Marta Stepniewska-Dziubinska
Marta Stepniewska-Dziubinska
It's an old issue, but maybe this answer will useful for someone. It's probably related to output filtering - by default sequences with 90% pairwise identity are removed (see `-id`...
Happy to hear that! I created a PR with my changes ( #6 )
Update: @mwojcikowski compiled rdkit with numpy=1.12, and indeed it works both with 1.12 and 1.13
Yes, I'm using linux. If I understood correctly, this line: https://github.com/rdkit/conda-rdkit/blob/7e80fec107a1dd887ae24fdcf9878c08f7c80c8f/rdkit/meta.yaml#L25 should be `numpy ==1.12`. When its >=1.12, conda can use the most recent version (1.13) to build this package...
@ko3n1g unfortunately not - `Optional_L2_NeMo_2_EVAL` was added in this PR and it's failing, I need to fix it first. Also I added tests to `cicd-main-export-deploy` which was skipped. Is there...
> CI has passed, feel free to merge I had to resolve conflicts but I think we're good to go now
Closing (changes merged in #13627 )