Upgrade pyranges and pandas

.github/workflows/testing.yml

@@ -15,7 +15,7 @@ jobs:
         echo $CONDA/bin >> $GITHUB_PATH
     - name: Install dependencies
       run: |
-        conda install -n base python=3.9 conda-forge::biopython numpy==1.23 bioconda::pyranges==0.0.120 packaging bioconda::scanpy pytest -y
+        conda install -n base python=3.10 conda-forge::biopython numpy==1.26 bioconda::pyranges==0.0.129 packaging bioconda::scanpy pytest -y
 
     - name: pytest
       run: |

docs/source/conf.py

@@ -22,7 +22,7 @@
 author = "Dongze He, Rob Patro"
 
 # The full version, including alpha/beta/rc tags
-release = "0.8.1"
+release = "0.10.0"
 
 master_doc = "index"
 

docs/source/index.rst

@@ -4,7 +4,7 @@ Welcome to the documentation for pyroe
 What is pyroe?
 ===================
 
-The pyroe package provides useful functions for analyzing single-cell or single-nucleus RNA-sequencing data using `alevin-fry`.
+The pyroe package provides useful functions for analyzing single-cell or single-nucleus RNA-sequencing data using `alevin-fry`. Since `simpleaf` version 0.14.0, `roers <https://github.com/COMBINE-lab/roers>`_, instead of pyroe, became as the default augmented reference constructor for `alevin-fry` and `simpleaf`. Now, the main purpose of `pyroe` is to provide the function `load_fry` to load `alevin-fry` quantification results into Python as an `anndata <http://anndata.readthedocs.io/>`_ object, so as to be compatible with `scanpy <https://scanpy.readthedocs.io/en/stable/index.html>`_. If you have trouble installing `pyroe`, you can also define the ``load_fry`` function in your own Python script, the definition of ``load_fry`` can be found at here: `load_fry <https://github.com/COMBINE-lab/pyroe/blob/main/src/pyroe/load_fry.py>`_. 
 
 .. toctree::
    :maxdepth: 2

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyroe
-version = 0.9.3
+version = 0.10.0
 author = Dongze He, Rob Patro
 author_email = [email protected], [email protected]
 description = utilities of alevin-fry
@@ -21,8 +21,8 @@ scripts =
 python_requires = >=3.7
 include_package_data = True
 install_requires = 
-    pandas >= 1.3.0, < 2.0.0
-    pyranges == 0.0.120
+    pandas >= 1.3.0, < 2.2.0
+    pyranges == 0.0.129
     biopython >= 1.77
     packaging >= 21.0
     scanpy >= 1.8.2

src/pyroe/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.9.3"
+__version__ = "0.10.0"
 
 from pyroe.load_fry import load_fry
 from pyroe.make_txome import make_splici_txome, make_spliceu_txome

src/pyroe/id_to_name.py

@@ -13,7 +13,7 @@ def id_to_name(params):
     annot_reader = None
     if params.format is None:
         p = pathlib.Path(params.gtf_file)
-        suffs = [z.lower().strip('.') for z in p.suffixes]
+        suffs = [z.lower().strip(".") for z in p.suffixes]
 
         z = None
         if len(suffs) >= 1:

src/pyroe/load_fry.py

@@ -235,7 +235,7 @@ def process_output_format(output_format, quiet):
                 print(
                     f"Will populate output field X with sum of counts frorm {predefined_format[output_format]['X']}."
                 )
-                for (k, v) in predefined_format[output_format].items():
+                for k, v in predefined_format[output_format].items():
                     if k != "X":
                         print(f"Will combine {v} into output layer {k}.")
 
@@ -253,7 +253,7 @@ def process_output_format(output_format, quiet):
                     f"Will populate output field X with sum of counts frorm {output_format['X']}."
                 )
 
-            for (k, v) in output_format.items():
+            for k, v in output_format.items():
                 if not v:
                     # empty list
                     raise ValueError(

src/pyroe/make_splici_txome.py

@@ -577,7 +577,7 @@ def check_bedtools_version(bt_check_path):
                     # init seq list
                     intron_seqs = []
                     # for each intron record
-                    for (idx, intron_record) in chr_records.iterrows():
+                    for idx, intron_record in chr_records.iterrows():
                         # create Seqeture object for extracting sequence from chromosome
                         intron_feature = SeqFeature(
                             FeatureLocation(intron_record.Start, intron_record.End),
@@ -601,12 +601,12 @@ def check_bedtools_version(bt_check_path):
                 if not chr_records.empty:
                     txp_seqs = []
                     # as spliced txps are the concat of all exon sequences, fist get the sequence of each exon separately,then sum them up.
-                    for (tid, exon_records) in chr_records.groupby("Name"):
+                    for tid, exon_records in chr_records.groupby("Name"):
 
                         # init exon seq list
                         exon_seqs = []
                         # get the sequence of each exon
-                        for (idx, exon_record) in exon_records.iterrows():
+                        for idx, exon_record in exon_records.iterrows():
                             # create SeqFeature object for the exon record
                             # ignore strand for now, get reverse complement later if needed
                             exon_feature = SeqFeature(

src/pyroe/make_txome.py

@@ -798,7 +798,7 @@ def make_splici_txome(
                     # init seq list
                     intron_seqs = []
                     # for each intron record
-                    for (idx, intron_record) in chr_records.iterrows():
+                    for idx, intron_record in chr_records.iterrows():
                         # create Seqeture object for extracting sequence from chromosome
                         intron_feature = SeqFeature(
                             FeatureLocation(intron_record.Start, intron_record.End),
@@ -823,12 +823,12 @@ def make_splici_txome(
                 if not chr_records.empty:
                     txp_seqs = []
                     # as spliced txps are the concat of all exon sequences, fist get the sequence of each exon separately,then sum them up.
-                    for (tid, exon_records) in chr_records.groupby("Name"):
+                    for tid, exon_records in chr_records.groupby("Name"):
 
                         # init exon seq list
                         exon_seqs = []
                         # get the sequence of each exon
-                        for (idx, exon_record) in exon_records.iterrows():
+                        for idx, exon_record in exon_records.iterrows():
                             # create SeqFeature object for the exon record
                             # ignore strand for now, get reverse complement later if needed
                             exon_feature = SeqFeature(
@@ -1155,7 +1155,7 @@ def make_spliceu_txome(
                     # init seq list
                     unspliced_seqs = []
                     # for each unspliced record
-                    for (idx, unspliced_record) in chr_records.iterrows():
+                    for idx, unspliced_record in chr_records.iterrows():
                         # create Seqeture object for extracting sequence from chromosome
                         unspliced_feature = SeqFeature(
                             FeatureLocation(
@@ -1181,12 +1181,12 @@ def make_spliceu_txome(
                 if not chr_records.empty:
                     txp_seqs = []
                     # as spliced txps are the concat of all exon sequences, fist get the sequence of each exon separately,then sum them up.
-                    for (tid, exon_records) in chr_records.groupby("Name"):
+                    for tid, exon_records in chr_records.groupby("Name"):
 
                         # init exon seq list
                         exon_seqs = []
                         # get the sequence of each exon
-                        for (idx, exon_record) in exon_records.iterrows():
+                        for idx, exon_record in exon_records.iterrows():
                             # create SeqFeature object for the exon record
                             # ignore strand for now, get reverse complement later if needed
                             exon_feature = SeqFeature(

src/pyroe/pyroe_utils.py

@@ -11,7 +11,7 @@ def check_dataset_ids(n_ds, dataset_ids):
     # check the validity of dataset_ids
     invalid_ids = []
     for idx, dataset_id in enumerate(dataset_ids):
-        if type(dataset_id) == int:
+        if type(dataset_id) is int:
             if dataset_id > n_ds or dataset_id < 1:
                 print(f"Found invalid dataset id '{dataset_id}', ignored.")
                 invalid_ids.append(idx)