subject:"\[Rdkit\-devel\] Two 'Labute' descriptors seem to be always returning 0.0"

Re: [Rdkit-devel] Two 'Labute' descriptors seem to be always returning 0.0

2018-03-15 Thread Greg Landrum

Hi Jeff,

On Thu, Mar 15, 2018 at 10:26 PM, jeff godden  wrote:
>
>
> First and foremost thank you for your excellent offering of a singularly
> useful set of molecular descriptors!
>

Thanks for the kind words. :-)

> As one of the authors cited by Dr Labute (http://www.chemcomp.com/journ
> al/vsadesc.htm)
> ,
> i've appreciated RDKit's implementation of the "Labute descriptor" set.
> So i've noticed that two particular descriptors in that set, specifically
> SlogP_VSA9 and SMR_VSA8, appear to always return a value of 0.0 no matter
> which of a
> substantial 
> set of small molecules are tested via:
>
> from rdkit.Chem import Descriptors
> Descriptors.SlogP_VSA9(molecule)
> Descriptors.SMR_VSA8(molecule)
>

Let's look at the first one. SlogP_VSA9 is the sum of the VSA contributions
of atoms whose contribution to SlogP falls into bin 9. In the case of the
RDKit this is means an atomic SlogP contribution of between 0.3 and 0.4 (I
believe that this is the same as the definition in the original paper. This
RDKit bins are not always the same as the original publication, in this
case they are). So we need to look for atom types that have an SlogP
contribution between 0.3 and 0.4. Curiously, there don't seem to be any of
these. Going back to the original Wildman and Crippen paper (the source of
these values), there aren't any there either. This is "a bit" strange since
the Labute article says that they picked the bins in order to have evenly
distributed values.

So I don't think you're doing anything wrong; there's an oddity in the
definition of the bins and it looks like that descriptor is basically
always going to be zero. Thanks for pointing it out.

Since I have found the various "MOE like" descriptors to be quite useful in
the past, it's worth considering doing another version of them where the
bin definitions have been adjusted based on a larger set of molecules.
Something to think about for a future version...

Thanks for the great question,
-greg

>
> All other descriptors i've tried seem to produce sensible results (with
> those same molecules)
>
> Of course it's always possible that it's something i've mis-coded.  I'm
> attaching a simple python program which returns the anomalous descriptor
> values for me.
>
> Thank you very much for all your efforts!
> --
> jeff godden
>
>
> 
> --
> Check out the vibrant tech community on one of the world's most
> engaging tech sites, Slashdot.org! http://sdm.link/slashdot
> ___
> Rdkit-devel mailing list
> Rdkit-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/rdkit-devel
>
>
--
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot___
Rdkit-devel mailing list
Rdkit-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/rdkit-devel

[Rdkit-devel] Two 'Labute' descriptors seem to be always returning 0.0

2018-03-15 Thread jeff godden

Dear RDKit Developers
,


First and foremost thank you for your excellent offering of a singularly
useful set of molecular descriptors!

As one of the authors cited by Dr Labute (
http://www.chemcomp.com/journal/vsadesc.htm)
,
i've appreciated RDKit's implementation of the "Labute descriptor" set.  So
i've noticed that two particular descriptors in that set, specifically
SlogP_VSA9 and SMR_VSA8, appear to always return a value of 0.0 no matter
which of a
substantial 
set of small molecules are tested via:

from rdkit.Chem import Descriptors
Descriptors.SlogP_VSA9(molecule)
Descriptors.SMR_VSA8(molecule)

All other descriptors i've tried seem to produce sensible results (with
those same molecules)

Of course it's always possible that it's something i've mis-coded.  I'm
attaching a simple python program which returns the anomalous descriptor
values for me.

Thank you very much for all your efforts!
-- 
jeff godden
#!/usr/bin/python
# output some Labute descriptors via RDKit
from rdkit import Chem
from rdkit.Chem import Descriptors
import sys

if len(sys.argv) < 2:
print("need an SDF filename on the commandline.")
sys.exit(-1)

# Labute descriptors function pointers
dl = { 'SlogP_VSA1' : Descriptors.SlogP_VSA1, 'SlogP_VSA2' : Descriptors.SlogP_VSA2,
   'SlogP_VSA3' : Descriptors.SlogP_VSA3, 'SlogP_VSA4' : Descriptors.SlogP_VSA4,
   'SlogP_VSA5' : Descriptors.SlogP_VSA5, 'SlogP_VSA6' : Descriptors.SlogP_VSA6,
   'SlogP_VSA7' : Descriptors.SlogP_VSA7, 'SlogP_VSA8' : Descriptors.SlogP_VSA8,
   'SlogP_VSA9' : Descriptors.SlogP_VSA9, 'SlogP_VSA10' : Descriptors.SlogP_VSA10,
   'SlogP_VSA11' : Descriptors.SlogP_VSA11, 'SlogP_VSA12' : Descriptors.SlogP_VSA12,
   'SMR_VSA1' : Descriptors.SMR_VSA1, 'SMR_VSA2' : Descriptors.SMR_VSA2,
   'SMR_VSA3' : Descriptors.SMR_VSA3, 'SMR_VSA4' : Descriptors.SMR_VSA4,
   'SMR_VSA5' : Descriptors.SMR_VSA5, 'SMR_VSA6' : Descriptors.SMR_VSA6,
   'SMR_VSA7' : Descriptors.SMR_VSA7, 'SMR_VSA8' : Descriptors.SMR_VSA8,
   'SMR_VSA9' : Descriptors.SMR_VSA9, 'SMR_VSA10' : Descriptors.SMR_VSA10,
   'PEOE_VSA1' : Descriptors.PEOE_VSA1, 'PEOE_VSA2' : Descriptors.PEOE_VSA2,
   'PEOE_VSA3' : Descriptors.PEOE_VSA3, 'PEOE_VSA4' : Descriptors.PEOE_VSA4,
   'PEOE_VSA5' : Descriptors.PEOE_VSA5, 'PEOE_VSA6' : Descriptors.PEOE_VSA6,
   'PEOE_VSA7' : Descriptors.PEOE_VSA7, 'PEOE_VSA8' : Descriptors.PEOE_VSA8,
   'PEOE_VSA9' : Descriptors.PEOE_VSA9, 'PEOE_VSA10' : Descriptors.PEOE_VSA10,
   'PEOE_VSA11' : Descriptors.PEOE_VSA11, 'PEOE_VSA12' : Descriptors.PEOE_VSA12,
   'PEOE_VSA13' : Descriptors.PEOE_VSA13, 'PEOE_VSA14' : Descriptors.PEOE_VSA14 }

a = dl.keys()

print('{0:13s} {1:7s} '
  '{2:12s} {3:12s} {4:12s} {5:12s} {6:12s} {7:12s} {8:12s} {9:12s} '
  '{10:12s} {11:12s} {12:12s} {13:12s} {14:12s} {15:12s} {16:12s} '
  '{17:12s} {18:12s} {19:12s} {20:12s} {21:12s} {22:12s} {23:12s} '
  '{24:12s} {25:12s} {26:12s} {27:12s} {28:12s} {29:12s} {30:12s} '
  '{31:12s} {32:12s} {33:12s} {34:12s} {35:12s} {36:12s} {37:12s}'.format('name', 'mw', *a))

with open(sys.argv[1], 'rb') as fin: # 'rb' rdkit wants this to be bytes *sigh*
mols = Chem.ForwardSDMolSupplier(fin)
for m in mols:
name = m.GetProp('_Name') # s
mw = Descriptors.MolWt(m) # f
a = []
for k, f in dl.items():
a.append(f(m))
print('{0:13s} {1:7.3f} '
  '{2:12.6f} {3:12.6f} {4:12.6f} {5:12.6f} {6:12.6f} {7:12.6f} {8:12.6f} {9:12.6f} '
  '{10:12.6f} {11:12.6f} {12:12.6f} {13:12.6f} {14:12.6f} {15:12.6f} {16:12.6f} '
  '{17:12.6f} {18:12.6f} {19:12.6f} {20:12.6f} {21:12.6f} {22:12.6f} {23:12.6f} '
  '{24:12.6f} {25:12.6f} {26:12.6f} {27:12.6f} {28:12.6f} {29:12.6f} {30:12.6f} '
  '{31:12.6f} {32:12.6f} {33:12.6f} {34:12.6f} {35:12.6f} {36:12.6f} {37:12.6f}'.format(name, mw, *a))

# import pandas as pd
# d = pd.read_fwf('data')
# for k in d.keys():
# if 'name' not in k:
# print(k, d[k].mean())

# output from 3133 'random' ZINC database molecules
## descriptor	mean
# mw		319.9400134014041
# SlogP_VSA1	9.619846179961822
# SlogP_VSA2	34.997968996171075
# SlogP_VSA3	9.793027915762599
# SlogP_VSA4	6.049321886407102
# SlogP_VSA5	25.947096066368807
# SlogP_VSA6	32.45248890906195
# SlogP_VSA7	0.7908396506062566
# SlogP_VSA8	4.296596145181884
# SlogP_VSA9	0.0
# SlogP_VSA10	4.070114919272454
# SlogP_VSA11	2.3151243225909495
# SlogP_VSA12	4.265721061263566
# SMR_VSA1	12.63901541544354
# SMR_VSA2	0.25907870899808505
# SMR_VSA3	10.056625507019914
# SMR_VSA4	2.714953877153796
# SMR_VSA5	25.574662986917733
# SMR_VSA6	19.44462612635612
# SMR_VSA7	44.14966515762617
# SMR_VSA8	0.0
# SMR_VSA9	4.360574342054924
# SMR_VSA10	15.398944225590286
# PEOE_VSA1	12.060297876515577
# PEOE_VSA2	6.086653529674543
# PEOE_VSA3	5.443402438098357
# PEOE_VSA4	2.052723992022967
# PEOE_VSA5	1.953408211550721
# PEOE_VSA6	18.40846272878091
# PEOE_VSA7

Re: [Rdkit-devel] Two 'Labute' descriptors seem to be always returning 0.0

[Rdkit-devel] Two 'Labute' descriptors seem to be always returning 0.0

2 matches

Site Navigation

Mail list logo

Footer information