AF2样图1

代码1-分块

#将b_factor对应到每个氨基酸残基上


from biopandas.pdb import PandasPdb


file = '/home/databank/lywu/vp37/af2-vp37/ranked_0.pdb'
data = PandasPdb().read_pdb(file)
#data.df.keys()
#data.df['ATOM'].columns
atom_df = data.df['ATOM']


#根据氨基酸编号进行去重，并重设Index
residue_list = atom_df.drop_duplicates(subset=['residue_number']).reset_index(drop=True)


#输出去重后每个氨基酸对应的b_factor
b_factor_list = residue_list['b_factor']


'''
根据筛选条件，输出对应的氨基酸编号，注意+1
'''
#very low
filter1 = np.where([(b_factor_list < 50)])[1]
#low
filter2 = np.where([(b_factor_list >= 50)&(b_factor_list < 70)])[1]
#Confident
filter3 = np.where([(b_factor_list >= 70)&(b_factor_list < 90)])[1]
#very high
filter4 = np.where([(b_factor_list >= 90)])[1]




#根据b_factor分类对残基重新着色
from pymol import cmd


cmd.delete("all")
cmd.load(file)


color_list = ['orange','yellow','palecyan', 'skyblue']
filetr_list = [filter1, filter2, filter3, filter4]


for i in range(4):
    colorid = color_list[i]
    f_index = filetr_list[i]
    for index in f_index:
        resid = index + 1
        cmd.color(colorid,"resi " + str(resid))


cmd.save("test2.pse")

样图2

代码2-连续

b_factor的归一化处理

from biopandas.pdb import PandasPdb


file = '/home/databank/lywu/vp37/af2-vp37/ranked_0.pdb'
data = PandasPdb().read_pdb(file)
data.df.keys()
data.df['ATOM'].columns
df = data.df['ATOM'].b_factor


df_normalized = df.apply(lambda x:(x - 0)/(100 - 0))
#df_normalized此时对应的是单个原子，需要另外处理时期对应每个残基

绘制colorbar

使用默认的colormap

fig, ax = plt.subplots(figsize=(1, 6))
fig.subplots_adjust(bottom=0.5)


cmap = mpl.cm.Pastel1
norm = mpl.colors.Normalize(vmin=40, vmax=100)


fig.colorbar(mpl.cm.ScalarMappable(norm=norm, cmap=cmap),
             cax=ax, orientation='vertical', label='Some Units')

自定义colormap, 即colorlist

from matplotlib import colors
fig, ax = plt.subplots(figsize=(1, 6))
fig.subplots_adjust(bottom=0.5)


colorslist = ['#104E8B','white']
cmap = colors.LinearSegmentedColormap.from_list('mylist',colorslist,N=10)
norm = mpl.colors.Normalize(vmin=40, vmax=100)


fig.colorbar(mpl.cm.ScalarMappable(norm=norm, cmap=cmap),
             cax=ax, orientation='vertical', label='Some Units')

color in pymol

from pymol import cmd


num_classes = 100
cmap = cm.rainbow(np.linspace(0.0, 1.0, num_classes))


for i in range(num_classes):
    colorname='color%d'%(i)
    cmd.set_color(colorname, '[%f,%f,%f]'%(cmap[i][0],cmap[i][1],cmap[i][2]))


cmd.delete("all")
cmd.load(file)
 
for index in df_normalized.index.values:
    resid = index + 1
    rmsf = df_normalized.iloc[index]
    colorid="color%d"%(int(float(rmsf)))
    cmd.color(colorid,"resi " + str(resid))
cmd.save("test.pse")

其他