Chapter 11, leftover active decoys
altayg opened this issue · 3 comments
altayg commented
Did you forget to drop the leftover active decoy molecules or did you left them as is deliberately?
After this ratio check, there is no further dropping for the 12 leftover active decoys:
charged = revised_decoy_df[revised_decoy_df["charge"] != 0]
charged.shape[0]/revised_decoy_df.shape[0] # 0.00263
charged.shape[0] # 12
PatWalters commented
The active molecules and decoy molecules are two different sets. The
reason that there are a few charged molecules left in the set is that
the NeutraliseCharges function does not have the appropriate SMARTS
patterns for neutralization of all of the molecules. When I looked at the
12 structures, it was either functionality like N-oxides or what appears to
be incorrect structures from the DUD-E database.
Pat
…On Thu, Sep 26, 2019 at 2:20 PM Goekman Altay ***@***.***> wrote:
Did you forget to drop the leftover active decoy molecules or did you left
them as is deliberately?
After this ratio check, there is no further dropping for the 12 leftover
active decoys:
charged = revised_decoy_df[revised_decoy_df["charge"] != 0]
charged.shape[0]/revised_decoy_df.shape[0] # 0.00263
charged.shape[0] # 12
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#15?email_source=notifications&email_token=AAVCVTKYWOV7BBSS7TAODNDQLT4QNA5CNFSM4I25NY7KYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HN6ZDYQ>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAVCVTJFAZUWUPXNMALZNQLQLT4QNANCNFSM4I25NY7A>
.
altayg commented
Would it not be better to remove them and not include in the model?
PatWalters commented
Probably, although I don't think it would make that much of a difference.
Pat
…On Fri, Sep 27, 2019 at 1:11 PM Goekman Altay ***@***.***> wrote:
Would it not be better to remove them and not include in the model?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#15?email_source=notifications&email_token=AAVCVTNSNYDRBF2F4FBM6JLQLY5FPA5CNFSM4I25NY7KYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD7ZRFQI#issuecomment-536023745>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AAVCVTINEZHTOQQJHY44OM3QLY5FPANCNFSM4I25NY7A>
.