geoseeq 0.7.3.dev4__py3-none-any.whl → 0.7.4__py3-none-any.whl

geoseeq/cli/constants.py

@@ -1,11 +1,11 @@
 SINGLE_END="short_read::single_end"
 PAIRED_END="short_read::paired_end"
 NANOPORE="long_read::nanopore"
+PACBIO="long_read::pacbio"
 
 READ_MODULE_NAMES = [
     SINGLE_END,
     PAIRED_END,
     NANOPORE,
+    PACBIO,
 ]
-
-

geoseeq/cli/main.py

@@ -55,7 +55,7 @@ def version():
     Use of this tool implies acceptance of the GeoSeeq End User License Agreement.
     Run `geoseeq eula show` to view the EULA.
     """
-    click.echo("0.7.3dev0")  # remember to update pyproject.toml
+    click.echo("0.7.4")  # remember to update pyproject.toml
 
 
 @main.group("advanced")

geoseeq/cli/upload/upload_reads.py

@@ -1,9 +1,10 @@
+# pylint: disable=line-too-long
 import logging
 import click
 import requests
 from os.path import basename
 import pandas as pd
-from multiprocessing import Pool, current_process
+from multiprocessing import current_process
 
 from geoseeq.cli.constants import *
 from geoseeq.cli.shared_params import (
@@ -46,10 +47,10 @@ def _upload_one_file(args):
 
 def _get_regex(knex, filepaths, module_name, lib, regex):
     """Return a regex that will group the files into samples
-    
+
     Tell the user how many files did could not be matched using the regex.
     """
-    seq_length, seq_type = module_name.split('::')[:2]
+    _, seq_type = module_name.split('::')[:2]
     args = {
         'filenames': list(filepaths.keys()),
         'sequence_type': seq_type,
@@ -181,7 +182,13 @@ def flatten_list_of_bams(filepaths):
 @private_option
 @link_option
 @no_new_versions_option
-@click.option('--name-map', default=None, nargs=3, help="A file to use for converting names. Takes three arguments: a file name, a column name for current names, and a column name for new names.")
+@click.option(
+    '--name-map',
+    default=None,
+    nargs=3,
+    required=False,
+    help='Optional CSV and column names used to map existing names to new ones. Provide: <file> <current_name_col> <new_name_col>.'
+)
 @module_option(FASTQ_MODULE_NAMES)
 @project_id_arg
 @click.argument('fastq_files', type=click.Path(exists=True), nargs=-1)
@@ -214,15 +221,23 @@ def cli_upload_reads_wizard(state, cores, overwrite, yes, regex, private, link_t
     $ ls -1 path/to/fastq/files/*.fastq.gz > file_list.txt
     $ geoseeq upload reads --yes --overwrite "GeoSeeq/Example CLI Project" file_list.txt
 
+    \b
+    # Remap sample names using a CSV file with current and new names
+    $ geoseeq upload reads --name-map sample_map.csv current_name new_name "GeoSeeq/Example CLI Project" fastq_files.txt
+
     ---
 
+    The optional ``--name-map`` flag takes three values: a CSV filename,
+    the column containing current names and the column containing new names.
+    When provided, sample names will be translated during upload.
+
     Command Arguments:
-    
+
     [PROJECT_ID] Can be a project UUID, GeoSeeq Resource Number (GRN), or an
     organization name and project name separated by a slash.
 
     \b
-    Examples: 
+    Examples:
      - Name pair: "GeoSeeq/Example CLI Project"
      - UUID: "ed59b913-91ec-489b-a1b9-4ea137a6e5cf"
      - GRN: "grn:gs1:project:ed59b913-91ec-489b-a1b9-4ea137a6e5cf"
@@ -284,12 +299,12 @@ def cli_upload_reads_wizard(state, cores, overwrite, yes, regex, private, link_t
     ---
 
     Command Arguments:
-    
+
     [PROJECT_ID] Can be a project UUID, GeoSeeq Resource Number (GRN), or an
     organization name and project name separated by a slash.
 
     \b
-    Examples: 
+    Examples:
      - Name pair: "GeoSeeq/Example CLI Project"
      - UUID: "ed59b913-91ec-489b-a1b9-4ea137a6e5cf"
      - GRN: "grn:gs1:project:ed59b913-91ec-489b-a1b9-4ea137a6e5cf"
@@ -303,4 +318,14 @@ def cli_upload_reads_wizard(state, cores, overwrite, yes, regex, private, link_t
     # filepaths = {basename(line): line for line in flatten_list_of_bams(files)}
     # click.echo(f'Found {len(filepaths)} files to upload.', err=True)
     # groups = _group_files(knex, filepaths, 'bam::bam', regex, yes)
-    # _do_upload(groups, 'bam::bam', link_type, proj, filepaths, overwrite, no_new_versions, cores, state)
+    # _do_upload(
+    #     groups,
+    #     'bam::bam',
+    #     link_type,
+    #     proj,
+    #     filepaths,
+    #     overwrite,
+    #     no_new_versions,
+    #     cores,
+    #     state,
+    # )

geoseeq/constants.py

@@ -7,6 +7,7 @@ FASTQ_MODULE_NAMES = [
     'short_read::paired_end',
     'short_read::single_end',
     'long_read::nanopore',
+    'long_read::pacbio',
     'raw::raw_reads',
     'genome::fasta',
 ]
@@ -16,4 +17,12 @@ CONFIG_FOLDER = environ.get("XDG_CONFIG_HOME", join(environ["HOME"], ".config"))
 CONFIG_DIR = environ.get("GEOSEEQ_CONFIG_DIR", join(CONFIG_FOLDER, "geoseeq"))
 PROFILES_PATH = join(CONFIG_DIR, "profiles.json")
 
-OBJECT_TYPE_STR = Literal['org', 'project', 'sample', 'sample_result_folder', 'project_result_folder', 'sample_result_file', 'project_result_file']
+OBJECT_TYPE_STR = Literal[
+    'org',
+    'project',
+    'sample',
+    'sample_result_folder',
+    'project_result_folder',
+    'sample_result_file',
+    'project_result_file',
+]

geoseeq/sample.py

@@ -1,6 +1,6 @@
 import urllib
 from .remote_object import RemoteObject
-from .result import SampleResultFile, SampleResultFolder
+from .result import SampleResultFolder
 
 
 class Sample(RemoteObject):
@@ -166,12 +166,14 @@ class Sample(RemoteObject):
             "short_read::paired_end"
             "short_read::single_end"
             "long_read::nanopore"
+            "long_read::pacbio"
         """
         if preference_order is None:
             preference_order = [
                 "short_read::paired_end",
                 "short_read::single_end",
                 "long_read::nanopore",
+                "long_read::pacbio",
             ]
         all_fastqs = self.get_all_fastqs()
         for read_type in preference_order:

{geoseeq-0.7.3.dev4.dist-info → geoseeq-0.7.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: geoseeq
-Version: 0.7.3.dev4
+Version: 0.7.4
 Summary: GeoSeeq command line tools and python API
 Project-URL: Homepage, https://github.com/biotia/geoseeq_api_client
 Project-URL: Issues, https://github.com/biotia/geoseeq_api_client/issues
@@ -84,7 +84,7 @@ $ geoseeq download files --extension fastq.gz "GeoSeeq/Example CLI Project"
 
 GeoSeeq can automatically group fastq files into samples according to their
 sample name, read number, and lane number. It supports paired end, single end,
-and nanopore reads.
+nanopore, and pacbio reads.
 
 Assume you have data from a single ended sequencing run stored as fastq files:
  - Sample1_L1_R1.fastq.gz
@@ -115,6 +115,12 @@ GeoSeeq will automatically create a new sample named `Sample1` if it does not al
 
 This command would upload data [to this project.](https://portal.geoseeq.com/sample-groups/ed59b913-91ec-489b-a1b9-4ea137a6e5cf/samples). Since only organization members can upload data, you will need to replace `GeoSeeq` with your organization name.
 
+To rename samples on the fly, provide a CSV file with current and new names using the `--name-map` option:
+
+```
+$ geoseeq upload reads --name-map sample_map.csv current_name new_name "GeoSeeq/Example CLI Project" fastq_files.txt
+```
+
 Note: You will need to have an API token set to use this command (see above)
 
 ## Using the Python API in a program

{geoseeq-0.7.3.dev4.dist-info → geoseeq-0.7.4.dist-info}/RECORD

@@ -2,14 +2,14 @@ geoseeq/__init__.py,sha256=YqYqeHbqjgWI5OBIxkPXNvLISOjVWaNwVFy6AGJ7uwc,982
 geoseeq/app.py,sha256=Y6d1UzxFLfE3RNccATbFCVi6kH3eFmzwoUbeR2Ry09A,2387
 geoseeq/blob_constructors.py,sha256=AkWpDQY0EdGMxF1p6eRspyHKubcUdiW4it-_Q7S2QWk,188
 geoseeq/bulk_creators.py,sha256=pdn-Dv7yv5SFv-PfDuQbuOnw2W4-BfIfRJVRAhM8U6s,2115
-geoseeq/constants.py,sha256=KmWH3gwHLd3toTWLWSViV_1eAYzPOPZ5bv6INpgwzQI,665
+geoseeq/constants.py,sha256=Vi9tahoQI6vnRaYoXuzZ7Dq12oAwwPCBfmPYeDWbjDE,722
 geoseeq/file_system_cache.py,sha256=HzVZWtwLD2fjWWSo_UfWmGeBltm9He4lP_OqzKwNGWg,4138
 geoseeq/knex.py,sha256=zcjafsmUn9SC3LlRnvvaXpr-pHYZ0IXk7LpzuUoE3MI,8312
 geoseeq/organization.py,sha256=bJkYL8_D-k6IYAaii2ZbxjwYnXy6lvu6iLXscxKlA3w,2542
 geoseeq/pipeline.py,sha256=89mhWaecsKnm6tyRkdkaVp4dmZh62_v42Ze0oXf8OTY,9873
 geoseeq/project.py,sha256=jryxHMx5PdQNaMJWjlzgQmxJt_s2M-HAHARBCPd1Vzc,17075
 geoseeq/remote_object.py,sha256=GYN6PKU7Zz3htIdpFjfZiFejzGqqJHbJyKlefM1Eixk,7151
-geoseeq/sample.py,sha256=LeLJytRYERY5dkMIOWqANTPTun9wqei393qeNlPBw1U,10895
+geoseeq/sample.py,sha256=oVUNnfqsRCCDUZdyI6fGylaMgLHd_7FLLJVGuOd5Jb8,10946
 geoseeq/search.py,sha256=gawad6Cx5FxJBPlYkXWb-UKAO-UC0_yhvyU9Ca1kaNI,3388
 geoseeq/smart_table.py,sha256=rihMsFUIn-vn4w6ukVZTHI9bjDSEr8xHExBfX8mwCHM,6169
 geoseeq/smart_tree.py,sha256=bSjDlwmOuNXutYJhytA1RovwRCHV6ZxXXJPiIGFhPaA,1825
@@ -18,14 +18,14 @@ geoseeq/user.py,sha256=tol8i1UGLRrbMw5jeJDnna1ikRgrCDd50Jxz0a1lSgg,690
 geoseeq/utils.py,sha256=ZXpWb2MetUIeLrExiXb7IaOXYrW1pvrdP3o0KWzbwCs,4035
 geoseeq/work_orders.py,sha256=5uLVVfdKE8qh4gGaHkdBpXJGRTujuSg59knWCqEET4A,8071
 geoseeq/cli/__init__.py,sha256=4WnK87K5seRK3SGJAxNWnQTqyg5uBhdhrOrzB1D4b3M,24
-geoseeq/cli/constants.py,sha256=Do5AUf9lMO9_P8KpFJ3XwwFBAWsxSjZ6sx9_QEGyC_c,176
+geoseeq/cli/constants.py,sha256=NtRSNBuna42605LE0sVywTPfmzYQnG-3yrT_M7Ml5B0,213
 geoseeq/cli/copy.py,sha256=02U9kdrAIbbM8MlRMLL6p-LMYFSuRObE3h5jyvcL__M,2275
 geoseeq/cli/detail.py,sha256=q8Suu-j2k18knfSVFG-SWWGNsKM-n8y9RMA3LcIIi9Y,4132
 geoseeq/cli/download.py,sha256=Znjuc9IFOcIa5_Od9mFXHJdYAJtgw9Bc_wPPcOVXn7s,21298
 geoseeq/cli/fastq_utils.py,sha256=-bmeQLaiMBm57zWOF0R5OlWTU0_3sh1JBC1RYw2BOFM,3083
 geoseeq/cli/find_grn.py,sha256=oMDxkzGQBQb2_cCuvmwoeHOsFHqyO9RLeJzrB6bAe5M,439
 geoseeq/cli/get_eula.py,sha256=79mbUwyiF7O1r0g6UTxG9kJGQEqKuH805E6eLkPC6Y4,997
-geoseeq/cli/main.py,sha256=_P_pp_ohm0Pq390FgWjNw-oQA06KGbQPAGbvgY-iL6U,4137
+geoseeq/cli/main.py,sha256=gHZzocvIrfigz9EP3V1BxPh5OFNsp6i6_jqbP6vb_a8,4133
 geoseeq/cli/manage.py,sha256=wGXAcVaXqE5JQEU8Jh6OlHr02nB396bpS_SFcOZdrEo,5929
 geoseeq/cli/progress_bar.py,sha256=p1Xl01nkYxSBZCB30ue2verIIi22W93m3ZAMAxipD0g,738
 geoseeq/cli/project.py,sha256=V5SdXm2Hwo2lxrkpwRDedw-mAE4XnM2uwT-Gj1D90VQ,3030
@@ -44,7 +44,7 @@ geoseeq/cli/shared_params/opts_and_args.py,sha256=_DcJ-TqgrbBaeDd-kuHEx2gLZPQN6E
 geoseeq/cli/upload/__init__.py,sha256=tRrljqG7uBM6zVBKpDw1zevHz6Vy418HuIYZKwByyWg,862
 geoseeq/cli/upload/upload.py,sha256=tBga8TW_5qXM4avXH5BAfLrYNms_5eqdyJZex47hZ90,14294
 geoseeq/cli/upload/upload_advanced.py,sha256=1pjtbe8EidIo4eR1_oVD00rPCTxYj8CRqB8D9buA62M,12432
-geoseeq/cli/upload/upload_reads.py,sha256=dZK_Mh3a3NdC4zVB4Yyfz-NViCK9_rROQbmLWTrh8Pc,11642
+geoseeq/cli/upload/upload_reads.py,sha256=da_a-ojltmcUa1MGycMg8LLKd0ZXCZ8-F3zpuijwWd4,12181
 geoseeq/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geoseeq/contrib/ncbi/README.md,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geoseeq/contrib/ncbi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -92,8 +92,8 @@ geoseeq/vc/vc_cache.py,sha256=P4LXTbq2zOIv1OhP7Iw5MmypR2vXuy29Pq5K6gRvi-M,730
 geoseeq/vc/vc_dir.py,sha256=A9CLTh2wWCRzZjiLyqXD1vhtsWZGD3OjaMT5KqlfAXI,457
 geoseeq/vc/vc_sample.py,sha256=qZeioWydXvfu4rGMs20nICfNcp46y_XkND-bHdV6P5M,3850
 geoseeq/vc/vc_stub.py,sha256=IQr8dI0zsWKVAeY_5ybDD6n49_3othcgfHS3P0O9tuY,3110
-geoseeq-0.7.3.dev4.dist-info/METADATA,sha256=4bfJLyjpSn16lfEIK8OvC5xbfLI4nKHhqGieH7PPsVE,5415
-geoseeq-0.7.3.dev4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-geoseeq-0.7.3.dev4.dist-info/entry_points.txt,sha256=yF-6KDM8zXib4Al0qn49TX-qM7PUkWUIcYtsgt36rjM,45
-geoseeq-0.7.3.dev4.dist-info/licenses/LICENSE,sha256=IuhIl1XCxXLPLJT_coN1CNqQU4Khlq7x4IdW7ioOJD8,1067
-geoseeq-0.7.3.dev4.dist-info/RECORD,,
+geoseeq-0.7.4.dist-info/METADATA,sha256=cJnudtWL38eoOqQF1IfjmYaslq5beDTFMNPYP7Y2vio,5652
+geoseeq-0.7.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+geoseeq-0.7.4.dist-info/entry_points.txt,sha256=yF-6KDM8zXib4Al0qn49TX-qM7PUkWUIcYtsgt36rjM,45
+geoseeq-0.7.4.dist-info/licenses/LICENSE,sha256=IuhIl1XCxXLPLJT_coN1CNqQU4Khlq7x4IdW7ioOJD8,1067
+geoseeq-0.7.4.dist-info/RECORD,,