From owner-chemistry@ccl.net Fri Jul 11 11:43:01 2008
From: "Iain Wallace iain.m.wallace * gmail.com" <owner-chemistry(!)server.ccl.net>
To: CCL
Subject: CCL: Estimating applicability of fingerprint model
Message-Id: <-37328-080711114039-5883-pH1IHqHGl2bNIq4kwaWcgw(!)server.ccl.net>
X-Original-From: "Iain Wallace" <iain.m.wallace{=}gmail.com>
Content-Type: multipart/alternative; 
	boundary="----=_Part_29212_610929.1215790402926"
Date: Fri, 11 Jul 2008 11:33:22 -0400
MIME-Version: 1.0


Sent to CCL by: "Iain Wallace" [iain.m.wallace!^!gmail.com]
------=_Part_29212_610929.1215790402926
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

Hi all,

I have built a model to classify compounds into two classes using the
Pipeline pilot Bayesian fingerprint classifier (ECFP_4 Fingerprints).   I
was wondering if anyone has any experience on how to estimate how well the
model I have built will transfer to other libraries? I know that I should
only apply the model to compounds drawn from a similar distribution, but I
have no idea how to what steps I should take to ensure that this criteria is
met.

For instance, I would like to score the Zinc database (all commercially
available compounds) to find new interesting molecules, and I am wondering
if anyone has any tips on problems I should look out for,

Thanks for alot for any advice

Iain

------=_Part_29212_610929.1215790402926
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

Hi all,<br><br>I have built a model to classify compounds into two classes using the Pipeline pilot Bayesian fingerprint classifier (ECFP_4 Fingerprints). &nbsp; I was wondering if anyone has any experience on how to estimate how well the model I have built will transfer to other libraries? I know that I should only apply the model to compounds drawn from a similar distribution, but I have no idea how to what steps I should take to ensure that this criteria is met.<br>
<br>For instance, I would like to score the Zinc database (all commercially available compounds) to find new interesting molecules, and I am wondering if anyone has any tips on problems I should look out for,<br><br>Thanks for alot for any advice <br>
<br>Iain<br><br>

------=_Part_29212_610929.1215790402926--