REDItools3 3.1a0__py3-none-any.whl → 3.2a0__py3-none-any.whl

{REDItools3-3.1a0.dist-info → REDItools3-3.2a0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: REDItools3
-Version: 3.1a0
+Version: 3.2a0
 Author: Ernesto Picardi
 Author-email: Adam Handen <adam.handen@gmail.com>
 Project-URL: homepage, https://github.com/BioinfoUNIBA/REDItools3
@@ -13,7 +13,7 @@ Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: GNU General Public License (GPL)
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: Unix
-Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.7
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown

{REDItools3-3.1a0.dist-info → REDItools3-3.2a0.dist-info}/RECORD

@@ -2,20 +2,20 @@ reditools/__init__.py,sha256=7nSB0hrQznxrn6l95cv_pSonJTG6jZCQdbn7aT1TtvY,46
 reditools/__main__.py,sha256=mWJ9O2LDiOpBWDBJJUN7OiM4SyltW-kVXXAGBe_JxgQ,842
 reditools/alignment_file.py,sha256=YFyCEhMek2t93DpmpwEst5v3gDZkmRotbd6Fy_mP0aE,4258
 reditools/alignment_manager.py,sha256=_FXwvqGWoXRdzVrwBxki2heaVZA2cQbGXqCopr-g1Hs,4138
-reditools/analyze.py,sha256=u38yN5DmXUCW8nQP_BMfsXuvb59rFO12di5cYT8Ye58,15280
+reditools/analyze.py,sha256=tW9Rz-R_8R-mJ2uQP5fpGFTH7TEv-2pOsigtbKqwYDY,14649
 reditools/compiled_position.py,sha256=v540uUEie_HHUwsYQmBqeeOkUvtYlcnWj1v8gAhLUiE,3858
 reditools/compiled_reads.py,sha256=7Hm5f7g1T8q1zDOOxZUD7aZax9b7SdQ0PlmT93hmcaE,4154
 reditools/fasta_file.py,sha256=KBsJBs7OnBpew2PGWGp0mTxPLlpBmRrtXL4uvQw4t34,2212
-reditools/file_utils.py,sha256=AJjU9leOxSou5U_4RAgapR9PGQz0OYQlkCudvTcXGeQ,3284
-reditools/homopolymerics.py,sha256=BCYXBJa6YuouzccFisBFOtGfZAEOSqeqJsO-c37At84,2123
-reditools/index.py,sha256=K3JQTMx4ojUUiPQTDMDsoYoFQQ_o-ZNqTrh5dIVFVSQ,7398
+reditools/file_utils.py,sha256=MfQPzJ4ogbwNvIiEu1oooS64EJH1CFdRS8eoqT9Zo4w,2763
+reditools/homopolymerics.py,sha256=UsHTr0e_OP_dkGq5te-oTSe5u6kzi5UJOF9t9QAunUk,2269
+reditools/index.py,sha256=jLgWwKXIA_e-bqVu74SDZXmrdWch_syDSmMnFZPbqz4,7537
 reditools/logger.py,sha256=u4L2SYxy4vJ4KDHEymd0b1sCa8BXXHchx8LR_wcFq1A,1210
-reditools/reditools.py,sha256=Rb5bllqjE1wHti98p-v2t4Vu-YEvZgNv-FXcUPgDVO0,12725
+reditools/reditools.py,sha256=RNH7aKC2QnbafA7T9E6UpV5Llv3FjfDIabjPCuwDgW0,13111
 reditools/region.py,sha256=_BiKDc5lCl1snjkokRiUWOgzA57ME3yLydEIwK9ku7U,3780
-reditools/rtchecks.py,sha256=tkaosQDBc2XN_RlVMtNwrxZjCQoQo2bWfQISROXCmKA,8221
+reditools/rtchecks.py,sha256=TmCow38fCRwSICvx3nlOxy6Q216BcDXESGhM7bB_ixo,8878
 reditools/utils.py,sha256=a2qfhMcrH2QlK-JoR-HHF6_bnlo5v3jihAqqknvVIjc,2733
-REDItools3-3.1a0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-REDItools3-3.1a0.dist-info/METADATA,sha256=EPD47hLxZoozfc0Gd4uFPOaid9uz81DkWI4Pkv0STpo,1289
-REDItools3-3.1a0.dist-info/WHEEL,sha256=a7TGlA-5DaHMRrarXjVbQagU3Man_dCnGIWMJr5kRWo,91
-REDItools3-3.1a0.dist-info/top_level.txt,sha256=wrvvbFXhmNg7s6LQqjlV_fVQYUZOOpF93IcMu_hBCx4,10
-REDItools3-3.1a0.dist-info/RECORD,,
+REDItools3-3.2a0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+REDItools3-3.2a0.dist-info/METADATA,sha256=NRwZTGGmlHBkP6XiQ4Sdql-XXRR2Ii27beCDf_jCt90,1288
+REDItools3-3.2a0.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+REDItools3-3.2a0.dist-info/top_level.txt,sha256=wrvvbFXhmNg7s6LQqjlV_fVQYUZOOpF93IcMu_hBCx4,10
+REDItools3-3.2a0.dist-info/RECORD,,

{REDItools3-3.1a0.dist-info → REDItools3-3.2a0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.4.0)
+Generator: setuptools (75.5.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

reditools/analyze.py

@@ -79,19 +79,11 @@ def setup_rtools(options):  # noqa:WPS213,WPS231
         rtools.log_level = Logger.info_level
 
     if options.load_omopolymeric_file:
-        regions = file_utils.load_omopolymeric_regions(
-            options.load_omopolymeric_file,
-        )
+        regions = file_utils.read_bed_file(options.load_omopolymeric_file)
         rtools.exclude(regions)
 
-    if options.create_omopolymeric_file:
-        rtools.create_omopolymeric_positions(
-            options.create_omopolymeric_file,
-            options.omopolymeric_span,
-        )
-
     if options.splicing_file:
-        rtools.load_splicing_file(
+        rtools.splice_positions = file_utils.load_splicing_file(
             options.splicing_file,
             options.splicing_span,
         )
@@ -109,10 +101,11 @@ def setup_rtools(options):  # noqa:WPS213,WPS231
     rtools.max_base_position = options.max_base_position
     rtools.min_base_quality = options.min_base_quality
 
-    rtools.min_column_length = options.min_column_length
+    rtools.min_column_length = options.min_read_depth
     rtools.min_edits = options.min_edits
     rtools.min_edits_per_nucleotide = options.min_edits_per_nucleotide
     rtools.strand = options.strand
+    rtools.max_alts = options.max_editing_nucleotides
 
     rtools.strand_confidence_threshold = options.strand_confidence_threshold
 
@@ -225,21 +218,26 @@ def parse_options():  # noqa:WPS213
     Returns:
         namespace: commandline args
     """
-    parser = argparse.ArgumentParser(description='REDItools 2.0')
+    parser = argparse.ArgumentParser(
+        prog="reditools analyze",
+        description='REDItools3',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
     parser.add_argument(
         'file',
         nargs='+',
-        help='The bam file to be analyzed',
+        help='The bam file(s) to be analyzed.',
     )
     parser.add_argument(
         '-r',
         '--reference',
-        help='The reference FASTA file',
+        help='Reference FASTA file.',
     )
     parser.add_argument(
         '-o',
         '--output-file',
-        help='The output statistics file',
+        help='Path to write output to.',
+        default='/dev/stdout',
     )
     parser.add_argument(
         '-s',
@@ -248,96 +246,85 @@ def parse_options():  # noqa:WPS213
         type=int,
         default=0,
         help='Strand: this can be 0 (unstranded),' +
-        '1 (secondstrand oriented) or ' +
-        '2 (firststrand oriented)',
+        '1 (second strand oriented) or ' +
+        '2 (first strand oriented).',
     )
     parser.add_argument(
         '-a',
         '--append-file',
         action='store_true',
-        help='Appends results to file (and creates if not existing)',
+        help='Appends results to file (and creates if not existing).',
     )
     parser.add_argument(
         '-g',
         '--region',
-        help='The self.region of the bam file to be analyzed',
+        help='Only analyzes the specified region.',
     )
     parser.add_argument(
         '-m',
         '--load-omopolymeric-file',
-        help='The file containing the omopolymeric positions',
-    )
-    parser.add_argument(
-        '-c',
-        '--create-omopolymeric-file',
-        default=False,
-        help='Path to write omopolymeric positions to',
-        action='store_true',
+        help='BED file of omopolymeric positions.',
     )
     parser.add_argument(
         '-os',
         '--omopolymeric-span',
         type=int,
         default=5,
-        help='The omopolymeric span',
+        help='The omopolymeric span.',
     )
     parser.add_argument(
         '-sf',
         '--splicing-file',
-        help='The file containing the splicing sites positions',
+        help='The file containing splicing site positions.',
     )
     parser.add_argument(
         '-ss',
         '--splicing-span',
         type=int,
         default=4,
-        help='The splicing span',
+        help='The splicing span.',
     )
     parser.add_argument(
         '-mrl',
         '--min-read-length',
         type=int,
         default=30,  # noqa:WPS432
-        help='Reads whose length is below this value will be discarded.',
+        help='Reads with length below -mrl will be discarded.',
     )
     parser.add_argument(
         '-q',
         '--min-read-quality',
         type=int,
         default=20,  # noqa:WPS432
-        help='Reads with mapping quality below this value will be discarded.',
+        help='Reads with mapping quality below -q will be discarded.',
     )
     parser.add_argument(
         '-bq',
         '--min-base-quality',
         type=int,
         default=30,  # noqa:WPS432
-        help='Base quality below this value will not be included in ' +
-        'the analysis.',
+        help='Base quality below -bq will bed discarded.',
     )
     parser.add_argument(
         '-mbp',
         '--min-base-position',
         type=int,
         default=0,
-        help='Bases which reside in a previous position (in the read)' +
-        'will not be included in the analysis.',
+        help='Ignores the first -mbp bases in each read.',
     )
     parser.add_argument(
         '-Mbp',
         '--max-base-position',
         type=int,
         default=0,
-        help='Bases which reside in a further position (in the read)' +
-        'will not be included in the analysis.',
+        help='Ignores the last -Mpb bases in each read.',
     )
     parser.add_argument(
         '-l',
-        '--min-column-length',
+        '--min-read-depth',
         type=int,
         default=1,
-        help='Positions whose columns have length below this value will' +
-        'not be included in the analysis.',
+        help='Only report on positions with at least -l read depth',
     )
     parser.add_argument(
         '-e',
@@ -351,8 +338,7 @@ def parse_options():  # noqa:WPS213
         '--min-edits-per-nucleotide',
         type=int,
         default=0,
-        help='Positions whose columns have bases with less than' +
-        'min-edits-per-base edits will not be included in the analysis.',
+        help='Positions with fewer than -men edits will not be discarded.',
     )
     parser.add_argument(
         '-me',
@@ -360,16 +346,14 @@ def parse_options():  # noqa:WPS213
         type=int,
         default=0,  # noqa:WPS432
         help='The minimum number of editing events (per position). ' +
-        'Positions whose columns have bases with less than ' +
-        '"min-edits-per-base edits" will not be included in the ' +
-        'analysis.',
+        'Positions with fewer than -me edits will be discarded.',
     )
     parser.add_argument(
         '-Men',
         '--max-editing-nucleotides',
         type=int,
-        default=100,  # noqa:WPS432
-        help='The maximum number of editing nucleotides, from 0 to 4 ' +
+        default=4,  # noqa:WPS432
+        help='The maximum number of editing nucleotides, from 0 to 3 ' +
         '(per position). Positions whose columns have more than ' +
         '"max-editing-nucleotides" will not be included in the analysis.',
     )
@@ -378,8 +362,8 @@ def parse_options():  # noqa:WPS213
         '--strand-confidence-threshold',
         type=float,
         default=0.7,  # noqa:WPS432
-        help='Only report the strandedness if at least this proportion of ' +
-        'reads are of a given strand',
+        help='Only report the strandedness if at least -T proportion of ' +
+        'reads are of a given strand.',
     )
     parser.add_argument(
         '-C',
@@ -393,25 +377,25 @@ def parse_options():  # noqa:WPS213
         '-V',
         '--verbose',
         default=False,
-        help='Verbose information in stderr',
+        help='Run in verbose mode.',
         action='store_true',
     )
     parser.add_argument(
         '-N',
         '--dna',
         default=False,
-        help='Run REDItools 2.0 on DNA-Seq data',
+        help='Run REDItools on DNA-Seq data.',
         action='store_true',
     )
     parser.add_argument(
         '-B',
         '--bed_file',
-        help='Path of BED file containing target self.regions',
+        help='Only analyze regions in the provided BED file.',
     )
     parser.add_argument(
         '-t',
         '--threads',
-        help='Number of threads to run',
+        help='Number of threads for parallel processing.',
         type=int,
         default=1,
     )
@@ -419,7 +403,7 @@ def parse_options():  # noqa:WPS213
         '-w',
         '--window',
         help='How many bp should be processed by each thread at a time. ' +
-        'Defaults to full contig.',
+        'Zero uses the full contig.',
         type=int,
         default=0,
     )
@@ -427,18 +411,18 @@ def parse_options():  # noqa:WPS213
         '-k',
         '--exclude_regions',
         nargs='+',
-        help='Path of BED file containing regions to exclude from analysis',
+        help='Skip regions in the provided BED file(s).',
     )
     parser.add_argument(
         '-E',
         '--exclude_reads',
-        help='Path to a text file listing read names to exclude from analysis',
+        help='Text file listing read names to exclude from analysis.',
     )
     parser.add_argument(
         '-d',
         '--debug',
         default=False,
-        help='REDItools is run in DEBUG mode.',
+        help='Run in debug mode.',
         action='store_true',
     )
 

reditools/file_utils.py

@@ -2,11 +2,8 @@
 
 import csv
 import os
-from collections import defaultdict
 from gzip import open as gzip_open
 
-from sortedcontainers import SortedSet
-
 from reditools.region import Region
 
 
@@ -68,54 +65,36 @@ def concat(output, *fnames, clean_up=True, encoding='utf-8'):
             os.remove(fname)
 
 
-def load_poly_regions(fname):
-    """
-    Read omopolymeric positions from a file.
-
-    Parameters:
-        fname (str): File path
-
-    Returns:
-        (dict): Contigs and regions
-    """
-    poly_regions = defaultdict(set)
-    with read_bed_file(fname) as reader:
-        for row in reader:
-            poly_regions[row[0]] = Region(
-                contig=row[0],
-                start=row[1],
-                stop=row[2],
-            )
-    return poly_regions
-
-
-def load_splicing_file(splicing_file, span):
+def load_splicing_file(splicing_file, splicing_span):
     """
     Read splicing positions from a file.
 
     Parameters:
         splicing_file (str): File path
-        span(int): Width of splice sites
+        splicing_span(int): Width of splice sites
 
-    Returns:
-        (dict): Contig and positions
+    Yeilds:
+        Splicing file contents as Regions.
     """
-    splice_positions = defaultdict(SortedSet)
     strand_map = {'-': 'D', '+': 'A'}
 
-    with open_stream(splicing_file, 'r') as stream:
-        for line in stream:
-            fields = line.strip().split()
-
-            chrom = fields[0]
-            strand = fields[4]
-            splice = fields[3]
-            span = int(fields[1])
-
-            coe = -1 if strand_map.get(strand, None) == splice else 1
-            new_positions = [1 + span + coe * fctr for fctr in range(span)]
-            splice_positions[chrom] |= new_positions
-        return splice_positions
+    stream = open_stream(splicing_file)
+    reader = csv.reader(
+        filter(lambda row: row[0] != '#', stream),
+        delimiter=' ',
+    )
+    for row in reader:
+        contig = row[0]
+        span = int(row[1])
+        splice = row[3]
+        strand = row[4]
+
+        coe = -1 if strand_map.get(strand, None) == splice else 1
+        start = 1 + span
+        stop = start + splicing_span * coe
+        if start > stop:
+            start, stop = stop, start
+        yield Region(contig=contig, start=start, stop=stop)
 
 
 def load_text_file(file_name):

reditools/homopolymerics.py

@@ -42,7 +42,11 @@ def parse_options():
     Returns:
         namespace
     """
-    parser = argparse.ArgumentParser(description='REDItools 2.0')
+    parser = argparse.ArgumentParser(
+        prog="reditools find-repeats",
+        description='REDItools3',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
     parser.add_argument(
         'file',
         help='The fasta file to be analyzed',
@@ -57,6 +61,7 @@ def parse_options():
     parser.add_argument(
         '-o',
         '--output',
+        default='/dev/stdout',
         help='Destination to write results. Default is to use STDOUT. ' +
         'If the filename ends in .gz, the contents will be gzipped.',
     )

reditools/index.py

@@ -180,7 +180,11 @@ def parse_options():  # noqa:WPS213
     Returns:
         namespace: commandline args
     """
-    parser = argparse.ArgumentParser(description='REDItools 2.0')
+    parser = argparse.ArgumentParser(
+        prog="reditools index",
+        description='REDItools3',
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
     parser.add_argument(
         'file',
         nargs='+',
@@ -189,6 +193,7 @@ def parse_options():  # noqa:WPS213
     parser.add_argument(
         '-o',
         '--output-file',
+        default='/dev/stdout',
         help='The output statistics file',
     )
     parser.add_argument(
@@ -239,7 +244,7 @@ def main():
             indexer.add_target_from_bed(trg_fname)
 
     if options.output_file:
-        stream = open_stream(options.output_fipe, 'w')
+        stream = open_stream(options.output_file, 'w')
     else:
         stream = sys.stdout
 

reditools/reditools.py

@@ -127,7 +127,6 @@ class REDItools(object):
         self._target_positions = False
         self._exclude_positions = {}
         self._splice_positions = []
-
         self._specific_edits = None
 
         self.reference = None
@@ -294,6 +293,20 @@ class REDItools(object):
         """
         return self._exclude_positions
 
+    @property
+    def max_alts(self):
+        """Maximum number of alternative bases for a position."""
+        return self._max_alts
+
+    @max_alts.setter
+    def max_alts(self, max_alts):
+        self._max_alts = max_alts
+        function = self._rtqc.check_max_alts
+        if max_alts < 3:
+            self._rtqc.add(function)
+        else:
+            self._rtqc.discard(function)
+
     def exclude(self, regions):
         """
         Explicitly skip specified genomic regions.

reditools/rtchecks.py

@@ -272,3 +272,26 @@ class RTChecks(object):
                 )
                 return False
         return True
+
+    def check_max_alts(self, bases, rtools):
+        """
+        Check that there are no more than a max number of alts.
+
+        Parameters:
+            bases (CompiledPosition): Base position under analysis
+            rtools (REDItools): Object running the analysis
+
+        Returns:
+            (bool): True if there are n or fewer alts
+        """
+
+        alts = bases.get_variants()
+        if len(alts) > rtools.max_alts:
+            rtools.log(
+                Logger.debug_level,
+                'DISCARD COLUMN alts={} > {}',
+                len(alts),
+                rtools.max_alts,
+            )
+            return False
+        return True