geoseeq 0.6.8a2__py3-none-any.whl → 0.6.10__py3-none-any.whl

geoseeq/cli/download.py

@@ -98,6 +98,7 @@ def cli_download_metadata(state, sample_ids):
 
 cores_option = click.option('--cores', default=1, help='Number of downloads to run in parallel')
 head_option = click.option('--head', default=None, type=int, help='Download the first N bytes of each file')
+alt_id_option = click.option('--alt-sample-id', default=None, help='Specify an alternate sample id from the project metadata to id samples')
 
 @cli_download.command("files")
 @use_common_state
@@ -113,6 +114,7 @@ head_option = click.option('--head', default=None, type=int, help='Download the
 @click.option("--extension", multiple=True, help="Only download files with this extension. e.g. 'fastq.gz', 'bam', 'csv'")
 @click.option("--with-versions/--without-versions", default=False, help="Download all versions of a file, not just the latest")
 @ignore_errors_option
+@alt_id_option
 @project_id_arg
 @sample_ids_arg
 def cli_download_files(
@@ -129,6 +131,7 @@ def cli_download_files(
     with_versions,
     download,
     ignore_errors,
+    alt_sample_id,
     project_id,
     sample_ids,
 ):
@@ -164,6 +167,13 @@ def cli_download_files(
         haib17CEM4890_H2NYMCCXY_SL254769 haib17CEM4890_H2NYMCCXY_SL254773 `# specify the samples by name` \\ 
         --folder-type sample --extension '.contigs.fasta' # filter for contig files
 
+    \b
+    # Download files from a sample in the metasub project using an alternate sample id called "barcode"
+    $ geoseeq download files 'MetaSUB Consortium/Cell Paper' `# specify the project` \\
+        235183938 `# the alternate sample name (in this case a barcode number)` \\
+        --alt-sample-id barcode `# specify the alternate sample id column name` \\
+        --folder-type 'sample' `# only download files from sample folders`
+
     ---
 
     Command Arguments:
@@ -184,7 +194,7 @@ def cli_download_files(
     samples = []
     if sample_ids:
         logger.info(f"Fetching info for {len(sample_ids)} samples.")
-        samples = handle_multiple_sample_ids(knex, sample_ids, proj=proj)
+        samples = handle_multiple_sample_ids(knex, sample_ids, proj=proj, alternate_id_col=alt_sample_id)
 
     response = proj.bulk_find_files(
         sample_uuids=[s.uuid for s in samples],
@@ -377,9 +387,21 @@ def cli_download_ids(state, cores, target_dir, file_name, yes, download, head, i
 @click.option("--download/--urls-only", default=True, help="Download files or just print urls")
 @module_option(FASTQ_MODULE_NAMES, use_default=False)
 @ignore_errors_option
+@alt_id_option
 @project_id_arg
 @sample_ids_arg
-def cli_download_fastqs(state, cores, target_dir, yes, first, download, module_name, ignore_errors, project_id, sample_ids):
+def cli_download_fastqs(state,
+                        cores,
+                        target_dir,
+                        yes,
+                        first,
+                        download,
+                        module_name,
+                        ignore_errors,
+                        alt_sample_id,
+                        project_id,
+                        sample_ids
+):
     """Download fastq files from a GeoSeeq project.
 
     This command will download fastq files from a GeoSeeq project. You can filter
@@ -401,6 +423,10 @@ def cli_download_fastqs(state, cores, target_dir, yes, first, download, module_n
     # Download all fastq files from two samples in "My Org/My Project"
     $ geoseeq download fastqs "My Org/My Project" S1 S2
 
+    \b
+    # Download all fastq files from a single sample using an alternate sample id called "barcode"
+    $ geoseeq download fastqs 'MetaSUB Consortium/Cell Paper' 235183938 --alt-sample-id barcode
+
     ---
 
     Command Arguments:
@@ -422,7 +448,7 @@ def cli_download_fastqs(state, cores, target_dir, yes, first, download, module_n
     samples = []
     if sample_ids:
         logger.info(f"Fetching info for {len(sample_ids)} samples.")
-        samples = handle_multiple_sample_ids(knex, sample_ids, proj=proj)
+        samples = handle_multiple_sample_ids(knex, sample_ids, proj=proj, alternate_id_col=alt_sample_id)
     else:
         logger.info("Fetching info for all samples in project.")
         samples = proj.get_samples()

geoseeq/cli/main.py

@@ -54,7 +54,7 @@ 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('0.6.8a2')  # remember to update setup
+    click.echo('0.6.10')  # remember to update pyproject.toml
 
 
 @main.group('advanced')

geoseeq/cli/shared_params/id_handlers.py

@@ -133,7 +133,30 @@ def handle_folder_id(knex, folder_id, yes=False, private=True, create=True):
     raise ValueError('sample_folder_id must be a UUID, an organization name and project name, or a GRN')
 
 
-def handle_multiple_sample_ids(knex, sample_ids, proj=None):
+def map_alternate_ids_to_uuids(proj, alternate_id_col, sample_ids):
+    """Return a list of sample UUIDs
+    
+    `proj` is a project object
+    `alternate_id_col` is the name of the column containing alternate IDs
+    `sample_ids` is a list of alternate IDs
+    """
+    metadata = proj.get_sample_metadata()
+    if alternate_id_col not in metadata:
+        raise ValueError(f'Column "{alternate_id_col}" not found in project metadata')
+    alt_col_df = metadata[["uuid", alternate_id_col]]
+    # filter to the alt ids in our list- it is possible alt_id_col as a whole is not
+    # unique but that our list of alt ids is
+    alt_col_df = alt_col_df[alt_col_df[alternate_id_col].isin(sample_ids)]
+    if alt_col_df.shape[0] == 0:
+        raise ValueError(f'No samples found with the given alternate IDs in list')
+    if alt_col_df.shape[0] < len(sample_ids):
+        raise ValueError(f'Not all alternate IDs in list are found')
+    if alt_col_df.shape[0] > len(sample_ids):
+        raise ValueError(f'More than one sample found with the same alternate ID')
+    return list(alt_col_df['uuid'])
+
+
+def handle_multiple_sample_ids(knex, sample_ids, proj=None, alternate_id_col=None):
     """Return a list of fetched sample objects
     
     `sample_ids` may have three different structures:
@@ -144,7 +167,9 @@ def handle_multiple_sample_ids(knex, sample_ids, proj=None):
     Any sample may in fact be a file containing sample IDs, in which case the file will be read line by line
     and each element will be a sample ID
 
-    If `one_project` is True, all samples must be from the same project
+    If `proj` is provided then `alternate_id_col` may also be provided.
+    If so then alternate IDs will be used to fetch samples. If alternate ids are 
+    not present or not unique then fail.
     """
     project_as_arg = bool(proj)
     if proj or (proj := el_is_project_id(knex, sample_ids[0])):
@@ -155,7 +180,10 @@ def handle_multiple_sample_ids(knex, sample_ids, proj=None):
             return list(proj.get_samples(cache=False))
         else:
             samples = []
-            for el in flatten_list_of_els_and_files(sample_ids):
+            sample_ids = flatten_list_of_els_and_files(sample_ids)
+            if alternate_id_col:
+                sample_ids = map_alternate_ids_to_uuids(proj, alternate_id_col, sample_ids)
+            for el in sample_ids:
                 if is_grn_or_uuid(el):
                     el = el.split(':')[-1]
                     samples.append(sample_from_uuid(knex, el))

geoseeq/knex.py

@@ -214,7 +214,8 @@ class Knex:
         """Return a knex authenticated with a profile."""
         endpoint, token = load_auth_profile(profile)
         knex = cls(endpoint)
-        knex.add_api_token(token)
+        if token:
+            knex.add_api_token(token)
         return knex
     
 

geoseeq/project.py

@@ -256,9 +256,14 @@ class Project(RemoteObject):
 
     def get_sample_metadata(self):
         """Return a pandas dataframe with sample metadata."""
-        url = f"sample_groups/{self.uuid}/metadata"
-        blob = self.knex.get(url)
-        return pd.DataFrame.from_dict(blob, orient="index")
+        url = f"sample_groups/{self.uuid}/samples-list?page=1&page_size=500&&"
+        rows = []
+        while url:
+            blob = self.knex.get(url)
+            rows.extend(blob["results"])
+            url = blob["next"]
+        return pd.DataFrame(rows)
+    
     
     @property
     def n_samples(self):

geoseeq/sample.py

@@ -205,18 +205,17 @@ class Sample(RemoteObject):
             files[read_type] = {}
             for folder_name, file_grns in folders.items():
                 files[read_type][folder_name] = []
-                for file_grn in file_grns:
-                    if read_type in ["short_read::paired_end"]:
-                        files[read_type][folder_name].append(
-                            [
-                                self._grn_to_file(file_grn[0]),
-                                self._grn_to_file(file_grn[1]),
-                            ]
-                        )
-                    else:
-                        files[read_type][folder_name].append(
-                            self._grn_to_file(file_grn[0])
-                        )
+                if read_type in ["short_read::paired_end"]:
+                    files[read_type][folder_name].append(
+                        [
+                            self._grn_to_file(file_grns[0]),
+                            self._grn_to_file(file_grns[1]),
+                        ]
+                    )
+                else:
+                    files[read_type][folder_name].append(
+                        self._grn_to_file(file_grns[0])
+                    )
         return files
     
     def get_one_fasta(self):

geoseeq/utils.py

@@ -16,11 +16,19 @@ logger.addHandler(logging.NullHandler())  # No output unless configured by calli
 def load_auth_profile(profile=""):
     """Return an endpoit and a token"""
     profile = profile or "__default__"
-    with open(PROFILES_PATH, "r") as f:
-        profiles = json.load(f)
-    if profile in profiles:
-        return profiles[profile]["endpoint"], profiles[profile]["token"]
-    raise KeyError(f"Profile {profile} not found.")
+    try:
+        with open(PROFILES_PATH, "r") as f:
+            profiles = json.load(f)
+        if profile in profiles:
+            return profiles[profile]["endpoint"], profiles[profile]["token"]
+        raise KeyError(f"Profile {profile} not found.")
+    except FileNotFoundError:
+        endpoint, token = environ.get("GEOSEEQ_ENDPOINT", DEFAULT_ENDPOINT), environ.get("GEOSEEQ_API_TOKEN", None)
+        if token:
+            logger.debug("Using environment variables for authentication.")
+        else:
+            logger.warning("Accessing anonymously, functionality may be limited. Configure profiles or set GEOSEEQ_API_TOKEN to authenticate.")
+        return endpoint, token
 
 
 def set_profile(token, endpoint=DEFAULT_ENDPOINT, profile="", overwrite=False):

{geoseeq-0.6.8a2.dist-info → geoseeq-0.6.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geoseeq
-Version: 0.6.8a2
+Version: 0.6.10
 Summary: GeoSeeq command line tools and python API
 Author: David C. Danko
 Author-email: "David C. Danko" <dcdanko@biotia.io>

{geoseeq-0.6.8a2.dist-info → geoseeq-0.6.10.dist-info}/RECORD

@@ -4,25 +4,25 @@ geoseeq/blob_constructors.py,sha256=AkWpDQY0EdGMxF1p6eRspyHKubcUdiW4it-_Q7S2QWk,
 geoseeq/bulk_creators.py,sha256=pdn-Dv7yv5SFv-PfDuQbuOnw2W4-BfIfRJVRAhM8U6s,2115
 geoseeq/constants.py,sha256=z_ninEd7WsS5DaLntdR-sqAFib6Ie22jlhPKzLvLerw,449
 geoseeq/file_system_cache.py,sha256=HzVZWtwLD2fjWWSo_UfWmGeBltm9He4lP_OqzKwNGWg,4138
-geoseeq/knex.py,sha256=SlK3Z9Y51APecIeJep4eNvFqlwKpQzvtokBnKe0L5Oc,7965
+geoseeq/knex.py,sha256=GXPsV65w1co1OvpB4pngH4f5I1p1AAxDWX7e2QkMXw0,7987
 geoseeq/organization.py,sha256=bJkYL8_D-k6IYAaii2ZbxjwYnXy6lvu6iLXscxKlA3w,2542
 geoseeq/pipeline.py,sha256=89mhWaecsKnm6tyRkdkaVp4dmZh62_v42Ze0oXf8OTY,9873
-geoseeq/project.py,sha256=pVx4etzkYmYAYwcPJsjN9PrI-7GZEkAaz2Q5GFdng1s,13810
+geoseeq/project.py,sha256=kN6m1N4Tlud7saU03Sbir-oIBnXet_Cwi2OVVdaeag0,13929
 geoseeq/remote_object.py,sha256=GYN6PKU7Zz3htIdpFjfZiFejzGqqJHbJyKlefM1Eixk,7151
-geoseeq/sample.py,sha256=TNtYL8ph2pG0R5ukDC4J2AwdA0xDK9Bx7dVQmQKIMQs,8394
+geoseeq/sample.py,sha256=OU4H-U8XxsFosfa9wcWWrHq9NVT3nDKZcvPtPGGlLlk,8310
 geoseeq/search.py,sha256=gawad6Cx5FxJBPlYkXWb-UKAO-UC0_yhvyU9Ca1kaNI,3388
 geoseeq/upload_download_manager.py,sha256=FMRqLLg77o1qFbWZc5Yc86a2pjeZrrn1rHJr1iaxKCU,8757
 geoseeq/user.py,sha256=tol8i1UGLRrbMw5jeJDnna1ikRgrCDd50Jxz0a1lSgg,690
-geoseeq/utils.py,sha256=PDRiEQIZYTcfEV9AYvloQVvfqs5JaebcFZodAa2SUW8,3577
+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/copy.py,sha256=02U9kdrAIbbM8MlRMLL6p-LMYFSuRObE3h5jyvcL__M,2275
 geoseeq/cli/detail.py,sha256=q8Suu-j2k18knfSVFG-SWWGNsKM-n8y9RMA3LcIIi9Y,4132
-geoseeq/cli/download.py,sha256=QTNA7qFjCdRJg2vKbAm5yH8WGlcF5fb5bSjm5QiI4XE,17768
+geoseeq/cli/download.py,sha256=W3OswqpHg1thzW6CJ7IcSS0Te2LA2WfgYISQMSl4GQg,18921
 geoseeq/cli/fastq_utils.py,sha256=-bmeQLaiMBm57zWOF0R5OlWTU0_3sh1JBC1RYw2BOFM,3083
 geoseeq/cli/get_eula.py,sha256=79mbUwyiF7O1r0g6UTxG9kJGQEqKuH805E6eLkPC6Y4,997
-geoseeq/cli/main.py,sha256=iZtDhmUGO7zKTG6pA5WG1FosxwR8BYp6n6b5tSJhfhM,3910
+geoseeq/cli/main.py,sha256=NPW0EHw2JSdyQ5_nCSPiCsEsy0ZKJ1u7WJa9RQfMmqI,3918
 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
@@ -35,7 +35,7 @@ geoseeq/cli/view.py,sha256=P-o2YKBkTrPzSI-JOv7xROc63HLSUygZNZsjp9TGvSw,6783
 geoseeq/cli/shared_params/__init__.py,sha256=ckNHGCBJUpJbQmcYi7lW-lsC0xKud6CCMznwcG5Vte4,325
 geoseeq/cli/shared_params/common_state.py,sha256=jiHZtL3TATMjEoqhbO7HT8KkLJr1QPsy7ZHT4qcoQ1E,4095
 geoseeq/cli/shared_params/config.py,sha256=HQ0xQh_jdt3EKI5VXYqQXzo-s8Rm6YlziMyVX-kg598,1072
-geoseeq/cli/shared_params/id_handlers.py,sha256=501K9sCVkI0YGDQ62vXk_DM5lMMDrdB5spIS3cw9x9U,9299
+geoseeq/cli/shared_params/id_handlers.py,sha256=KtzflnplYVkXsyqI5Ej6r-_BwQnuXVHPr7JcYumTKNc,10700
 geoseeq/cli/shared_params/obj_getters.py,sha256=ZSkt6LnDkVFlNVYKgLrjzg60-6BthZMr3eeD3HNqzac,2741
 geoseeq/cli/shared_params/opts_and_args.py,sha256=_DcJ-TqgrbBaeDd-kuHEx2gLZPQN6EHZYWh8Ag-d8Vg,2091
 geoseeq/cli/upload/__init__.py,sha256=3C9_S9t7chmYU-2ot89NV03x-EtmsjibulErKaU9w1k,627
@@ -85,9 +85,9 @@ geoseeq/vc/vc_stub.py,sha256=IQr8dI0zsWKVAeY_5ybDD6n49_3othcgfHS3P0O9tuY,3110
 tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/test_api_client.py,sha256=TS5njc5pcPP_Ycy-ljcfPVT1hQRBsFVdQ0lCqBmoesU,12810
 tests/test_plotting.py,sha256=TcTu-2ARr8sxZJ7wPQxmbs3-gHw7uRvsgrhhhg0qKik,784
-geoseeq-0.6.8a2.dist-info/LICENSE,sha256=IuhIl1XCxXLPLJT_coN1CNqQU4Khlq7x4IdW7ioOJD8,1067
-geoseeq-0.6.8a2.dist-info/METADATA,sha256=Z44188Ooqx6AxBedAxOXv-m1xPrMIiGKwLloBh09Veo,4917
-geoseeq-0.6.8a2.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-geoseeq-0.6.8a2.dist-info/entry_points.txt,sha256=yF-6KDM8zXib4Al0qn49TX-qM7PUkWUIcYtsgt36rjM,45
-geoseeq-0.6.8a2.dist-info/top_level.txt,sha256=zZk7mmeaqAYqFJG8nq2DTgSQPbflRjJwkDIhNURPDEU,14
-geoseeq-0.6.8a2.dist-info/RECORD,,
+geoseeq-0.6.10.dist-info/LICENSE,sha256=IuhIl1XCxXLPLJT_coN1CNqQU4Khlq7x4IdW7ioOJD8,1067
+geoseeq-0.6.10.dist-info/METADATA,sha256=moKunTjFSy4nQVg0X-Es5JmhsyPwtU9DZr-LIR6bCUE,4916
+geoseeq-0.6.10.dist-info/WHEEL,sha256=A3WOREP4zgxI0fKrHUG8DC8013e3dK3n7a6HDbcEIwE,91
+geoseeq-0.6.10.dist-info/entry_points.txt,sha256=yF-6KDM8zXib4Al0qn49TX-qM7PUkWUIcYtsgt36rjM,45
+geoseeq-0.6.10.dist-info/top_level.txt,sha256=zZk7mmeaqAYqFJG8nq2DTgSQPbflRjJwkDIhNURPDEU,14
+geoseeq-0.6.10.dist-info/RECORD,,

{geoseeq-0.6.8a2.dist-info → geoseeq-0.6.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.7.0)
 Root-Is-Purelib: true
 Tag: py3-none-any