import streamlit as st from stmol import showmol import py3Dmol import requests import biotite.structure.io as bsio import random import hashlib import urllib3 from Bio.Blast import NCBIWWW, NCBIXML from Bio.Seq import Seq from Bio.SeqRecord import SeqRecord import time import urllib.parse urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) st.set_page_config(layout='wide') st.sidebar.title('🔮 GenPro2') st.sidebar.write('GenPro2 is an end-to-end protein sequence generator, structure predictor, and analysis that uses [ESMFold](https://esmatlas.com/explore?at=1%2C1%2C21.999999344348925) and the ESM-2 language model | beta v2.12') 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)) def render_mol(pdb): viewer = py3Dmol.view(width='100%', height='400px') viewer.addModel(pdb, 'pdb') viewer.setStyle({'cartoon': {'color': 'spectrum'}}) viewer.setBackgroundColor('white') viewer.zoomTo() viewer.zoom(0.8) # Slightly zoomed out view viewer.spin(True) viewer.render() # Responsive design for mobile st.markdown(""" """, unsafe_allow_html=True) showmol(viewer, height=400, width=None) def perform_blast_analysis(sequence): st.subheader('Protein Analysis') with st.spinner("Analyzing generated protein... This may take several minutes. Stay tuned!"): progress_bar = st.progress(0) for i in range(100): progress_bar.progress(i + 1) time.sleep(1.9) # Analysis time try: record = SeqRecord(Seq(sequence), id='random_protein') result_handle = NCBIWWW.qblast("blastp", "swissprot", record.seq) blast_record = NCBIXML.read(result_handle) if blast_record.alignments: alignment = blast_record.alignments[0] # Get the top hit hsp = alignment.hsps[0] # Get the first (best) HSP # Extract protein name and organism title_parts = alignment.title.split('|') protein_name = title_parts[-1].strip() organism = title_parts[-2].split('OS=')[-1].split('OX=')[0].strip() # Calculate identity percentage identity_percentage = (hsp.identities / hsp.align_length) * 100 st.write(f"**Top Match:** {protein_name}") st.write(f"**UniProt ID:** {organism}") st.write(f"**Sequence Identity Match:** {identity_percentage:.2f}%") # Fetch protein function (if available) if hasattr(alignment, 'description') and alignment.description: st.write(f"**Potential Function:** {alignment.description}") else: st.write("No significant matches found in the database. This might be a unique protein sequence!") except Exception as e: st.error(f"An error occurred during protein analysis: {str(e)}") st.write("Please try again later, BLAST servers could be experiencing a delay.") 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, timeout=300) response.raise_for_status() 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) st.session_state.structure_info = { 'pdb_string': pdb_string, 'b_value': b_value, 'word1': word1, 'word2': word2, 'word3': word3, 'sequence_length': sequence_length } st.session_state.show_analyze_button = True 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.") def share_on_twitter(word1, word2, word3, length, plddt): tweet_text = f"I just generated a unique protein using #GenPro2 by @WandsAI using the seed words #{word1}, #{word2}, #{word3} + sequence length of {length}. My Protein has a {plddt}% plDDT score! #PostYourProtein" tweet_url = f"https://twitter.com/intent/tweet?text={urllib.parse.quote(tweet_text)}" return tweet_url # Initialize session state variables if 'sequence' not in st.session_state: st.session_state.sequence = None if 'show_analyze_button' not in st.session_state: st.session_state.show_analyze_button = False if 'structure_info' not in st.session_state: st.session_state.structure_info = None st.title("📖 User Guide:") 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) # Information for users st.info(""" Protein Length Guide: - 50-100 amino acids: Small proteins/peptides - 100-300 amino acids: Average protein domains - 300-500 amino acids: Larger single-domain proteins """) st.markdown(""" 1. Start by entering any three seed words of your choice and select a sequence length in the sidebar. 2. Click 'Generate and Predict' to generate a unique protein sequence based on your inputs. 3. GenPro2 then predicts the 3D structure of your protein and provides a confidence score. More about GenPro2 and Proteins: Your unique protein could be the key to unlocking new therapeutic possibilities or understanding disease mechanisms. Who knows? Your next generated sequence might just lead to a breakthrough. Start your journey into computational protein exploration! [Learn more](https://www.youtube.com/watch?v=KpedmJdrTpY) """) if st.sidebar.button('Generate and Predict'): if word1 and word2 and word3: sequence = generate_sequence_from_words([word1, word2, word3], sequence_length) st.session_state.sequence = sequence st.sidebar.text_area("Generated Sequence", sequence, height=100) st.sidebar.info("Note: The same words and sequence 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.") # Display structure information if available if st.session_state.structure_info: info = st.session_state.structure_info st.subheader(f'Predicted protein structure using seed: {info["word1"]}, {info["word2"]}, and {info["word3"]} + sequence length {info["sequence_length"]}') render_mol(info['pdb_string']) st.subheader('plDDT Confidence Score') st.write('plDDT is a bench mark for scoring the confidence level of protein folding predictions based on a scale from 0-100%. 70% or more is good!') plddt_score = int(info["b_value"] * 100) st.info(f'Your plDDT score is: {plddt_score}%') st.subheader("Share your unique protein on X(Twitter)") st.markdown("""