BioPython-PDB-1

#读取结构文件
#(1)读取mmcif文件
#创建一个mmcif解析器
from Bio.PDB.MMCIFParser import MMCIFParser
parser = MMCIFParser()
#导入mmcif结构文件
structure = parser.get_structure('1fat', '1fat.cif')


#（2）读取pdb格式文件
#创建一个pdb解析器
from Bio.PDB.PDBParser import PDBParser
p = PDBParser()
#导入pdb文件
structure = p.get_structure('1d3z','1D3Z.pdb')


#这样就拿到了蛋白结构
#看下结构的表示
#一个 Structure 对象的整体布局遵循称为SMCRA（Structure/Model/Chain/Residue/Atom，结构/模型/链/残基/原子）的体系架构：


#结构由模型组成
#模型由多条链组成
#链由残基组成
#多个原子构成残基


#上一副UML图，官方的。。。自己悟

#再来一个经典的案例
#看一下help文档
help(structure)


for model in structure:
for chain in model:
for residue in chain:
for atom in residue:
print(atom)


#然后一层一层看下来
structure.get_full_id()
('1d3z',)


model_list=structure.get_list()


model_list


[<Model id=0>,
<Model id=1>,
<Model id=2>,
<Model id=3>,
<Model id=4>,
<Model id=5>,
<Model id=6>,
<Model id=7>,
<Model id=8>,
<Model id=9>]


chain_list=model_list[0].get_list()
chain_list


[<Chain id=A>]


res_list=chain_list[0].get_list()
res_list

[<Residue MET het=  resseq=1 icode= >,
<Residue GLN het=  resseq=2 icode= >,
<Residue ILE het=  resseq=3 icode= >,
<Residue PHE het=  resseq=4 icode= >,
<Residue VAL het=  resseq=5 icode= >,
<Residue LYS het=  resseq=6 icode= >,
<Residue THR het=  resseq=7 icode= >,
<Residue LEU het=  resseq=8 icode= >,
<Residue THR het=  resseq=9 icode= >,
<Residue GLY het=  resseq=10 icode= >,
<Residue LYS het=  resseq=11 icode= >,
<Residue THR het=  resseq=12 icode= >,
<Residue ILE het=  resseq=13 icode= >,
<Residue THR het=  resseq=14 icode= >,
<Residue LEU het=  resseq=15 icode= >,
<Residue GLU het=  resseq=16 icode= >,
<Residue VAL het=  resseq=17 icode= >,
<Residue GLU het=  resseq=18 icode= >,
<Residue PRO het=  resseq=19 icode= >,
<Residue SER het=  resseq=20 icode= >,
<Residue ASP het=  resseq=21 icode= >,
<Residue THR het=  resseq=22 icode= >,
<Residue ILE het=  resseq=23 icode= >,
<Residue GLU het=  resseq=24 icode= >,
<Residue ASN het=  resseq=25 icode= >,
<Residue VAL het=  resseq=26 icode= >,
<Residue LYS het=  resseq=27 icode= >,
<Residue ALA het=  resseq=28 icode= >,
<Residue LYS het=  resseq=29 icode= >,
<Residue ILE het=  resseq=30 icode= >,
<Residue GLN het=  resseq=31 icode= >,
<Residue ASP het=  resseq=32 icode= >,
<Residue LYS het=  resseq=33 icode= >,
<Residue GLU het=  resseq=34 icode= >,
<Residue GLY het=  resseq=35 icode= >,
<Residue ILE het=  resseq=36 icode= >,
<Residue PRO het=  resseq=37 icode= >,
<Residue PRO het=  resseq=38 icode= >,
<Residue ASP het=  resseq=39 icode= >,
<Residue GLN het=  resseq=40 icode= >,
<Residue GLN het=  resseq=41 icode= >,
<Residue ARG het=  resseq=42 icode= >,
<Residue LEU het=  resseq=43 icode= >,
<Residue ILE het=  resseq=44 icode= >,
<Residue PHE het=  resseq=45 icode= >,
<Residue ALA het=  resseq=46 icode= >,
<Residue GLY het=  resseq=47 icode= >,
<Residue LYS het=  resseq=48 icode= >,
<Residue GLN het=  resseq=49 icode= >,
<Residue LEU het=  resseq=50 icode= >,
<Residue GLU het=  resseq=51 icode= >,
<Residue ASP het=  resseq=52 icode= >,
<Residue GLY het=  resseq=53 icode= >,
<Residue ARG het=  resseq=54 icode= >,
<Residue THR het=  resseq=55 icode= >,
<Residue LEU het=  resseq=56 icode= >,
<Residue SER het=  resseq=57 icode= >,
<Residue ASP het=  resseq=58 icode= >,
<Residue TYR het=  resseq=59 icode= >,
<Residue ASN het=  resseq=60 icode= >,
<Residue ILE het=  resseq=61 icode= >,
<Residue GLN het=  resseq=62 icode= >,
<Residue LYS het=  resseq=63 icode= >,
<Residue GLU het=  resseq=64 icode= >,
<Residue SER het=  resseq=65 icode= >,
<Residue THR het=  resseq=66 icode= >,
<Residue LEU het=  resseq=67 icode= >,
<Residue HIS het=  resseq=68 icode= >,
<Residue LEU het=  resseq=69 icode= >,
<Residue VAL het=  resseq=70 icode= >,
<Residue LEU het=  resseq=71 icode= >,
<Residue ARG het=  resseq=72 icode= >,
<Residue LEU het=  resseq=73 icode= >,
<Residue ARG het=  resseq=74 icode= >,
<Residue GLY het=  resseq=75 icode= >,
<Residue GLY het=  resseq=76 icode= >]


res=res_list[0]
res
<Residue MET het=  resseq=1 icode= >


atom_list=res.get_list()
atom_list


[<Atom N>,
<Atom CA>,
<Atom C>,
<Atom O>,
<Atom CB>,
<Atom CG>,
<Atom SD>,
<Atom CE>,
<Atom H1>,
<Atom H2>,
<Atom H3>,
<Atom HA>,
<Atom HB2>,
<Atom HB3>,
<Atom HG2>,
<Atom HG3>,
<Atom HE1>,
<Atom HE2>,
<Atom HE3>]

atom_list[1]
<Atom CA>

atom_list[1].coord
array([ 51.653, -89.304,   8.833], dtype=float32)