Yakov Pechersky

A new paper came out: https://arxiv.org/abs/1703.01925 They were able to implement a VAE that autoencodes the SMILES grammar as a context-free grammar, which is a pretty good approximation. They improved...

Try Gomez-Bombarelli's TerminalGRU

4

I was looking to see whether the paper's authors had any draft code for the model they describe, to check whether they did something differently. I found that R GB...

fix: installing wheel from trailing slash url

6

# Pull Request Check List Resolves: n/a Provide a step-by-step description of the suggested enhancement in as many details as possible. Currently, the `poetry add ...` code looks for wheels...

Support allenes in canonicalizing double bonds, fixes #7044

3

#### Reference Issue Fixes #7044 #### What does this implement/fix? Explain your changes. During canonicalization of double bonds, neighbor bonds have to be found to correctly label the stereochem. During...

Parasubstituted chiral cyclobutyl causes "zero final chiral volume" warnings depending on 2D coords

2

**Describe the bug** An exported SDF from a parasubstituted chiral cyclobutyl raises an ambiguous stereochemistry warning, but only under some 2D coordinates. I thought it might be due to a...

Canonicalize shifts double bond out of conjugated system

9

**Describe the bug** The TautomerEnumerator.Canonicalize is creating a tautomer that is moving a double bond from out of a conjugated system further into a ring. This tautomer is not corroborated...

Double bond stereo is retained in terminal olefin if a single explicit hydrogen is included

1

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** ``` from rdkit import Chem smis = [ "C=CCC", "CCC=C", "CCC=C([H])", "CCC=C([H])[H]", "CCC=C[H]", "CC/C=C([H])/[H]", "CC/C=C/[H]",...

**Describe the bug** The output of `Canonicalize` is clearing double bond stereo that I set manually via the API. This does not happen if the input molecule was read in...

**Describe the bug** Two molecules drawn in ChemDraw, then saved as SDF generate different (opposite) chiral tags. This seems to stem from a difference in atom index order. **To Reproduce**...

**Describe the bug** On molecules (V3K input) where the atoms aren't indexed from 1, stereo groups are not found. Or more precisely, they _are_ found, but only if the atom...