import pandas as pd
ann_rows = [{'gene': 'APOE', 'name': 'apolipoprotein E', 'protein_class': "['Cancer-related genes', 'Candidate cardiovascular disease g", 'disease_involvement': "['Alzheimer disease', 'Amyloidosis', 'Cancer-related genes', 'Disease variant', "}, {'gene': 'BDNF', 'name': 'brain derived neurotrophic factor', 'protein_class': "['Cancer-related genes', 'Human disease related genes', 'Pla", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'BIOGENESIS', 'name': 'ribosomal biogenesis factor', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'CREB1', 'name': 'cAMP responsive element binding protein 1', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Predicted", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'DMPK', 'name': 'DM1 protein kinase', 'protein_class': "['Disease related genes', 'Enzymes', 'Human disease related ", 'disease_involvement': "['Cataract']"}, {'gene': 'ESSENTIAL', 'name': 'essential tremor 2', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'FACTORS', 'name': 'interaction protein for cytohesin exchange factors 1', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'FOXO3', 'name': 'forkhead box O3', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Predicted", 'disease_involvement': "['Cancer-related genes', 'Proto-oncogene']"}, {'gene': 'GDNF', 'name': 'glial cell derived neurotrophic factor', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Human dis", 'disease_involvement': "['Cancer-related genes', 'Disease variant', 'Hirschsprung disease']"}, {'gene': 'GENES', 'name': 'MIR142 host genes', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'HMGCR', 'name': '3-hydroxy-3-methylglutaryl-CoA reductase', 'protein_class': "['Enzymes', 'Essential proteins', 'FDA approved drug targets", 'disease_involvement': "['Disease variant', 'FDA approved drug targets', 'Limb-girdle muscular dystrophy"}, {'gene': 'HTT', 'name': 'huntingtin', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Pl", 'disease_involvement': "['Disease variant', 'Intellectual disability', 'Neurodegeneration']"}, {'gene': 'IDENTITY', 'name': 'TPD52-MRPS28 readthrough', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'INTEGRATED', 'name': 'CXXC finger protein 4', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'LDLR', 'name': 'low density lipoprotein receptor', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Me", 'disease_involvement': "['Disease variant']"}, {'gene': 'MITOCHONDRIAL', 'name': 'ferritin mitochondrial', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'MSH3', 'name': 'mutS homolog 3', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Pl", 'disease_involvement': '—'}, {'gene': 'MUTATIONS', 'name': 'deafness, autosomal recessive 83', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'NEURONAL', 'name': 'neuronal differentiation 6', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'NRF2', 'name': 'NRF2 regulation associated lncRNA', 'protein_class': '—', 'disease_involvement': '—'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Regulation Of Neuron Apoptotic Process (GO:0043523)', 'p_value': 3.257034782011995e-06, 'odds_ratio': 49.20544554455446, 'genes': ['GDNF', 'BDNF', 'APOE', 'FOXO3']}, {'rank': 2, 'term': 'Positive Regulation Of Lipid Biosynthetic Process (GO:0046889)', 'p_value': 7.637120838980064e-06, 'odds_ratio': 97.76470588235294, 'genes': ['CREB1', 'APOE', 'LDLR']}, {'rank': 3, 'term': 'Memory (GO:0007613)', 'p_value': 2.5474983887326053e-05, 'odds_ratio': 63.93048128342246, 'genes': ['BDNF', 'APOE', 'LDLR']}, {'rank': 4, 'term': 'Negative Regulation Of Nitrogen Compound Metabolic Process (GO:0051172)', 'p_value': 5.196871583395421e-05, 'odds_ratio': 246.55555555555554, 'genes': ['APOE', 'LDLR']}, {'rank': 5, 'term': 'Negative Regulation Of Neuron Apoptotic Process (GO:0043524)', 'p_value': 5.297635608106871e-05, 'odds_ratio': 49.48384424192212, 'genes': ['GDNF', 'BDNF', 'APOE']}, {'rank': 6, 'term': 'Regulation Of Nitrogen Compound Metabolic Process (GO:0051171)', 'p_value': 7.361293042472065e-05, 'odds_ratio': 201.7070707070707, 'genes': ['APOE', 'LDLR']}, {'rank': 7, 'term': 'Negative Regulation Of Neuron Death (GO:1901215)', 'p_value': 8.888334603409306e-05, 'odds_ratio': 41.30449826989619, 'genes': ['GDNF', 'BDNF', 'APOE']}, {'rank': 8, 'term': 'Regulation Of Amyloid-Beta Clearance (GO:1900221)', 'p_value': 9.897575036981038e-05, 'odds_ratio': 170.65811965811966, 'genes': ['HMGCR', 'APOE']}, {'rank': 9, 'term': 'Regulation Of Protein Metabolic Process (GO:0051246)', 'p_value': 0.00011514055840279769, 'odds_ratio': 37.73624288425047, 'genes': ['APOE', 'FOXO3', 'LDLR']}, {'rank': 10, 'term': 'Regulation Of Myotube Differentiation (GO:0010830)', 'p_value': 0.00023734441315945642, 'odds_ratio': 105.60317460317461, 'genes': ['DMPK', 'BDNF']}]
go_df = pd.DataFrame(go_bp)[['term','p_value','odds_ratio','genes']]
go_df['p_value'] = go_df['p_value'].apply(lambda p: f'{p:.2e}')
go_df['odds_ratio'] = go_df['odds_ratio'].round(1)
go_df['term'] = go_df['term'].str[:60]
go_df['n_hits'] = go_df['genes'].apply(len)
go_df['genes'] = go_df['genes'].apply(lambda g: ', '.join(g))
go_df[['term','n_hits','p_value','odds_ratio','genes']]

import matplotlib.pyplot as plt
import numpy as np

go_bp = [{'rank': 1, 'term': 'Regulation Of Neuron Apoptotic Process (GO:0043523)', 'p_value': 3.257034782011995e-06, 'odds_ratio': 49.20544554455446, 'genes': ['GDNF', 'BDNF', 'APOE', 'FOXO3']}, {'rank': 2, 'term': 'Positive Regulation Of Lipid Biosynthetic Process (GO:0046889)', 'p_value': 7.637120838980064e-06, 'odds_ratio': 97.76470588235294, 'genes': ['CREB1', 'APOE', 'LDLR']}, {'rank': 3, 'term': 'Memory (GO:0007613)', 'p_value': 2.5474983887326053e-05, 'odds_ratio': 63.93048128342246, 'genes': ['BDNF', 'APOE', 'LDLR']}, {'rank': 4, 'term': 'Negative Regulation Of Nitrogen Compound Metabolic Process (GO:0051172)', 'p_value': 5.196871583395421e-05, 'odds_ratio': 246.55555555555554, 'genes': ['APOE', 'LDLR']}, {'rank': 5, 'term': 'Negative Regulation Of Neuron Apoptotic Process (GO:0043524)', 'p_value': 5.297635608106871e-05, 'odds_ratio': 49.48384424192212, 'genes': ['GDNF', 'BDNF', 'APOE']}, {'rank': 6, 'term': 'Regulation Of Nitrogen Compound Metabolic Process (GO:0051171)', 'p_value': 7.361293042472065e-05, 'odds_ratio': 201.7070707070707, 'genes': ['APOE', 'LDLR']}, {'rank': 7, 'term': 'Negative Regulation Of Neuron Death (GO:1901215)', 'p_value': 8.888334603409306e-05, 'odds_ratio': 41.30449826989619, 'genes': ['GDNF', 'BDNF', 'APOE']}, {'rank': 8, 'term': 'Regulation Of Amyloid-Beta Clearance (GO:1900221)', 'p_value': 9.897575036981038e-05, 'odds_ratio': 170.65811965811966, 'genes': ['HMGCR', 'APOE']}]
terms = [t['term'][:45] for t in go_bp][::-1]
neglogp = [-np.log10(max(t['p_value'], 1e-300)) for t in go_bp][::-1]
fig, ax = plt.subplots(figsize=(9, 4.5))
ax.barh(terms, neglogp, color='#4fc3f7')
ax.set_xlabel('-log10(p-value)')
ax.set_title('Top GO:BP enrichment (Enrichr)')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

ppi = [{'protein1': 'APOE', 'protein2': 'BDNF', 'score': 0.477, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.477}, {'protein1': 'APOE', 'protein2': 'LDLR', 'score': 0.783, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.549, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'REV1', 'protein2': 'BDNF', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.401}, {'protein1': 'HTT', 'protein2': 'CREB1', 'score': 0.963, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.314, 'dscore': 0.8, 'tscore': 0.758}]
ppi_df = pd.DataFrame(ppi).sort_values('score', ascending=False)
display_cols = [c for c in ['protein1','protein2','score','escore','tscore'] if c in ppi_df.columns]
print(f'{len(ppi_df)} STRING edges')
ppi_df[display_cols].head(20)

import math
ppi = [{'protein1': 'APOE', 'protein2': 'BDNF', 'score': 0.477, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.477}, {'protein1': 'APOE', 'protein2': 'LDLR', 'score': 0.783, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.549, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'REV1', 'protein2': 'BDNF', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.401}, {'protein1': 'HTT', 'protein2': 'CREB1', 'score': 0.963, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.314, 'dscore': 0.8, 'tscore': 0.758}]
if ppi:
    nodes = sorted({p for e in ppi for p in (e['protein1'], e['protein2'])})
    n = len(nodes)
    pos = {n_: (math.cos(2*math.pi*i/n), math.sin(2*math.pi*i/n)) for i, n_ in enumerate(nodes)}
    fig, ax = plt.subplots(figsize=(7, 7))
    for e in ppi:
        x1,y1 = pos[e['protein1']]; x2,y2 = pos[e['protein2']]
        ax.plot([x1,x2],[y1,y2], color='#888', alpha=0.3+0.5*e.get('score',0))
    for name,(x,y) in pos.items():
        ax.scatter([x],[y], s=450, color='#ffd54f', edgecolors='#333', zorder=3)
        ax.annotate(name, (x,y), ha='center', va='center', fontsize=8, fontweight='bold', zorder=4)
    ax.set_aspect('equal'); ax.axis('off')
    ax.set_title(f'STRING PPI network ({len(ppi)} edges)')
    plt.tight_layout(); plt.show()

pw_rows = [{'gene': 'APOE', 'n_pathways': 8, 'top_pathway': 'Nuclear signaling by ERBB4'}, {'gene': 'BDNF', 'n_pathways': 8, 'top_pathway': 'PIP3 activates AKT signaling'}, {'gene': 'BIOGENESIS', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'CREB1', 'n_pathways': 8, 'top_pathway': 'PKA-mediated phosphorylation of CREB'}, {'gene': 'DMPK', 'n_pathways': 1, 'top_pathway': 'Ion homeostasis'}, {'gene': 'ESSENTIAL', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'FACTORS', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'FOXO3', 'n_pathways': 8, 'top_pathway': 'Signaling by NODAL'}, {'gene': 'GDNF', 'n_pathways': 4, 'top_pathway': 'NCAM1 interactions'}, {'gene': 'GENES', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'HMGCR', 'n_pathways': 4, 'top_pathway': 'Cholesterol biosynthesis'}, {'gene': 'HTT', 'n_pathways': 1, 'top_pathway': 'Serotonin clearance from the synaptic cleft'}, {'gene': 'IDENTITY', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'INTEGRATED', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'LDLR', 'n_pathways': 5, 'top_pathway': 'Cargo recognition for clathrin-mediated endocytosis'}, {'gene': 'MITOCHONDRIAL', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'MSH3', 'n_pathways': 3, 'top_pathway': 'Mismatch repair (MMR) directed by MSH2:MSH3 (MutSbeta)'}, {'gene': 'MUTATIONS', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'NEURONAL', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'NRF2', 'n_pathways': 8, 'top_pathway': 'Neddylation'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Prime Editing Precision Correction of APOE4 to APOE3 in', 0.827), ('Context-Dependent CRISPR Activation in Specific Neurona', 0.682), ('Temporal CAG Repeat Stabilization via CRISPR-Mediated D', 0.681), ('CRISPR-Mediated Mitochondrial Genome Editing for Comple', 0.681), ('Acid-Degradable LNP-Mediated Prenatal CRISPR Interventi', 0.638), ('Programmable Neuronal Circuit Repair via Epigenetic CRI', 0.63), ('Multi-Modal CRISPR Platform for Simultaneous Editing an', 0.629), ('Cholesterol-CRISPR Convergence Therapy for Neurodegener', 0.622), ('Trinucleotide Repeat Sequestration via CRISPR-Guided RN', 0.613), ("Epigenetic Memory Reprogramming for Alzheimer's Disease", 0.611), ('Metabolic Reprogramming via Coordinated Multi-Gene CRIS', 0.599), ('Multiplexed Base Editing for Simultaneous Neuroprotecti', 0.59), ('Epigenetic Memory Reprogramming via CRISPRa-Mediated Ch', 0.544), ('Conditional CRISPR Kill Switches for Aberrant Protein C', 0.496)]
titles = [h[0] for h in hyp_data][::-1]
scores = [h[1] for h in hyp_data][::-1]
fig, ax = plt.subplots(figsize=(10, max(8, len(titles)*0.4)))
colors = ['#ef5350' if s >= 0.6 else '#ffa726' if s >= 0.5 else '#66bb6a' for s in scores]
ax.barh(range(len(titles)), scores, color=colors)
ax.set_yticks(range(len(titles))); ax.set_yticklabels(titles, fontsize=7)
ax.set_xlabel('Composite Score'); ax.set_title('CRISPR-based therapeutic approaches for neurodegenerative diseases')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Prime Editing Precision Correction of AP', 'Context-Dependent CRISPR Activation in S', 'Temporal CAG Repeat Stabilization via CR', 'CRISPR-Mediated Mitochondrial Genome Edi', 'Acid-Degradable LNP-Mediated Prenatal CR', 'Programmable Neuronal Circuit Repair via', 'Multi-Modal CRISPR Platform for Simultan', 'Cholesterol-CRISPR Convergence Therapy f', 'Trinucleotide Repeat Sequestration via C', 'Epigenetic Memory Reprogramming for Alzh']
matrix = np.array([[0.8, 0.65, 0.85, 0.75, 0.682, 0.7, 0.75, 0.8, 0.7], [0.8, 0.4, 0.7, 0.7, 0.385, 0.7, 0.6, 0.3, 0.5], [0.75, 0.4, 0.7, 0.55, 0.597, 0.7, 0.6, 0.5, 0.25], [0.9, 0.3, 0.75, 0.5, 0.56, 0.4, 0.45, 0.4, 0.5], [0.95, 0.2, 0.8, 0.45, 0.638, 0.35, 0.3, 0.25, 0.15], [0.4, 0.2, 0.4, 0.7, 0.385, 0.825, 0.4, 0.7, 0.6], [0.4, 0.3, 0.3, 0.7, 0.385, 0.775, 0.4, 0.69, 0.6], [0.6, 0.6, 0.5, 0.5, 0.17, 0.6, 0.6, 0.7, 0.6], [0.7, 0.5, 0.7, 0.6, 0.09, 0.5, 0.5, 0.4, 0.4], [0.9, 0.3, 0.6, 0.4, 0.13, 0.4, 0.4, 0.2, 0.3]])
dims = ['novelty_score', 'feasibility_score', 'impact_score', 'mechanistic_plausibility_score', 'clinical_relevance_score', 'data_availability_score', 'reproducibility_score', 'druggability_score', 'safety_profile_score']
if matrix.size:
    fig, ax = plt.subplots(figsize=(10, 5))
    im = ax.imshow(matrix, cmap='RdYlGn', aspect='auto', vmin=0, vmax=1)
    ax.set_xticks(range(len(dims)))
    ax.set_xticklabels([d.replace('_score','').replace('_',' ').title() for d in dims],
                       rotation=45, ha='right', fontsize=8)
    ax.set_yticks(range(len(labels))); ax.set_yticklabels(labels, fontsize=7)
    ax.set_title('Score dimensions — top hypotheses')
    plt.colorbar(im, ax=ax, shrink=0.8)
    plt.tight_layout(); plt.show()
else:
    print('No score data available')

lit_data = [{'year': '2020', 'journal': 'Autophagy', 'title': 'Activation of PPARA-mediated autophagy reduces Alzheimer disease-like pathology ', 'pmid': '30898012'}]
if lit_data:
    df = pd.DataFrame(lit_data)
    print(f'{len(lit_data)} PubMed results')
    display(df)
else:
    print('No PubMed results')

print('No PubMed results for hypothesis h-63b7bacd')

print('No PubMed results for hypothesis h-3e7d4f97')

print('No PubMed results for hypothesis h-420db533')

print('No PubMed results for hypothesis h-10b5bf6f')

print('No PubMed results for hypothesis h-9d22b570')

print('No PubMed results for hypothesis h-e23f05fb')

print('No PubMed results for hypothesis h-a87702b6')

print('No PubMed results for hypothesis h-3a4f2027')

print('No PubMed results for hypothesis h-29ef94d5')

print('No PubMed results for hypothesis h-827a821b')

print('No PubMed results for hypothesis h-47ab2be5')

print('No PubMed results for hypothesis h-7c3c0f40')

print('No PubMed results for hypothesis h-a11f71b5')