Error "StreamModeError: Fasta files must be opened in text mode" in BioPython on a Streamlit App - biopython

Question

Please Assist, How can I resolve this Error?
I am building a streamlit app that take uploaded FASTA Files as input and read them.
I am getting the error below when I try to read an uploaded fasta file on my streamlit app
THE ERROR:
StreamModeError: Fasta files must be opened in text mode.
Traceback:
File "C:\Users\Sir Roberto\AppData\Local\Programs\Python\Python310\lib\site-packages\streamlit\scriptrunner\script_runner.py", line 475, in _run_script
exec(code, module.__dict__)
File "C:\Users\Sir Roberto\PycharmProjects\SARS_CoV_2_Mutation_Forecasting_GUI\SARS_CoV_2_Mutation_Forecasting_GUI.py", line 45, in <module>
main()
File "C:\Users\Sir Roberto\PycharmProjects\SARS_CoV_2_Mutation_Forecasting_GUI\SARS_CoV_2_Mutation_Forecasting_GUI.py", line 21, in main
protein_sample = SeqIO.read(seq_file, 'fasta')
File "C:\Users\Sir Roberto\AppData\Local\Programs\Python\Python310\lib\site-packages\Bio\SeqIO\__init__.py", line 652, in read
iterator = parse(handle, format, alphabet)
File "C:\Users\Sir Roberto\AppData\Local\Programs\Python\Python310\lib\site-packages\Bio\SeqIO\__init__.py", line 605, in parse
return iterator_generator(handle)
File "C:\Users\Sir Roberto\AppData\Local\Programs\Python\Python310\lib\site-packages\Bio\SeqIO\FastaIO.py", line 183, in __init__
super().__init__(source, mode="t", fmt="Fasta")
File "C:\Users\Sir Roberto\AppData\Local\Programs\Python\Python310\lib\site-packages\Bio\SeqIO\Interfaces.py", line 53, in __init__
raise StreamModeError(
THE CODE GIVING THE ERROR
import streamlit as st
import tensorflow as tf
import tensorflow_io as tfio
from Bio import SeqIO
def main():
st.title('Covid-19 Mutation Forecasting App')
menu = ['Forecast Mutation', 'About The App']
choice = st.sidebar.selectbox('Select Activity', menu)
if choice == 'Forecast Mutation':
st.subheader('Mutation Forecasting Workspace')
seq_file = st.file_uploader('Upload a Sequence File:', type=['fasta'])
if seq_file is not None:
protein_sample = SeqIO.read(seq_file, 'fasta')
st.write(protein_sample)
loaded_model = tf.keras.models.load_model("")
next_step = st.checkbox('Forecast')
if next_step:
states = None
next_char = tfio.genome.read_fastaq(protein_sample)
result = [next_char]
for n in range(100):
next_char, states = one_step_reloaded.generate_one_step(next_char, states=states)
result.append(next_char)
print(tf.strings.join(result)[0].numpy().decode("utf-8"))
else:
st.subheader('About The App')
st.caption('Given the first few codons of a SARS-CoV-2 Spike Protein, '
'the App forecasts and display the complete sequence of the mutant')
if __name__ == '__main__':
main()`

Answer 1

The following code should get you started:
import streamlit as st
import tensorflow as tf
import tensorflow_io as tfio
from Bio import SeqIO
from io import StringIO
def main():
st.title('Covid-19 Mutation Forecasting App')
menu = ['Forecast Mutation', 'About The App']
choice = st.sidebar.selectbox('Select Activity', menu)
if choice == 'Forecast Mutation':
st.subheader('Mutation Forecasting Workspace')
seq_file = st.file_uploader('Upload a Sequence File:', type=['fasta'])
if seq_file is not None:
# To convert to a string based IO:
stringio = StringIO(seq_file.getvalue().decode("utf-8"))
for record in SeqIO.parse(stringio, 'fasta'):
sequence = str(record.seq)
st.write(f'Length of sequence: {len(sequence)}')
# The unique characters in the FASTA file
vocab = sorted(set(sequence))
st.write(f"{len(vocab)} unique characters: {', '.join(vocab)}")
tensor = tfio.genome.sequences_to_onehot(sequence)
st.write(tensor)
else:
st.subheader('About The App')
st.caption('Given the first few codons of a SARS-CoV-2 Spike Protein, '
'the App forecasts and display the complete sequence of the mutant')
if __name__ == '__main__':
main()
It looks as follows:
I used tfio.genome.sequence_to_onehot instead of tfio.genome.read_fastaq, because you are reading a FASTA file, not a FASTQ file.