From f5d0a39359afc5fd8ad8e6fa5557099588341775 Mon Sep 17 00:00:00 2001
From: sepro <sebastian.proost@gmail.com>
Date: Thu, 27 Apr 2017 14:07:18 +0200
Subject: [PATCH] initial commit

---
 .gitignore          | 95 +++++++++++++++++++++++++++++++++++++++++++++
 blast_on_cluster.py | 82 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 177 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 blast_on_cluster.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..0646b06
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,95 @@
+# Created by .ignore support plugin (hsz.mobi)
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+.hypothesis/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# dotenv
+.env
+
+# virtualenv
+.venv/
+venv/
+ENV/
+
+# Spyder project settings
+.spyderproject
+
+# Rope project settings
+.ropeproject
+
+# pycharm/intellij
+.idea/
\ No newline at end of file
diff --git a/blast_on_cluster.py b/blast_on_cluster.py
new file mode 100644
index 0000000..f8154a6
--- /dev/null
+++ b/blast_on_cluster.py
@@ -0,0 +1,82 @@
+import sys
+from datetime import datetime
+from math import ceil
+import shlex
+import subprocess
+
+cluster_template = """#!/bin/bash
+#
+
+#$ -N blast_on_cluster
+#$ -cwd
+#$ -j y
+#$ -S /bin/bash
+#$ -o OUT_$JOB_NAME.$JOB_ID
+#$ -e ERR_$JOB_NAME.$JOB_ID
+
+module load biotools/ncbi-blast-2.3.0+
+date
+hostname
+blastp -outfmt 6 -evalue 0.001 -query ${q} -db ${db} -out ${o} -num_threads {t}
+date
+"""
+
+
+def check_line(line):
+    """
+    Checks if a line is a blastp command
+
+    :param line: string to check
+    :return: True if the line is a blastp command
+    """
+    return line.startswith("blastp -outfmt")
+
+
+def write_template(filename=None):
+    if filename is None:
+        filename = "blast_on_cluster" + str(ceil(datetime.utcnow().timestamp())) + ".sh"
+
+    with open(filename, "w") as t:
+        print(cluster_template, file=t)
+
+    return filename
+
+
+def execute_command_on_cluster(submission_script, cmd, threads=1):
+    """
+    Parses blastp command reported by OrthoFinder and submits an equivalent job to the cluster
+
+    :param submission_script: path to the submission script
+    :param cmd: command reported by OrthoFinder
+    :param threads: number of desired thread for each BLAST
+    :return:
+    """
+    cmd_args = shlex.split(cmd)
+
+    query, db, output = cmd_args[6], cmd_args[8], cmd_args[10]
+
+    qsub_cmd = ['qsub',
+                '-pe', 'cores', str(threads),
+                '-v', 'q=%s,db=%s,out=%s,t=%d' % (query, db, output, threads),
+                submission_script]
+
+    print(qsub_cmd)
+    # subprocess.call(qsub_cmd)
+
+
+def run():
+    """
+    Main loop, will get STDIN, parse the line and submit the job using qsub
+    """
+    print("Writing template")
+    submission_script = write_template()
+
+    print("Waiting for command to execute...")
+
+    for line in sys.stdin():
+        if check_line(line):
+            print("\n\tCommand found! Executing")
+            execute_command_on_cluster(submission_script, line.strip())
+
+if __name__ == "main":
+    run()