File size: 32,185 Bytes
9916f6b 884be71 9916f6b 884be71 9916f6b 884be71 9916f6b 884be71 9916f6b 884be71 9916f6b 884be71 9916f6b 884be71 9916f6b 35e900e 884be71 9916f6b 35e900e 884be71 35e900e 9916f6b 600e193 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 |
# app.py
# AI-Powered Drug Discovery Pipeline Streamlit Application
# This script integrates four phases of drug discovery into a single, interactive web app.
import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import requests
import io
from PIL import Image
import base64
# RDKit and BioPython imports
from rdkit import Chem
from rdkit.Chem import Draw, AllChem, Descriptors
from Bio import SeqIO
# Scikit-learn for ML models
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
# 3D Visualization
import py3Dmol
# Suppress warnings for cleaner output
import warnings
warnings.filterwarnings('ignore')
# --- Page Configuration ---
st.set_page_config(
page_title="AI Drug Discovery Pipeline",
page_icon="🔬",
layout="wide",
initial_sidebar_state="collapsed", # Sidebar is removed, but this is good practice
)
# Custom CSS for a professional, minimalist look
def apply_custom_styling():
st.markdown(
"""
<style>
@import url('https://fonts.googleapis.com/css2?family=Roboto:wght@400;700&display=swap');
html, body, [class*="st-"] {
font-family: 'Roboto', sans-serif;
}
.stApp {
background-color: rgb(28, 28, 28);
color: white;
}
/* Tab styles */
.stTabs [data-baseweb="tab-list"] {
gap: 24px;
}
.stTabs [data-baseweb="tab"] {
height: 50px;
white-space: pre-wrap;
background: none;
border-radius: 0px;
border-bottom: 2px solid #333;
padding: 10px 4px;
color: #AAA;
}
.stTabs [data-baseweb="tab"]:hover {
background: #222;
color: #FFF;
}
.stTabs [aria-selected="true"] {
border-bottom: 2px solid #00A0FF; /* Highlight color for active tab */
color: #FFF;
}
/* Button styles */
.stButton>button {
border-color: #00A0FF;
color: #00A0FF;
}
.stButton>button:hover {
border-color: #FFF;
color: #FFF;
background-color: #00A0FF;
}
</style>
""",
unsafe_allow_html=True
)
apply_custom_styling()
# --- 2. Core Functions from All Phases ---
# These functions are adapted from the provided Python scripts.
# ===== Phase 1 Functions =====
@st.cache_data(show_spinner="Fetching PDB structure...")
def fetch_pdb_structure(pdb_id: str):
"""
Fetches a PDB file and returns its content.
"""
log = ""
try:
url = f"https://files.rcsb.org/download/{pdb_id}.pdb"
response = requests.get(url, timeout=20)
if response.status_code == 200:
log += f"✅ Successfully fetched PDB data for {pdb_id}.\n"
return response.text, log
else:
log += f"⚠️ Failed to fetch PDB file for {pdb_id} (Status: {response.status_code}). Please check the PDB ID and try again.\n"
return None, log
except Exception as e:
log += f"❌ An error occurred while fetching PDB data: {e}\n"
return None, log
@st.cache_data(show_spinner="Fetching FASTA sequence...")
def fetch_fasta_sequence(protein_id: str):
"""
Fetches a protein's FASTA sequence from NCBI.
"""
log = ""
try:
url = f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=protein&id={protein_id}&rettype=fasta&retmode=text"
response = requests.get(url, timeout=20)
if response.status_code == 200:
parsed_fasta = SeqIO.read(io.StringIO(response.text), "fasta")
log += f"✅ Successfully fetched FASTA sequence for {protein_id}.\n\n"
log += f"--- Protein Sequence Information ---\n"
log += f"ID: {parsed_fasta.id}\n"
log += f"Description: {parsed_fasta.description}\n"
log += f"Sequence Length: {len(parsed_fasta.seq)}\n"
log += f"Sequence Preview: {parsed_fasta.seq[:60]}...\n"
return log
else:
log += f"⚠️ Failed to fetch FASTA file (Status: {response.status_code}).\n"
return log
except Exception as e:
log += f"❌ An error occurred while fetching FASTA data: {e}\n"
return log
def visualize_protein_3d(pdb_data: str, title="Protein 3D Structure"):
"""
Generates an interactive 3D protein visualization using py3Dmol.
"""
if not pdb_data:
return None, "Cannot generate 3D view: No PDB data provided."
try:
viewer = py3Dmol.view(width='100%', height=600)
# MODIFIED: Changed background color
viewer.setBackgroundColor('#1C1C1C')
viewer.addModel(pdb_data, "pdb")
viewer.setStyle({'cartoon': {'color': 'spectrum', 'thickness': 0.8}})
viewer.addSurface(py3Dmol.VDW, {'opacity': 0.3, 'color': 'lightblue'})
viewer.zoomTo()
html = viewer._make_html()
log = f"✅ Generated 3D visualization for {title}."
return html, log
except Exception as e:
return None, f"❌ 3D visualization error: {e}"
def create_sample_molecules():
"""
Returns a list of sample SMILES strings for initial analysis.
"""
return [
"CC(=O)N[C@@H]1[C@@H](N)C=C(C(=O)O)O[C@H]1[C@H](O)[C@H](O)CO",
"CC(C)C[C@H](NC(=O)C)C(=O)N[C@@H]1[C@@H](O)C=C(C(=O)O)O[C@H]1[C@H](O)[C@H](O)CO",
"CC(C)CCCCCCCCCCCCCCCCCCCCCCCCCCCCC(=O)O",
"CCO",
]
def calculate_molecular_properties(smiles_list: list):
"""
Calculates key physicochemical properties for a list of molecules using RDKit.
"""
properties = []
log = ""
for i, smiles in enumerate(smiles_list):
mol = Chem.MolFromSmiles(smiles)
if mol:
props = {
'Molecule': f'Compound_{i+1}',
'SMILES': smiles,
'MW': Descriptors.MolWt(mol),
'LogP': Descriptors.MolLogP(mol),
'HBD': Descriptors.NumHDonors(mol),
'HBA': Descriptors.NumHAcceptors(mol),
'TPSA': Descriptors.TPSA(mol),
'RotBonds': Descriptors.NumRotatableBonds(mol),
}
properties.append(props)
else:
log += f"⚠️ Invalid SMILES string skipped: {smiles}\n"
df = pd.DataFrame(properties).round(2)
log += f"✅ Calculated properties for {len(df)} valid molecules.\n"
return df, log
def assess_drug_likeness(df: pd.DataFrame):
"""
Assesses drug-likeness based on Lipinski's Rule of Five.
"""
if df.empty:
return pd.DataFrame(), "Cannot assess drug-likeness: No properties data."
df_copy = df.copy()
df_copy['MW_OK'] = df_copy['MW'] <= 500
df_copy['LogP_OK'] = df_copy['LogP'] <= 5
df_copy['HBD_OK'] = df_copy['HBD'] <= 5
df_copy['HBA_OK'] = df_copy['HBA'] <= 10
df_copy['Lipinski_Violations'] = (~df_copy[['MW_OK', 'LogP_OK', 'HBD_OK', 'HBA_OK']]).sum(axis=1)
df_copy['Drug_Like'] = df_copy['Lipinski_Violations'] <= 1
log = "✅ Assessed drug-likeness using Lipinski's Rule of Five.\n"
return df_copy, log
def plot_properties_dashboard(df: pd.DataFrame):
"""
Creates a 2x2 dashboard of molecular property visualizations.
"""
if df.empty:
return None, "Cannot plot: No analysis data."
plt.style.use('dark_background')
fig, axes = plt.subplots(2, 2, figsize=(12, 10))
fig.suptitle("Molecular Properties Analysis", fontsize=16)
fig.patch.set_facecolor('none')
for ax_row in axes:
for ax in ax_row:
ax.set_facecolor('none')
axes[0,0].scatter(df['MW'], df['LogP'], c=df['Drug_Like'].map({True: 'green', False: 'red'}), s=80, alpha=0.7)
axes[0,0].set_title('Molecular Weight vs LogP')
axes[0,0].set_xlabel('Molecular Weight (Da)')
axes[0,0].set_ylabel('LogP')
axes[0,0].axvline(500, color='r', linestyle='--', alpha=0.6, label='MW < 500')
axes[0,0].axhline(5, color='r', linestyle='--', alpha=0.6, label='LogP < 5')
axes[0,0].legend()
axes[0,1].scatter(df['HBD'], df['HBA'], c=df['Drug_Like'].map({True: 'green', False: 'red'}), s=80, alpha=0.7)
axes[0,1].set_title('Hydrogen Bonding Properties')
axes[0,1].set_xlabel('Hydrogen Bond Donors')
axes[0,1].set_ylabel('Hydrogen Bond Acceptors')
axes[0,1].axvline(5, color='r', linestyle='--', alpha=0.6, label='HBD < 5')
axes[0,1].axhline(10, color='r', linestyle='--', alpha=0.6, label='HBA < 10')
axes[0,1].legend()
axes[1,0].scatter(df['TPSA'], df['RotBonds'], c=df['Drug_Like'].map({True: 'green', False: 'red'}), s=80, alpha=0.7)
axes[1,0].set_title('TPSA vs Flexibility')
axes[1,0].set_xlabel('Topological Polar Surface Area (Ų)')
axes[1,0].set_ylabel('Rotatable Bonds')
drug_like_counts = df['Drug_Like'].value_counts()
labels = ['Drug-like' if i else 'Non-drug-like' for i in drug_like_counts.index]
colors = ['green' if i else 'red' for i in drug_like_counts.index]
axes[1,1].pie(drug_like_counts.values, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90)
axes[1,1].set_title('Drug-likeness Distribution')
plt.tight_layout(rect=[0, 0, 1, 0.96])
return fig, "✅ Generated properties dashboard."
# ===== Phase 2 Functions =====
def get_phase2_molecules():
return {
'Oseltamivir (Tamiflu)': "CCC(CC)O[C@H]1[C@H]([C@@H]([C@H](C=C1C(=O)OCC)N)N)NC(=O)C",
'Zanamivir (Relenza)': "C[C@H](N)C(=O)N[C@H]1[C@@H](O)C=C(O[C@H]1[C@@H](O)[C@H](O)CO)C(O)=O",
'Aspirin': "CC(=O)OC1=CC=CC=C1C(=O)O",
'Ibuprofen': "CC(C)CC1=CC=C(C=C1)C(C)C(=O)O",
}
def simulate_virtual_screening(smiles_dict: dict):
np.random.seed(42)
scores = np.random.uniform(2.0, 9.8, len(smiles_dict))
results = [{'Molecule': name, 'SMILES': smiles, 'Predicted_Binding_Affinity': round(score, 2)} for (name, smiles), score in zip(smiles_dict.items(), scores)]
df = pd.DataFrame(results).sort_values('Predicted_Binding_Affinity', ascending=False).reset_index(drop=True)
df['Ranking'] = df.index + 1
return df, f"✅ Simulated virtual screening for {len(df)} molecules.\n"
def predict_admet_properties(smiles_dict: dict):
admet_data = []
log = ""
for i, (name, smiles) in enumerate(smiles_dict.items()):
mol = Chem.MolFromSmiles(smiles)
if not mol: continue
mw, logp, hbd, hba = Descriptors.MolWt(mol), Descriptors.MolLogP(mol), Descriptors.NumHDonors(mol), Descriptors.NumHAcceptors(mol)
np.random.seed(42 + i)
admet_data.append({'Molecule': name, 'MW': round(mw, 2), 'LogP': round(logp, 2), 'HBD': hbd, 'HBA': hba,
'Solubility (logS)': round(np.random.uniform(-4, -1), 2),
'Toxicity Risk': round(np.random.uniform(0.05, 0.4), 3),
'Lipinski Violations': sum([mw > 500, logp > 5, hbd > 5, hba > 10])})
df = pd.DataFrame(admet_data)
log += f"✅ Predicted ADMET properties for {len(df)} molecules.\n"
return df, log
def visualize_molecule_2d_3d(smiles: str, name: str):
"""Generates a side-by-side 2D SVG and 3D py3Dmol HTML view for a single molecule."""
log = ""
try:
mol = Chem.MolFromSmiles(smiles)
if not mol: return f"<p>Invalid SMILES for {name}</p>", f"❌ Invalid SMILES for {name}"
drawer = Draw.rdMolDraw2D.MolDraw2DSVG(400, 300)
drawer.DrawMolecule(mol)
drawer.FinishDrawing()
svg_2d = drawer.GetDrawingText().replace('svg:', '')
mol_3d = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol_3d, randomSeed=42)
AllChem.MMFFOptimizeMolecule(mol_3d)
sdf_data = Chem.MolToMolBlock(mol_3d)
viewer = py3Dmol.view(width=400, height=300)
# MODIFIED: Changed background color
viewer.setBackgroundColor('#1C1C1C')
viewer.addModel(sdf_data, "sdf")
viewer.setStyle({'stick': {}, 'sphere': {'scale': 0.25}})
viewer.zoomTo()
html_3d = viewer._make_html()
combined_html = f"""
<div style="display: flex; flex-direction: row; align-items: center; justify-content: space-around; border: 1px solid #444; border-radius: 10px; padding: 10px; margin-bottom: 10px; background-color: #2b2b2b;">
<div style="text-align: center;">
<h4 style="color: white; font-family: 'Roboto', sans-serif;">{name} (2D Structure)</h4>
{svg_2d}
</div>
<div style="text-align: center;">
<h4 style="color: white; font-family: 'Roboto', sans-serif;">{name} (3D Interactive)</h4>
{html_3d}
</div>
</div>
"""
log += f"✅ Generated 2D/3D view for {name}.\n"
return combined_html, log
except Exception as e:
return f"<p>Error visualizing {name}: {e}</p>", f"❌ Error visualizing {name}: {e}"
def visualize_protein_ligand_interaction(pdb_data: str, pdb_id: str, ligand_resn='G39'):
"""Visualizes a protein-ligand binding site using py3Dmol."""
if not pdb_data: return None, "Cannot generate view: No PDB data provided."
try:
viewer = py3Dmol.view(width='100%', height=700)
# MODIFIED: Changed background color
viewer.setBackgroundColor('#1C1C1C')
viewer.addModel(pdb_data, "pdb")
viewer.setStyle({'cartoon': {'color': 'spectrum', 'thickness': 0.8}})
viewer.addSurface(py3Dmol.VDW, {'opacity': 0.2, 'color': 'lightblue'})
viewer.addStyle({'resn': ligand_resn}, {'stick': {'colorscheme': 'greenCarbon', 'radius': 0.3}, 'sphere': {'scale': 0.4, 'colorscheme': 'greenCarbon'}})
viewer.addStyle({'within': {'distance': 4, 'sel': {'resn': ligand_resn}}}, {'stick': {'colorscheme': 'orangeCarbon', 'radius': 0.2}})
viewer.zoomTo({'resn': ligand_resn})
html = viewer._make_html()
log = (f"✅ Generated protein-ligand interaction view for PDB {pdb_id}.\n"
f"🟢 Green: Ligand ({ligand_resn})\n"
f"🟠 Orange: Residues within 4Å of ligand\n")
return html, log
except Exception as e:
return None, f"❌ Protein-ligand visualization error: {e}"
# ===== Phase 3 Functions =====
def get_phase3_molecules():
return {
'Oseltamivir': 'CCC(CC)O[C@H]1[C@H]([C@@H]([C@H](C=C1C(=O)OCC)N)N)NC(=O)C',
'Aspirin': 'CC(=O)OC1=CC=CC=C1C(=O)O',
'Remdesivir': 'CCC(CC)COC(=O)[C@@H](C)N[P@](=O)(OC[C@@H]1O[C@](C#N)([C@H]([C@@H]1O)O)C2=CC=C3N2N=CN=C3N)OC4=CC=CC=C4',
'Penicillin G': 'CC1([C@@H](N2[C@H](S1)[C@@H](C2=O)NC(=O)CC3=CC=CC=C3)C(=O)O)C'
}
def calculate_comprehensive_properties(smiles_dict: dict):
analysis = []
log = ""
for name, smiles in smiles_dict.items():
mol = Chem.MolFromSmiles(smiles)
if not mol: continue
mw, logp, hbd, hba = Descriptors.MolWt(mol), Descriptors.MolLogP(mol), Descriptors.NumHDonors(mol), Descriptors.NumHAcceptors(mol)
violations = sum([mw > 500, logp > 5, hbd > 5, hba > 10])
analysis.append({'Compound': name, 'Molecular_Weight': mw, 'LogP': logp, 'HBD': hbd, 'HBA': hba,
'TPSA': Descriptors.TPSA(mol), 'Rotatable_Bonds': Descriptors.NumRotatableBonds(mol),
'Aromatic_Rings': Descriptors.NumAromaticRings(mol),
'Lipinski_Violations': violations, 'Drug_Like': 'Yes' if violations <= 1 else 'No'})
df = pd.DataFrame(analysis).round(2)
log += f"✅ Calculated comprehensive properties for {len(df)} compounds.\n"
return df, log
def predict_toxicity(properties_df: pd.DataFrame):
if properties_df.empty: return pd.DataFrame(), "Cannot predict toxicity: No properties data."
np.random.seed(42)
n_compounds = 500
training_data = pd.DataFrame({'molecular_weight': np.random.normal(400, 100, n_compounds),
'logp': np.random.normal(2.5, 1.5, n_compounds),
'tpsa': np.random.normal(80, 30, n_compounds),
'rotatable_bonds': np.random.randint(0, 15, n_compounds),
'aromatic_rings': np.random.randint(0, 5, n_compounds)})
toxicity_score = ((training_data['molecular_weight'] > 550) * 0.4 + (abs(training_data['logp']) > 4.5) * 0.4 + np.random.random(n_compounds) * 0.2)
training_data['toxic'] = (toxicity_score > 0.5).astype(int)
features = ['molecular_weight', 'logp', 'tpsa', 'rotatable_bonds', 'aromatic_rings']
rf_model = RandomForestClassifier(n_estimators=50, random_state=42)
rf_model.fit(training_data[features], training_data['toxic'])
X_pred = properties_df[['Molecular_Weight', 'LogP', 'TPSA', 'Rotatable_Bonds', 'Aromatic_Rings']]
X_pred.columns = features
toxicity_prob = rf_model.predict_proba(X_pred)[:, 1]
results_df = properties_df[['Compound']].copy()
results_df['Toxicity_Probability'] = np.round(toxicity_prob, 3)
results_df['Predicted_Risk'] = ["🟢 LOW" if p < 0.3 else "🟡 MODERATE" if p < 0.7 else "🔴 HIGH" for p in toxicity_prob]
return results_df, "✅ Predicted toxicity using a pre-trained simulation model.\n"
# ===== Phase 4 Functions =====
def get_regulatory_summary():
summary = {'Component': ['Data Governance', 'Model Architecture', 'Model Validation', 'Interpretability'],
'Description': ['Data sourced from ChEMBL, PDB, GISAID. Bias assessed via geographic distribution analysis.',
'Graph Convolutional Network (Target ID), Random Forest (ADMET), K-Means (Patient Stratification).',
'ADMET Model validated with AUC-ROC > 0.85 on an independent test set.',
'SHAP used for patient stratification model outputs.']}
return pd.DataFrame(summary), "✅ Generated AI/ML documentation summary."
def simulate_rwd_analysis(adverse_event_text):
np.random.seed(42)
base_events = list(np.random.choice(['headache', 'nausea', 'fatigue', 'dizziness', 'rash', 'fever'], 100, p=[0.25, 0.2, 0.15, 0.15, 0.15, 0.1]))
user_events = [e.strip().lower() for e in adverse_event_text.split(',') if e.strip()]
all_events = base_events + user_events
event_counts = pd.Series(all_events).value_counts()
log = f"✅ Analyzed {len(all_events)} simulated adverse event reports.\n"
plt.style.use('dark_background')
fig_bar, ax_bar = plt.subplots(figsize=(10, 6))
fig_bar.patch.set_facecolor('none')
ax_bar.set_facecolor('none')
sns.barplot(x=event_counts.values, y=event_counts.index, palette='viridis', ax=ax_bar, orient='h')
ax_bar.set_title('Simulated Adverse Event Frequencies')
ax_bar.set_xlabel('Number of Reports')
ax_bar.set_ylabel('Adverse Event')
plt.tight_layout()
return event_counts.reset_index().rename(columns={'index': 'Event', 0: 'Count'}), fig_bar, log
def get_ethical_framework():
framework = {'Pillar': ['1. Beneficence & Non-Maleficence', '2. Justice & Fairness', '3. Transparency & Explainability', '4. Accountability & Governance'],
'Description': ['AI should help patients and do no harm. Requires rigorous validation and safety monitoring.',
'AI must not create or worsen health disparities. Requires bias detection and mitigation.',
'Clinical decisions influenced by AI must be understandable. Requires interpretable models.',
'Clear lines of responsibility for AI systems must be established. Requires human oversight.']}
return pd.DataFrame(framework), "✅ Generated ethical framework summary."
# --- 3. Streamlit Interface Definition ---
st.title("🔬 AI-Powered Drug Discovery Pipeline")
st.markdown("""
Welcome to the AI Drug Discovery Pipeline Demonstrator. This application integrates the four major phases of drug development,
showcasing how AI and computational tools can accelerate the process from target identification to post-market surveillance.
Navigate through the tabs below to explore each phase.
""")
# Initialize session state for logs and results
if 'log_p1' not in st.session_state: st.session_state.log_p1 = "Phase 1 logs will appear here."
if 'results_p1' not in st.session_state: st.session_state.results_p1 = {}
if 'log_p2' not in st.session_state: st.session_state.log_p2 = "Phase 2 logs will appear here."
if 'results_p2' not in st.session_state: st.session_state.results_p2 = {}
if 'log_p3' not in st.session_state: st.session_state.log_p3 = "Phase 3 logs will appear here."
if 'results_p3' not in st.session_state: st.session_state.results_p3 = {}
if 'log_p4' not in st.session_state: st.session_state.log_p4 = "Phase 4 logs will appear here."
if 'results_p4' not in st.session_state: st.session_state.results_p4 = {}
tab1, tab2, tab3, tab4 = st.tabs([
"Phase 1: Discovery & Target ID",
"Phase 2: Lead Generation & Optimization",
"Phase 3: Preclinical Development",
"Phase 4: Implementation & Post-Market"
])
# ===== TAB 1: DISCOVERY & TARGET IDENTIFICATION =====
with tab1:
st.header("🧬 Step 1: Target Identification and Initial Analysis")
st.markdown("Fetch protein data from public databases and perform a high-level analysis of potential drug-like molecules.")
with st.form(key="phase1_form"):
st.subheader("Analysis Controls")
col1, col2 = st.columns(2)
with col1:
pdb_id_input = st.text_input("Enter PDB ID", value="3B7E", key="p1_pdb")
protein_id_input = st.text_input("Enter Protein ID (for FASTA)", value="ACF54602.1", key="p1_protein")
with col2:
smiles_input_p1 = st.text_area("Enter SMILES strings (one per line)", value="\n".join(create_sample_molecules()), height=150, key="p1_smiles")
run_phase1_btn = st.form_submit_button("🚀 Run Phase 1 Analysis", use_container_width=True)
if run_phase1_btn:
full_log = "--- Starting Phase 1 Analysis ---\n"
pdb_data, log_pdb_fetch = fetch_pdb_structure(pdb_id_input)
full_log += log_pdb_fetch
fasta_log = fetch_fasta_sequence(protein_id_input)
full_log += fasta_log
protein_view_html, log_3d_viz = visualize_protein_3d(pdb_data, pdb_id_input)
full_log += log_3d_viz
smiles_list = [s.strip() for s in smiles_input_p1.split('\n') if s.strip()]
props_df, log_props = calculate_molecular_properties(smiles_list)
full_log += log_props
analysis_df, log_lipinski = assess_drug_likeness(props_df)
full_log += log_lipinski
props_plot, log_plot = plot_properties_dashboard(analysis_df)
full_log += log_plot
full_log += "\n--- Phase 1 Analysis Complete ---"
st.session_state.log_p1 = full_log
lipinski_cols = ['Molecule', 'MW', 'LogP', 'HBD', 'HBA', 'Lipinski_Violations', 'Drug_Like']
lipinski_subset_df = analysis_df[lipinski_cols] if not analysis_df.empty else pd.DataFrame(columns=lipinski_cols)
st.session_state.results_p1 = {
'protein_view_html': protein_view_html,
'fasta_log': fasta_log,
'lipinski_subset_df': lipinski_subset_df,
'props_df': props_df,
'props_plot': props_plot
}
st.text_area("Status & Logs", st.session_state.log_p1, height=200, key="log_p1_area")
if st.session_state.results_p1:
res1 = st.session_state.results_p1
p1_tabs = st.tabs(["Protein Information", "Molecule Analysis", "Analysis Plots"])
with p1_tabs[0]:
st.subheader("Protein 3D Structure (Interactive)")
st.components.v1.html(res1.get('protein_view_html', '<p>No data</p>'), height=600, scrolling=False)
st.subheader("FASTA Sequence Information")
st.text_area("", res1.get('fasta_log', 'No data'), height=200, key="fasta_info_area")
with p1_tabs[1]:
st.subheader("Drug-Likeness Assessment (Lipinski's Rule of Five)")
st.dataframe(res1.get('lipinski_subset_df', pd.DataFrame()), use_container_width=True)
st.subheader("Calculated Molecular Properties")
st.dataframe(res1.get('props_df', pd.DataFrame()), use_container_width=True)
with p1_tabs[2]:
st.subheader("Molecular Properties Dashboard")
if res1.get('props_plot'):
st.pyplot(res1['props_plot'])
# ===== TAB 2: LEAD GENERATION & OPTIMIZATION =====
with tab2:
st.header("💊 Step 2: Virtual Screening and ADMET Prediction")
st.markdown("Screen candidate molecules against the target, predict their ADMET properties, and visualize the top candidates.")
with st.form(key="phase2_form"):
st.subheader("Analysis Controls")
col1, col2 = st.columns(2)
with col1:
phase2_pdb_id_input = st.text_input("Enter PDB ID for Interaction View", value="3B7E", key="p2_pdb")
with col2:
phase2_ligand_resn = st.text_input("Ligand Residue Name (in PDB)", value="G39", key="p2_ligand")
run_phase2_btn = st.form_submit_button("🚀 Run Phase 2 Analysis", use_container_width=True)
if run_phase2_btn:
full_log = "--- Starting Phase 2 Analysis ---\n"
smiles_dict = get_phase2_molecules()
screening_df, log_screening = simulate_virtual_screening(smiles_dict)
full_log += log_screening
admet_df, log_admet = predict_admet_properties(smiles_dict)
full_log += log_admet
combined_viz_html = ""
for name, smiles in smiles_dict.items():
html_block, log_mol_viz = visualize_molecule_2d_3d(smiles, name)
combined_viz_html += html_block
full_log += log_mol_viz
pdb_data, log_pdb_fetch_2 = fetch_pdb_structure(phase2_pdb_id_input)
full_log += log_pdb_fetch_2
interaction_html, log_interaction = visualize_protein_ligand_interaction(pdb_data, phase2_pdb_id_input, phase2_ligand_resn)
full_log += log_interaction
full_log += "\n--- Phase 2 Analysis Complete ---"
st.session_state.log_p2 = full_log
st.session_state.results_p2 = {
'screening_df': screening_df,
'admet_df': admet_df,
'combined_viz_html': combined_viz_html,
'interaction_html': interaction_html
}
st.text_area("Status & Logs", st.session_state.log_p2, height=200, key="log_p2_area")
if st.session_state.results_p2:
res2 = st.session_state.results_p2
p2_tabs = st.tabs(["Virtual Screening & ADMET", "Molecule Visualization (2D & 3D)", "Protein-Ligand Interaction"])
with p2_tabs[0]:
col1, col2 = st.columns(2)
with col1:
st.subheader("Virtual Screening Results (Simulated)")
st.dataframe(res2.get('screening_df', pd.DataFrame()), use_container_width=True)
with col2:
st.subheader("ADMET Properties Prediction")
st.dataframe(res2.get('admet_df', pd.DataFrame()), use_container_width=True)
with p2_tabs[1]:
st.subheader("Interactive 2D and 3D views of candidate molecules.")
st.components.v1.html(res2.get('combined_viz_html', '<p>No data</p>'), height=700, scrolling=True)
with p2_tabs[2]:
st.subheader("Detailed view of the top candidate binding to the protein.")
st.components.v1.html(res2.get('interaction_html', '<p>No data</p>'), height=700, scrolling=False)
# ===== TAB 3: PRECLINICAL DEVELOPMENT =====
with tab3:
st.header("🧪 Step 3: In-Depth Candidate Analysis and Toxicity Prediction")
st.markdown("Perform a comprehensive analysis of the most promising lead compounds and use a simulated AI model to predict toxicity risk.")
with st.form(key="phase3_form"):
st.subheader("Analysis Controls")
run_phase3_btn = st.form_submit_button("🚀 Run Phase 3 Analysis", use_container_width=True)
if run_phase3_btn:
full_log = "--- Starting Phase 3 Analysis ---\n"
smiles_dict = get_phase3_molecules()
comp_props_df, log_comp_props = calculate_comprehensive_properties(smiles_dict)
full_log += log_comp_props
tox_df, log_tox = predict_toxicity(comp_props_df)
full_log += log_tox
combined_viz_html = ""
for name, smiles in smiles_dict.items():
html_block, log_mol_viz_p3 = visualize_molecule_2d_3d(smiles, name)
combined_viz_html += html_block
full_log += log_mol_viz_p3
full_log += "\n--- Phase 3 Analysis Complete ---"
st.session_state.log_p3 = full_log
st.session_state.results_p3 = {
'comp_props_df': comp_props_df,
'tox_df': tox_df,
'combined_viz_html': combined_viz_html
}
st.text_area("Status & Logs", st.session_state.log_p3, height=200, key="log_p3_area")
if st.session_state.results_p3:
res3 = st.session_state.results_p3
p3_tabs = st.tabs(["Comprehensive Properties & Toxicity", "Molecule Visualization (3D Gallery)"])
with p3_tabs[0]:
st.subheader("Comprehensive Molecular Properties & AI-Powered Toxicity Prediction (Simulated)")
col1, col2 = st.columns(2)
with col1:
st.dataframe(res3.get('comp_props_df', pd.DataFrame()), use_container_width=True)
with col2:
st.dataframe(res3.get('tox_df', pd.DataFrame()), use_container_width=True)
with p3_tabs[1]:
st.subheader("Interactive 3D gallery of the compounds under analysis.")
st.components.v1.html(res3.get('combined_viz_html', '<p>No data</p>'), height=1000, scrolling=True)
# ===== TAB 4: POST-MARKET SURVEILLANCE =====
with tab4:
st.header("📈 Step 4: Regulatory Submission and Pharmacovigilance")
st.markdown("Explore summaries of the documentation needed for regulatory approval and simulate how AI can monitor real-world data for adverse events.")
with st.form(key="phase4_form"):
st.subheader("Analysis Controls")
rwd_input = st.text_area("Enter new adverse events (comma-separated)", value="severe allergic reaction, joint pain, severe allergic reaction", height=100, key="p4_rwd")
run_phase4_btn = st.form_submit_button("🚀 Run Phase 4 Analysis", use_container_width=True)
if run_phase4_btn:
full_log = "--- Starting Phase 4 Analysis ---\n"
reg_df, log_reg = get_regulatory_summary()
full_log += log_reg
eth_df, log_eth = get_ethical_framework()
full_log += log_eth
rwd_df, plot_bar, log_rwd = simulate_rwd_analysis(rwd_input)
full_log += log_rwd
full_log += "\n--- Phase 4 Analysis Complete ---"
st.session_state.log_p4 = full_log
st.session_state.results_p4 = {
'rwd_df': rwd_df,
'plot_bar': plot_bar,
'reg_df': reg_df,
'eth_df': eth_df
}
st.text_area("Status & Logs", st.session_state.log_p4, height=200, key="log_p4_area")
if st.session_state.results_p4:
res4 = st.session_state.results_p4
p4_tabs = st.tabs(["Pharmacovigilance Analysis", "Regulatory & Ethical Frameworks"])
with p4_tabs[0]:
st.subheader("Simulated Adverse Event Analysis")
st.pyplot(res4['plot_bar'])
st.dataframe(res4['rwd_df'], use_container_width=True)
with p4_tabs[1]:
col1, col2 = st.columns(2)
with col1:
st.subheader("AI/ML Documentation Summary for Submission")
st.dataframe(res4.get('reg_df', pd.DataFrame()), use_container_width=True)
with col2:
st.subheader("Ethical Framework for AI in Healthcare")
st.dataframe(res4.get('eth_df', pd.DataFrame()), use_container_width=True)
|