Merge pull request #111 from pepkit/dev

v0.12.1

Author: khoroshevskyi

docs/changelog.md

@@ -1,7 +1,8 @@
 # Changelog
 
-## [0.12.0] -- 2023-01-23
+## [0.12.0] -- 2023-03-27
 - Added functionality that saves gse metadata to config file
+- Fixed description in initialization of pepy object
 
 ## [0.11.2] -- 2022-12-25
 - Changed sample_name of PEP of processed files to file oriented

geofetch/_version.py

@@ -1 +1 @@
-__version__ = "0.12.0"
+__version__ = "0.12.1"

geofetch/finder.py

@@ -133,8 +133,10 @@ def _run_search_query(url: str) -> list:
             x_result = xmltodict.parse(x.text)["eSearchResult"]
             _LOGGER.info(f"Found elements: {x_result['Count']}")
             _LOGGER.info(f"Additional information: {x_result['TranslationSet']}")
-
-            return x_result["IdList"]["Id"]
+            if isinstance(x_result["IdList"]["Id"], list):
+                return x_result["IdList"]["Id"]
+            else:
+                return [x_result["IdList"]["Id"]]
         except Exception:
             return []
 

geofetch/geofetch.py

@@ -376,7 +376,6 @@ def fetch_all(self, input: str, name: str = None) -> Union[NoReturn, peppy.Proje
             description="Processing... ",
             disable=self.disable_progressbar,
         ):
-
             ncount += 1
             if ncount <= self.skip:
                 continue
@@ -563,7 +562,6 @@ def _process_sra_meta(
         gsm_multi_table = {}
         runs = []
         for line in srp_list_result:
-
             # Only download if it's in the include list:
             experiment = line["Experiment"]
             run_name = line["Run"]
@@ -889,7 +887,6 @@ def _expand_metadata_list_item(self, metadata_list: list, dict_key: str):
                         for elem in metadata_list[n_elem][dict_key]:
                             separated_elements = elem.split(": ")
                             if len(separated_elements) >= 2:
-
                                 # if first element is larger than 40 then treat it like simple string
                                 if len(separated_elements[0]) > 40:
                                     just_string = True
@@ -1046,6 +1043,9 @@ def _write_processed_annotation(
 
             conf = yaml.load(template, Loader=yaml.Loader)
             proj = peppy.Project().from_pandas(pd_value, config=conf)
+            proj_exp_data = conf.get("experiment_metadata")
+            if proj_exp_data:
+                proj["description"] = proj_exp_data.get("series_title")
             return proj
 
     @staticmethod
@@ -1165,6 +1165,9 @@ def _write_raw_annotation_new(
             conf = yaml.load(template, Loader=yaml.Loader)
 
             proj = peppy.Project().from_pandas(meta_df, sub_meta_df, conf)
+            proj_exp_data = conf.get("experiment_metadata")
+            if proj_exp_data:
+                proj["description"] = proj_exp_data.get("series_title")
             return proj
 
     def _create_config_processed(
@@ -1535,7 +1538,6 @@ def _get_list_of_processed_files(
         meta_processed_samples = []
         meta_processed_series = {"GSE": "", "files": []}
         for line in file_gse_content:
-
             if re.compile(r"!Series_geo_accession").search(line):
                 gse_numb = _get_value(line)
                 meta_processed_series["GSE"] = gse_numb
@@ -1583,7 +1585,6 @@ def _get_list_of_processed_files(
                     nb = len(meta_processed_samples) - 1
                     sample_table = False
                     for line_gsm in file_gsm_content:
-
                         # handles #103
                         if line_gsm == "!sample_table_begin":
                             sample_table = True
@@ -1931,7 +1932,6 @@ def _read_gsm_metadata(
         sample_table = False
 
         for line in file_gsm_content:
-
             # handles #103
             if line == "!sample_table_begin":
                 sample_table = True

mkdocs.yml

@@ -3,6 +3,7 @@ site_url: http://code.databio.org/geofetch/
 repo_url: http://github.com/pepkit/geofetch
 site_logo: img/geofetch_logo_dark.svg
 pypi_name: geofetch
+paper_link: https://doi.org/10.1093/bioinformatics/btad069
 
 nav:
   - Getting started: