Devcontainer to projetct

.devcontainer/Dockerfile

@@ -0,0 +1,12 @@
+# Note: You can use any Debian/Ubuntu based image you want. 
+FROM mcr.microsoft.com/devcontainers/base:bullseye
+
+WORKDIR /tmp
+
+RUN wget https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_6_x/ViennaRNA-2.6.4.tar.gz
+RUN tar -zxvf ViennaRNA-2.6.4.tar.gz
+RUN cd ViennaRNA-2.6.4 && ./configure && make && sudo make install
+
+# [Optional] Uncomment this section to install additional OS packages.
+RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+    && apt-get -y install --no-install-recommends ncbi-blast+

.devcontainer/devcontainer.json

@@ -0,0 +1,31 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/docker-outside-of-docker-compose
+{
+	"name": "Docker from Docker Compose",
+	"dockerComposeFile": "docker-compose.yml",
+	"service": "app",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
+
+	// Use this environment variable if you need to bind mount your local source code into a new container.
+	"remoteEnv": {
+		"LOCAL_WORKSPACE_FOLDER": "${localWorkspaceFolder}"
+	},
+
+	"features": {
+		"ghcr.io/devcontainers/features/docker-outside-of-docker:1": {
+			"version": "latest",
+			"enableNonRootDocker": "true",
+			"moby": "true"
+		},
+		"ghcr.io/devcontainers/features/python:1": {},
+		"ghcr.io/akhildevelops/devcontainer-features/pip:0": {}
+	}
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	// "postCreateCommand": "docker --version",
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.devcontainer/docker-compose.yml

@@ -0,0 +1,26 @@
+version: '3'
+
+services:
+  app:
+    build: 
+      context: .
+      dockerfile: Dockerfile
+
+    volumes:
+      # Forwards the local Docker socket to the container.
+      - /var/run/docker.sock:/var/run/docker-host.sock 
+      # Update this to wherever you want VS Code to mount the folder of your project
+      - ../..:/workspaces:cached
+
+    # Overrides default command so things don't shut down after the process ends.
+    entrypoint: /usr/local/share/docker-init.sh
+    command: sleep infinity 
+
+    # Uncomment the next four lines if you will use a ptrace-based debuggers like C++, Go, and Rust.
+    # cap_add:
+    #  - SYS_PTRACE
+    # security_opt:
+    #   - seccomp:unconfined
+
+    # Use "forwardPorts" in **devcontainer.json** to forward an app port locally. 
+    # (Adding the "ports" property to this file will not forward from a Codespace.)

.github/dependabot.yml

@@ -0,0 +1,12 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for more information:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# https://containers.dev/guide/dependabot
+
+version: 2
+updates:
+ - package-ecosystem: "devcontainers"
+   directory: "/"
+   schedule:
+     interval: weekly

.gitignore

@@ -0,0 +1,167 @@
+# 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/
+share/python-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/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# 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/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+tmp
+Genomes/GCF_000005845.2/**
+Genomes/GCF_000006765.1/**
+DataFiles

AddGenome.py

@@ -210,7 +210,7 @@ def determine_closest_relatives(GENOME_DIR):
         seq_16S = get_16S_sequence(GENOME_DIR)
         with open(TEMP_FILENAME1, 'w') as out_file:
                 out_file.write('>16S' + '\n' + seq_16S + '\n')
-        p = subprocess.run(['./blastn', '-db', DB_16S, '-query', TEMP_FILENAME1, '-evalue', '0.01', '-max_target_seqs', str(BLAST_RESULTS+1), '-num_threads', str(NUM_THREADS), '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', TEMP_FILENAME2], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastn', '-db', DB_16S, '-query', TEMP_FILENAME1, '-evalue', '0.01', '-max_target_seqs', str(BLAST_RESULTS+1), '-num_threads', str(NUM_THREADS), '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', TEMP_FILENAME2], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
         # Read in BLAST results
         replicates = {}
@@ -310,14 +310,14 @@ def create_blast_filter_for_relatives(GENOME_DIR, target_ID_to_genome):
                         for t in targets: out_file.write(t + '\n')
 
         # Format Blast filter file
-        p = subprocess.run(['./blastdb_aliastool', '-seqid_file_in', FILTER_FILE], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastdb_aliastool', '-seqid_file_in', FILTER_FILE], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
 
 # Helper function for computing target homologs
 # PERFORM BLAST WITHOUT USING MULTIPLE PROCESSORS
 def blast_targets_against_database_SINGLE_PROCESS(protein_file):
         BLAST_OUTPUT_FILE = str(time.time()) + '.blast'
-        p = subprocess.run(['./blastp', '-db', DB_FAA, '-query', protein_file, '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', BLAST_OUTPUT_FILE, '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-seqidlist', FILTER_FILE + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastp', '-db', DB_FAA, '-query', protein_file, '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', BLAST_OUTPUT_FILE, '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-seqidlist', FILTER_FILE + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         if (os.path.exists(protein_file)): os.remove(protein_file)
         if (os.path.exists(FILTER_FILE)): os.remove(FILTER_FILE)
         if (os.path.exists(FILTER_FILE + '.bsl')): os.remove(FILTER_FILE + '.bsl')
@@ -331,7 +331,7 @@ def run_blast(target_subset):
                 for target in target_subset:
                         GENOME_DIR, accession, protein_seq = target
                         out_file.write('>' + accession + '\n' + protein_seq + '\n')
-        p = subprocess.run(['./blastp', '-db', DB_FAA, '-query', accession_file, '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', GENOME_DIR + accession + '.blast.xyz', '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-seqidlist', FILTER_FILE + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastp', '-db', DB_FAA, '-query', accession_file, '-outfmt', '6 qseqid sseqid evalue bitscore', '-out', GENOME_DIR + accession + '.blast.xyz', '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-seqidlist', FILTER_FILE + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         if (os.path.exists(accession_file)): os.remove(accession_file)
 
 
@@ -482,7 +482,7 @@ def run_RNAplfold(target):
         accession, mRNA_name, mRNA_sequence, count = target
         with open(GENOME_DIR + RNAPLFOLD_DIR + accession + '____' + mRNA_name + '.fa', 'w') as out_file:
                 out_file.write('>' + accession + '____' + mRNA_name + '\n' + mRNA_sequence + '\n')
-        p = subprocess.run(['./RNAplfold', '-u', '40', '-O', '--plex_output', '--auto-id', '--id-prefix', 'TR' + count], input=mRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['RNAplfold', '-u', '40', '-O', '--plex_output', '--auto-id', '--id-prefix', 'TR' + count], input=mRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         if (p.returncode != 0) or (len(p.stderr.decode()) > 0):
                 error('Problem executing RNAplfold:\t' + str(p.stderr.decode()) + '\n')
         renameAndRemoveOutputFiles('TR' + count + '_0001', accession + '____' + mRNA_name)
@@ -501,7 +501,7 @@ def RNAplfold_MULTI_PROCESS(targets):
 # Helper function for computing target accessibility
 # CREATE BINARY VERSIONS OF ACCESSIBILITY FILES USING RNAplex
 def create_binary_files():
-        p = subprocess.run(['./RNAplex', '-a', GENOME_DIR + RNAPLFOLD_DIR, '-k'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['RNAplex', '-a', GENOME_DIR + RNAPLFOLD_DIR, '-k'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         filelist = os.listdir(GENOME_DIR + RNAPLFOLD_DIR)
         for f in filelist:
                 if (f.endswith('_openen')): os.remove(GENOME_DIR + RNAPLFOLD_DIR + f)

TargetRNA3.py

@@ -251,10 +251,10 @@ def get_sRNA_homologs(SRNA_FILENAME, genome):
         RESTRICT_FILENAME = FILENAME + '.restrict'
         with open(RESTRICT_FILENAME, 'w') as out_file:
                 for accession in genome: out_file.write(accession + '\n')
-        p = subprocess.run(['./blastdb_aliastool', '-seqid_file_in', RESTRICT_FILENAME], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastdb_aliastool', '-seqid_file_in', RESTRICT_FILENAME], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
         # BLAST sRNA sequence
-        p = subprocess.run(['./blastn', '-db', DB, '-query', SRNA_FILENAME, '-outfmt', '6 qseqid sseqid evalue bitscore qstart qend', '-out', SRNA_HOMOLOGS_FILENAME, '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-negative_seqidlist', RESTRICT_FILENAME + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['blastn', '-db', DB, '-query', SRNA_FILENAME, '-outfmt', '6 qseqid sseqid evalue bitscore qstart qend', '-out', SRNA_HOMOLOGS_FILENAME, '-evalue', '0.01', '-max_target_seqs', '100', '-num_threads', str(NUM_THREADS), '-negative_seqidlist', RESTRICT_FILENAME + '.bsl'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
         # Determine homologs of sRNA
         sRNA_homologs = {}
@@ -299,10 +299,10 @@ def get_homologs(GENOME_DIR, SRNA_FILENAME, genome, genes):
 def determine_sRNA_accessibility(GENOME_DIR, sRNA_name, sRNA_sequence):
         TIME_STR = str(time.time())
         WINDOW_SIZE = min(70, len(sRNA_sequence))
-        p = subprocess.run(['nice', './RNAplfold', '-u', '40', '-O', '--plex_output', '-W', str(WINDOW_SIZE), '--auto-id', '--id-prefix', TIME_STR], input=sRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['nice', 'RNAplfold', '-u', '40', '-O', '--plex_output', '-W', str(WINDOW_SIZE), '--auto-id', '--id-prefix', TIME_STR], input=sRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         if (p.returncode != 0) or (len(p.stderr.decode()) > 0):
                 sys.stderr.write('ERROR executing RNAplfold:\t' + str(p.stderr.decode()) + '\n')
-        p = subprocess.run(['./RNAplex', '-a', '.', '-k'], input=sRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['RNAplex', '-a', '.', '-k'], input=sRNA_sequence.encode(), stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
         # Clean up
         shutil.move(TIME_STR + '_0001_openen_bin', GENOME_DIR + RNAPLFOLD_DIR + sRNA_name + '_openen_bin')
@@ -313,7 +313,7 @@ def determine_sRNA_accessibility(GENOME_DIR, sRNA_name, sRNA_sequence):
 
 # HELPER FUNCTION FOR COMPUTING INTERACTION ENERGIES. COMPUTES ENERGIES USING RNAPLEX.
 def run_RNAplex(GENOME_DIR, SRNA_FILENAME, f):
-        p = subprocess.run(['nice', './RNAplex', '-f', '0', '-q', SRNA_FILENAME, '-t', GENOME_DIR + RNAPLFOLD_DIR + f, '-a', GENOME_DIR + RNAPLFOLD_DIR, '-b'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        p = subprocess.run(['nice', 'RNAplex', '-f', '0', '-q', SRNA_FILENAME, '-t', GENOME_DIR + RNAPLFOLD_DIR + f, '-a', GENOME_DIR + RNAPLFOLD_DIR, '-b'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         structure_info = p.stdout.decode().strip().split('\n')[2]
         return (f, structure_info)