programming python

Phân tích cú pháp tệp genbank Python

Định dạng có các

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 lặp lại [được phân tách bằng

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

9], trong đó mỗi

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 là một protein. Mỗi

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 có một số phần trong đó có phần

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

2 với một số trường cố định, chẳng hạn như

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

1 và

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

2, với các giá trị đề cập đến thông tin cụ thể cho

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 đó

Tôi quan tâm đến việc sử dụng

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

5 của

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

4 để phân tích cú pháp tệp này thành một

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

6 liệt kê cho từng ID bản ghi, các giá trị của

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 và

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

9 từ trường

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

1 của nó, các giá trị

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

01 và

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 từ trường

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

0 và giá trị

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8 của nó . Ngoại trừ trường

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

06, có thể xuất hiện nhiều lần trong phần

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

2 của

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

8, các trường

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

1 và

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

0 chỉ xuất hiện một lần trong phần

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

2 của

from Bio import SeqIO
filename = "example.protein.gpff"
for record in SeqIO.parse[filename, "genbank"]:
  for feature in record.features:
    if feature.type == "CDS":
      symbol = feature.qualifiers.get["gene", ["???"]][0]
      gene_id = feature.qualifiers.get["db_xref", ["???"]][0]
      gene_id = re.sub['GeneID:', '', gene_id]
      transcript_id = feature.qualifiers.get["coded_by", ["???"]][0]
      transcript_id = re.sub[':.*', '', transcript_id]
      if feature.type == "source":
        species_name = feature.qualifiers.get["organism", ["???"]][0]
        species_id = feature.qualifiers.get["db_xref", ["???"]][0]
        species_id = re.sub['taxon:', '', species_id]
      if feature.type == "Region":
        cdd_id = feature.qualifiers.get["db_xref", ["???"]][0]
        cdd_id = re.sub['CDD:', '', cdd_id]
      print["%s,%s,%s,%s,%s,%s,%s" % [record.id, cdd_id, transcript_id, symbol, gene_id, species_name, species_id]]

Định dạng tệp Genbank là gì?

Định dạng Ngân hàng gen cho phép lưu trữ thông tin ngoài trình tự DNA/protein . Nó chứa nhiều thông tin hơn định dạng FASTA. Các định dạng tương tự như Genbank đã được phát triển bởi ENA [định dạng EMBL] và bởi DDBJ [định dạng DDBJ].

SeqIO là gì?

SeqIO cung cấp giao diện thống nhất đơn giản để nhập và xuất các định dạng tệp trình tự khác nhau [bao gồm nhiều sắp xếp trình tự], nhưng sẽ chỉ xử lý các trình tự . Có một giao diện chị em Bio. AlignIO để làm việc trực tiếp với các tệp căn chỉnh trình tự dưới dạng đối tượng Căn chỉnh.

Định dạng tệp Genbank là gì?

SeqIO là gì?

Bài Viết Liên Quan

Toplist mới

Bài mới nhất

Chủ Đề