update readme and fix some bugs

README.md

@@ -1,8 +1,7 @@
 <h1 align="center">
 <img src="https://raw.githubusercontent.com/Starlitnightly/omicverse/master/README.assets/logo.png" width="400">
 </h1><br>
-
-[![Lifecycle:maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://www.tidyverse.org/lifecycle/#maturing) [![bulid:passing](https://img.shields.io/appveyor/build/gruntjs/grunt)](https://img.shields.io/appveyor/build/gruntjs/grunt) [![License:GPL](https://img.shields.io/badge/license-GNU-blue)](https://img.shields.io/apm/l/vim-mode) [![pypi-badge](https://img.shields.io/pypi/v/omicverse)](https://pypi.org/project/omicverse) [![Documentation Status](https://readthedocs.org/projects/omicverse/badge/?version=latest)](https://omicverse.readthedocs.io/en/latest/?badge=latest) [![CodeQL](https://github.com/Starlitnightly/omicverse/workflows/CodeQL/badge.svg)](https://github.com/Starlitnightly/omicverse/workflows/CodeQL/badge.svg) [![Pytest](https://github.com/Starlitnightly/omicverse/workflows/py38|py39/badge.svg)](https://github.com/Starlitnightly/omicverse/)
+[![Lifecycle:maturing](https://img.shields.io/badge/lifecycle-maturing-blue.svg)](https://www.tidyverse.org/lifecycle/#maturing) [![bulid:passing](https://img.shields.io/appveyor/build/gruntjs/grunt)](https://img.shields.io/appveyor/build/gruntjs/grunt) [![License:GPL](https://img.shields.io/badge/license-GNU-blue)](https://img.shields.io/apm/l/vim-mode) [![pypi-badge](https://img.shields.io/pypi/v/omicverse)](https://pypi.org/project/omicverse) [![Documentation Status](https://readthedocs.org/projects/omicverse/badge/?version=latest)](https://omicverse.readthedocs.io/en/latest/?badge=latest) [![pypiDownloads](https://static.pepy.tech/badge/omicverse)](https://pepy.tech/project/omicverse)[![condaDownloads](https://img.shields.io/conda/dn/conda-forge/omicverse?logo=Anaconda)](https://anaconda.org/conda-forge/omicverse)[![Pytest](https://github.com/Starlitnightly/omicverse/workflows/py38|py39/badge.svg)](https://github.com/Starlitnightly/omicverse/) 
 
 OmicVerse is the fundamental package for multi omics included bulk and single cell analysis with Python. For more information, please read our paper: [OmicVerse: A single pipeline for exploring the entire transcriptome universe](https://www.biorxiv.org/content/10.1101/2023.06.06.543913v1)
 
@@ -65,6 +64,7 @@ Please checkout the documentations and tutorials at [omicverse.readthedocs.io](h
 - [19] [Scanorama](https://github.com/brianhie/scanorama) was originally published in [*Nature Biotechnology*](https://www.nature.com/articles/s41587-019-0113-3)
 - [20] [Combat](https://github.com/epigenelabs/pyComBat/) was originally published in [*biorxiv*](https://doi.org/10.1101/2020.03.17.995431)
 - [21] [TAPE](https://github.com/poseidonchan/TAPE) was originally published in [*Nature Communications*](https://doi.org/10.1038/s41467-022-34550-9)
+- [22] [SEACells](https://github.com/dpeerlab/SEACells) was originally published in [*Nature Biotechnology*](https://www.nature.com/articles/s41587-023-01716-9)
 
 
 ## Included Package not published or preprint

omicverse/bulk2single/_bulktrajblend.py

@@ -15,10 +15,11 @@ class BulkTrajBlend(object):
     """
     BulkTrajBlend: A class for bulk and single cell data integration and trajectory inference using beta-VAE and GNN.
 
+
     """
 
     def __init__(self,bulk_seq:pd.DataFrame,single_seq:anndata.AnnData,
-                 celltype_key:str,bulk_group=None,
+                 celltype_key:str,bulk_group=None,max_single_cells:int=5000,
                  top_marker_num:int=500,ratio_num:int=1,gpu:Union[int,str]=0) -> None:
         """
         Initialize the BulkTrajBlend class
@@ -30,6 +31,7 @@ def __init__(self,bulk_seq:pd.DataFrame,single_seq:anndata.AnnData,
             top_marker_num: The number of top marker genes for each cell type.
             ratio_num: The number of cells to be selected for each cell type.
             gpu: The gpu id or 'cpu' or 'mps'.
+            max_single_cells: The maximum number of single cells to be used. Default is 5000.
 
         """
 
@@ -40,6 +42,7 @@ def __init__(self,bulk_seq:pd.DataFrame,single_seq:anndata.AnnData,
         self.ratio_num=ratio_num
         self.gpu=gpu
         self.group=bulk_group
+        self.max_single_cells=max_single_cells
         if gpu=='mps' and torch.backends.mps.is_available():
             print('Note that mps may loss will be nan, used it when torch is supported')
             self.used_device = torch.device("mps")
@@ -104,12 +107,13 @@ def vae_configure(self,cell_target_num=None,**kwargs):
         """
         self.vae_model=Bulk2Single(bulk_data=self.bulk_seq,single_data=self.single_seq,
                                    celltype_key=self.celltype_key,bulk_group=self.group,
+                                      max_single_cells=self.max_single_cells,
                  top_marker_num=self.top_marker_num,ratio_num=self.ratio_num,gpu=self.gpu)
         if cell_target_num!=None:
             self.vae_model.cell_target_num=dict(zip(list(set(self.single_seq.obs[self.celltype_key])),
                                                 [cell_target_num]*len(list(set(self.single_seq.obs[self.celltype_key])))))
         else:
-            self.vae_model.predicted_fraction(*kwargs)
+            self.vae_model.predicted_fraction(**kwargs)
 
         self.vae_model.bulk_preprocess_lazy()
         self.vae_model.single_preprocess_lazy()

omicverse/single/_nocd.py

@@ -79,7 +79,8 @@ def matrix_transform(self,clustertype='leiden'):
 
         self.N, self.K = self.Z_gt.shape
 
-
+
+
     def matrix_normalize(self,cuda=False):
         if torch.cuda.is_available():
             cuda=True

omicverse/via/utils_via.py

@@ -203,7 +203,10 @@ def pruning_clustergraph(adjacency, global_pruning_std=1, max_outgoing=30, prese
                     for i in range(len(locxy[0])):
                         if comp_labels[locxy[0][i]] != comp_labels[locxy[1][i]]:
                             x, y = locxy[0][i], locxy[1][i]
-
+                        else:
+                            x, y = 0, 0
+                    #if x==0 and y==0:
+                    #    continue
                     cluster_graph_csr[x, y] = adjacency[x, y]
                     cluster_graph_csr[y, x] = adjacency[y, x]
 

omicverse_guide/docs/Release_notes.md

@@ -303,4 +303,8 @@ update `conda install omicverse -c conda-forge`
 - Fix the matrix error when the symbol of genes not unique.
 - Fix the `interpolation` of BulkTrajBlend when the target cells not exist.
 - Fix the `generate` of BulkTrajBlend.
+- Fix thhe arguement of `vae_configure` in BulkTrajBlend when cell_target_num is None
+- Add `max_single_cells` for BulkTrajBlend input
 
+### single module
+- Fix the error of pyVIA when root is None