSH/CDC
E-mail: gep4@cdc.gov