PDB Parse basics

src/atom.py

@@ -0,0 +1,20 @@
+class Atom:
+
+    def __init__(self, ATOM_ID, ATOM_NAME, ALT_LOCAT, RES_NAME, CHAIN_ID,
+                 RES_SEQ_NB, RES_INSER_CODE, COORD_X, COORD_Y, COORD_Z,
+                 OCCUPANCY, TEMP_FACT, ELEM_SYMBOL, ATOM_CHARGE):
+        
+        self.ATOM_ID = ATOM_ID
+        self.ATOM_NAME = ATOM_NAME
+        self.ALT_LOCAT = ALT_LOCAT 
+        self.RES_NAME = RES_NAME
+        self.CHAIN_ID = CHAIN_ID
+        self.RES_SEQ_NB = RES_SEQ_NB
+        self.RES_INSER_CODE = RES_INSER_CODE
+        self.COORD_X = COORD_X
+        self.COORD_Y = COORD_Y
+        self.COORD_Z = COORD_Z
+        self.OCCUPANCY = OCCUPANCY
+        self.TEMP_FACT = TEMP_FACT
+        self.ELEM_SYMBOL = ELEM_SYMBOL
+        self.ATOM_CHARGE = ATOM_CHARGE

src/pdb.py

@@ -0,0 +1,68 @@
+import sys
+#import collections
+
+
+# custom imports
+from atom import *
+
+class PDBFile:
+
+    def getContent(self, filename):
+        with open(filename) as f:
+            return(f.readlines())
+
+    def getHeader(self):
+        #Metadata = collections.namedtuple("Metadata", ["header", "compound", "source", "author"])
+        Metadata = {}
+        for line in self.rawLines:
+            # no need to continue if meta are complete
+            if(len(Metadata) <4):
+                if(line[0:10] == "HEADER    "):
+                    Metadata['header']=line
+                elif(line[0:10] == "COMPND   2"):
+                    Metadata['compound']=line
+                elif(line[0:10] == "SOURCE   2"):
+                    Metadata['source']=line
+                elif(line[0:10] == "AUTHOR    "):
+                    Metadata['author']=line
+            else:
+                # if meta are complete, stop parsing
+                break     
+        return(Metadata)
+
+    def getAtoms(self):
+        self.ATOMS = []
+        
+        for line in self.rawLines:
+            if line.startswith("ATOM" or "HETATM"):
+                atom = Atom(ATOM_ID = int(line[6:11].strip()),
+                            ATOM_NAME = line[12:16].strip(),
+                            ALT_LOCAT = line[16:17].strip(),
+                            RES_NAME = line[17:20].strip(),
+                            CHAIN_ID = line[21:22].strip(),
+                            RES_SEQ_NB = int(line[22:26].strip()),
+                            RES_INSER_CODE = line[26:27].strip(),
+                            COORD_X = float(line[30:38].strip()),
+                            COORD_Y = float(line[38:46].strip()),
+                            COORD_Z = float(line[46:54].strip()),
+                            OCCUPANCY = float(line[54:60].strip()),
+                            TEMP_FACT = float(line[60:66].strip()),
+                            ELEM_SYMBOL = line[76:78].strip(),
+                            ATOM_CHARGE = line[78:80].strip())
+                self.ATOMS.append(atom)
+                      
+    
+    def __init__(self, filename):
+        self.rawLines = self.getContent(filename)
+        self.Metadata = self.getHeader()
+        self.getAtoms()
+        for elem in self.Metadata :    
+            print(self.Metadata[elem], end="")
+
+
+if __name__ == "__main__":
+    if(len(sys.argv)<2):
+        print("Not enough arguments! Run with --help to learn more about proper"
+              "call structure and parameters.")
+    else:
+        pdbFile = PDBFile(sys.argv[1])