exprmat 0.1.28__tar.gz → 0.1.29__tar.gz

{exprmat-0.1.28 → exprmat-0.1.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: exprmat
-Version: 0.1.28
+Version: 0.1.29
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
@@ -54,7 +54,8 @@ Requires-Dist: multiprocessing-on-dill
 Requires-Dist: pysam
 Requires-Dist: hdbscan
 Requires-Dist: graphtools
-Requires-Dist: bincsync
+Requires-Dist: bincsync>=0.3.0
+Requires-Dist: pybigwig
 Requires-Dist: sphinx ; extra == 'dev'
 Requires-Dist: sphinx-rtd-theme ; extra == 'dev'
 Requires-Dist: twine ; extra == 'dev'

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/__init__.py

@@ -10,15 +10,10 @@ import anndata as ad
 import scanpy as sc
 import pathlib
 
-# core method exports
-from exprmat.utils import setup_styles
-from exprmat.reader.experiment import experiment, load_experiment
-from exprmat.reader.metadata import metadata, load_metadata
 from exprmat.configuration import default as config
 from exprmat.ansi import warning, info
 
 mu.set_options(pull_on_update = False)
-setup_styles()
 
 
 DATABASE_SETUP_MESSAGE = """
@@ -44,11 +39,22 @@ default_finders = [
 
 for finder in default_finders:
     if os.path.exists(finder):
-        info(f'load configuration from {finder}.')
+        info(f'load configuration from {finder}')
         with open(finder, 'r') as f:
             import json
             workspace_config = json.load(f)
             config.update(workspace_config)
+            break
+
+basepath = config['data']
+
+# core method exports
+from exprmat.utils import setup_styles
+from exprmat.reader.experiment import experiment, load_experiment
+from exprmat.reader.metadata import metadata, load_metadata
+
+setup_styles()
+
 
 def version_db():
     dbpath = config['data']
@@ -62,6 +68,7 @@ def version_db():
     
     return db_ver
 
+
 # perform database integrity check.
 if PERFORM_DATABASE_CHECK:
     db_ver = version_db()

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/data/finders.py

@@ -1,10 +1,10 @@
 
 import os
 import pandas
+from exprmat import basepath
 from exprmat.ansi import warning, info
 from exprmat.configuration import default as cfg
 
-basepath = cfg['data']
 genome = {}
 
 def refresh_genome():

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/descriptive/kde.py

@@ -100,9 +100,12 @@ def density(
             cat_mask = adata.obs[groupby] == cat
             embed_x = adata.obsm[f"{basis}"][cat_mask, components[0]]
             embed_y = adata.obsm[f"{basis}"][cat_mask, components[1]]
-
-            dens_embed = kde(embed_x, embed_y)
-            density_values[cat_mask] = dens_embed
+            n, = embed_x.shape
+            if n <= 5:
+                density_values[cat_mask] = 1 / n
+            else:
+                dens_embed = kde(embed_x, embed_y)
+                density_values[cat_mask] = dens_embed
 
         adata.obs[density_covariate] = density_values
 

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/plotting/expression.py

@@ -61,7 +61,7 @@ def barplot(
     axes.legend().remove()
     axes.set_xlabel('')
     axes.set_ylabel(gene)
-    axes.set_xticks(selected_groups)
+    # axes.set_xticks(selected_groups)
     axes.set_yticks([0.0, 2.5])
 
     # axes.set_xticklabels(selected_groups, rotation = 45)

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/plotting/track.py

@@ -83,7 +83,7 @@ def initialize_tracks(
                 fmtstring = 'Gb'
 
             xticklabels = [
-                str(x * scaler)
+                str(x * scaler).replace('.0', '')
                 for x in range(xticksfrom, xticksto + 1)]
             xticklabels[-1] = xticklabels[-1] + ' ' + fmtstring
             lastax.set_xticklabels(xticklabels)
@@ -255,8 +255,12 @@ def gene_track(
             if show_gene_name:
                 ens = gtable['ensembl'].tolist()
                 dname = gtable['gene'].tolist()
-                if name in ens: displayname = dname[ens.index(name)]
+                if name in ens: displayname = dname[ens.index(name)] \
+                    if str(ens.index(name)) != 'nan' else name
             
+            if displayname == 'nan':
+                displayname = ''
+                
             ntranscript = len(gene[gene['type'] == 'transcript'])
             if ntranscript > 1: displayname += f' ({ntranscript})'
             text = ax.text(max(requested_x, xfrom), requested_y + 0.25, displayname, verticalalignment = 'center')
@@ -435,6 +439,30 @@ def coverage_track_from_bam(
     return coverage_track(ax, xfrom, xto, xticks, depth[['x', 'y']], color, xlabel, ylabel, show_x_axis)
 
 
+def coverage_track_from_bigwig(
+    ax, bigwig, xfrom, xto, chrm, xticks, ncpus = 4,
+    color = 'blue', xlabel = None, ylabel = None, show_x_axis = True
+):
+    '''
+    Examples
+    --------
+    >>> coverage_track_from_bam(
+    >>>     axes[3], './fc.bigwig', 
+    >>>     xfrom, xto, chr_bam, xticks, ncpus = 4, xlabel = None, ylabel = 'WT', 
+    >>>     show_x_axis = True
+    >>> )
+    '''
+    import pyBigWig
+    from exprmat.ansi import error, warning
+    import os
+    import pandas
+
+    bw = pyBigWig.open(bigwig)
+    if not bw.chroms(chrm): error(f'specified chromosome {chrm} do not exist in the bigwig file.')
+    depth = pandas.DataFrame({'x': [x for x in range(xfrom, xto)], 'y': bw.values(chrm, xfrom, xto)})
+    return coverage_track(ax, xfrom, xto, xticks, depth[['x', 'y']], color, xlabel, ylabel, show_x_axis)
+
+
 def architecture(assembly, figsize = (4, 8), dpi = 100, cby = 'assembly'):
     '''
     Examples
@@ -537,4 +565,26 @@ def genes(
         from exprmat.ansi import error
         error('must specify a range or a gene name flanking.')
         return None
+    
+
+def whereis(assembly, where, upstream = 10000, downstream = 10000):
+
+    from exprmat.configuration import default as cfg
+    from exprmat.data.finders import get_genome
+
+    gtable = get_genome(cfg['taxa.reference'][assembly.lower()])
+    ens = gtable['ensembl'].tolist()
+    name = gtable['gene'].tolist()
+
+    if where in ens:
+        geneattr = gtable.iloc[ens.index(where), :].copy()
+    elif where in name:
+        geneattr = gtable.iloc[name.index(where), :].copy()
+    else: geneattr = gtable[where, :].copy()
+
+    chr = geneattr['.seqid']
+    xfrom = geneattr['.start'] - upstream
+    xto = geneattr['.end'] + downstream
+
+    return chr, xfrom, xto
     

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/reader/experiment.py

@@ -71,7 +71,7 @@ class experiment:
 
             attempt_path = os.path.join(dump, i_mod, i_sample + '.h5ad')
             if os.path.exists(attempt_path):
-                if not i_loc in self.modalities.keys(): self.modalities[i_mod] = {}
+                if not i_mod in self.modalities.keys(): self.modalities[i_mod] = {}
                 self.modalities[i_mod][i_sample] = sc.read_h5ad(attempt_path)
                 warning(f'load pre-exisiting file `{i_mod}/{i_sample}.h5ad`.')
                 continue
@@ -534,7 +534,7 @@ class experiment:
         self, run_on_samples, func,
         run_on_splits = False, split_key = None, split_selection = None, **kwargs
     ):
-        self.plot_for_modality(
+        return self.plot_for_modality(
             'rna', run_on_samples, func, 
             run_on_splits, split_key, split_selection, **kwargs
         )
@@ -543,7 +543,7 @@ class experiment:
         self, run_on_samples, func,
         run_on_splits = False, split_key = None, split_selection = None, **kwargs
     ):
-        self.plot_for_modality(
+        return self.plot_for_modality(
             'atac', run_on_samples, func, 
             run_on_splits, split_key, split_selection, **kwargs
         )
@@ -552,17 +552,16 @@ class experiment:
         self, run_on_samples, func,
         run_on_splits = False, split_key = None, split_selection = None, **kwargs
     ):
-        self.plot_for_modality(
+        return self.plot_for_modality(
             'atac.cp', run_on_samples, func, 
             run_on_splits, split_key, split_selection, **kwargs
         )
 
-
     def plot_for_atac_gene_activity(
         self, run_on_samples, func,
         run_on_splits = False, split_key = None, split_selection = None, **kwargs
     ):
-        self.plot_for_modality(
+        return self.plot_for_modality(
             'atac.g', run_on_samples, func, 
             run_on_splits, split_key, split_selection, **kwargs
         )

{exprmat-0.1.28 → exprmat-0.1.29}/exprmat/utils.py

@@ -368,6 +368,28 @@ seurat_to_10x <- function(srat, outdir) {
     sparse <- Matrix(srat @ assays $ RNA @ counts, sparse = T)
     writeMM(sparse, file = paste(outdir, 'matrix.mtx', sep = '/'))
 }
+
+spmatrix_to_mtx <- function(sp, outdir) {
+    features <- data.frame(
+        ensembl = rownames(sp),
+        gene = rownames(sp),
+        tag = "Gene Expression"
+    )
+
+    write(
+        x = colnames(sp),
+        file = paste(outdir, 'barcodes.tsv', sep = '/')
+    )
+    
+    write.table(
+        x = features,
+        file = paste(outdir, 'features.tsv', sep = '/'),
+        sep = "\t", quote = FALSE, col.names = FALSE, row.names = FALSE
+    )
+
+    require(Matrix)
+    writeMM(sp, file = paste(outdir, 'matrix.mtx', sep = '/'))
+}
 '''
 
 

{exprmat-0.1.28 → exprmat-0.1.29}/pyproject.toml

@@ -18,7 +18,7 @@ description = "exprmat: Routines for expression matrices"
 readme = "readme.md"
 license = {file = "license"}
 requires-python = ">=3.9, <3.13"
-version = "0.1.28"
+version = "0.1.29"
 authors = [
     {name = "Zheng Yang", email = "xornent@outlook.com"}
 ]
@@ -80,7 +80,8 @@ dependencies = [
     'pysam',
     'hdbscan',
     'graphtools',
-    'bincsync'
+    'bincsync >= 0.3.0',
+    'pyBigWig'
 ]
 
 [project.optional-dependencies]