Aug12 2025 updates

singlecellmultiomics/bamProcessing/bamCopyNumber.py

@@ -644,6 +644,15 @@ def bulk_trace(pdf_path, copy_mat, cell_cluster_names, cell_order,segmented_matr
     ignore_contigs = None if args.ignore_contigs is None else args.ignore_contigs.split(',')
 
     reference = pysam.FastaFile(args.ref)
+    # Determine contig lengths and skip contigs which are smaller than the provided bin size:
+    for contig, clen in zip(reference.references, reference.lengths):
+        if clen < bin_size:
+            if ignore_contigs is None:
+                ignore_contigs = [contig]
+            elif contig not in ignore_contigs:
+                ignore_contigs.append(contig)
+
+
     h=GenomicPlot(reference, ignore_contigs=ignore_contigs)
     contigs = GenomicPlot(reference).contigs
 

singlecellmultiomics/bamProcessing/bamToCountTable.py

@@ -502,7 +502,7 @@ def create_count_table(args, return_df=False):
                 for i, read in enumerate(pysam_iterator):
                     if i % 1_000_000 == 0:
                         print(
-                            f"{bamFile} Processed {i} reads, assigned {assigned}, completion:{100*(i/(0.001+f.mapped+f.unmapped+f.nocoordinate))}%")
+                            f"{bamFile} Processed {i} reads, assigned {assigned}, completion:{100*(i/(0.001+f.mapped+f.unmapped+f.nocoordinate)):.2f}%")
 
                     if args.head is not None and i > args.head:
                         break
@@ -547,7 +547,9 @@ def create_count_table(args, return_df=False):
                 f"Finished: {bamFile} Processed {i} reads, assigned {assigned}")
     print(f"Finished counting, now exporting to {args.o}")
     df = pd.DataFrame.from_dict(countTable)
-
+    # Sort indices:
+    df = df.sort_index(axis=1).sort_index(axis=0)
+
     # Set names of indices
     if not args.noNames:
         df.columns.set_names([tagToHumanName(t, TagDefinitions)

singlecellmultiomics/version.py

@@ -1,2 +1,2 @@
-__version__ = '0.1.41'
+__version__ = '0.1.43'