Skip to content

Main#344

Merged
priyankvyas merged 16 commits intoreleasefrom
main
Mar 13, 2026
Merged

Main#344
priyankvyas merged 16 commits intoreleasefrom
main

Conversation

@martinaoliver
Copy link
Contributor

No description provided.

sgraf2002 and others added 13 commits March 3, 2026 15:16
* changed to tf on ensembl

* added info on genes expressed and mapped

* logger

* github pr rerun checks

* Bump version to 1.8.1

---------

Co-authored-by: maxime <maxime@helical-ai.com>
Included embeddings for the following species:
* canis_lupus_familiaris
* macaca_fascicularis
* rattus_norvegicus
* sus_scrofa

as per [Ensembl](https://ftp.ensembl.org/pub/current/fasta/)
Fixing typo in ESM-2 configs on S3 for 4 additional species
This change allows transcriptformer
to accept multiple vocabularies
of gene embeddings for out-of-sample species
add function to get all gene ranks from adata object using rve
Current implementation permutes indices of special tokens:
```
[START]: 2 -> 1
[END]: 3 -> 2
[RD]: 4 -> 3
[CELL]: 5 -> 4
[PAD]: 1 -> 5
[MASK]: 6 -> 6
```
This fix makes sure we preserve the indices
of the special tokens when performing vocabulary surgery.
@dmiv-helical
Copy link
Contributor

Please do not squash when merging

@priyankvyas priyankvyas marked this pull request as ready for review March 13, 2026 18:14
@priyankvyas priyankvyas merged commit 46e341d into release Mar 13, 2026
10 checks passed
Copy link
Contributor

@dmiv-helical dmiv-helical left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This one is huge because we have to replay some of the history due to a previous squash

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

6 participants