Genome IGR selection: Genome listed on Rfam cannot be accessed #31
Description
I wanted to use DIMPL to analyze the genome of Xylella fastidiosa for ncRNA, but the genome that is deposited doesnt seem to work.
Here is a copy of the code in the first Jupyter notebook and the error I get:
upid = 'UP000000812' #Enter your uniprot ID
annotated_df, fig, layout, genome = display_genome(upid)
display(fig)
error Traceback (most recent call last)
/tmp/ipykernel_33/91208399.py in
1 upid = 'UP000000812' #Enter your uniprot ID
----> 2 annotated_df, fig, layout, genome = display_genome(upid)
3 display(fig)
~/work/src/visualization/visualize.py in display_genome(upid)
139 session.close()
140 download_genome(genome)
--> 141 igr_df = extract_igrs(genome, igr_length_cutoff=1)
142 annotated_df = annotate_igrs(genome, igr_df)
143 scatter_plots = graph_genome(annotated_df)
~/work/src/data/make_dataset.py in extract_igrs(genome, igr_length_cutoff)
134
135 # Create a Seqrecord for each "chromosome" in the file
--> 136 for seqrecord in SeqIO.parse(genbank_file, "gb"):
137
138 cds_list = []
/opt/conda/lib/python3.7/site-packages/Bio/SeqIO/Interfaces.py in next(self)
72 def next(self):
73 try:
---> 74 return next(self.records)
75 except Exception:
76 if self.should_close_stream:
/opt/conda/lib/python3.7/site-packages/Bio/GenBank/Scanner.py in parse_records(self, handle, do_features)
514 with as_handle(handle) as handle:
515 while True:
--> 516 record = self.parse(handle, do_features)
517 if record is None:
518 break
/opt/conda/lib/python3.7/site-packages/Bio/GenBank/Scanner.py in parse(self, handle, do_features)
497 )
498
--> 499 if self.feed(handle, consumer, do_features):
500 return consumer.data
501 else:
/opt/conda/lib/python3.7/site-packages/Bio/GenBank/Scanner.py in feed(self, handle, consumer, do_features)
473
474 # Footer and sequence
--> 475 misc_lines, sequence_string = self.parse_footer()
476 self._feed_misc_lines(consumer, misc_lines)
477
/opt/conda/lib/python3.7/site-packages/Bio/GenBank/Scanner.py in parse_footer(self)
1240 raise ValueError("Sequence line mal-formed, '%s'" % line)
1241 seq_lines.append(line[10:]) # remove spaces later
-> 1242 line = self.handle.readline()
1243
1244 self.line = line
/opt/conda/lib/python3.7/gzip.py in read1(self, size)
298 if size < 0:
299 size = io.DEFAULT_BUFFER_SIZE
--> 300 return self._buffer.read1(size)
301
302 def peek(self, n):
/opt/conda/lib/python3.7/_compression.py in readinto(self, b)
66 def readinto(self, b):
67 with memoryview(b) as view, view.cast("B") as byte_view:
---> 68 data = self.read(len(byte_view))
69 byte_view[:len(data)] = data
70 return len(data)
/opt/conda/lib/python3.7/gzip.py in read(self, size)
480 buf = self._fp.read(io.DEFAULT_BUFFER_SIZE)
481
--> 482 uncompress = self._decompressor.decompress(buf, size)
483 if self._decompressor.unconsumed_tail != b"":
484 self._fp.prepend(self._decompressor.unconsumed_tail)
error: Error -3 while decompressing data: invalid stored block lengths