allpy
changeset 111:62e38970ffa2
broken: lib::project::column -- new returning value
sequence::pdb_chain_chain_add completed
author | boris <bnagaev@gmail.com> |
---|---|
date | Sat, 23 Oct 2010 12:57:07 +0400 |
parents | b43daeb9d767 |
children | b7b963287d31 |
files | lib/monomer.py lib/project.py lib/sequence.py |
diffstat | 3 files changed, 40 insertions(+), 17 deletions(-) [+] |
line diff
1.1 --- a/lib/monomer.py Sat Oct 23 12:07:21 2010 +0400 1.2 +++ b/lib/monomer.py Sat Oct 23 12:57:07 2010 +0400 1.3 @@ -31,6 +31,10 @@ 1.4 @staticmethod 1.5 def from_name(name): 1.6 return index_name[name.capitalize()] 1.7 + 1.8 + @staticmethod 1.9 + def from_pdb_residue(pdb_residue): 1.10 + return MonomerType.from_code3(pdb_residue.get_resname()) 1.11 1.12 # TO DISCUSS 1.13 def __eq__(self, other): 1.14 @@ -47,10 +51,10 @@ 1.15 """ 1.16 def __init__(self, monomer_type): 1.17 self.type = monomer_type 1.18 - self.pdb_residue = [] 1.19 + self.pdb_residues = {} 1.20 1.21 - def pdb_residue_add(self, pdb_chain, pdb_residue): 1.22 - self.pdb_residue[pdb_chain] = pdb_residue 1.23 + def pdb_residue_add(self, chain, residue): 1.24 + self.pdb_residues[chain] = residue 1.25 1.26 def __eq__(self, other): 1.27 return self.type == other.type
2.1 --- a/lib/project.py Sat Oct 23 12:07:21 2010 +0400 2.2 +++ b/lib/project.py Sat Oct 23 12:57:07 2010 +0400 2.3 @@ -12,7 +12,6 @@ 2.4 import allpy_data 2.5 import os 2.6 from tempfile import mkstemp 2.7 -import sys 2.8 2.9 class Project(object): 2.10 """ 2.11 @@ -198,8 +197,8 @@ 2.12 """ 2.13 returns list of columns of alignment 2.14 sequence or sequences: 2.15 - if sequence is given, then column is monomer 2.16 - if sequences is given, then column is dict {sequence: monomer} 2.17 + if sequence is given, then column is (original_monomer, monomer) 2.18 + if sequences is given, then column is dict (original_monomer, {sequence: monomer}) 2.19 if both of them are given, it is an error 2.20 original (Sequence type): 2.21 if given, this filters only columns represented by original sequence 2.22 @@ -210,11 +209,11 @@ 2.23 alignment = self.alignment.items() 2.24 alignment.sort(key=lambda i: indexes[i[0]]) 2.25 alignment = [monomers for seq, monomers in alignment] 2.26 - for column in zip(alignment): 2.27 - if not original or column[index[original]]: 2.28 + for column in zip(*alignment): 2.29 + if not original or column[indexes[original]]: 2.30 if sequence: 2.31 - yield column[index[sequence]] 2.32 + yield (column[indexes[original]], column[indexes[sequence]]) 2.33 else: 2.34 - yield dict([(s, column[index[s]]) for s in sequences]) 2.35 + yield (column[indexes[original]], dict([(s, column[indexes[s]]) for s in sequences])) 2.36 2.37
3.1 --- a/lib/sequence.py Sat Oct 23 12:07:21 2010 +0400 3.2 +++ b/lib/sequence.py Sat Oct 23 12:57:07 2010 +0400 3.3 @@ -3,6 +3,8 @@ 3.4 from Bio.PDB import PDBParser, CaPPBuilder 3.5 from allpy_pdb import Pdb 3.6 import project 3.7 +import sys 3.8 + 3.9 3.10 cappbuilder = CaPPBuilder() 3.11 3.12 @@ -17,10 +19,13 @@ 3.13 TODO: class Protein: container of multiple Sequences, 3.14 class ProteinMononer: container of multiple Monomers 3.15 """ 3.16 - def __init__(self, monomers, name='', description=""): 3.17 + def __init__(self, monomers=None, name='', description=""): 3.18 + if not monomers: 3.19 + monomers = [] 3.20 self.name = name 3.21 self.description = description 3.22 self.monomers = monomers 3.23 + self.pdb_chains = [] 3.24 3.25 def __len__(self): 3.26 return len(self.monomers) 3.27 @@ -41,13 +46,14 @@ 3.28 and align each Monomer with PDB.Residue (TODO) 3.29 """ 3.30 name = Pdb.std_id(pdb_id, pdb_chain, pdb_model) 3.31 - self.pdb_chain = PDBParser().get_structure(name, pdb_file)[pdb_model][pdb_chain] 3.32 - peptide = cappbuilder.build_peptides(self.pdb_chain) 3.33 - pdb_sequence = Sequence.from_str(str(peptide[0].get_sequence())) # TRU? 3.34 + chain = PDBParser().get_structure(name, pdb_file)[pdb_model][pdb_chain] 3.35 + self.pdb_chains.append(chain) 3.36 + pdb_sequence = Sequence.from_pdb_chain(chain) 3.37 alignment = project.Project.from_sequences(self, pdb_sequence) 3.38 alignment.muscle_align() 3.39 - for pdb_monomer in alignment.column(sequence=pdb_sequence, original=self): 3.40 - pdb_monomer.pdb_residue_add(self.pdb_chain, 3.41 + for monomer, pdb_monomer in alignment.column(sequence=pdb_sequence, original=self): 3.42 + monomer.pdb_residue_add(chain, pdb_monomer.pdb_residues[chain]) 3.43 + #~ pdb_monomer.pdb_residue_add(self.pdb_chain, 3.44 # FIXME: align and map 3.45 3.46 @staticmethod 3.47 @@ -55,6 +61,21 @@ 3.48 monomers = [monomer_kind.from_code1(aa).instance() for aa in fasta_str] 3.49 return Sequence(monomers, name, description) 3.50 3.51 + @staticmethod 3.52 + def from_pdb_chain(chain): 3.53 + """ 3.54 + chain is Bio.PDB.Chain 3.55 + returns Sequence with Monomers with link to Bio.PDB.Residue 3.56 + """ 3.57 + peptide = cappbuilder.build_peptides(chain)[0] 3.58 + sequence = Sequence() 3.59 + sequence.pdb_chains = [chain] 3.60 + for ca_atom in peptide.get_ca_list(): 3.61 + residue = ca_atom.get_parent() 3.62 + monomer = AminoAcidType.from_pdb_residue(residue).instance() 3.63 + monomer.pdb_residue_add(chain, residue) 3.64 + sequence.monomers.append(monomer) 3.65 + return sequence 3.66 3.67 3.68 3.69 @@ -63,4 +84,3 @@ 3.70 3.71 3.72 3.73 -