smftools 0.1.1__py3-none-any.whl → 0.1.3__py3-none-any.whl

smftools/informatics/helpers/generate_converted_FASTA.py

@@ -57,23 +57,42 @@ def generate_converted_FASTA(input_fasta, modification_types, strands, output_fa
     from Bio import SeqIO
     from Bio.SeqRecord import SeqRecord
     from Bio.Seq import Seq
+    import gzip
     modified_records = []
     unconverted = modification_types[0]
     # Iterate over each record in the input FASTA
-    for record in SeqIO.parse(input_fasta, 'fasta'):
-        record_description = record.description
-        # Iterate over each modification type of interest
-        for modification_type in modification_types:
-            # Iterate over the strands of interest
-            for i, strand in enumerate(strands):
-                if i > 0 and modification_type == unconverted: # This ensures that the unconverted is only added once.
-                    pass
-                else:
-                    # Add the modified record to the list of modified records
-                    print(f'converting {modification_type} on the {strand} strand of record {record}')
-                    new_seq, new_id = convert_FASTA_record(record, modification_type, strand, unconverted)
-                    new_record = SeqRecord(Seq(new_seq), id=new_id, description=record_description)
-                    modified_records.append(new_record)
+    if '.gz' in input_fasta:
+        with gzip.open(input_fasta, 'rt') as handle:    
+            for record in SeqIO.parse(handle, 'fasta'):
+                record_description = record.description
+                # Iterate over each modification type of interest
+                for modification_type in modification_types:
+                    # Iterate over the strands of interest
+                    for i, strand in enumerate(strands):
+                        if i > 0 and modification_type == unconverted: # This ensures that the unconverted is only added once.
+                            pass
+                        else:
+                            # Add the modified record to the list of modified records
+                            print(f'converting {modification_type} on the {strand} strand of record {record}')
+                            new_seq, new_id = convert_FASTA_record(record, modification_type, strand, unconverted)
+                            new_record = SeqRecord(Seq(new_seq), id=new_id, description=record_description)
+                            modified_records.append(new_record)
+    else:
+        for record in SeqIO.parse(input_fasta, 'fasta'):
+            record_description = record.description
+            # Iterate over each modification type of interest
+            for modification_type in modification_types:
+                # Iterate over the strands of interest
+                for i, strand in enumerate(strands):
+                    if i > 0 and modification_type == unconverted: # This ensures that the unconverted is only added once.
+                        pass
+                    else:
+                        # Add the modified record to the list of modified records
+                        print(f'converting {modification_type} on the {strand} strand of record {record}')
+                        new_seq, new_id = convert_FASTA_record(record, modification_type, strand, unconverted)
+                        new_record = SeqRecord(Seq(new_seq), id=new_id, description=record_description)
+                        modified_records.append(new_record)
+                        
     with open(output_fasta, 'w') as output_handle:
         # write out the concatenated FASTA file of modified sequences
         SeqIO.write(modified_records, output_handle, 'fasta')

smftools/informatics/helpers/get_chromosome_lengths.py

@@ -0,0 +1,32 @@
+# get_chromosome_lengths
+
+def get_chromosome_lengths(fasta):
+    """
+    Generates a file containing chromosome lengths within an input FASTA.
+
+    Parameters:
+        fasta (str): Path to the input fasta
+    """
+    import os
+    import subprocess
+    from .index_fasta import index_fasta
+
+    # Make a fasta index file if one isn't already available
+    index_path = f'{fasta}.fai'
+    if os.path.exists(index_path):
+        print(f'Using existing fasta index file: {index_path}')
+    else:
+        index_fasta(fasta)
+
+    parent_dir = os.path.dirname(fasta)
+    fasta_basename = os.path.basename(fasta)
+    chrom_basename = fasta_basename.split('.fa')[0] + '.chrom.sizes'
+    chrom_path = os.path.join(parent_dir, chrom_basename)
+
+    # Make a chromosome length file
+    if os.path.exists(chrom_path):
+        print(f'Using existing chrom length index file: {chrom_path}')
+    else:
+        with open(chrom_path, 'w') as outfile:
+            command = ["cut", "-f1,2", index_path]
+            subprocess.run(command, stdout=outfile)

smftools/informatics/helpers/index_fasta.py

@@ -0,0 +1,12 @@
+# index_fasta
+
+def index_fasta(fasta):
+    """
+    Generate a FASTA index file for an input fasta.
+
+    Parameters:
+        fasta (str): Path to the input fasta to make an index file for.
+    """
+    import subprocess
+
+    subprocess.run(["samtools", "faidx", fasta])

smftools/informatics/helpers/modcall.py

@@ -21,6 +21,8 @@ def modcall(model, pod5_dir, barcode_kit, mod_list, bam, bam_suffix):
     output = bam + bam_suffix
     command = [
     "dorado", "basecaller", model, pod5_dir, "--kit-name", barcode_kit, "-Y",
-    "--modified-bases", ",".join(mod_list)]  # Join MOD_LIST elements with commas
+    "--modified-bases"]
+    command += mod_list
+    print(f'Running: {" ".join(command)}')
     with open(output, "w") as outfile:
         subprocess.run(command, stdout=outfile)