LLM Module

• Added GeneFromer, scGPT, scFoundation, UCE, CellPLM to call directly in OmicVerse.

Pl Module

• Optimized the visualization effect of embedding.
• Added ov.pl.umap, ov.pl.pca, ov.pl.mde, and ov.pl.tsne

Pl Module

• Optimated the plot effect of ov.pl.box_plot
• Optimated the plot effect of ov.pl.volcano
  Optimated the plot effect of ov.pl.violin
• Added beautiful dotplot than scanpy (#318)
• Added the similar visualization function of CellChat. (#313)

Space Module

• Added 3D cell-cell interaction analysis in COMMOT (#315)

Single Module

• Fixed the error of pathway_enrichment. (#184)
• Added SCENIC module with GPU-accerlate. (#331)

utils Module

• Added scICE to calculate the best cluster (#329)

Single Module

• Fixed some error of ov.single.lazy.
• Fixed the format of ov.single.generate_scRNA_report
• Updated some functions of palantir
• Added CellOntologyMapper to map cell name.

CellOntologyMapper is a very useful function. Hopefully it would be help for your job.

Tutorial of CellOntologyMapper: https://omicverse.readthedocs.io/en/latest/Tutorials-single/t_cellmatch/

Added cpu-gpu-mixed to accelerate the analysis of scrna-seq using GPU.
Changed the logo presentation of Omicverse to ov.plot_set

Bulk Module

• Added limma, edgeR in different expression gene analysis. (#238)
• Fixed the version error of DEseq2 analysis.

Single Module

• Added lazy function to calculate all function of scrna-seq (#291)
• Added generate_scRNA_report and generate_reference_table to generate the report and reference (#291) (#292)
• Fixed geneset_prepare not being able to read gmt not split by \t\t (#235) (#238)
• Added geneset_aucell_tmp,pathway_aucell_tmp,pathway_aucell_enrichment_tmp to test the chunk_size (#238)
• Added data enhancement of Fate
• Added plot_atlas_view_ov in VIA
• Fixed an error when the matrix is too large in recover_counts.
• Added forceatlas2 to calculate the X_force_directed.
• Added milo and scCODA to analysis different celltype abundance.
• Added memento to analysis different gene expression.

Space Module

• Added GASTON to learn a topographic map of a tissue slice from spatially resolved transcriptomics (SRT) data (#238)
• Added super kwargs in plot_tensor_single of STT.
• Updated COMMOT using GPU-accerlate

Plot Module

• Added dotplot_doublegroup to visual the genes in doublegroup.
• Added transpose argument of cpdb_interacting_heatmap to transpose the figure.
• Added calculate_gene_density to plot the gene's density.

v 1.6.9

PP Module

• Added recover_counts to recover counts after ov.pp.preprocess
• removed the lognorm layers added in ov.pp.pca

Single Module

• Added MultiMap module to integrate multi species
• Added CellVote to vote the best cells
• Added CellANOVA to integrate samples and correct the batch effect
• Added StaVia to calculate the pseudotime and infer trajectory.

Space Module

• Added ov.space.cluster to identify the spatial domain
• Added Binary for spatial cluster
• Added Spateo to calculate the SVG

Bulk Module

• Fixed the error of log_init in gsea_obj.enrichment (#184)
• Added ax argument to visualize the geneset_plot

Space Module

• Added CAST to integrate multi slice
• Added crop_space_visium in omicverse.tl to crop the sub area of space data

Pl Module

• Added legend argument to visualize the cpdb_heatmap
• Added text_show argument to visualize the cellstackarea
• Added ForbiddenCity color system

Space Module

• Added n_jobs argument to adjust thread in extenel.STT.pl.plot_tensor_single
• Fixed an error in extenel.STT.tl.construct_landscape
• Updated the tutorial of COMMOT and Flowsig

Pl Module

• Added legend_awargs to adjust the legend set in pl.cellstackarea and pl.cellproportion

Single Module

• Fixed the error of get_results and get_results_rfc in cNMF module. (#143) (#139)
• Added sccaf to obtain the best clusters.
• Fixed the .str error in cytotrace2 (#146)

Bulk Module

• Fixed the import error of gseapy in bulk.geneset_enrichment
• Optimized code logic for offline enrichment analysis, added background parameter
• Added pyWGCNA package replace the raw calculation of pyWGCNA (#162)

Bulk2Single Module

• Remove _stat_axis in bulk2single_data_prepare and use index instead of it (#160).

PP Module

• Fixed a return bugs in pp.regress_and_scale (#156)
• Fixed a scanpy version error when using ov.pp.pca (#154)

Pl Module

• Fixed the 'celltyep_key' error of ov.pl.cpdb_group_heatmap #109
• Fixed an error in ov.utils.roe when some expected frequencies are less than expected value.
• Added cellstackarea to visual the Percent stacked area chart of celltype in samples.

Single Module

• Fixed the bug of ov.single.cytotrace2 when adata.X is not sparse data. #115, #116
• Fixed the groupby error in ov.single.get_obs_value of SEACells.
• Fixed the error of cNMF #107, #85
• Fixed the plot error when Pycomplexheatmap version > 1.7 #136

Bulk Module

• Fixed an key error in ov.bulk.Matrix_ID_mapping
• Added enrichment_multi_concat in ov.bulk to concat the result of enrichment.
• Fixed the pandas version error in gseapy #137

Bulk2Single Module

• Added adata.var_names_make_unique() to avoid mat shape error if gene not unique. #100

Space Module

• Fixed an error in construct_landscape of ov.space.STT
• Fixed an error of get_image_idx_1D in ov.space.svg #117
• Added COMMOT to calculate the cell-cell interaction of spatial RNA-seq.
• Added starfysh to deconvolute spatial transcriptomic without scRNA-seq (#108)

PP Module

• Updated constraint error of ov.pp.mde #129
• Fixed type error of float128 #134

Bulk Module

• Optimised pyGSEA's geneset_plot visualisation of coordinate effects
• Fixed an error of pyTCGA.survival_analysis when the matrix is sparse. #62, #68, #95
• Added tqdm to visualize the process of pyTCGA.survial_analysis_all
• Fixed an error of data_drop_duplicates_index with remove duplicate indexes to retain only the highest expressed genes #45
• Added geneset_plot_multi in ov.bulk to visualize the multi results of enrichment. #103

Single Module

• Added mellon_density to calculate the cell density. #103

PP Module

• Fixed an error of ov.pp.pca when pcs smaller than 13. #102
• Added COMPOSITE in ov.pp.qc's method to predicted doublet cells. #103
• Added species argument in score_genes_cell_cycle to calculate the cell phase without gene manual input

• Added ov.setting.cpu_init to change the environment to CPU.
• Move module tape,SEACells and palantir to externel

Single Module

• Added CytoTrace2 to predict cellular potency categories and absolute developmental potential from single-cell RNA-sequencing data.
• Added cpdb_exact_target and cpdb_exact_source to exact the means of special ligand/receptor
• Added gptcelltype_local to identify the celltype using local LLM #96 #99

Bulk Module

• Added MaxBaseMean columns in dds.result to help people ignore the empty samples.

Space Module

• Added **kwargs in STT.compute_pathway
• Added GraphST to identify the spatial domain

pl Module

• Added cpdb_network, cpdb_chord, cpdb_heatmap, cpdb_interacting_network,cpdb_interacting_heatmap and cpdb_group_heatmap to visualize the result of CellPhoneDB

utils Module

• Added mclust_py to identify the Gaussian Mixture cluster
• Added mclust methdo in cluster function

What's Changed

• Add a function of cell types annotation with local LLMs by @fredsamhaak in #96
• Add guidance on using local LLMs for cell types annotation by @fredsamhaak in #99

New Contributors

• @fredsamhaak made their first contribution in #96

Full Changelog: v1.6.2...v1.6.3