From 50744f046fdbb05ab9c57d4954325d6448c4c9b9 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Tue, 17 Nov 2020 13:56:23 +0000
Subject: [PATCH] added my_pdbtools containing pdbtools cloned from a git repo

---
 scripts/my_pdbtools/chain_splitter.py     | 28 +++++++++
 scripts/my_pdbtools/pdb_chain_splitter.py | 71 +++++++++++++++++++++++
 scripts/my_pdbtools/pdbtools              |  1 +
 scripts/my_pdbtools/pdbtools_commands     |  6 ++
 4 files changed, 106 insertions(+)
 create mode 100755 scripts/my_pdbtools/chain_splitter.py
 create mode 100755 scripts/my_pdbtools/pdb_chain_splitter.py
 create mode 160000 scripts/my_pdbtools/pdbtools
 create mode 100644 scripts/my_pdbtools/pdbtools_commands

diff --git a/scripts/my_pdbtools/chain_splitter.py b/scripts/my_pdbtools/chain_splitter.py
new file mode 100755
index 0000000..b798dde
--- /dev/null
+++ b/scripts/my_pdbtools/chain_splitter.py
@@ -0,0 +1,28 @@
+#!/usr/bin/python3
+
+#=======================================================================
+# TASK: extract chain from pdb and save each chain as a separate file
+
+# link for saving each chain as a separate file
+#=======================================================================   
+__description__ = \
+"""
+pdb_chain_splitter.py
+
+extracts chains and saves them as separate pdb files.
+"""
+__author__ = "Tanushree Tunstall"
+__date__ = ""
+
+from Bio.PDB import Select, PDBIO
+from Bio.PDB.PDBParser import PDBParser
+
+class ChainSelect(Select):
+    def __init__(self, chain):
+        self.chain = chain
+
+    def accept_chain(self, chain):
+        if chain.get_id() == self.chain:
+            return 1
+        else:          
+            return 0
diff --git a/scripts/my_pdbtools/pdb_chain_splitter.py b/scripts/my_pdbtools/pdb_chain_splitter.py
new file mode 100755
index 0000000..030971e
--- /dev/null
+++ b/scripts/my_pdbtools/pdb_chain_splitter.py
@@ -0,0 +1,71 @@
+#!/usr/bin/env python3
+
+# Copyright 2020, Tanushree Tunstall
+# This program is distributed under General Public License v. 3.  See the file
+# COPYING for a copy of the license.
+
+__description__ = \
+"""
+chain_splitter.py
+
+extract chain/s from pdb and saves each chain as a separate file
+"""
+__author__ = "Tanushree Tunstall"
+__date__ = ""
+#=======================================================================
+import os, shutil, sys
+#from pdbtools.helper import cmdline
+from chain_splitter import ChainSelect
+from Bio.PDB import Select, PDBIO
+from Bio.PDB.PDBParser import PDBParser
+#io = PDBIO()
+import argparse
+#=======================================================================
+
+def main():
+    """
+    Function to call if run from command line.
+
+    Example use:
+    pdb_chain_splitter.py -f <your_pdb_file> -c <chainid1><chainid2>
+    Extracts chain 'A' by default.
+    FIXME: extract all chains from the given pdb and write them out individually
+    """
+    arg_parser = argparse.ArgumentParser()
+    arg_parser.add_argument('-i', '--pdb_file', help='provide pdb file', default = 'None')
+    arg_parser.add_argument('-c', '--chain', help='chain/s to extract without spaces.', nargs = '+',  default = 'A', type = list)
+    arg_parser.add_argument('-p', '--out_path', help='specify output path',  default = '.', type = str)
+    arg_parser.add_argument('-o', '--out_file', help='specify output filename. Will be used as a prefix to append chain id and pdb file extension',  default = 'pdb_file_chain', type = str)
+    args = arg_parser.parse_args()
+
+    # Extract chains and write each chain as a separate file
+    pdb_file = args.pdb_file
+    print('input pdb file:', pdb_file)
+    
+    # type = list, makes it a list of lists. Hence extracting the list of chains.
+    chains = args.chain[0]
+    #chains = ['A','B','C']
+    print ('user supplied chain:', chains)
+    
+    # output filename and path
+    outpath = args.out_path
+    outfile = args.out_file
+
+    # get structure
+    p = PDBParser(PERMISSIVE=1)       
+    structure = p.get_structure(pdb_file, pdb_file)
+    print('input pdb filename:', structure.get_id())
+
+    for chain in chains:
+        chain = chain.upper()
+        print ('Extracting chain:', chain)
+
+        pdb_chain_file = outpath + '/' + outfile + '_{}.pdb'.format(chain)
+                                             
+        io = PDBIO()               
+        io.set_structure(structure)
+        io.save('{}'.format(pdb_chain_file), ChainSelect(chain))
+
+if __name__ == "__main__":
+    main()
+
diff --git a/scripts/my_pdbtools/pdbtools b/scripts/my_pdbtools/pdbtools
new file mode 160000
index 0000000..881ff8f
--- /dev/null
+++ b/scripts/my_pdbtools/pdbtools
@@ -0,0 +1 @@
+Subproject commit 881ff8f27aaf1db4266a84fb03baad3dab552c64
diff --git a/scripts/my_pdbtools/pdbtools_commands b/scripts/my_pdbtools/pdbtools_commands
new file mode 100644
index 0000000..0a85be7
--- /dev/null
+++ b/scripts/my_pdbtools/pdbtools_commands
@@ -0,0 +1,6 @@
+#======================================================
+# pdb_seq.py: extract seq from structure
+#======================================================
+~/git/LSHTM_analysis/scripts/my_pdbtools/pdbtools/scripts/pdb_seq -c B -a <input> > <output>
+
+