app.py

import streamlit as st
from stmol import showmol
import py3Dmol
import requests
import biotite.structure.io as bsio
import random
import hashlib
import urllib3

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

st.set_page_config(layout='wide')
st.sidebar.title('🎈 ESMFold Protein Structure Predictor')
st.sidebar.write('[*ESMFold*](https://esmatlas.com/about) is an end-to-end single sequence protein structure predictor based on the ESM-2 language model. For more information, read the [research article](https://www.biorxiv.org/content/10.1101/2022.07.20.500902v2) and the [news article](https://www.nature.com/articles/d41586-022-03539-1) published in *Nature*.')

# Function to generate protein sequence from words
def generate_sequence_from_words(words, length):
    seed = ' '.join(words).encode('utf-8')
    random.seed(hashlib.md5(seed).hexdigest())
    amino_acids = "ACDEFGHIKLMNPQRSTVWY"
    return ''.join(random.choice(amino_acids) for _ in range(length))

# stmol
def render_mol(pdb):
    pdbview = py3Dmol.view()
    pdbview.addModel(pdb,'pdb')
    pdbview.setStyle({'cartoon':{'color':'spectrum'}})
    pdbview.setBackgroundColor('white')
    pdbview.zoomTo()
    pdbview.zoom(2, 800)
    pdbview.spin(True)
    showmol(pdbview, height = 500,width=800)

# ESMfold
def update(sequence, word1, word2, word3, sequence_length):
    headers = {
        'Content-Type': 'application/x-www-form-urlencoded',
    }
    try:
        response = requests.post('https://api.esmatlas.com/foldSequence/v1/pdb/', 
                                 headers=headers, 
                                 data=sequence, 
                                 verify=False,  # Disable SSL verification
                                 timeout=300)  # Set a longer timeout
        response.raise_for_status()  # Raise an exception for bad status codes
        pdb_string = response.content.decode('utf-8')
        
        with open('predicted.pdb', 'w') as f:
            f.write(pdb_string)
        
        struct = bsio.load_structure('predicted.pdb', extra_fields=["b_factor"])
        b_value = round(struct.b_factor.mean(), 2)
        
        # Display protein structure
        st.subheader(f'Predicted protein structure using seed: {word1}, {word2}, and {word3} + length ({sequence_length})')
        render_mol(pdb_string)
        
        # plDDT value is stored in the B-factor field
        st.subheader('plDDT Score')
        st.write('plDDT is a per-residue estimate of the confidence in prediction on a scale from 0-100.')
        st.info(f'Average plDDT: {b_value}%')
        
        st.download_button(
            label="Download PDB",
            data=pdb_string,
            file_name='predicted.pdb',
            mime='text/plain',
        )
    except requests.exceptions.RequestException as e:
        st.error(f"An error occurred while calling the API: {str(e)}")
        st.write("Please try again later or contact support if the issue persists.")

# Streamlit app
st.title("Word-Seeded Protein Sequence Generator and Structure Predictor")

# Input for word-seeded sequence generation
st.sidebar.subheader("Generate Sequence from Words")
word1 = st.sidebar.text_input("Word 1")
word2 = st.sidebar.text_input("Word 2")
word3 = st.sidebar.text_input("Word 3")
sequence_length = st.sidebar.number_input("Sequence Length", min_value=50, max_value=400, value=100, step=10)

# Generate and predict button
if st.sidebar.button('Generate and Predict'):
    if word1 and word2 and word3:
        sequence = generate_sequence_from_words([word1, word2, word3], sequence_length)
        st.sidebar.text_area("Generated Sequence", sequence, height=100)
        st.sidebar.info("Note: The same words and length will always produce the same sequence.")
        
        with st.spinner("Predicting protein structure... This may take a few minutes."):
            update(sequence, word1, word2, word3, sequence_length)
    else:
        st.sidebar.warning("Please enter all three words to generate a sequence.")

# Information display
st.sidebar.markdown("""
## What to do next:
1. Enter three words and a sequence length.
2. Click 'Generate and Predict' to generate the sequence, visualize the protein, and get its plDDT score.
3. Explore the 3D structure and download the PDB file if desired.
4. Experiment with different words or sequence lengths to see how they affect the predicted structure.

Remember, these predictions are based on AI models and should be interpreted with caution.
""")