Re: [Rdkit-discuss] Understanding and visualizing counts fingerprints using GetHashedMorganFingerprint

[Jan H. J. <jhj...@ch...>]

Here’s code to draw the on-bit fragments in the hashed Morgan fingerprints.

mol = Chem.MolFromSmiles('CCC')
bi = {}
cfp = AllChem.GetHashedMorganFingerprint(mol, 2, nBits=1024, bitInfo=bi)
on_bits = [x for x in bi]
prints = [(mol, x, bi) for x in on_bits]
Draw.DrawMorganBits(prints, molsPerRow=4, legends=[str(x) for x in on_bits])

On 2 Nov 2022, at 16.52, Brianna Greenstein <BL...@pi...<mailto:BL...@pi...>> wrote:


You don't often get email from bl...@pi...<mailto:bl...@pi...>. Learn why this is important<https://aka.ms/LearnAboutSenderIdentification>


Some people who received this message don't often get email from bl...@pi...<mailto:bl...@pi...>. Learn why this is important<https://aka.ms/LearnAboutSenderIdentification>

Hi, I had some questions about Morgan fingerprint counts. I used AllChem.GetHashedMorganFingerprint(mol, 2, nBits=2048) to get counts as descriptors for ML models. I am looking at the feature importance and some of these bits came up as important. I had a few questions on understanding these hashed fingerprints.


  1.  Are the structures the bits represent the same for GetHashedMorganFingerprint and GetMorganFingerprintasBitVect?

  1.  How can I visualize what a specific bit in the hashed morgan fingerprint looks like? Can I use DrawMorganBit to visualize it the same way I would for the normal fingerprint?


_______________________________________________
Rdkit-discuss mailing list
Rdk...@li...<mailto:Rdk...@li...>
https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Flists.sourceforge.net%2Flists%2Flistinfo%2Frdkit-discuss&amp;data=05%7C01%7Cjhjensen%40chem.ku.dk%7C03ef15818e8042dcc1e108dabd082573%7Ca3927f91cda14696af898c9f1ceffa91%7C0%7C0%7C638030139958745514%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C2000%7C%7C%7C&amp;sdata=Df42SquCavEVi8efFOKYIEYif8yW9baNhbf8%2BELDSmY%3D&amp;reserved=0