Merge branch 'dev_gtfdev' into dev

.gitignore

@@ -0,0 +1,168 @@
+# 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
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# 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/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# 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
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+### JetBrains template
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio and WebStorm
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/
+

bin/Modules/Ensembl/ActivityCategorizer.py

@@ -4,21 +4,21 @@
 
 class ActivityCategorizer:
 
-    def __init__(self, release, organism):
+    def __init__(self, release, organism, wd):
 
         # List of all Folders with Activity Tables
 
         self.folderlist = []
 
         # Dictionary from celltypes_organism.json mit key = Kategorie und Value = [Ordner]
 
-        self.c_dict = self.read_config(organism)
+        self.c_dict = self.read_config(organism, wd)
 
         # Activity table from all files as dict
 
         self.activity = {}
 
-        self.get_activity_data(release, organism)
+        self.get_activity_data(release, organism, wd)
 
         # Categorized Activity from Json-config
         print("Categorization: This may take a while")
@@ -29,23 +29,23 @@ def __init__(self, release, organism):
     def get_categorization(self):
         return self.categorization
 
-    def read_config(self, organism):
+    def read_config(self, organism, wd):
 
         c_dict = {}
-        path_to_config = os.path.join("../config/celltypes_"+organism+".json")
-        with open(path_to_config) as input:
-            data = json.loads(input.read())
+        path_to_config = os.path.join(wd, "/config/celltypes_"+organism+".json")
+        with open(path_to_config) as input_file:
+            data = json.loads(input_file.read())
             for x in data:
                 c_dict[x["type"]] = x["alias_ensembl"]
                 self.folderlist.extend(x["alias_ensembl"])
 
         return c_dict
 
-    def get_activity_data(self, release, organism):
+    def get_activity_data(self, release, organism, wd):
 
         for folder in self.folderlist:
             # Generate path to binary File
-            file = os.path.join("./EnsemblData", release, organism, "activity", folder, "table.bin")
+            file = os.path.join(wd, "/EnsemblData", release, organism, "activity", folder, "table.bin")
             with open(file, "rb") as tables:
                 self.activity[folder] = bytearray(tables.read())
 

bin/Modules/Ensembl/ActivityTable.py

@@ -15,8 +15,8 @@ class ActivityTable:
     4, "activity=NA"
     """
 
-    def __init__(self, organism, current_release):
-        self.link = os.path.join("./EnsemblData/", current_release, organism, "activity")
+    def __init__(self, organism, current_release, wd):
+        self.link = os.path.join(wd, "/EnsemblData/", current_release, organism, "activity")
         self.folders = next(os.walk(self.link))[1]
         self.generator = ATGenerator(["activity=ACTIVE",
                                "activity=POISED",

bin/Modules/Ensembl/Ensembl.py

@@ -1,20 +1,20 @@
-from Modules.Ensembl.ActivityTable import ActivityTable
-from Modules.Ensembl.FTPHandling.VersionChecker import EnsemblRegulationFTPRetriever as FTPRetriever
-from Modules.Ensembl.ActivityCategorizer import ActivityCategorizer
-from Modules.Ensembl.GTFGen import GTFGen
+from bin.Modules.Ensembl.ActivityTable import ActivityTable
+from bin.Modules.Ensembl.FTPHandling.VersionChecker import EnsemblRegulationFTPRetriever as FTPRetriever
+from bin.Modules.Ensembl.ActivityCategorizer import ActivityCategorizer
+from bin.Modules.Ensembl.GTFGen import GTFGen
 
 
 class Ensembl:
 
-    def __init__(self, organism):
+    def __init__(self, organism, wd):
         print("Starting Ensembl")
-        self.updater = FTPRetriever(organism)
+        self.updater = FTPRetriever(organism, wd)
         self.release = self.updater.get_release()
-        self.acttable = ActivityTable(organism, self.release)
+        self.acttable = ActivityTable(organism, self.release, wd)
         self.acttable.check_and_generate_activity_table()
-        self.categorizer = ActivityCategorizer(self.release, organism)
+        self.categorizer = ActivityCategorizer(self.release, organism, wd)
         print("Generating GTF")
-        self.gtf_generator = GTFGen(organism, self.release)
+        self.gtf_generator = GTFGen(organism, self.release, wd)
 
         print("Ensembl Finished !")
 

bin/Modules/Ensembl/FTPHandling/URLRetrieve.py

@@ -1,5 +1,5 @@
 import ftplib
-from Modules.Ensembl.FTPHandling.FTPEntry import FTPEntry
+from bin.Modules.Ensembl.FTPHandling.FTPEntry import FTPEntry
 
 
 class FTPHandler:

bin/Modules/Ensembl/FTPHandling/VersionChecker.py

@@ -1,4 +1,4 @@
-from Modules.Ensembl.FTPHandling.URLRetrieve import FTPHandler
+from bin.Modules.Ensembl.FTPHandling.URLRetrieve import FTPHandler
 import os.path
 
 
@@ -9,12 +9,12 @@ class EnsemblRegulationFTPRetriever:
     And downloading newest version if necessary
     """
 
-    def __init__(self, organism):
+    def __init__(self, organism, wd):
         self.site_ftp = FTPHandler("ftp.ensembl.org", "pub")
         self.remoteversion = self.get_current_ftp_version()
-        self.localversion = self.get_current_local_version()
-        if self.check_version_difference(organism):
-            self.download_currentversion_version(self.remoteversion, organism)
+        self.localversion = self.get_current_local_version(wd)
+        if self.check_version_difference(organism, wd):
+            self.download_currentversion_version(self.remoteversion, organism, wd)
         else:
             print("Newest Version installed, no update needed.")
 
@@ -31,15 +31,15 @@ def get_current_ftp_version(self):
         print("Current release is "+c_release)
         return c_release
 
-    def check_organism(self, organism, release):
-        if organism in next(os.walk("./EnsemblData/"+release+"/"))[1]:
+    def check_organism(self, organism, release, wd):
+        if organism in next(os.walk(os.path.join(wd, "/EnsemblData/"+release+"/")))[1]:
             return False
         else:
             print("No Local Version for "+organism+" installed. Installing...")
             return True
 
-    def get_current_local_version(self):
-        directories = next(os.walk("./EnsemblData/"))[1]
+    def get_current_local_version(self, wd):
+        directories = next(os.walk(os.path.join(wd, "/EnsemblData/")))[1]
         for dir in directories:
             if "release" in dir:
                 localversion = sorted(directories, reverse=True)[0]
@@ -51,7 +51,7 @@ def get_current_local_version(self):
         print("No Version installed !")
         return None
 
-    def check_version_difference(self, organism):
+    def check_version_difference(self, organism, wd):
 
         local_version = self.localversion
         remote_version = self.remoteversion
@@ -64,16 +64,16 @@ def check_version_difference(self, organism):
             print("Outdated Version detected ! local: " + local_version + " remote: " + remote_version)
             return True
         else:
-            if self.check_organism(organism, local_version):
+            if self.check_organism(organism, local_version, wd):
                 return True
             else:
                 return False
 
-    def download_currentversion_version(self, version, organism):
+    def download_currentversion_version(self, version, organism, wd):
 
         # Download Base File
 
-        targetfolder = os.path.join("./EnsemblData/", version, organism)
+        targetfolder = os.path.join(wd, "/EnsemblData/", version, organism)
         os.makedirs(targetfolder)
         folder_url = "/pub/"+version+"/regulation/"+organism+"/"
         self.site_ftp.change_dir(folder_url)

bin/Modules/Ensembl/GTFGen.py

@@ -5,14 +5,14 @@
 
 class GTFGen:
 
-    def __init__(self, organism, release):
+    def __init__(self, organism, release, wd):
 
-        self.gff_lines = self.get_organism_as_gff(organism, release)
+        self.gff_lines = self.get_organism_as_gff(organism, release, wd)
         self.value_map = {0: "ACTIVE", 1: "POISED", 2: "REPRESSED", 3: "INACTIVE", 4: "NA"}
 
-    def get_organism_as_gff(self, organism, release):
+    def get_organism_as_gff(self, organism, release, wd):
 
-        directory = os.path.join("./EnsemblData/", release, organism)
+        directory = os.path.join(wd, "/EnsemblData/", release, organism)
         inputfile = ""
         for file in os.listdir(directory):
             if file.endswith("gff.gz"):