Biopython -- SeqRecord

创建Seq object

from Bio.Seq import Seq

my_seq = Seq("AGTACACTGGT")  #seq objetc & like string but differ from python string

my_seq

Seq('AGTACACTGGT', Alphabet())

基础操作

互补序列

my_seq.complement()  #

Seq('TCATGTGACCA', Alphabet())

反向完全互补序列

my_seq.reverse_complement()

Seq('ACCAGTGTACT', Alphabet())

迭代打印序列

for index,letter in enumerate(my_seq):
    print("%i %s" %(index,letter))

0 A
1 G
2 T
3 A
4 C
5 A
6 C
7 T
8 G
9 G
10 T

切片

my_seq[0:2]

Seq('AG', Alphabet())

my_seq[0::2]  #just like string 

Seq('ATCCGT', Alphabet())

统计字符或者subseq

my_seq.count("A")

3

100 * float(my_seq.count("G") + my_seq.count("C")) / len(my_seq)

45.45454545454545

获得GC含量

from Bio.SeqUtils import GC
GC(my_seq)   #same as up example  & you should cope with mixed case and ambiguous nucleotides 

45.45454545454545

像操作字符串一样操作Seq object

#turn Seq object into string
str(my_seq) # or

#concatenating of adding sequences
protein_seq = Seq("EVRNAK")
dna_seq = Seq("ACGT")
protein_seq + dna_seq

Seq('EVRNAKACGT', Alphabet())

dna_seq + "GGG"

Seq('ACGTGGG', Alphabet())

my_seq.lower()
my_seq.upper()

Seq('AGTACACTGGT', Alphabet())

"AGCT" in my_seq

False

"AGCT" not in my_seq

True

转录

my_seq.transcribe() #transform seq to mRNA

Seq('AGUACACUGGU', RNAAlphabet())

my_seq.reverse_complement().transcribe()

Seq('ACCAGUGUACU', RNAAlphabet())

my_seq.transcribe().back_transcribe() #reverse mRNA to DNA

Seq('AGTACACTGGT', DNAAlphabet())

翻译

my_seq.translate()  #translate to protein  or 

/home/djs/miniconda3/lib/python3.8/site-packages/biopython-1.69-py3.8-linux-x86_64.egg/Bio/Seq.py:2092: BiopythonWarning: Partial codon, len(sequence) not a multiple of three. Explicitly trim the sequence or add trailing N before translation. This may become an error in future.
  warnings.warn("Partial codon, len(sequence) not a multiple of three. "





Seq('STL', ExtendedIUPACProtein())

my_seq.transcribe().translate() #same as coding DNA

Seq('STL', ExtendedIUPACProtein())

my_seq.translate(tabel= ,to_stop=True)

直接操作seq string

#working with string directly
from Bio.Seq import reverse_complement,translate,back_transcribe,transcribe
my_string = "TCGATCGATCGATCGA"
reverse_complement(my_string)
translate(my_string)

'SIDRS'

SeqIO模块的简单应用

from Bio import SeqIO

for seq_record in SeqIO.parse("test.gbk","genbank"):
    print(seq_record.id)
    print(seq_record.seq)
    print(len(seq_record)) #length of seq

for seq_record in SeqIO.parse("test.fa","fasta"):
    print(seq_record.id)
    print(seq_record.seq)
    print(len(seq_record)) #length of seq