def main():

    if len(sys.argv) != 6:  # if no input
        print("ERORR:")
        print(
            "syntex: mol2_energy_filter mol2_file(docked poses) energy_threshold energyname cnum output "
        )
        print(
            " energyname is the name of the energy term and cnum is the column, eg 'Total Energy' where cnum is 4 or 'Footprint_Similarity_Score:' where cnum is 3"
        )
        return

    infilemol2_poses = sys.argv[1]
    val = float(sys.argv[2])
    ename = sys.argv[3]
    cnum = int(sys.argv[4])
    outfile = sys.argv[5]

    print("input file (poses)     = %s" % infilemol2_poses)
    print("energy threshold       = %f" % val)
    print("outputprefix           = %s" % outfile)

    if infilemol2_poses.split('.')[-1] == 'mol2':
        print("reading in mol2")
        #mol2_vector  = mol2.read_Mol2_file(infilemol2_poses)
        mol2_vector = mol2.read_Mol2_file_head(infilemol2_poses)
    if infilemol2_poses.split('.')[-1] == 'gz':
        print("reading in gz mol2 file")
        mol2_vector = mol2.read_Mol2_file_head_gz(infilemol2_poses)

    count = 0
    for mol in mol2_vector:
        #print(mol.header)
        lines = mol.header.split('\n')  #file1.close()
        for line in lines:
            #print(line)
            if ename in line:
                #print(line)
                splitline = line.split()
                energy = float(splitline[cnum - 1])
                #print(energy)
        if energy < val:
            print(energy)
            mol2.append_mol2(mol, outfile + '.mol2')
def main():

    if len(sys.argv) != 4:  # if no input
        print("ERORR:")
        print(
            "syntex: mol2_energy_filter mol2_file(docked poses) energy_threshold output "
        )
        return

    infilemol2_poses = sys.argv[1]
    val = float(sys.argv[2])
    outfile = sys.argv[3]

    print("input file (poses)     = %s" % infilemol2_poses)
    print("energy threshold       = %f" % val)
    print("outputprefix           = %s" % outfile)

    if infilemol2_poses.split('.')[-1] == 'mol2':
        print("reading in mol2")
        #mol2_vector  = mol2.read_Mol2_file(infilemol2_poses)
        mol2_vector = mol2.read_Mol2_file_head(infilemol2_poses)
    if infilemol2_poses.split('.')[-1] == 'gz':
        print("reading in gz mol2 file")
        mol2_vector = mol2.read_Mol2_file_head_gz(infilemol2_poses)

    count = 0
    for mol in mol2_vector:
        #print(mol.header)
        lines = mol.header.split('\n')  #file1.close()
        for line in lines:
            #print(line)
            if 'Total' in line:
                #print(line)
                splitline = line.split()
                energy = float(splitline[3])
                #print(energy)
        if energy < val:
            print(energy)
            mol2.append_mol2(mol, outfile + '.mol2')
def main():

    if len(sys.argv) != 3:  # if no input
        print("ERORR:")
        print("syntex: mol2_energy_sort mol2_file(docked poses) output ")
        return

    infilemol2_poses = sys.argv[1]
    outfile = sys.argv[2]

    print("input file (poses)     = %s" % infilemol2_poses)
    print("outputprefix           = %s" % outfile)

    if infilemol2_poses.split('.')[-1] == 'mol2':
        print("reading in mol2")
        #mol2_vector  = mol2.read_Mol2_file(infilemol2_poses)
        mol2_vector = mol2.read_Mol2_file_head(infilemol2_poses)
    if infilemol2_poses.split('.')[-1] == 'gz':
        print("reading in gz mol2 file")
        mol2_vector = mol2.read_Mol2_file_head_gz(infilemol2_poses)

    count = 0
    energy_vec = []
    for mol in mol2_vector:
        lines = mol.header.split('\n')  #file1.close()
        for line in lines:
            if 'Total' in line:
                splitline = line.split()
                energy = float(splitline[3])
                energy_vec.append(energy)
    energy_vec_sort = sorted(enumerate(energy_vec), key=lambda x: x[1])
    #energy_vec_sort = sorted(enumerate(energy_vec), key=lambda x: -x[1])
    for entry in energy_vec_sort:
        print(entry)
        print(entry[0])
        mol2.append_mol2(mol2_vector[entry[0]], outfile + '.mol2')
    print("wrong number of arguments. there must be 5 or 6, not %d. " %
          len(sys.argv))
    exit()

infile = sys.argv[1]
outfile = sys.argv[2]
a1_ori = sys.argv[3]  # ori
a2_rep = sys.argv[4]
a3_search = sys.argv[5]

if (len(sys.argv) == 7):
    a2_name = sys.argv[6]  #new atom name
else:
    a2_name = "NONE"

print(
    'infile=%s,\noutfile=%s,\na1_ori=%s,\na2_rep=%s,\na3_search=%s\na2_name=%s\n'
    % (infile, outfile, a1_ori, a2_rep, a3_search, a2_name))

mol_list = mol2.read_Mol2_file(infile)
print(len(mol_list))
count = 0
for mol in mol_list:
    moln = loop_bonds(a1_ori, a2_rep, a3_search, a2_name, mol)
    if (count == 0):
        mol2.write_mol2(moln, outfile)
    else:
        mol2.append_mol2(moln, outfile)
    count = count + 1
print("processed %d mol2 entries" % count)
Example #5
0
def modify_mol2_file(mol2file, outputprefix):
    ## read in mol2 file
    frist = True
    mollist = mol2.read_Mol2_file(mol2file) 
    for mol in mollist:
       ori_formal_charge = mol2.formal_charge(mol)
       n = len(mol.atom_list) 
       Si_atoms_index = []
       for i in range(n):
           if mol.atom_list[i].type == 'Si':
              print (mol.atom_list[i].type, mol.atom_list[i].name)
              Si_atoms_index.append(i)

       #if len(Si_atoms_index) != 2:
       if len(Si_atoms_index) != 1:
           print ("error")
           exit()

       count_h = [0,0] # remember how meny atoms are connected to the both Si
       Hlist = []  # remember which the atom index that are the connected bonds. 
       Si1 = Si_atoms_index[0]
       #Si2 = Si_atoms_index[1]
       for bond in mol.bond_list:
           if bond.a1_num-1 == Si1: 
              if (mol.atom_list[bond.a2_num-1].type == 'H'):
                  count_h[0]=count_h[0]+1
                  Hlist.append(bond.a2_num)
           if bond.a2_num-1 == Si1:
              if (mol.atom_list[bond.a1_num-1].type == 'H'):
                  count_h[0]=count_h[0]+1
                  Hlist.append(bond.a1_num)
           #if bond.a1_num-1 == Si2:
           #   if (mol.atom_list[bond.a2_num-1].type == 'H'):
           #       count_h[1]=count_h[1]+1
           #       Hlist.append(bond.a2_num)
           #if bond.a2_num-1 == Si2:
           #   if (mol.atom_list[bond.a1_num-1].type == 'H'):
           #       count_h[1]=count_h[1]+1
           #       Hlist.append(bond.a1_num)
       print (Hlist) 
       print (count_h) 

       # (1) remove 5 hydrogen atoms, 
       # (2) change Si to Du and the atom name, 

       new_atomlist = []
       for i,atom in enumerate(mol.atom_list):
           print(i, atom.num)
           #exit()
           if atom.num in Hlist: 
              continue
           if atom.num-1 == Si1: 
              atom.type = 'Du'
              atom.Q = 0.0
              if count_h[0] == 3: 
                 #atom.name = 'D2'
                 atom.name = 'D1'
              elif count_h[0] == 2:
                 #atom.name = 'D1'
                 print ("error")
                 exit()
#          if atom.num-1 == Si2: 
#             atom.type = 'Du'
#             atom.Q = 0.0
#             if count_h[1] == 3: 
#                atom.name = 'D2'
#             elif count_h[1] == 2: # 
#                atom.name = 'D1'
           
           new_atomlist.append(copy.copy(atom))
       # (3) generate mapping from old to new atom numbering to be used in the bond modification. 
       atom_num_map = {}
       for i,atom in enumerate(new_atomlist):
           atom_num_map[atom.num] = i+1
           atom.num = i+1

       # (4) remove bonds that contain any of the removed hydrogens.
       new_bondlist = []
       for i,bond in enumerate(mol.bond_list):
           if bond.a1_num in Hlist or bond.a2_num in Hlist:
              continue  
           new_bondlist.append(copy.copy(bond))

       # (5) renumber the bonds, map old atom numbering to new atom number for bonds
       i = 1
       for bond in new_bondlist:
           bond.num = i
           bond.a1_num = atom_num_map[bond.a1_num]
           bond.a2_num = atom_num_map[bond.a2_num]
           i = i + 1

       mol.atom_list = new_atomlist
       mol.bond_list = new_bondlist

       # ajust the partial charge to make it an integer.  
       make_integer_charge(mol, ori_formal_charge)

       #exit()
       filename = outputprefix + '.mol2'
       if frist:
          mol2.write_mol2(mol,filename)
          frist = False
       else:
          mol2.append_mol2(mol,filename)
          
    return