BugFix: CLI grn - output of list of adjacencies is TSV or CSV (default) based on provided file extension.
0.9.9
New functionality: support for multiple embeddings then exporting to loom file.
0.9.8
New functionality: minimal integration of SCENIC with scanpy (https://scanpy.readthedocs.io/en/latest/). The approach is fully explained in the Jupyter notebook: https://github.com/aertslab/pySCENIC/blob/master/notebooks/pySCENIC%20-%20Integration%20with%20scanpy.ipynb
0.9.7
- BugFix: Changed load_adjacencies to use fixed column types to avoid type errors (e.g. 'nan' as gene name in D. melanogaster incorrectly got interpreted as a floating point number).
0.9.6
- Added new Singularity file incorporating version tags. - Small correction in documentation on Docker. - BugFix: Incorrect warning message about number of genes being present in expression matrix when calculating recovery (based on 57).
0.9.5
Fixing versions for pandas and dask because github issues: - https://github.com/aertslab/pySCENIC/issues/51 - https://github.com/aertslab/pySCENIC/issues/45
Fixed an issue where the regulon assignment matrix was not being added to row attributes (loom output).
Changed lp.connect to read-only mode when importing expression matrix from a loom file.