Re: [Cdk-devel] BCUT Validation

[<ten...@gm...>]

hi,

that would be great Uli. Maybe you can calculate the BCUT for the ZINK
testset with Dragon and MOE, I will make the same with CDK BCUT. When you
send me the stuff (csv file: smile, values), I can do the comparison
(center, scale, PCA). Dragon uses indeed other charges, but we should look
if we are able to get at least a similar grouping in the BCUT space.
One problem I already observe with CDK BCUTs are extremly (infinitive) high
values (eg 10e+23).

best regards
Christian

> --- Ursprüngliche Nachricht ---
> Von: Uli Fechner <u.f...@ch...>
> An: cdk...@li...
> Betreff: Re: [Cdk-devel] BCUT Validation
> Datum: Fri, 31 Mar 2006 15:18:45 +0200
> 
> To my best knowledge, nobody has validated the BCUT descriptors against 
> another implementation. May be very intersting though!
> 
> If you do need any help (we have dragon here and MOE as comparison 
> implementations) I would very much appreciate it to support such a 
> comparison study.
> 
> Uli
> 
> ten...@gm... wrote:
> > hi,
> > 
> > has someone validated the CDK BCUT against another BCUT calculating
> program
> > like Dragon to check if the *space* descripted is similar?
> > 
> > 
> > best regards
> > Christian
> > 
> 
> 
> -------------------------------------------------------
> This SF.Net email is sponsored by xPML, a groundbreaking scripting
> language
> that extends applications into web and mobile media. Attend the live
> webcast
> and join the prime developer group breaking into this new coding
> territory!
> http://sel.as-us.falkag.net/sel?cmd=lnk&kid=110944&bid=241720&dat=121642
> _______________________________________________
> Cdk-devel mailing list
> Cdk...@li...
> https://lists.sourceforge.net/lists/listinfo/cdk-devel
> 

-- 
E-Mails und Internet immer und überall!
1&1 PocketWeb, perfekt mit GMX: http://www.gmx.net/de/go/pocketweb