Merge pull request #45 from an-altosian/develop

Develop

.github/workflows/testing.yml

@@ -15,7 +15,7 @@ jobs:
         echo $CONDA/bin >> $GITHUB_PATH
     - name: Install dependencies
       run: |
-        conda install -n base python=3.10 conda-forge::biopython numpy==1.26 bioconda::pyranges==0.0.129 packaging bioconda::scanpy pytest -y
+        conda install -n base -c bioconda -c conda-forge python=3.10 packaging pandas scanpy pytest -y
 
     - name: pytest
       run: |

bin/pyroe

@@ -1,11 +1,6 @@
 #!/usr/bin/env python
 
 import logging
-from pyroe import make_splici_txome, make_spliceu_txome
-from pyroe import id_to_name
-
-if make_spliceu_txome is None or make_splici_txome is None or id_to_name is None:
-    raise ImportError("To run pyroe CLI, Please install pyranges, biopython and bedtools.")
 from pyroe import fetch_processed_quant
 from pyroe import convert
 from pyroe import output_formats
@@ -37,133 +32,6 @@ if __name__ == "__main__":
         help="additional help",
     )
 
-    # make-splici
-    parser_makeSplici = subparsers.add_parser(
-        "make-spliced+intronic",
-        help="Make spliced + intronic reference",
-        aliases=["make-splici"],
-    )
-    parser_makeSplici.set_defaults(command="make-spliced+intronic")
-    parser_makeSplici.add_argument(
-        "genome_path",
-        metavar="genome-path",
-        type=str,
-        help="The path to a genome fasta file.",
-    )
-    parser_makeSplici.add_argument(
-        "gtf_path", metavar="gtf-path", type=str, help="The path to a gtf file."
-    )
-    parser_makeSplici.add_argument(
-        "read_length",
-        metavar="read-length",
-        type=int,
-        help="The read length of the single-cell experiment being processed (determines flank size).",
-    )
-    parser_makeSplici.add_argument(
-        "output_dir",
-        metavar="output-dir",
-        type=str,
-        help="The output directory where splici reference files will be written.",
-    )
-    parser_makeSplici.add_argument(
-        "--filename-prefix",
-        type=str,
-        default="splici",
-        help="The file name prefix of the generated output files.",
-    )
-    parser_makeSplici.add_argument(
-        "--flank-trim-length",
-        type=int,
-        default=5,
-        help="Determines the amount subtracted from the read length to get the flank length.",
-    )
-    parser_makeSplici.add_argument(
-        "--extra-spliced",
-        type=str,
-        help="The path to an extra spliced sequence fasta file.",
-    )
-    parser_makeSplici.add_argument(
-        "--extra-unspliced",
-        type=str,
-        help="The path to an extra unspliced sequence fasta file.",
-    )
-    parser_makeSplici.add_argument(
-        "--bt-path",
-        type=str,
-        default="bedtools",
-        help="The path to bedtools v2.30.0 or greater.",
-    )
-    parser_makeSplici.add_argument(
-        "--no-bt",
-        action="store_true",
-        help="A flag indicates whether bedtools will be used for generating splici reference files.",
-    )
-    parser_makeSplici.add_argument(
-        "--dedup-seqs",
-        action="store_true",
-        help="A flag indicates whether identical sequences will be deduplicated.",
-    )
-    parser_makeSplici.add_argument(
-        "--no-flanking-merge",
-        action="store_true",
-        help="A flag indicates whether flank lengths will be considered when merging introns.",
-    )
-
-    # make-spliceu
-    parser_makeSpliceu = subparsers.add_parser(
-        "make-spliced+unspliced",
-        help="Make spliced + unspliced reference",
-        aliases=["make-spliceu"],
-    )
-    parser_makeSpliceu.set_defaults(command="make-spliced+unspliced")
-    parser_makeSpliceu.add_argument(
-        "genome_path",
-        metavar="genome-path",
-        type=str,
-        help="The path to a genome fasta file.",
-    )
-    parser_makeSpliceu.add_argument(
-        "gtf_path", metavar="gtf-path", type=str, help="The path to a gtf file."
-    )
-    parser_makeSpliceu.add_argument(
-        "output_dir",
-        metavar="output-dir",
-        type=str,
-        help="The output directory where Spliceu reference files will be written.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--filename-prefix",
-        type=str,
-        default="spliceu",
-        help="The file name prefix of the generated output files.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--extra-spliced",
-        type=str,
-        help="The path to an extra spliced sequence fasta file.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--extra-unspliced",
-        type=str,
-        help="The path to an extra unspliced sequence fasta file.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--bt-path",
-        type=str,
-        default="bedtools",
-        help="The path to bedtools v2.30.0 or greater.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--no-bt",
-        action="store_true",
-        help="A flag indicates whether bedtools will be used for generating Spliceu reference files.",
-    )
-    parser_makeSpliceu.add_argument(
-        "--dedup-seqs",
-        action="store_true",
-        help="A flag indicates whether identical sequences will be deduplicated.",
-    )
-
     # parse available datasets
     available_datasets = fetch_processed_quant()
     epilog = "\n".join(
@@ -213,20 +81,6 @@ if __name__ == "__main__":
         help="A flag indicates whether help messaged should not be printed.",
     )
 
-    parser_id_to_name = subparsers.add_parser(
-        "id-to-name", help="Generate a gene id to gene name mapping file from a GTF."
-    )
-    parser_id_to_name.set_defaults(command="id-to-name")
-    parser_id_to_name.add_argument("gtf_file", help="The GTF input file.")
-    parser_id_to_name.add_argument(
-        "output", help="The path to where the output tsv file will be written."
-    )
-    parser_id_to_name.add_argument(
-        "--format",
-        help="The input format of the file (must be either GTF or GFF3). This will be inferred from the filename, but if that fails it can be provided explicitly.",
-        default=None,
-    )
-
     out_formats = output_formats()
     parser_convert = subparsers.add_parser(
         "convert", help="Convert alevin-fry quantification result to another format."
@@ -244,7 +98,7 @@ if __name__ == "__main__":
     )
     parser_convert.add_argument(
         "--output-structure",
-        help="The structure that U,S and A counts should occupy in the output matrix.",
+        help="The structure that U,S and A counts should occupy in the output matrix. It will be passed to the output_format argument of the `load_fry` function.",
     )
     parser_convert.add_argument(
         "--output-format",
@@ -262,34 +116,7 @@ if __name__ == "__main__":
 
     # Execute the parse_args() method
     args = parser.parse_args()
-    if args.command == "make-spliced+intronic":
-        make_splici_txome(
-            genome_path=args.genome_path,
-            gtf_path=args.gtf_path,
-            read_length=args.read_length,
-            output_dir=args.output_dir,
-            flank_trim_length=args.flank_trim_length,
-            filename_prefix=args.filename_prefix,
-            extra_spliced=args.extra_spliced,
-            extra_unspliced=args.extra_unspliced,
-            dedup_seqs=args.dedup_seqs,
-            no_bt=args.no_bt,
-            bt_path=args.bt_path,
-            no_flanking_merge=args.no_flanking_merge,
-        )
-    elif args.command == "make-spliced+unspliced":
-        make_spliceu_txome(
-            genome_path=args.genome_path,
-            gtf_path=args.gtf_path,
-            output_dir=args.output_dir,
-            filename_prefix=args.filename_prefix,
-            extra_spliced=args.extra_spliced,
-            extra_unspliced=args.extra_unspliced,
-            dedup_seqs=args.dedup_seqs,
-            no_bt=args.no_bt,
-            bt_path=args.bt_path,
-        )
-    elif args.command == "fetch-quant":
+    if args.command == "fetch-quant":
         fetch_processed_quant(
             dataset_ids=args.dataset_ids,
             fetch_dir=args.fetch_dir,
@@ -299,8 +126,6 @@ if __name__ == "__main__":
         )
     elif args.command == "convert":
         convert(args)
-    elif args.command == "id-to-name":
-        id_to_name(args)
     else:
         print(parser.print_help())
         sys.exit(1)

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyroe
-version = 0.10.0
+version = 0.11.0
 author = Dongze He, Rob Patro
 author_email = [email protected], [email protected]
 description = utilities of alevin-fry
@@ -16,14 +16,14 @@ classifiers =
 packages = find:
 package_dir =
     = src
-# scripts =
-#     bin/pyroe
+scripts =
+    bin/pyroe
 python_requires = >=3.7
 include_package_data = True
 install_requires = 
     packaging >= 21.0
     scanpy >= 1.8.2
-
+    pandas >= 1.3.0
 
 [options.packages.find]
 where = src

src/pyroe/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.10.0"
+__version__ = "0.11.0"
 
 from pyroe.load_fry import load_fry
 from pyroe.fetch_processed_quant import fetch_processed_quant
@@ -7,13 +7,4 @@
 from pyroe.convert import convert
 from pyroe.pyroe_utils import output_formats
 
-
-# try:
-#     from pyroe.make_txome import make_splici_txome, make_spliceu_txome
-#     from pyroe.id_to_name import id_to_name
-# except ImportError:
-#     make_splici_txome = None
-#     make_spliceu_txome = None
-#     id_to_name = None
-
 # flake8: noqa