Inferelator v0.6.3

Inferelator v0.6.3 July 8, 2024

Bug Fixes:

• Removed import-time setting environment variables for threading control. Threading is now handled directly by parallelization (e.g. through joblib).

• Updated code to address breaking changes in Numpy 2.0.0 and Scipy 1.14.0

v0.6.1

Inferelator v0.6.1 January 3, 2023

New Functionality:

• Extended support for mRNA velocity & decay calculations
• Added new experimental TFA modules

Code Refactoring:

• Workflow, ResultProcessor, and InferelatorData restructured for readability and clearer commenting

Bug Fixes:

• Slicing individual gene data returns numpy vector instead of anndata view
• Corrected several deprecated pandas calls to eliminate FutureWarnings

v0.6.0

Inferelator v0.6.0 September 14, 2022

New Functionality:

• Support for grouping arbitrary genes from multiple tasks into learning groups
• Workflow to learn homology groups together
• Workflow to explicitly incorporate velocity and decay into learning
• Added support for batching parallelization calls to reduce overhead when data is relatively small

Code Refactoring:

• Refactored multi-task learning to parameterize tfs and genes for each task
• Refactored parallelization around joblib & dask
• Removed pathos and replaced with joblib
• Optimized StARS-LASSO by replacing standalone LASSO with lasso_path

Bug Fixes:

• Fixed several messages to be more informative
• use_no_prior is appropriately applied in multitask learning

v0.5.8

Bug Fixes:

• Corrected combining multi-task gene and tf labels

v0.5.7

New Functionality:

• Added support for numba acceleration of AMuSR with .set_run_parameters(use_numba=True) (PR #46)

Code Refactoring:

• Updated example scripts
• Removed deprecated KVS multiprocessing and associated code

Bug Fixes:

• Gene labels are included as the first column of the produced confidences TSV file by default
• Matplotlib backend selection checks for non-interactive mode

v0.5.6

Inferelator v0.5.6 August 16, 2021

New Functionality:

• Added code to randomly generate noise in prior with .set_shuffle_parameters(add_prior_noise=None)
• Added in-workflow benchmarks for CellOracle and pySCENIC

Code Refactoring:

• Minor changes to matplotlib interface
• Improved testing for multitask workflows
• Improved error messaging around prior and gold standard
• Switch from Travis.ci to GitHub Actions for continuous integration

v0.5.5

Merge pull request #41 from flatironinstitute/dev

v0.5.5

v0.5.4

Merge pull request #40 from flatironinstitute/dev

v0.5.4

v0.5.3

Merge pull request #38 from flatironinstitute/dev

v0.5.3

v0.5.2

Add vscode