From 60430a41bb1a48ad0b1d4f9ef97486b0e1f41c09 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?M=C3=A1t=C3=A9=20Balajti?= <mate.balajti@unibas.ch>
Date: Mon, 4 Sep 2023 14:31:23 +0200
Subject: [PATCH] refactor: update gitignore, requirements, cli
---
.gitignore | 69 ++++++++-
requirements.txt | 1 -
tests/input_files/expression.csv | 8 +-
tests/test_match_reptrans_explvl.py | 200 +++++++++++++------------
transcript_sampler/cli.py | 34 ++---
transcript_sampler/poisson_sampling.py | 13 +-
6 files changed, 191 insertions(+), 134 deletions(-)
diff --git a/.gitignore b/.gitignore
index 2a680d3..e6b679b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,12 +1,67 @@
-# ignore ALL .log files
-*.log
+# Created by https://www.toptal.com/developers/gitignore/api/macos,visualstudiocode
+# Edit at https://www.toptal.com/developers/gitignore?templates=macos,visualstudiocode
-# ignore ALL files in ANY directory named temp
-temp/
-__pycache__
-output_files
+### macOS ###
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+### macOS Patch ###
+# iCloud generated files
+*.icloud
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+.vscode
+
+# End of https://www.toptal.com/developers/gitignore/api/macos,visualstudiocode
+
+__pycache__/
*_cache
*egg-info/
.coverage
build/
-*/play.py
\ No newline at end of file
+*/play.py
+*.log
+temp/
+output_files
diff --git a/requirements.txt b/requirements.txt
index 3fd96b3..98d4d62 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,6 +1,5 @@
argparse
biopython
gtfparse
-polars == 0.16.17
numpy >= 1.23.3
pandas >= 1.4.4
\ No newline at end of file
diff --git a/tests/input_files/expression.csv b/tests/input_files/expression.csv
index d6fc944..f4ba134 100644
--- a/tests/input_files/expression.csv
+++ b/tests/input_files/expression.csv
@@ -1,4 +1,4 @@
-ENST00000472194 0.8914783511010855
-ENST00000308647 1.0887715239511602
-ENST00000442483 0.8381441606416928
-ENST00000511072 0.9145581387636652
+ENST00000472194,0.8914783511010855
+ENST00000308647,1.0887715239511602
+ENST00000442483,0.8381441606416928
+ENST00000511072,0.9145581387636652
diff --git a/tests/test_match_reptrans_explvl.py b/tests/test_match_reptrans_explvl.py
index 96b878d..ae3bb89 100644
--- a/tests/test_match_reptrans_explvl.py
+++ b/tests/test_match_reptrans_explvl.py
@@ -157,105 +157,107 @@ class TestMatchReptrans:
assert tFun.duplicated_index(df_match).empty, \
"at least one index element is duplicated"
- # def test_match_repr_transcript_expression_level(self):
- # """Test match_repr_transcript_expression_level().
-
- # This function test that the right output is generated by the
- # function match_repr_transcript_expression_level().
- # """
- # input_path = tFun.find_path("test_gene_exprL")
- # intermediate_path = tFun.find_path_intermediate_file()
- # dict_repr_test = {
- # 'ENSMUSG00000079415': 'ENSMUST00000112933',
- # "ENSMUSG00000024691": "ENSMUST00000025595",
- # "ENSMUSG00000063683": "ENSMUST00000119960"}
-
- # match.match_repr_transcript_expression_level(self,
- # exprTrans=input_path,
- # dict_reprTrans=dict_repr_test,
- # gtf_file=intermediate_path)
-
- # ref_path = tFun.find_path("test_ref_output.tsv")
- # output_path = tFun.find_output()
-
- # with open(ref_path, 'r', encoding="utf-8") as t1,\
- # open(output_path, 'r', encoding="utf-8") as t2,\
- # open(input_path, 'r', encoding="utf-8") as t3:
- # fileRef = t1.readlines()
- # fileOutput = t2.readlines()
- # fileInput = t3.readlines()
-
- # assert (
- # sorted(fileRef) == sorted(fileOutput)
- # ), "the output does't match the expected tsv file"
- # assert (
- # sorted(fileRef) != sorted(fileInput)
- # ), "the output does't match the expected tsv file"
-
- # def test_txt_to_dict(self):
- # """This function tests if txt is convertod to dict"""
- # path = tFun.find_path("test_dict_repr_trans.txt")
- # dico = match.txt_to_dict(path)
- # dict_test = {'ENSMUSG00000079415': 'ENSMUST00000112933',
- # "ENSMUSG00000024691": "ENSMUST00000025595",
- # "ENSMUSG00000063683": "ENSMUST00000119960"}
- # assert dico == dict_test
-
- # def test_transcripts_by_gene_inDf():
- # """
- # This function test if a dataframe generated from
- # the intermediate file is converted in another
- # dataframe without the support level column.
- # """
- # path = tFun.find_path_intermediate_file()
- # df = repr.import_gtfSelection_to_df(path)
- # df_gene = match.transcripts_by_gene_inDf(df)
- # datatype = {'Gene': np.dtype('O'), 'Transcript': np.dtype('O')}
- # assert tFun.column_number(df_gene) == (
- # 2, "number of columns is not equal to 2")
- # assert tFun.column_d_type(df_gene) == (
- # datatype, "at least one column has the wrong datatype")
- # assert tFun.duplicated_rows(df_gene).empty, \
- # "at least one row are duplicated"
- # assert tFun.na_value(df_gene) == 0, \
- # "at least one row contain NA values"
-
- # def test_output_tsv():
- # """
- # This function test if a tsv file is generated from a pandas
- # dataframe in the right format.
- # """
-
- # dict_repr_test = {
- # 'ENSMUSG00000079415': 'ENSMUST00000112933',
- # "ENSMUSG00000024691": "ENSMUST00000025595",
- # "ENSMUSG00000063683": "ENSMUST00000119960"}
- # df_dict_repr_trans = match.dict_repr_trans_to_df(dict_repr_test)
-
- # path_tsv = tFun.find_path(r"test_gene_exprL")
- # df_tsv_exp_lvl = match.tsv_or_csv_to_df(path_tsv)
- # path_intermediate = tFun.find_path_intermediate_file()
- # df_intermediate = repr.import_gtfSelection_to_df(path_intermediate)
- # df_gene_transcript = match.transcripts_by_gene_inDf(df_intermediate)
-
- # df_exp_lvl = match.expr_level_by_gene(
- # df_tsv_exp_lvl, df_gene_transcript
- # )
-
- # df_match = match.match_by_gene(df_dict_repr_trans, df_exp_lvl)
-
- # match.output_tsv(df_match)
-
- # ref_path = tFun.find_path("test_ref_output.tsv")
- # output_path = tFun.find_output()
-
- # with open(ref_path, 'r') as t1, open(output_path, 'r') as t2:
- # fileRef = t1.readlines()
- # fileOutput = t2.readlines()
-
- # assert (
- # sorted(fileRef) == sorted(fileOutput)
- # ), "the output does't match the expected tsv file"
+ def test_match_repr_transcript_expression_level(self):
+ """Test match_repr_transcript_expression_level().
+
+ This function test that the right output is generated by the
+ function match_repr_transcript_expression_level().
+ """
+ input_path = tFun.find_path("test_gene_exprL")
+ intermediate_path = tFun.find_path_intermediate_file()
+ dict_repr_test = {
+ 'ENSMUSG00000079415': 'ENSMUST00000112933',
+ "ENSMUSG00000024691": "ENSMUST00000025595",
+ "ENSMUSG00000063683": "ENSMUST00000119960"}
+
+ match.match_repr_transcript_expression_level(
+ self,
+ exprTrans=input_path,
+ dict_reprTrans=dict_repr_test,
+ gtf_file=intermediate_path
+ )
+
+ ref_path = tFun.find_path("test_ref_output.tsv")
+ output_path = tFun.find_output()
+
+ with open(ref_path, 'r', encoding="utf-8") as t1,\
+ open(output_path, 'r', encoding="utf-8") as t2,\
+ open(input_path, 'r', encoding="utf-8") as t3:
+ fileRef = t1.readlines()
+ fileOutput = t2.readlines()
+ fileInput = t3.readlines()
+
+ assert (
+ sorted(fileRef) == sorted(fileOutput)
+ ), "the output does't match the expected tsv file"
+ assert (
+ sorted(fileRef) != sorted(fileInput)
+ ), "the output does't match the expected tsv file"
+
+ def test_txt_to_dict(self):
+ """This function tests if txt is convertod to dict"""
+ path = tFun.find_path("test_dict_repr_trans.txt")
+ dico = match.txt_to_dict(path)
+ dict_test = {'ENSMUSG00000079415': 'ENSMUST00000112933',
+ "ENSMUSG00000024691": "ENSMUST00000025595",
+ "ENSMUSG00000063683": "ENSMUST00000119960"}
+ assert dico == dict_test
+
+ def test_transcripts_by_gene_inDf():
+ """
+ This function test if a dataframe generated from
+ the intermediate file is converted in another
+ dataframe without the support level column.
+ """
+ path = tFun.find_path_intermediate_file()
+ df = repr.import_gtfSelection_to_df(path)
+ df_gene = match.transcripts_by_gene_inDf(df)
+ datatype = {'Gene': np.dtype('O'), 'Transcript': np.dtype('O')}
+ assert tFun.column_number(df_gene) == (
+ 2, "number of columns is not equal to 2")
+ assert tFun.column_d_type(df_gene) == (
+ datatype, "at least one column has the wrong datatype")
+ assert tFun.duplicated_rows(df_gene).empty, \
+ "at least one row are duplicated"
+ assert tFun.na_value(df_gene) == 0, \
+ "at least one row contain NA values"
+
+ def test_output_tsv():
+ """
+ This function test if a tsv file is generated from a pandas
+ dataframe in the right format.
+ """
+
+ dict_repr_test = {
+ 'ENSMUSG00000079415': 'ENSMUST00000112933',
+ "ENSMUSG00000024691": "ENSMUST00000025595",
+ "ENSMUSG00000063683": "ENSMUST00000119960"}
+ df_dict_repr_trans = match.dict_repr_trans_to_df(dict_repr_test)
+
+ path_tsv = tFun.find_path(r"test_gene_exprL")
+ df_tsv_exp_lvl = match.tsv_or_csv_to_df(path_tsv)
+ path_intermediate = tFun.find_path_intermediate_file()
+ df_intermediate = repr.import_gtfSelection_to_df(path_intermediate)
+ df_gene_transcript = match.transcripts_by_gene_inDf(df_intermediate)
+
+ df_exp_lvl = match.expr_level_by_gene(
+ df_tsv_exp_lvl, df_gene_transcript
+ )
+
+ df_match = match.match_by_gene(df_dict_repr_trans, df_exp_lvl)
+
+ match.output_tsv(df_match)
+
+ ref_path = tFun.find_path("test_ref_output.tsv")
+ output_path = tFun.find_output()
+
+ with open(ref_path, 'r') as t1, open(output_path, 'r') as t2:
+ fileRef = t1.readlines()
+ fileOutput = t2.readlines()
+
+ assert (
+ sorted(fileRef) == sorted(fileOutput)
+ ), "the output does't match the expected tsv file"
# test_dict_repr_trans_to_df()
# test_txt_to_dict()
diff --git a/transcript_sampler/cli.py b/transcript_sampler/cli.py
index 8b65042..f4d2788 100644
--- a/transcript_sampler/cli.py
+++ b/transcript_sampler/cli.py
@@ -25,31 +25,31 @@ def main():
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
)
parser.add_argument(
- "--input_gtf", required=True, default=None,
- help="GTF file with genome annotation"
+ "-ic", "--input_csv", required=True, default=None,
+ help="CSV or TSV file with transcripts and their expression level"
)
parser.add_argument(
- "--input_csv", required=True, default=None,
- help="CSV or TSV file with transcripts and their expression level"
+ "-ig", "--input_gtf", required=True, default=None,
+ help="GTF file with genome annotation"
)
parser.add_argument(
- "--output_gtf", required=True, default=None,
- help="Output path for the new GTF file of representative transcripts"
+ "-oc", "--output_csv", required=True, default=None,
+ help="Output path for the new CSV file of representative transcripts "
+ "and their sampled number"
)
parser.add_argument(
- "--output_csv", required=True, default=None,
- help="Output path for the new CSV file of representative transcripts \
- and their sampled number"
+ "-og", "--output_gtf", required=True, default=None,
+ help="Output path for the new GTF file of representative transcripts"
)
parser.add_argument(
- "--n_to_sample", required=True, default=None,
+ "-n", "--n_to_sample", required=True, default=None,
help="Total number of transcripts to sample"
)
args = parser.parse_args()
log = logging.getLogger("main")
start = time.time()
- log.info("Started transcript sampler...")
+ log.info("Started transcript sampler.")
dict_repr_trans = find_rep_trans.get_rep_trans(args.input_gtf)
df_repr = match_reptrs_explvl.match_repr_transcript_expression_level(
dict_reprTrans=dict_repr_trans,
@@ -57,20 +57,20 @@ def main():
gtf_file=args.input_gtf
)
log.info(
- "Finding match between representative transcripts \
- and expression level file"
+ "Finding match between representative transcripts "
+ "and expression level file..."
)
- log.info("Poisson sampling of transcripts")
+ log.info("Poisson sampling of transcripts...")
poisson_sample.transcript_sampling(
args.n_to_sample, df_repr, args.output_csv)
- log.info("Output CSV file ready")
+ log.info("Output CSV file ready.")
- log.info("Writing output GTF file")
+ log.info("Writing output GTF file...")
find_rep_trans.gtf_file_writer(
args.input_gtf, dict_repr_trans, args.output_gtf)
end = time.time()
- log.info("Script executed in %s sec", (end - start))
+ log.info("Script executed in %s sec.", round(end - start, 2))
if __name__ == "__main__":
diff --git a/transcript_sampler/poisson_sampling.py b/transcript_sampler/poisson_sampling.py
index 6c586ac..f86e2bb 100644
--- a/transcript_sampler/poisson_sampling.py
+++ b/transcript_sampler/poisson_sampling.py
@@ -1,12 +1,12 @@
-"""Sample transcripts by Poisson-sampling"""
+"""Sample transcripts by Poisson-sampling."""
import pandas as pd
import numpy as np
+# pylint: disable=R0903
class SampleTranscript:
- '''
- Sample transcript
+ """Sample transcript.
This part of the code does Poisson sampling proportionally
to gene expression levels for each gene.
@@ -17,10 +17,11 @@ class SampleTranscript:
output: csv file with gene id and count
gtf file with transcript samples
- '''
+ """
+
@staticmethod
def transcript_sampling(total_transcript_number, df_repr, output_csv):
- """Samples transcript based on Poisson-sampling"""
+ """Sample transcript based on Poisson-sampling."""
total = df_repr["level"].sum()
total_transcript_number = int(total_transcript_number)
normalized = total_transcript_number / total
@@ -28,7 +29,7 @@ class SampleTranscript:
transcript_numbers = pd.DataFrame({
"id": df_repr["id"], "count": levels
})
- transcript_numbers.to_csv(output_csv, index=False)
+ transcript_numbers.to_csv(output_csv, index=False, header=False)
# python_version = "3.7.13"
--
GitLab