v0.4.0

Bug fixes:

• Fixed compatibility with latest version of anndata.
• Fixed trainers when "use_cell_type" is used, see this PR.
• Allowed CUDA_VISIBLE_DEVICES to override autodevice.

New features:

• A general anchored guidance graph construction function anchored_guidance_graph.
• Add function classify_data to retrieve the cell type classification from compatible models.
• Add support for CITE-seq data via NBMixture, see this PR.
• Add preliminary support for region-based ATAC-Methyl integration.
• Added skip_balance option for `fit_SCGLUE``.

v0.3.2

Bug fixes:

• Fixed "real_cross" loss in PairedSCGLUETrainer and SCCLUETrainer.

v0.3.1

Bug fixes:

• Fixed NaN loss in PairedSCGLUETrainer.
• Restored rna_anchored_prior_graph as a deprecated function (to be replaced by rna_anchored_guidance_graph).

v0.3.0

New features:

• New tutorial and functions for regulatory inference (Resolves #15, #41).
• New tutorial for training on partially paired data (Resolves #24).

Enhancements:

• Modularized scglue.dx.integration_consistency to allow for non-raw-count input (Resolves #30).
• Added documentation translation in Chinese.

v0.2.3

Minor improvements and bug fixes

Bug fixes:

• Data frame in obsm no longer triggers an error during model training (Resolves #32).

Enhancements:

• scglue.data.transfer_labels uses a new strategy with SNN-based estimation of transfer confidence (Resolves #23).
• Allow setting custom bedtools path via scglue.config.BEDTOOLS_PATH (Resolves #22).

v0.2.2

Minor improvements and bug fixes

Bug fixes:

• Device detection is now more reliable (Resolves #17).

Enhancements:

• Custom encoders and decoders can now be registered without changing package code (Resolves #14).

v0.2.1

Minor improvements and dependency fixes

v0.2.0

New features

• Added fit_SCGLUE function to simplify model training
  • Incorporates weighted adversarial alignment by default, with increased robustness on datasets with highly-skewed cell type compositions
• Added support for batch effect correction, which can be activated by setting use_batch in configure_dataset
• Added a model diagnostics metric “integration consistency score”

Enhancements

Support for training directly on disk-backed AnnData objects, scaling to almost infinite number of cells

Bug fixes

Fixed a bug where the graph dataset was not shuffled across epochs

Experimental features

• A partially paired GLUE model for utilizing paired cells whenever available
• The CLUE model that won the NeurIPS 2020 competition in multimodal integration (modality matching task) is here!

v0.1.1

First public release