From 32c933a310da5bd8c1e9e76bfa61823829de72a6 Mon Sep 17 00:00:00 2001
From: Maciej Bak <bakma@kb-rgmz01-pdl04.pz.unibas.ch>
Date: Mon, 23 Aug 2021 13:22:42 +0200
Subject: [PATCH] refactor: remove everything labkey-related
---
README.md | 51 --
install/environment.dev.yml | 1 -
scripts/labkey_api.py | 27 -
scripts/prepare_inputs.dict.tsv | 51 --
scripts/prepare_inputs.py | 665 ------------------
scripts/requirements.txt | 3 -
.../expected_output.md5 | 2 -
.../test.sh | 55 --
.../expected_output.md5 | 2 -
.../input_table.tsv | 3 -
.../test_scripts_prepare_inputs_table/test.sh | 45 --
11 files changed, 905 deletions(-)
delete mode 100755 scripts/labkey_api.py
delete mode 100644 scripts/prepare_inputs.dict.tsv
delete mode 100755 scripts/prepare_inputs.py
delete mode 100644 scripts/requirements.txt
delete mode 100644 tests/test_scripts_prepare_inputs_labkey/expected_output.md5
delete mode 100755 tests/test_scripts_prepare_inputs_labkey/test.sh
delete mode 100644 tests/test_scripts_prepare_inputs_table/expected_output.md5
delete mode 100644 tests/test_scripts_prepare_inputs_table/input_table.tsv
delete mode 100755 tests/test_scripts_prepare_inputs_table/test.sh
diff --git a/README.md b/README.md
index 6bd20fa..5e3b047 100644
--- a/README.md
+++ b/README.md
@@ -218,56 +218,6 @@ your run.
bash run.sh
```
-### Configuring workflow runs via LabKey tables
-
-Our lab stores metadata for sequencing samples in a locally deployed
-[LabKey][labkey] instance. This repository provides two scripts that give
-programmatic access to the LabKey data table and convert it to the
-corresponding workflow inputs (`samples.tsv` and `config.yaml`), respectively.
-As such, these scripts largely automate step 3. of the above instructions.
-However, as these scripts were written specifically for the needs of our lab,
-they are likely not directly usable or, at least, will require considerable
-modification for other setups (e.g., different LabKey table structure).
-Nevertheless, they can serve as an example for interfacing between LabKey and
-your workflow.
-
-> **NOTE:** All of the below steps assume that your current working directory
-> is the repository's root directory.
-
-1. The scripts have additional dependencies that can be installed with:
-
- ```bash
- pip install -r scripts/requirements.txt
- ```
-
-2. In order to gain programmatic access to LabKey via its API, a credential
-file is required. Create it with the following command after replacing the
-placeholder values with your real credentials (talk to your LabKey manager if
-you do not have these):
-
- ```bash
- cat << EOF | ( umask 0377; cat >> ${HOME}/.netrc; )
- machine <remote-instance-of-labkey-server>
- login <user-email>
- password <user-password>
- EOF
- ```
-
-3. Generate the workflow configuration with the following command, after
-replacing the placeholders with the appropriate values (check out the
-help screen with option '--help' for further options and information):
-
- ```bash
- python scripts/prepare_inputs.py \
- --labkey-domain="my.labkey.service.io"
- --labkey-domain="/my/project/path"
- --input-to-output-mapping="scripts/prepare_inputs.dict.tsv" \
- --resources-dir="/path/to/my/genome/resources" \
- --output-table="config/my_run/samples.tsv" \
- --config_file="config/my_run/config.yaml" \
- <table_name>
- ```
-
#### Additional information
The metadata field names in the LabKey instance and those in the parameters
@@ -328,7 +278,6 @@ Contaminant sequences | contaminant_seqs
[conda]: <https://docs.conda.io/projects/conda/en/latest/index.html>
[profiles]: <https://snakemake.readthedocs.io/en/stable/executing/cli.html#profiles>
-[labkey]: <https://www.labkey.com/>
[miniconda-installation]: <https://docs.conda.io/en/latest/miniconda.html>
[rule-graph]: images/rule_graph.svg
[snakemake]: <https://snakemake.readthedocs.io/en/stable/>
diff --git a/install/environment.dev.yml b/install/environment.dev.yml
index 3fa2e72..4ec8e7d 100644
--- a/install/environment.dev.yml
+++ b/install/environment.dev.yml
@@ -10,5 +10,4 @@ dependencies:
- pip:
- pandas==1.0.1
- biopython==1.76
- - labkey==1.2.0
diff --git a/scripts/labkey_api.py b/scripts/labkey_api.py
deleted file mode 100755
index 759acb4..0000000
--- a/scripts/labkey_api.py
+++ /dev/null
@@ -1,27 +0,0 @@
-# This script targets the client api version 0.4.0 and later
-
-#
-# Check the page: https://github.com/LabKey/labkey-api-python/blob/master/samples/query_examples.py
-# for example about filtering in queries.
-# A starting point to investigate further is here:
-# https://www.labkey.org/download/clientapi_docs/javascript-api/symbols/LABKEY.Query.Filter.html
-
-import labkey
-import pandas as pd
-import sys
-
-# for convenience, load QueryFilter explicitly (avoids long lines in filter definitions)
-from labkey.query import QueryFilter
-
-if __name__ == "__main__":
- # These are values of variables for which the script works
- # project_name = "TEST_ABOERSCH"
- # query_name = "RNA_Seq_data_template"
- project_name = sys.argv[1]
- query_name = sys.argv[2]
- server_context = labkey.utils.create_server_context('labkey.scicore.unibas.ch', '/Zavolan Group/'+project_name, 'labkey', use_ssl=True)
- schema_name = "lists"
- results = labkey.query.select_rows(server_context,schema_name,query_name)
- table_of_data = pd.DataFrame(results["rows"])
- print(table_of_data)
-
diff --git a/scripts/prepare_inputs.dict.tsv b/scripts/prepare_inputs.dict.tsv
deleted file mode 100644
index ab2f741..0000000
--- a/scripts/prepare_inputs.dict.tsv
+++ /dev/null
@@ -1,51 +0,0 @@
-labkey snakemake
-Entry_Date entry_date
-Path_Fastq_Files fastq_path
-Condition_Name condition
-Sample_Name sample_name
-Single_Paired seqmode
-Mate1_File fq1
-Mate2_File fq2
-Mate1_Direction mate1_direction
-Mate2_Direction mate2_direction
-Mate1_5p_Adapter fq1_5p
-Mate1_3p_Adapter fq1_3p
-Mate2_5p_Adapter fq2_5p
-Mate2_3p_Adapter fq2_3p
-Fragment_Length_Mean mean
-Fragment_Length_SD sd
-Quality_Control_Flag quality_control_flag
-Checksum_Raw_FASTQ_Mate1 mate1_checksum
-Checksum_Raw_FASTQ_Mate2 mate2_checksum
-File_Name_Metadata_File metadata
-Name_Quality_Control_File_Mate1 mate1_quality
-Name_Quality_Control_File_Mate2 mate2_quality
-Organism organism
-TaxonID taxon_id
-Strain_Isolate_Breed_Ecotype strain_name
-Strain_Isolate_Breed_Ecotype_ID strain_id
-Biomaterial_Provider biomaterial_provider
-Source_Tissue_Name source_name
-Tissue_Code tissue_code
-Additional_Tissue_Description tissue_description
-Genotype_Short_Name genotype_name
-Genotype_Description genotype_description
-Disease_Short_Name disease_name
-Disease_Description disease_description
-Treatment_Short_Name treatment
-Treatment_Description treatment_description
-Gender gender
-Age age
-Developmental_Stage development_stage
-Passage_Number passage_number
-Sample_Preparation_Date sample_prep_date
-Prepared_By prepared_by
-Documentation documentation
-Protocol_File protocol_file
-Sequencing_Date seq_date
-Sequencing_Instrument seq_instrument
-Library_preparation_kit library_kit
-Cycles cycles
-Molecule molecule
-Contaminant_Sequences contaminant_seqs
-BioAnalyzer_File bioanalyser_file
diff --git a/scripts/prepare_inputs.py b/scripts/prepare_inputs.py
deleted file mode 100755
index bc164aa..0000000
--- a/scripts/prepare_inputs.py
+++ /dev/null
@@ -1,665 +0,0 @@
-#!/usr/bin/env python3
-
-"""Create input table and config for ZARP."""
-
-import argparse
-from functools import partial
-import gzip
-import logging
-import math
-import os
-import sys
-from typing import Tuple
-
-from Bio import SeqIO
-import labkey
-import pandas as pd
-
-logger = logging.getLogger(__name__)
-
-
-def parse_cli_args() -> argparse.Namespace:
- """
- Parses command line arguments.
-
- :returns: parsed CLI arguments
- """
- parser = argparse.ArgumentParser(
- description=__doc__,
- )
-
- parser.add_argument(
- "table",
- type=str,
- default=None,
- help="either local file path of input table *or* name of table on "
- "LabKey instance (see 'LabKey API' options below)",
- metavar="TABLE",
- )
-
- api = parser.add_argument_group("LabKey API")
- api.add_argument(
- "--labkey-domain",
- type=str,
- default=None,
- help="domain of LabKey instance to query; required for obtaining "
- "input table via LabKey API",
- metavar="STR",
- )
- api.add_argument(
- "--labkey-path",
- type=str,
- default=None,
- help="path to LabKey container that includes specified input table; "
- "required for obtaining input table via LabKey API",
- metavar="STR",
- )
-
- io = parser.add_argument_group("input/output")
- io.add_argument(
- "--input-to-output-mapping",
- type=argparse.FileType('r'),
- default=os.path.join(
- os.path.dirname(__file__),
- 'prepare_inputs.dict.tsv',
- ),
- help="lookup table with mappings from input (LabKey or LabKey-like) "
- "to output (Snakemake) table; default: '%(default)s'",
- metavar="FILE",
- )
- io.add_argument(
- "--resources-dir",
- type=str,
- default=os.getcwd(),
- help="path containing the genome resources for all organisms "
- "(default: %(default)s)",
- metavar="DIR",
- )
- io.add_argument(
- "--output-table",
- type=argparse.FileType('w'),
- default="samples.tsv",
- help="output sample table for use in ZARP (default: %(default)s)",
- metavar="FILE",
- )
- io.add_argument(
- "--config-file",
- type=argparse.FileType('w'),
- default="config.yaml",
- help="output Snakemake configuration file for use in ZARP (default: "
- "%(default)s)",
- metavar="FILE",
- )
- io.add_argument(
- "--output-dir",
- type=str,
- default=os.getcwd(),
- help="directory to which ZARP results and logs are to be written "
- "(default: %(default)s)",
- metavar="DIR",
- )
- parser.add_argument(
- "--no-process-paths",
- action="store_true",
- default=False,
- help="do not attempt to create absolute paths in output files",
- )
-
- behavior = parser.add_argument_group("workflow behavior")
- behavior.add_argument(
- "--trim-polya",
- type=int,
- choices=[True, False],
- default=True,
- help="cutadapt: trim poly(A) tails option (default: %(default)s)",
- )
- behavior.add_argument(
- "--multimappers",
- type=int,
- default=100,
- help="STAR: number of multimappers to report (default: %(default)s)",
- metavar='INT',
- )
- behavior.add_argument(
- "--soft-clip",
- type=str,
- default="EndToEnd",
- help="STAR: soft-clipping option (default: %(default)s)",
- choices=['EndToEnd', 'Local'],
- )
- behavior.add_argument(
- "--pass-mode",
- type=str,
- default="None",
- help="STAR: 2-pass mode option (default: %(default)s)",
- choices=["None", "Basic"],
- )
- behavior.add_argument(
- "--libtype",
- type=str,
- default="",
- help="Salmon library type (default: %(default)s). Leave empty to infer one of 'SF', 'SR', 'ISF', 'ISR'."
- "Warning: If value is provided by user, it will be applied to ALL samples. If the table contains samples from different sequencing modes this might cause errors in zarp.",
- metavar="STR",
- choices=["", "SF", "SR", "ISF", "ISR", "OSF", "OSR", "MSF", "MSR"]
- )
-
- report = parser.add_argument_group("report")
- report.add_argument(
- "--description",
- type=str,
- default="N/A",
- help="short description to be added to the report (default: "
- "%(default)s)",
- metavar="STR",
- )
- report.add_argument(
- "--logo",
- type=argparse.FileType('r'),
- default=None,
- help="path to image file to be added to the report (default: "
- "%(default)s)",
- metavar="FILE",
- )
- report.add_argument(
- "--url",
- type=str,
- default="N/A",
- help="contact URL to be added to the report (default: %(default)s)",
- metavar="STR",
- )
-
- parser.add_argument(
- "-v", "--verbose",
- action="store_true",
- default=False,
- help="print log messages to STDERR",
- )
- parser.add_argument(
- "--debug",
- action="store_true",
- default=False,
- help="print log and debug messages to STDERR",
- )
-
- args = parser.parse_args()
-
- if args.logo:
- args.logo.close()
- args.logo = args.logo.name
- else:
- args.logo = ""
-
- if (args.labkey_domain and not args.labkey_path) or \
- (args.labkey_path and not args.labkey_domain):
- parser.print_help()
- sys.exit(
- "\n[ERROR] Either none or both of '--labkey-domain' and "
- "'--labkey-path' are required."
- )
- return args
-
-
-def setup_logging(
- logger: logging.Logger,
- verbose: bool = False,
- debug: bool = False,
-) -> None:
- """
- Configure logger.
-
- :param logger: the `logging.Logger` object to configure
- :param verbose: whether `logging.INFO` messages shall be logged
- :param debug: whether `logging.DEBUG` messages shall be logged
-
- :returns: None
- :raises ?: TODO
- """
- if debug:
- logger.setLevel(logging.DEBUG)
- elif verbose:
- logger.setLevel(logging.INFO)
- else:
- logger.setLevel(logging.WARNING)
- handler = logging.StreamHandler()
- handler.setFormatter(logging.Formatter(
- "[%(asctime)-15s: %(levelname)-8s @ %(funcName)s] %(message)s"
- ))
- logger.addHandler(handler)
-
-
-def fetch_labkey_table(
- domain: str,
- container_path: str,
- query_name: str,
- context_path: str = "labkey",
- schema_name: str = "lists",
-) -> pd.DataFrame:
- """
- Export LabKey table as Pandas data frame.
-
- :param domain: domain of LabKey instance
- :param container_path: path to LabKey container that includes the table of
- interest
- :param query_name: name of LabKey table to export
- :context_path: required by API; usage unclear TODO
- :schema_name: required by API; usage unclear TODO
-
- :returns: Pandas data frame
- :raises ?: TODO
- """
- server_context = labkey.utils.create_server_context(
- domain=domain,
- container_path=container_path,
- context_path=context_path,
- use_ssl=True,
- )
- results = labkey.query.select_rows(
- server_context=server_context,
- schema_name=schema_name,
- query_name=query_name,
- )
- input_table = pd.DataFrame(results["rows"])
- return input_table
-
-
-def get_read_length(file: str) -> int:
- """
- Returns read length of first entry of gzipped FASTQ file.
-
- :param file: path to gzipped FASTQ file
-
- :returns: read length
- :raises FileNotFoundError: file does not exist
- :raises IsADirectoryError: file is a directory
- :raises OSError: file is not gzipped
- :raises PermissionError: file cannot be read
- :raises ValueError: not a valid FASTQ file
- """
- with gzip.open(file, "rt") as handle:
- return len(next(SeqIO.parse(handle, "fastq")))
-
-
-def kmer_from_read_length(
- length: int,
- k_max: int = 31,
- k_min: int = 11,
-) -> int:
- """
- Given a read length, returns appropriate kmer parameter size for Salmon
- (https://salmon.readthedocs.io/) or similar k-mer-based quantification
- tools.
-
- References for implementation:
- https://salmon.readthedocs.io/en/latest/salmon.html#preparing-transcriptome-indices-mapping-based-mode
- https://groups.google.com/d/msg/sailfish-users/fphjX7OIGzY/bMBwlCaZAgAJ
-
- :param length: length of read in nucleotides
- :param k_max: maximum allowed k-mer size
- :param k_min: minimum allowed k-mer size
-
- :returns: k_max for l > 2 * k_max, or else the maximum of k and k_min,
- where k is biggest odd integer that fulfills k < l / 2
- """
- k = k_max
- if length < 2 * k_max + 1:
- # ensure kmer is smaller than half of read length
- k = math.floor((length - 1) / 2)
- # ensure kmer is odd
- if not k % 2:
- k -= 1
- if k < k_min:
- k = k_min
- return k
-
-
-def get_libtype(directionality: str, seqmode: str) -> str:
- """
- Returns libtype (https://salmon.readthedocs.io/en/latest/library_type.html) given strings indicating the
- "directionality", and sequencing mode of a sequencing library, respectively.
-
- :param directionality: direction in which library was sequenced (one of
- "SENSE" and "ANTISENSE")
-
- :param seqmode: sequencing mode(one of
- "pe" and "se")
-
- :returns: salmon code (one of 'SF', 'SR', 'ISF', 'ISR') for specified directionality;
- """
-
- if seqmode == "pe":
- option = "I"
- else:
- option = ""
-
- if directionality == "SENSE":
- option += "SF"
- elif directionality == "ANTISENSE":
- option += "SR"
- else:
- logger.error(
- f"[ERROR] Can't infer library type."
- f"Make sure directionality and sequencing mode are specified correctly."
- )
- sys.exit("Execution aborted.")
-
- return option
-
-
-def get_polya_adapter_seqs(directionality: str) -> Tuple[str, str]:
- """
- Returns repeat oligomers for detecting and trimming of poly(A) signals from
- a sequencing library, given a string indicating the library's
- "directionality".
-
- :param directionality: direction in which library was sequenced (one of
- "SENSE" and "ANTISENSE")
-
- :returns: tuple of two 15-mers to be used to detect and trim poly(A)
- signals from the 3' and 5' ends of the reads of sequencing library,
- respectively
- """
- if directionality == 'SENSE':
- three = 'AAAAAAAAAAAAAAA'
- five = 'XXXXXXXXXXXXXXX'
- elif directionality == 'ANTISENSE':
- three = 'XXXXXXXXXXXXXXX'
- five = 'TTTTTTTTTTTTTTT'
- else:
- three = 'XXXXXXXXXXXXXXX'
- five = 'XXXXXXXXXXXXXXX'
- return (three, five)
-
-
-def expand_path(
- *args: str,
- anchor: str = os.getcwd(),
- expand: bool = True,
- no_abs: bool = False,
-) -> str:
- """
- Constructs absolute path.
-
- Not tested with symbolic links.
-
- :param args: path fragments which will be joined to the anchor from left
- to right
- :param anchor: path relative to which the path fragments in *args shall
- be interpreted; can be absolute or relative; in the latter case, it is
- interpreted relative to the current working directory; if path
- fragments evaluate to absolute path (either before or after expansion),
- the path will be returned without considering the anchor
- :param expand: whether environment variables and user directories (e.g,
- `~`) shall be expanded
- :param join_only: path fragments in args are joined, but no further
- processing is done
-
- :returns: absolute path
- """
- suffix = os.path.join(*args)
- if no_abs:
- return suffix
- if os.path.isabs(suffix):
- return os.path.normpath(suffix)
- if expand:
- suffix = os.path.expanduser(
- os.path.expandvars(
- suffix
- )
- )
- if os.path.isabs(suffix):
- return os.path.normpath(suffix)
- anchor = os.path.expanduser(
- os.path.expandvars(
- anchor
- )
- )
- path = os.path.join(anchor, suffix)
- return os.path.normpath(path)
-
-
-def main(args):
- """
- Create input table and config for ZARP.
- """
- setup_logging(
- logger=logger,
- verbose=args.verbose,
- debug=args.debug,
- )
-
- # get input table from LabKey or CLI
- if args.labkey_domain:
- logger.info(
- f"Fetching input table from LabKey instance "
- "'{args.labkey_domain}'..."
- )
- input_table = fetch_labkey_table(
- domain=args.labkey_domain,
- container_path=args.labkey_path,
- query_name=args.table,
- )
- labkey_table = expand_path(
- '.'.join([args.output_table.name, "labkey"])
- )
- input_table.to_csv(
- labkey_table,
- sep='\t',
- index=False,
- )
- from_api = True
- else:
- logger.info(f"Reading input table from file '{args.table}'...")
- input_table = pd.read_csv(
- args.table,
- header=0,
- sep='\t',
- index_col=None,
- comment='#',
- engine='python',
- )
- from_api = False
-
- # get LabKey to Snakemake sample table field mappings
- input_dict = pd.read_csv(
- args.input_to_output_mapping,
- header=0,
- sep='\t',
- index_col=None,
- comment='#',
- engine='python',
- )
- args.input_to_output_mapping.close()
- input_dict.set_index('snakemake', inplace=True, drop=True)
-
- # create Snakemake table
- logger.info("Creating Snakemake input table...")
- snakemake_table = pd.DataFrame()
-
- for index, row in input_table.iterrows():
-
- # extract data from LabKey-like table
- lk_sample_name = row[input_dict.loc['sample_name', 'labkey']]
- lk_condition = row[input_dict.loc['condition', 'labkey']]
- lk_seqmode = row[input_dict.loc['seqmode', 'labkey']]
- lk_fastq_path = row[input_dict.loc['fastq_path', 'labkey']]
- lk_fq1 = row[input_dict.loc['fq1', 'labkey']]
- lk_fq2 = row[input_dict.loc['fq2', 'labkey']]
- lk_fq1_3p = row[input_dict.loc['fq1_3p', 'labkey']]
- lk_fq1_5p = row[input_dict.loc['fq1_5p', 'labkey']]
- lk_fq2_3p = row[input_dict.loc['fq2_3p', 'labkey']]
- lk_fq2_5p = row[input_dict.loc['fq2_5p', 'labkey']]
- lk_organism = row[input_dict.loc['organism', 'labkey']]
- lk_sd = row[input_dict.loc['sd', 'labkey']]
- lk_mean = row[input_dict.loc['mean', 'labkey']]
- lk_mate1_direction = row[input_dict.loc['mate1_direction', 'labkey']]
- lk_mate2_direction = row[input_dict.loc['mate2_direction', 'labkey']]
-
- # extract, infer or convert to Snakemake input format
- if from_api and not os.path.isabs(lk_fastq_path):
- anchor = os.getcwd()
- logger.warning(
- f"[WARNING] Don't know how to interpret relative paths "
- "inside LabKey table. Trying with current working directory "
- f"'{anchor}' as an anchor, but it may be better to use"
- "absolute paths wherever possible..."
- )
- else:
- anchor = os.path.abspath(os.path.dirname(args.table))
- sample = "_".join([lk_sample_name, lk_condition])
- if lk_seqmode == 'PAIRED':
- seqmode = 'pe'
- fq2 = expand_path(
- lk_fastq_path,
- lk_fq2,
- anchor=anchor,
- )
- elif lk_seqmode == 'SINGLE':
- seqmode = 'se'
- fq2 = "XXXXXXXXXXXXXXX"
- else:
- logger.error(
- f"[ERROR] Illegal sequencing mode '{lk_seqmode}' in row "
- f"{index+1}."
- )
- sys.exit("Execution aborted.")
- fq1 = expand_path(
- lk_fastq_path,
- lk_fq1,
- anchor=anchor,
- )
- read_length = get_read_length(fq1)
- index_size = read_length - 1
- kmer = kmer_from_read_length(read_length)
- fq1_3p = lk_fq1_3p
- fq1_5p = lk_fq1_5p
- fq2_3p = lk_fq2_3p
- fq2_5p = lk_fq2_5p
- organism = lk_organism.replace(' ', '_').lower()
- gtf = expand_path(
- args.resources_dir,
- organism,
- 'annotation.gtf',
- )
- genome = expand_path(
- args.resources_dir,
- organism,
- 'genome.fa',
- )
- sd = lk_sd
- mean = lk_mean
- fq1_polya_3p, fq1_polya_5p = get_polya_adapter_seqs(lk_mate1_direction)
- fq2_polya_3p, fq2_polya_5p = get_polya_adapter_seqs(lk_mate2_direction)
-
- # construct row in Snakemake input table
- snakemake_table.loc[index, 'sample'] = sample
- snakemake_table.loc[index, 'seqmode'] = seqmode
- snakemake_table.loc[index, 'fq1'] = fq1
- snakemake_table.loc[index, 'fq2'] = fq2
- snakemake_table.loc[index, 'index_size'] = index_size
- snakemake_table.loc[index, 'kmer'] = kmer
- snakemake_table.loc[index, 'fq1_3p'] = fq1_3p
- snakemake_table.loc[index, 'fq1_5p'] = fq1_5p
- snakemake_table.loc[index, 'fq2_3p'] = fq2_3p
- snakemake_table.loc[index, 'fq2_5p'] = fq2_5p
- snakemake_table.loc[index, 'organism'] = organism
- snakemake_table.loc[index, 'gtf'] = gtf
- snakemake_table.loc[index, 'genome'] = genome
- snakemake_table.loc[index, 'sd'] = sd
- snakemake_table.loc[index, 'mean'] = mean
-
- # add CLI argument-dependent parameters
- snakemake_table.loc[index, 'multimappers'] = args.multimappers
- snakemake_table.loc[index, 'soft_clip'] = args.soft_clip
- snakemake_table.loc[index, 'pass_mode'] = args.pass_mode
-
- if not args.libtype:
- snakemake_table.loc[index, 'libtype'] = get_libtype(lk_mate1_direction, seqmode)
- elif args.libtype in ['SF', 'SR', 'ISF', 'ISR', 'OSF', 'OSR', 'MSF', 'MSR']:
- snakemake_table.loc[index, 'libtype'] = args.libtype
- logger.warning(
- f"Library type {args.libtype} set for sample {sample}."
- )
-
- if args.trim_polya is True:
- snakemake_table.loc[index, 'fq1_polya_3p'] = fq1_polya_3p
- snakemake_table.loc[index, 'fq1_polya_5p'] = fq1_polya_5p
- snakemake_table.loc[index, 'fq2_polya_3p'] = fq2_polya_3p
- snakemake_table.loc[index, 'fq2_polya_5p'] = fq2_polya_5p
-
- # adjust sample table format
- snakemake_table.fillna('XXXXXXXXXXXXXXX', inplace=True)
- snakemake_table = snakemake_table.astype(
- {
- "sd": int,
- "mean": int,
- "multimappers": int,
- "kmer": int,
- "index_size": int,
- }
- )
-
- # write Snakemake sample table
- logger.info("Writing Snakemake input table...")
- snakemake_table.to_csv(
- args.output_table,
- sep='\t',
- header=True,
- index=False)
- args.output_table.close()
-
- # compile entries for Snakemake config file
- logger.info("Creating Snakemake config file...")
- results_dir = expand_path(
- args.output_dir,
- "results",
- )
- log_dir = expand_path(
- args.output_dir,
- "logs",
- )
- kallisto_indexes = expand_path(
- results_dir,
- "kallisto_indexes",
- )
- salmon_indexes = expand_path(
- results_dir,
- "salmon_indexes",
- )
- star_indexes = expand_path(
- results_dir,
- "star_indexes",
- )
- alfa_indexes = expand_path(
- results_dir,
- "alfa_indexes",
- )
-
- # write Snakemake config file
- logger.info("Writing Snakemake config file...")
- config_file_content = f'''---
- samples: "{expand_path(args.output_table.name)}"
- output_dir: "{results_dir}"
- log_dir: "{log_dir}"
- kallisto_indexes: "{kallisto_indexes}"
- salmon_indexes: "{salmon_indexes}"
- star_indexes: "{star_indexes}"
- alfa_indexes: "{alfa_indexes}"
- report_description: "{args.description}"
- report_logo: "{args.logo}"
- report_url: "{args.url}"
-...
-'''
- args.config_file.write(config_file_content)
- args.config_file.close()
-
-
-if __name__ == '__main__':
- args = parse_cli_args()
-
- # Set default according to CLI arg
- expand_path = partial(expand_path, no_abs=args.no_process_paths) # type: ignore
-
- main(args)
- logger.info("Program completed successfully.")
- sys.exit(0)
diff --git a/scripts/requirements.txt b/scripts/requirements.txt
deleted file mode 100644
index ba30bb9..0000000
--- a/scripts/requirements.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-biopython==1.76
-labkey==1.2.0
-pandas==0.25.3
diff --git a/tests/test_scripts_prepare_inputs_labkey/expected_output.md5 b/tests/test_scripts_prepare_inputs_labkey/expected_output.md5
deleted file mode 100644
index a94e93e..0000000
--- a/tests/test_scripts_prepare_inputs_labkey/expected_output.md5
+++ /dev/null
@@ -1,2 +0,0 @@
-aa583b9bad45eeb520d9d624cca0af78 samples.tsv
-c4cda83b069eb7ccb16547e1a9cdb34a config.yaml
\ No newline at end of file
diff --git a/tests/test_scripts_prepare_inputs_labkey/test.sh b/tests/test_scripts_prepare_inputs_labkey/test.sh
deleted file mode 100755
index dea4515..0000000
--- a/tests/test_scripts_prepare_inputs_labkey/test.sh
+++ /dev/null
@@ -1,55 +0,0 @@
-#!/bin/bash
-
-# Scripts requires environment variables 'LABKEY_HOST', 'LABKEY_USER' and
-# 'LABKEY_PASS' to be set with the appropriate values
-
-# Tear down test environment
-cleanup () {
- rc=$?
- rm -rf ${HOME}/.netrc
- rm -rf .snakemake/
- rm -rf config.yaml
- rm -rf samples.tsv.labkey
- rm -rf samples.tsv
- cd $user_dir
- echo "Exit status: $rc"
-}
-trap cleanup EXIT
-
-# Set up test environment
-set -eo pipefail # ensures that script exits at first command that exits with non-zero status
-set -u # ensures that script exits when unset variables are used
-set -x # facilitates debugging by printing out executed commands
-user_dir=$PWD
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" >/dev/null 2>&1 && pwd)"
-cd $script_dir
-cat << EOF | ( umask 0377; cat >> ${HOME}/.netrc; )
-machine ${LABKEY_HOST}
-login ${LABKEY_USER}
-password ${LABKEY_PASS}
-EOF
-
-# Run tests
-python "../../scripts/prepare_inputs.py" \
- --labkey-domain="${LABKEY_HOST}" \
- --labkey-path="/Zavolan Group/TEST_LABKEY" \
- --input-to-output-mapping="../../scripts/prepare_inputs.dict.tsv" \
- --resources-dir="../input_files" \
- --output-table="samples.tsv" \
- --config-file="config.yaml" \
- --multimappers='10' \
- --logo="../../images/logo.128px.png" \
- --debug \
- "RNA_Seq_data_template_raw"
-
-# Check if dry run completes
-snakemake \
- --snakefile="../../Snakefile" \
- --configfile="config.yaml" \
- --dryrun \
- --verbose
-
-#md5sum --check "expected_output.md5"
-# MD5 sums obtained with command:
-# md5sum config.yaml samples.tsv > expected_output.md5
-md5sum config.yaml samples.tsv
diff --git a/tests/test_scripts_prepare_inputs_table/expected_output.md5 b/tests/test_scripts_prepare_inputs_table/expected_output.md5
deleted file mode 100644
index aca34c0..0000000
--- a/tests/test_scripts_prepare_inputs_table/expected_output.md5
+++ /dev/null
@@ -1,2 +0,0 @@
-40bd0f0fcecdd0d9bc932f63c2811478 config.yaml
-d8fb1773e3b83b6fab0a0d44c9fa71e6 samples.tsv
\ No newline at end of file
diff --git a/tests/test_scripts_prepare_inputs_table/input_table.tsv b/tests/test_scripts_prepare_inputs_table/input_table.tsv
deleted file mode 100644
index 10b0244..0000000
--- a/tests/test_scripts_prepare_inputs_table/input_table.tsv
+++ /dev/null
@@ -1,3 +0,0 @@
-Mate2_5p_Adapter Condition_Name Name_Quality_Control_File_Mate1 Disease_Short_Name Single_Paired Gender Entry_Date Disease_Description Strain_Isolate_Breed_Ecotype Genotype_Description Mate1_File Source_Tissue_Name Developmental_Stage Mate1_Direction Quality_Control_Flag Genotype_Short_Name Strain_Isolate_Breed_Ecotype_ID Fragment_Length_Mean Organism Contaminant_Sequences TaxonID Documentation Prepared_By _labkeyurl_Entry_Date Molecule Mate2_Direction Library_preparation_kit Checksum_Raw_FASTQ_Mate1 Cycles Fragment_Length_SD Sample_Name Passage_Number Mate1_5p_Adapter Mate2_3p_Adapter Path_Fastq_Files Mate1_3p_Adapter Treatment_Short_Name Age Sequencing_Date Checksum_Raw_FASTQ_Mate2 Biomaterial_Provider Treatment_Description Sample_Preparation_Date BioAnalyzer_File Sequencing_Instrument Additional_Tissue_Description Protocol_File Name_Quality_Control_File_Mate2 Tissue_Code File_Name_Metadata_File Mate2_File
- synthetic_10_reads_paired xxx xxx PAIRED xxx Fri Dec 20 00:00:00 CET 2019 xxx xxx xxx synthetic.mate_1.fastq.gz xxx xxx SENSE xxx xxx xxx 250.0 Homo sapiens xxx 9606 xxx xxx /labkey/Zavolan%20Group/Test_labkey/list-details.view?listId=9&pk=../input_files/project1 xxx ANTISENSE xxx xxx xxx 100.0 synthetic_10_reads_paired xxx AGATCGGAAGAGCGT ../input_files/project1 AGATCGGAAGAGCACA xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx synthetic.mate_2.fastq.gz
- synthetic_10_reads_mate_1 xxx xxx SINGLE xxx Fri Dec 20 00:00:00 CET 2019 xxx xxx xxx synthetic.mate_1.fastq.gz xxx xxx SENSE xxx xxx xxx 250.0 Homo sapiens xxx 9606 xxx xxx /labkey/Zavolan%20Group/Test_labkey/list-details.view?listId=9&pk=../input_files/project2 xxx xxx xxx xxx 100.0 synthetic_10_reads_mate_1 xxx ../input_files/project2 AGATCGGAAGAGCACA xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx xxx
diff --git a/tests/test_scripts_prepare_inputs_table/test.sh b/tests/test_scripts_prepare_inputs_table/test.sh
deleted file mode 100755
index 3c57024..0000000
--- a/tests/test_scripts_prepare_inputs_table/test.sh
+++ /dev/null
@@ -1,45 +0,0 @@
-#!/bin/bash
-
-# Tear down test environment
-cleanup () {
- rc=$?
- rm -rf .snakemake/
- rm -rf config.yaml
- rm -rf samples.tsv
- rm -rf logs
- cd $user_dir
- echo "Exit status: $rc"
-}
-trap cleanup EXIT
-
-# Set up test environment
-set -eo pipefail # ensures that script exits at first command that exits with non-zero status
-set -u # ensures that script exits when unset variables are used
-set -x # facilitates debugging by printing out executed commands
-user_dir=$PWD
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" >/dev/null 2>&1 && pwd)"
-cd $script_dir/
-
-# Run tests
-python "../../scripts/prepare_inputs.py" \
- --input-to-output-mapping="../../scripts/prepare_inputs.dict.tsv" \
- --resources-dir="../input_files" \
- --output-table="samples.tsv" \
- --config-file="config.yaml" \
- --multimappers='10' \
- --logo="../../images/logo.128px.png" \
- --output-dir="" \
- --no-process-paths \
- "input_table.tsv"
-
-
-# Check if dry run completes
-snakemake \
- --snakefile="../../workflow/Snakefile" \
- --configfile="config.yaml" \
- --dryrun \
- --verbose
-
-md5sum --check "expected_output.md5"
-# MD5 sums obtained with command:
-# md5sum config.yaml samples.tsv > expected_output.md5
--
GitLab