celescope 2.3.0.dev1__tar.gz → 2.3.0.dev2__tar.gz

{celescope-2.3.0.dev1/celescope.egg-info → celescope-2.3.0.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: celescope
-Version: 2.3.0.dev1
+Version: 2.3.0.dev2
 Summary: Single Cell Analysis Pipelines
 Home-page: https://github.com/singleron-RD/CeleScope
 Author: zhouyiqi

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope/__init__.py

@@ -1,6 +1,6 @@
 import os
 
-__VERSION__ = "2.3.0dev1"
+__VERSION__ = "2.3.0dev2"
 __version__ = __VERSION__
 
 ASSAY_LIST = [

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope/bulk_rna/starsolo.py

@@ -23,9 +23,31 @@ from celescope.tools.step import Step, s_common
 SAM_attributes = "NH HI nM AS CR UR CB UB GX GN "
 
 
+def get_well_barcode(
+    bc_file: str,
+) -> dict[int, str]:
+    barcodes = utils.one_col_to_list(bc_file)
+    return {i: x for i, x in enumerate(barcodes, start=1)}
+
+
+def get_barcode_sample(
+    bc_file: str,
+    well_sample_file: str,
+) -> dict[str, str]:
+    well_barcode = get_well_barcode(bc_file)
+    well_sample = utils.two_col_to_dict(well_sample_file)
+    barcode_sample = {
+        well_barcode[well]: sample for well, sample in well_sample.items()
+    }
+    return barcode_sample
+
+
 class Starsolo(tools_Starsolo):
     def __init__(self, args, display_title=None):
         super().__init__(args, display_title=display_title)
+        self.well_barcode = get_well_barcode(self.bc[0])
+        self.barcode_sample = get_barcode_sample(self.bc[0], args.well_sample)
+
         self.tsv_matrix_file = f"{self.out_prefix}_matrix.tsv.gz"
         self.outs.append(self.tsv_matrix_file)
 
@@ -58,16 +80,16 @@ class Starsolo(tools_Starsolo):
     def keep_barcodes(self):
         """take in raw matrix, only keep barcodes in the input file, and convert barcodes to sample names"""
         matrix = CountMatrix.from_matrix_dir(self.raw_matrix)
-        barcode_sample = utils.two_col_to_dict(self.args.barcode_sample)
-        for barcode in barcode_sample:
+
+        for barcode in self.barcode_sample:
             if barcode not in matrix.get_barcodes():
-                barcode_sample.pop(barcode)
                 sys.stderr.write(
-                    f"WARNING: {barcode} {barcode_sample[barcode]} not found in raw matrix!\n"
+                    f"WARNING: barcode:{barcode} {self.barcode_sample[barcode]} not found in raw matrix!\n"
                 )
-        filtered = matrix.slice_matrix_bc(barcode_sample.keys())
+                self.barcode_sample.pop(barcode)
+        filtered = matrix.slice_matrix_bc(self.barcode_sample.keys())
         filtered.to_matrix_dir(self.filtered_matrix)
-        samples = [barcode_sample[bc] for bc in filtered.get_barcodes()]
+        samples = [self.barcode_sample[bc] for bc in filtered.get_barcodes()]
         converted = CountMatrix(filtered.get_features(), samples, filtered.get_matrix())
         df = converted.to_df()
         df.to_csv(self.tsv_matrix_file, sep="\t")
@@ -78,7 +100,7 @@ class Starsolo(tools_Starsolo):
         filtered = self.keep_barcodes()
         self.gzip_matrix()
         q30_cb, q30_umi = self.get_Q30_cb_UMI()
-        return q30_cb, q30_umi, filtered
+        return q30_cb, q30_umi, filtered, self.barcode_sample, self.well_barcode
 
 
 class Cells(Step):
@@ -98,7 +120,7 @@ class Cells(Step):
 
         return n_reads, q30_RNA, saturation
 
-    def run(self, filtered: CountMatrix):
+    def run(self, filtered: CountMatrix, barcode_sample: dict, well_barcode: dict):
         df_counts = pd.read_csv(self.counts_file, index_col=0, header=0, sep="\t")
         reads_total = df_counts["countedU"].sum()
         bcs = filtered.get_barcodes()
@@ -150,18 +172,35 @@ class Cells(Step):
             value_type="fraction",
             help_info="the fraction of read originating from an already-observed UMI.",
         )
+
+        # table
+        df_cells = df_counts[df_counts["mark"] == "CB"]
+        df_cells["Sample"] = df_cells.index.map(lambda x: barcode_sample[x])
+        df_cells["Genes"] = df_cells.index.map(lambda x: bc_geneNum[x])
+        df_cells["Barcode"] = df_cells.index
+        barcode_well = {v: k for k, v in well_barcode.items()}
+        df_cells["Well"] = df_cells["Barcode"].map(lambda x: barcode_well[x])
+        df_cells = df_cells.loc[:, ["Well", "Sample", "Barcode", "UMI", "Genes"]]
+
+        table_dict = self.get_table_dict(
+            title="Metrics for a Single Well",
+            table_id=self.assay,
+            df_table=df_cells,
+        )
+        self.add_data(table_dict=table_dict)
+
         return n_reads, q30_RNA
 
 
 def starsolo(args):
     with Starsolo(args) as runner:
-        q30_cb, q30_umi, filtered = runner.run()
+        q30_cb, q30_umi, filtered, barcode_sample, well_barcode = runner.run()
 
     with Mapping(args) as runner:
         valid_reads, corrected = runner.run()
 
-    with Cells(args) as runner:
-        n_reads, q30_RNA = runner.run(filtered)
+    with Cells(args, display_title="Wells") as runner:
+        n_reads, q30_RNA = runner.run(filtered, barcode_sample, well_barcode)
 
     with Demultiplexing(args) as runner:
         runner.run(valid_reads, n_reads, corrected, q30_cb, q30_umi, q30_RNA)
@@ -227,8 +266,8 @@ is higher than or equal to this value.""",
         default="1MM",
     )
     parser.add_argument(
-        "--barcode_sample",
-        help="tsv file of well barcodes and sample names. The first column is well barcodes and the second column is sample names.",
+        "--well_sample",
+        help="tsv file of well numbers and sample names. The first column is well numbers and the second column is sample names.",
         required=True,
     )
     if sub_program:

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope/templates/html/bulk_rna/base.html

@@ -12,7 +12,7 @@
 
     {% if cells_summary is defined%}
     {% set step_summary = cells_summary %}
-    {% include "html/rna/count.html" %}
+    {% include "html/bulk_rna/cells.html" %}
     {% endif %}
 
 

celescope-2.3.0.dev2/celescope/templates/html/bulk_rna/cells.html

@@ -0,0 +1,18 @@
+<div class="abc" style="float: left; margin-left: 15%; margin-right:15%; width: 70%" >
+    <h2>{{ step_summary.display_title}}    <i class="icon-help-circled" onClick="toggle1(this.parentNode.parentNode)" style="cursor:pointer;"></i></h2>
+    <div class="box">
+      {% include "html/utils/help_info.html" %}
+      {% include "html/utils/col1_metrics.html" %}
+  
+      <div id="myDivUMI" style="float: left; margin-left: 3%; margin-top: 1%;margin-right:0%; width: 47%">
+        {{ step_summary.chart|safe }}
+      </div>
+  
+      <div class="clear" ></div>
+    </div>
+  </div>
+
+<div class="abc" style="float: left; margin-left: 15%; margin-right:15%; width: 70%" >
+    {% include "html/utils/table_dict.html" %}
+    <div class="clear" ></div>
+</div>

celescope-2.3.0.dev2/celescope/templates/html/utils/table_script/bulk_rna.html

@@ -0,0 +1,10 @@
+<script>
+    $(document).ready(function () {
+        var table_id = {{ step_summary.table_dict['id']|safe }};
+        var table = $(table_id).DataTable({
+            dom: 'Bfrtip',
+            buttons: ['excel']
+        });
+        table.columns(0).order('asc').draw();
+    });
+</script>

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope/tools/matrix.py

@@ -234,9 +234,11 @@ class CountMatrix:
         gene_index, bc_index = self.__matrix.nonzero()
         total_genes = len(set(gene_index))
         bc_gene = defaultdict(set)
-        for gene, bc in zip(gene_index, bc_index):
-            bc_gene[bc].add(gene)
-        return {bc: len(bc_gene[bc]) for bc in bc_gene}, total_genes
+        for gene, bc_i in zip(gene_index, bc_index):
+            bc_gene[bc_i].add(gene)
+        return {
+            self.__barcodes[bc_i]: len(bc_gene[bc_i]) for bc_i in bc_gene
+        }, total_genes
 
     def get_barcodes(self):
         return self.__barcodes

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope/tools/split_fastq.py

@@ -6,6 +6,7 @@ import celescope.tools.parse_chemistry as parse_chemistry
 import pysam
 from celescope.chemistry_dict import chemistry_dict
 from celescope.__init__ import HELP_DICT
+from celescope.bulk_rna.starsolo import get_barcode_sample
 
 
 UMI_SEPARATOR = ":"
@@ -17,7 +18,6 @@ class Split_fastq(Step):
 
         self.fq1_list = args.fq1.split(",")
         self.fq2_list = args.fq2.split(",")
-        self.barcode_sample = utils.two_col_to_dict(args.barcode_sample)
 
         chemistry = parse_chemistry.get_chemistry(
             self.assay, args.chemistry, self.fq1_list
@@ -29,6 +29,8 @@ class Split_fastq(Step):
             parse_chemistry.create_mismatch_origin_dicts_from_whitelists(bc, 1)
         )
 
+        self.barcode_sample = get_barcode_sample(bc[0], args.well_sample)
+
     @utils.add_log
     def split(self):
         self.fh_dict = {}
@@ -82,8 +84,8 @@ def get_opts_split_fastq(parser, sub_program):
         help="Cell barcode whitelist file path, one cell barcode per line.",
     )
     parser.add_argument(
-        "--barcode_sample",
-        help="tsv file of well barcodes and sample names. The first column is well barcodes and the second column is sample names.",
+        "--well_sample",
+        help="tsv file of well numbers and sample names. The first column is well numbers and the second column is sample names.",
         required=True,
     )
     if sub_program:

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2/celescope.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: celescope
-Version: 2.3.0.dev1
+Version: 2.3.0.dev2
 Summary: Single Cell Analysis Pipelines
 Home-page: https://github.com/singleron-RD/CeleScope
 Author: zhouyiqi

{celescope-2.3.0.dev1 → celescope-2.3.0.dev2}/celescope.egg-info/SOURCES.txt

@@ -149,6 +149,7 @@ celescope/templates/css/fontello-323401c3/font/fontello.ttf
 celescope/templates/css/fontello-323401c3/font/fontello.woff
 celescope/templates/css/fontello-323401c3/font/fontello.woff2
 celescope/templates/html/bulk_rna/base.html
+celescope/templates/html/bulk_rna/cells.html
 celescope/templates/html/bulk_vdj/base.html
 celescope/templates/html/bulk_vdj/count_vdj.html
 celescope/templates/html/capture_rna/base.html

celescope-2.3.0.dev1/celescope/templates/html/utils/table_script/bulk_rna.html

@@ -1,32 +0,0 @@
-<script>
-
-    $(document).ready(function () {
-            var table = $('#bulk_rna').DataTable({
-                dom: 'Bfrtip',
-                buttons: ['excel'],
-                "aaSorting": []
-            });
-            var indexOfMyCol = 0 ;
-            var collator = new Intl.Collator(undefined, {numeric: true, sensitivity: 'base'});
-    $("#bulk_rna  thead th").each( function ( i ) {
-        if (i==indexOfMyCol){
-
-          var select = $('<select><option value=""></option></select>')
-            .appendTo( $(this).empty() )
-            .on( 'change', function () {
-                var pattern = ""
-                if ($(this).val()!="") {
-                    pattern= pattern="^"+$(this).val() +"$"
-                }
-                table.column( i )
-                .search(input=pattern, regex=true, smart=false)
-                .draw();
-            } );
- 
-        table.column( i).data().unique().sort(collator.compare).each( function ( d, j ) {
-            select.append( '<option value="'+d+'">'+d+'</option>' )
-        } );
-    }
-    } );
-    });
-</script>