Added option to NuQCJob to annotate filtered fastq.

sequence_processing_pipeline/Commands.py

@@ -130,3 +130,58 @@ def demux(id_map, fp, out_d, task, maxtask):
     for d in openfps.values():
         for f in d.values():
             f.close()
+
+
+def annotate_filtered_fastq(original_path, stripped_path, output_path):
+    """
+    Annotates a FASTQ file w/missing descriptions using original file.
+    :param original_path: A path to the original, unfiltered file.
+    :param stripped_path: A path to the filtered file.
+    :param output_path: A path for the output file.
+    :return: None
+    """
+    mapping = {}
+
+    # Per FASTQ specification: https://en.wikipedia.org/wiki/FASTQ_format
+    # lines beginning with '@' contain the sequence's identifier and an
+    # optional description or 'metadata'.
+
+    # minimap2 is a tool used to perform host filtering on fastq files.
+    # The preferred output for this program is SAM format:
+    # https://en.wikipedia.org/wiki/SAM_(file_format)
+
+    # SAM format cannot preserve the optional metadata field and hence the
+    # metadata will disappear after using minimap2 to filter a file and
+    # samtools to convert the file from SAM back to FASTQ format.
+
+    # It is straightforward to process even large fastq files line by line
+    # sequence identifier lines are unique and easily identified as they are
+    # the only lines in a FASTQ file beginning with '@'. It is thus straight-
+    # forward to process even large files to build a mapping between
+    # sequence identifiers and optional metadata fields.
+    with open(original_path, 'r') as f:
+        for line in f:
+            if line.startswith('@'):
+                line = line.strip().split()
+                if len(line) != 2:
+                    raise ValueError(f"'{original_path}' does not appear to "
+                                     "contain sequence identifiers with "
+                                     "optional metadata")
+                # where sequence identifier = line[0] and
+                # the optional description = line[1].
+                mapping[line[0]] = line[1]
+
+    # As the target file is read line by line, it is straightforward to
+    # annotate each sequence identifier line w/the optional description from
+    # the original file in place.
+    with open(stripped_path, 'r') as f:
+        with open(output_path, 'w') as of:
+            for line in f:
+                line = line.strip()
+                if line.startswith('@'):
+                    if line in mapping:
+                        print(line + ' ' + mapping[line], file=of)
+                    else:
+                        raise ValueError(f"'{line}' is not in mapping!")
+                else:
+                    print(line, file=of)

sequence_processing_pipeline/NuQCJob.py

@@ -44,7 +44,8 @@ def __init__(self, fastq_root_dir, output_path, sample_sheet_path,
                  wall_time_limit, jmem, fastp_path, minimap2_path,
                  samtools_path, modules_to_load, qiita_job_id,
                  max_array_length, known_adapters_path, movi_path, gres_value,
-                 pmls_path, bucket_size=8, length_limit=100, cores_per_task=4):
+                 pmls_path, bucket_size=8, length_limit=100, cores_per_task=4,
+                 annotate_fastq_files=False):
         """
         Submit a slurm job where the contents of fastq_root_dir are processed
         using fastp, minimap2, and samtools. Human-genome sequences will be
@@ -69,6 +70,8 @@ def __init__(self, fastq_root_dir, output_path, sample_sheet_path,
         :param bucket_size: the size in GB of each bucket to process
         :param length_limit: reads shorter than this will be discarded.
         :param cores_per_task: Number of CPU cores per node to request.
+        :param annotate_fastq_files: If True, copy optional descriptions in
+                                     original fastq files to filtered files.
         """
         super().__init__(fastq_root_dir,
                          output_path,
@@ -96,6 +99,7 @@ def __init__(self, fastq_root_dir, output_path, sample_sheet_path,
         self.movi_path = movi_path
         self.gres_value = gres_value
         self.pmls_path = pmls_path
+        self.annotate_fastq_files = annotate_fastq_files
 
         # for projects that use sequence_processing_pipeline as a dependency,
         # jinja_env must be set to sequence_processing_pipeline's root path,
@@ -427,9 +431,22 @@ def _generate_mmi_filter_cmds(self, working_dir):
         cmds.append(f"[ -e {tmp_file1} ] && rm {tmp_file1}")
         cmds.append(f"[ -e {tmp_file2} ] && rm {tmp_file2}")
 
+        if self.annotate_fastq_files is True:
+            annotated_final_output = join(working_dir,
+                                          "seqs.interleaved.filter_alignment"
+                                          ".annotated.fastq")
+
+            cmds.append(f"annotate_filtered_fastq {initial_input} "
+                        f"{final_output} {annotated_final_output}")
+
+            # if filtered sequence results were re-annotated using metadata
+            # from the original file, make sure the output from this operation
+            # becomes the true final output file.
+            cmds.append(f"mv {annotated_final_output} {final_output}")
+
         return "\n".join(cmds)
 
-    def _generate_job_script(self, max_bucket_size):
+    def _generate_job_script(self, max_bucket_size, annotate_fastq=False):
         # bypass generating job script for a force-fail job, since it is
         # not needed.
         if self.force_job_fail:

sequence_processing_pipeline/scripts/annotate_filtered_fastq.py

@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+import click
+from sequence_processing_pipeline.Commands import annotate_filtered_fastq
+
+
+@click.command()
+@click.argument('original_path', required=True)
+@click.argument('stripped_path', required=True)
+@click.argument('output_path', required=True)
+def main(original_path, stripped_path, output_path):
+    """
+        Annotates a stripped fastq file based on descriptions from original.
+        Additional info appears on stderr.
+        Exits w/(1) if an id appears in stripped file but not in original.
+    """
+    try:
+        annotate_filtered_fastq(original_path, stripped_path, output_path)
+    except ValueError as e:
+        # explicitly catch known potential errors and ensure they exit w/a
+        # return value of 1 after politely stating the cause of the error sans
+        # stacktrace.
+        print(str(e))
+        exit(1)
+
+
+if __name__ == '__main__':
+    main()

sequence_processing_pipeline/tests/data/seqs.interleaved.fastq

@@ -0,0 +1,38 @@
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:3900:1600/1 BX:Z:TAGACACGAAGGTTGGAC
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:3900:1600/2 BX:Z:TAGACACGAAGGTTGGAC
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:F:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FF,FFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:7740:1600/1 BX:Z:AAAGATGAGGGCAGTTAA
+CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:7740:1600/2 BX:Z:AAAGATGAGGGCAGTTAA
+GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:12790:1600/1 BX:Z:TGGGGGTCGTAACACGAA
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:12790:1600/2 BX:Z:TGGGGGTCGTAACACGAA
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFF::FFFFF,FFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13250:1600/1 BX:Z:CGAGGCAGACTTGAATGC
+CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFF:FFFFF:FFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13250:1600/2 BX:Z:CGAGGCAGACTTGAATGC
+GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFF:FFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13520:1600/1 BX:Z:CAGACACGTAGGTGGGAC
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13520:1600/2 BX:Z:CAGACACGTAGGTGGGAC
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT

sequence_processing_pipeline/tests/data/seqs.interleaved.filter_alignment.fastq

@@ -0,0 +1,38 @@
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:3900:1600/1
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:3900:1600/2
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:F:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FF,FFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:7740:1600/1
+CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:7740:1600/2
+GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:12790:1600/1
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:12790:1600/2
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFF::FFFFF,FFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13250:1600/1
+CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFFFFFFFFFFFFFFFFF:FFFFF:FFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13250:1600/2
+GGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF:FFF:FFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13520:1600/1
+AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
++
+FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+@1::MUX::FS10001773:68:BTR67708-1611:1:1101:13520:1600/2
+TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT

sequence_processing_pipeline/tests/test_NuQCJob.py

@@ -2106,9 +2106,52 @@ def test_generate_mmi_filter_cmds(self):
 
         exp = "\n".join(exp)
 
-        print(obs)
-        print("###")
-        print(exp)
+        self.assertEqual(obs, exp)
+
+    def test_generate_mmi_filter_cmds_w_annotate_fastq(self):
+        double_db_paths = ["db_path/mmi_1.db", "db_path/mmi_2.db"]
+        job = NuQCJob(
+            self.fastq_root_path,
+            self.output_path,
+            self.good_sample_sheet_path,
+            double_db_paths,
+            "queue_name",
+            1,
+            1440,
+            "8",
+            "fastp",
+            "minimap2",
+            "samtools",
+            [],
+            self.qiita_job_id,
+            1000,
+            "",
+            self.movi_path,
+            self.gres_value,
+            self.pmls_path,
+            annotate_fastq_files=True
+        )
+
+        obs = job._generate_mmi_filter_cmds("/my_work_dir")
+
+        exp = [
+            "minimap2 -2 -ax sr -t 2 db_path/mmi_1.db /my_work_dir/seqs."
+            "interleaved.fastq -a | samtools fastq -@ 2 -f 12 -F 256 > "
+            "/my_work_dir/foo",
+            "minimap2 -2 -ax sr -t 2 db_path/mmi_2.db /my_work_dir/foo -a | "
+            "samtools fastq -@ 2 -f 12 -F 256 > /my_work_dir/bar",
+            "mv /my_work_dir/bar /my_work_dir/seqs.interleaved.filter_"
+            "alignment.fastq",
+            "[ -e /my_work_dir/foo ] && rm /my_work_dir/foo",
+            "[ -e /my_work_dir/bar ] && rm /my_work_dir/bar",
+            "annotate_filtered_fastq /my_work_dir/seqs.interleaved.fastq "
+            "/my_work_dir/seqs.interleaved.filter_alignment.fastq "
+            "/my_work_dir/seqs.interleaved.filter_alignment.annotated.fastq",
+            "mv /my_work_dir/seqs.interleaved.filter_alignment.annotated.fastq"
+            " /my_work_dir/seqs.interleaved.filter_alignment.fastq"
+        ]
+
+        exp = "\n".join(exp)
 
         self.assertEqual(obs, exp)
 

sequence_processing_pipeline/tests/test_commands.py

@@ -3,13 +3,30 @@
 from tempfile import TemporaryDirectory
 import gzip
 import os
-from os.path import join
 from sequence_processing_pipeline.Commands import (split_similar_size_bins,
-                                                   demux)
+                                                   demux,
+                                                   annotate_filtered_fastq)
 import io
+from os.path import abspath, join, exists
+from functools import partial
+from os import remove
 
 
 class CommandTests(unittest.TestCase):
+    def setUp(self):
+        root = partial(join,
+                       abspath('./sequence_processing_pipeline'),
+                       'tests',
+                       'data')
+
+        self.stripped_fastq = root('seqs.interleaved.filter_alignment.fastq')
+        self.original_fastq = root('seqs.interleaved.fastq')
+        self.output_fastq = root('output.fastq')
+
+    def tearDown(self):
+        if exists(self.output_fastq):
+            remove(self.output_fastq)
+
     @patch('os.stat')
     @patch('glob.glob')
     def test_split_similar_size_bins(self, glob, stat):
@@ -84,6 +101,23 @@ def test_demux(self):
             self.assertFalse(os.path.exists(join(tmp, 'a_R1.fastq.gz')))
             self.assertFalse(os.path.exists(join(tmp, 'a_R2.fastq.gz')))
 
+    def test_annotate_filtered_fastq(self):
+        annotate_filtered_fastq(self.original_fastq, self.stripped_fastq,
+                                self.output_fastq)
+
+        with open(self.original_fastq, 'r') as exp_fp:
+            with open(self.output_fastq, 'r') as obs_fp:
+                # Within the sample fastq files, the first ten sequences of
+                # the original matched file passed successfully through
+                # host filtering and are present in the filtered result. Hence,
+                # the filtered version is the same as the original, minus the
+                # optional descriptions. Hence, if the optional descriptions
+                # are restored, the output fastq will be identical to the
+                # original.
+                exp = exp_fp.readlines()
+                obs = obs_fp.readlines()
+                self.assertEqual(obs, exp)
+
 
 if __name__ == '__main__':
     unittest.main()

setup.py

@@ -48,4 +48,7 @@
         ],
       entry_points={
           'console_scripts': ['demux=sequence_processing_pipeline.scripts.cli'
-                              ':demux', ], })
+                              ':demux',
+                              'annotate_filtered_fastq=sequence_processing_'
+                              'pipeline.scripts.annotate_filtered_fastq:main'],
+      })