Re: [Rdkit-discuss] explicit valence exceeds atom degree for GetHashedAtomPairFingerprintAsBitVect when using standardiser

2018-04-12 Thread Rebecca Mackenzie - UKRI STFC
ken...@stfc.ac.uk> From: Greg Landrum <greg.land...@gmail.com> Sent: 12 April 2018 07:29 To: Mackenzie, Rebecca (STFC,DL,SC) <rebecca.macken...@stfc.ac.uk> Cc: rdkit-discuss@lists.sourceforge.net; Francis Atkinson <fran...@ebi.ac.uk> Subject: Re: [Rdkit-discuss] explicit val

Re: [Rdkit-discuss] explicit valence exceeds atom degree for GetHashedAtomPairFingerprintAsBitVect when using standardiser

2018-04-12 Thread Greg Landrum
Hi Rebecca, It looks like the standardiser modifies the molecule but does not update computed values like valences. If you call UpdatePropertyCache(), everything seems fine: In [22]: m = Chem.MolFromSmiles("C(=O)(c1ccc(cc1)O)O") In [23]: std_m = rules.run(m) In [24]:

[Rdkit-discuss] explicit valence exceeds atom degree for GetHashedAtomPairFingerprintAsBitVect when using standardiser

2018-04-11 Thread Rebecca Mackenzie - UKRI STFC
Hi there, I typically use python's standardiser (https://pypi.python.org/pypi/standardiser) when preparing any molecules for machine learning, and I have found the GetHashedAtomPairFingerprintAsBitVect as very good tool for input into support vector machines and neural networks. However,