Merge pull request #123 from epifluidlab/develop

0.9.1

CHANGELOG.md

@@ -7,7 +7,25 @@ The format is based on
 and this project adheres to
 [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.9.0] - 2024-12-13
+## [0.9.1] - 2024-12-17
+
+### Fixed
+- CLI no longer prints an error message if `finaletoolkit` is called without args.
+- `frag-length-bins`, when writing a file, now writes the interval between
+`min` and `max` as inclusive. That is, previously when `min=1` and `max=2`,
+only fragments of length 1 are reported. Now when such a result is calculated, 
+the interval given is `min=1` and `max=1`.
+- Updated some descriptions and docstrings.
+
+### Added
+- `adjust-wps` now has an option `-S` or `--exclude-savgol` to not perform
+Savitsky-Golay filtering.
+
+### Changed
+- Several CLI options were renamed so that underscores become hyphens. This is
+for consistency and to simplify writing commands.
+
+## [0.9.0] - 2024-12-16
 
 ### Removed
 - `strand_location` arg from `agg_bigwig`

src/finaletoolkit/cli/main_cli.py

@@ -59,7 +59,7 @@ def main_cli_parser():
         'coverage over.')
     cli_coverage.add_argument(
         '-o',
-        '--output_file',
+        '--output-file',
         default='-',
         help='A BED file containing coverage values over the intervals '
         'specified in interval file.')
@@ -93,15 +93,15 @@ def main_cli_parser():
         )
     cli_coverage.add_argument(
         '-p',
-        '--intersect_policy',
+        '--intersect-policy',
         choices=['midpoint', 'any'],
         default='midpoint',
         type=str,
         help='Specifies what policy is used to include fragments in the'
         ' given interval. See User Guide for more information.')
     cli_coverage.add_argument(
         '-q',
-        '--quality_threshold',
+        '--quality-threshold',
         default=30,
         type=int,
         help='Minimum mapping quality threshold.')
@@ -162,7 +162,7 @@ def main_cli_parser():
         )
     cli_frag_length_bins.add_argument(
         '-p',
-        '--intersect_policy',
+        '--intersect-policy',
         choices=['midpoint', 'any'],
         default='midpoint',
         type=str,
@@ -176,7 +176,7 @@ def main_cli_parser():
         'into.')
     cli_frag_length_bins.add_argument(
         '-o',
-        '--output_file',
+        '--output-file',
         default='-',
         type=str,
         help='A .TSV file containing containing fragment lengths binned'
@@ -188,7 +188,7 @@ def main_cli_parser():
     )
     cli_frag_length_bins.add_argument(
         '-q',
-        '--quality_threshold',
+        '--quality-threshold',
         default=30,
         type=int,
         help="Minimum mapping quality threshold.")
@@ -231,7 +231,7 @@ def main_cli_parser():
         )
     cli_frag_length_intervals.add_argument(
         '-p',
-        '--intersect_policy',
+        '--intersect-policy',
         choices=['midpoint', 'any'],
         default='midpoint',
         type=str,
@@ -365,7 +365,7 @@ def main_cli_parser():
         'data.')
     cli_wps.add_argument(
         'site_bed',
-        help='Path to a BED file containing intervals to calculate WPS '
+        help='Path to a BED file containing sites to calculate WPS '
         'over. The intervals in this BED file should be sorted, first '
         'by `contig` then `start`.')
     cli_wps.add_argument(
@@ -374,20 +374,21 @@ def main_cli_parser():
         help='A .chrom.sizes file containing chromosome names and sizes.')
     cli_wps.add_argument(
         '-o',
-        '--output_file',
+        '--output-file',
         default='-',
         help='A bigWig file containing the WPS results over the '
         'intervals specified in interval file.')
     cli_wps.add_argument(
         '-i',
-        '--interval_size',
+        '--interval-size',
         default=5000,
         type=int,
-        help='Size in bp of each interval in the interval file. Default is '
-        '5000')
+        help='Size in bp of the intervals to calculate WPS over. These'
+        'new intervals are centered over those specified in the site_bed.'
+        'Default is 5000')
     cli_wps.add_argument(
         '-W',
-        '--window_size',
+        '--window-size',
         default=120,
         type=int,
         help='Size of the sliding window used to calculate WPS scores.'
@@ -422,7 +423,7 @@ def main_cli_parser():
         'calculation. Deprecated. Use --max-length instead.')
     cli_wps.add_argument(
         '-q',
-        '--quality_threshold',
+        '--quality-threshold',
         default=30,
         type=int,
         help="Minimum mapping quality threshold. Default is 30")
@@ -474,7 +475,7 @@ def main_cli_parser():
         '--median-window-size',
         default=1000,
         type=int,
-        help='Size of the median filter window used to adjust WPS scores.')
+        help='Size of the median filter or mean filter window used to adjust WPS scores.')
     cli_adjust_wps.add_argument(
         '-s',
         '--savgol-window-size',
@@ -488,6 +489,13 @@ def main_cli_parser():
         default=2,
         type=int,
         help='Degree polynomial for Savitsky-Golay filter.')
+    cli_adjust_wps.add_argument(
+        '-S',
+        '--exclude-savgol',
+        dest='savgol',
+        action='store_false',
+        help='Do not perform Savitsky-Golay filtering'
+        'scores.')
     cli_adjust_wps.add_argument(
         '-w',
         '--workers',
@@ -861,7 +869,7 @@ def main_cli_parser():
         help='Output BAM file path.')
     cli_filter_bam.add_argument(
         '-q',
-        '--quality_threshold',
+        '--quality-threshold',
         type=int,
         default=30,
         help='Minimum mapping quality threshold.')
@@ -975,15 +983,18 @@ def main_cli():
     parser = main_cli_parser()
 
     args = parser.parse_args()
-    try:
-        function = args.func
-        funcargs = vars(args)
-        funcargs.pop('func')
+    if hasattr(args, "func"):
+        try:
+            function = args.func
+            funcargs = vars(args)
+            funcargs.pop('func')
 
-        function(**funcargs)
-    except AttributeError as e:
-        stderr.write(f"FinaleToolkit recieved AttributeError: {e}\n")
-        stderr.write("Please see usage instructions below.\n")
+            function(**funcargs)
+        except AttributeError as e:
+            stderr.write(f"FinaleToolkit recieved AttributeError: {e}\n")
+            stderr.write("Please see usage instructions below.\n")
+            parser.print_help()
+    else:
         parser.print_help()
 
 

src/finaletoolkit/frag/adjust_wps.py

@@ -64,6 +64,7 @@ def _single_adjust_wps(
         mean: bool,
         subtract_edges: bool,
         edge_size: int,
+        savgol: bool,
 ):
     """
     Takes a wps WIG file and applies a median filter and a Savitsky-
@@ -123,9 +124,11 @@ def _single_adjust_wps(
         else:
             adjusted_positions, adjusted_scores = _mean_filter(
                 intervals['starts'], intervals['scores'], median_window_size)
-
-        filtered_scores = savgol_filter(
-            adjusted_scores, savgol_window_size, savgol_poly_deg)
+        if savgol:
+            filtered_scores = savgol_filter(
+                adjusted_scores, savgol_window_size, savgol_poly_deg)
+        else:
+            filtered_scores = adjusted_scores
 
         assert len(adjusted_positions) == len(filtered_scores)
 
@@ -161,6 +164,7 @@ def adjust_wps(
     median_window_size: int=1000,
     savgol_window_size: int=21,
     savgol_poly_deg: int=2,
+    savgol: bool=True,
     mean: bool=False,
     subtract_edges: bool=False,
     edge_size: int=500,
@@ -191,6 +195,8 @@ def adjust_wps(
         Size of Savitsky Golay filter window. Default is 21.
     savgol_poly_deg : int, optional
         Degree polynomial for Savitsky Golay filter. Default is 2.
+    savgol : bool, optional
+        Set to true to perform Savitsky-Golay filtering.
     mean : bool, optional
         If true, a mean filter is used instead of median. Default is
         False.
@@ -256,6 +262,7 @@ def adjust_wps(
                     mean,
                     subtract_edges,
                     edge_size,
+                    savgol
                 ))
     else:
         raise ValueError('Invalid filetype for interval_file.')

src/finaletoolkit/frag/frag_length.py

@@ -341,7 +341,7 @@ def frag_length_bins(
 
             out.write('min\tmax\tcount\n')
             for bin, count in zip(bins, counts):
-                out.write(f'{bin}\t{bin+bin_size}\t{count}\n')
+                out.write(f'{bin}\t{bin+bin_size-1}\t{count}\n')
 
             if histogram_path!=None:
                 plot_histogram(frag_len_dict, num_bins=n_bins,

src/finaletoolkit/frag/multi_wps.py

@@ -44,7 +44,7 @@ def multi_wps(
         BAM, SAM, or tabix file containing paired-end fragment reads or its
         path. `AlignmentFile` must be opened in read mode.
     site_bed: str
-        BED file containing intervals to perform WPS on. The intervals
+        BED file containing sites to perform WPS on. The intervals
         in this BED file should be sorted, first by `contig` then
         `start`.
     chrom_sizes: str or pathlike, optional
@@ -55,8 +55,11 @@ def multi_wps(
         Size of window to calculate WPS. Default is k = 120, equivalent
         to L-WPS.
     interval_size : int, optional
-        Size of each interval specified in the bed file. Should be the
-        same for every interval. Default is 5000.
+        Size of intervals to calculate WPS over. A mid-point is calculated
+        for each interval in the BED file, and an interval of the specified
+        size is used. This is helpful especially when calculating a window
+        around a genomic feature like transcription start sites. Default
+        is 5000.
     min_length : int, optional
         Specifies lowest fragment length included in calculation.
         Default is 120, equivalent to long fraction.

src/finaletoolkit/version.py

@@ -2,4 +2,4 @@
 Single-source module for the package version number.
 """
 
-__version__ = "0.9.0"
+__version__ = "0.9.1"