import pandas as pd
ann_rows = [{'gene': 'CHMP4B', 'name': 'charged multivesicular body protein 4B', 'protein_class': "['Disease related genes', 'Essential proteins', 'Human disea", 'disease_involvement': "['Cataract', 'Disease variant']"}, {'gene': 'HSP90AA1', 'name': 'heat shock protein 90 alpha family class A member 1', 'protein_class': "['Cancer-related genes', 'Enzymes', 'Plasma proteins', 'Pred", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'LRP1', 'name': 'LDL receptor related protein 1', 'protein_class': "['Candidate cardiovascular disease genes', 'CD markers', 'Di", 'disease_involvement': "['Disease variant']"}, {'gene': 'NLGN1', 'name': 'neuroligin 1', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Po", 'disease_involvement': "['Autism', 'Autism spectrum disorder', 'Disease variant']"}, {'gene': 'P2RX7', 'name': 'purinergic receptor P2X 7', 'protein_class': "['Predicted membrane proteins', 'Transporters']", 'disease_involvement': '—'}, {'gene': 'SNAP25', 'name': 'synaptosome associated protein 25', 'protein_class': "['Disease related genes', 'FDA approved drug targets', 'Huma", 'disease_involvement': "['Congenital myasthenic syndrome', 'Disease variant', 'FDA approved drug targets"}, {'gene': 'TREM2', 'name': 'triggering receptor expressed on myeloid cells 2', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Po", 'disease_involvement': "['Alzheimer disease', 'Amyloidosis', 'Disease variant', 'Neurodegeneration']"}, {'gene': 'VCP', 'name': 'valosin containing protein', 'protein_class': "['Disease related genes', 'Enzymes', 'Essential proteins', '", 'disease_involvement': "['Amyotrophic lateral sclerosis', 'Charcot-Marie-Tooth disease', 'Disease varian"}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Positive Regulation Of Amyloid-Beta Clearance (GO:1900223)', 'p_value': 2.0982540726248864e-06, 'odds_ratio': 1665.6666666666667, 'genes': ['LRP1', 'TREM2']}, {'rank': 2, 'term': 'Positive Regulation Of Endocytosis (GO:0045807)', 'p_value': 3.2745060493527168e-06, 'odds_ratio': 157.23157894736843, 'genes': ['NLGN1', 'LRP1', 'TREM2']}, {'rank': 3, 'term': 'Positive Regulation Of ATP Biosynthetic Process (GO:2001171)', 'p_value': 3.9152037969490335e-06, 'odds_ratio': 1110.3333333333333, 'genes': ['VCP', 'TREM2']}, {'rank': 4, 'term': 'Positive Regulation Of ATP Metabolic Process (GO:1903580)', 'p_value': 5.032841318877048e-06, 'odds_ratio': 951.6666666666666, 'genes': ['VCP', 'TREM2']}, {'rank': 5, 'term': 'Positive Regulation Of Protein Catabolic Process (GO:0045732)', 'p_value': 5.187357870686843e-06, 'odds_ratio': 134.17752808988763, 'genes': ['HSP90AA1', 'VCP', 'TREM2']}, {'rank': 6, 'term': 'Positive Regulation Of Purine Nucleotide Biosynthetic Process (GO:1900373)', 'p_value': 9.221402746009655e-06, 'odds_ratio': 666.0666666666667, 'genes': ['VCP', 'TREM2']}, {'rank': 7, 'term': 'Astrocyte Activation (GO:0048143)', 'p_value': 9.221402746009655e-06, 'odds_ratio': 666.0666666666667, 'genes': ['LRP1', 'TREM2']}, {'rank': 8, 'term': 'Positive Regulation Of Cellular Component Organization (GO:0051130)', 'p_value': 9.633449558779347e-06, 'odds_ratio': 108.44727272727273, 'genes': ['VCP', 'LRP1', 'TREM2']}, {'rank': 9, 'term': 'Regulation Of ATP Biosynthetic Process (GO:2001169)', 'p_value': 1.270931618352025e-05, 'odds_ratio': 555.0, 'genes': ['VCP', 'TREM2']}, {'rank': 10, 'term': 'Regulation Of Amyloid-Beta Clearance (GO:1900221)', 'p_value': 1.4661684218577711e-05, 'odds_ratio': 512.2820512820513, 'genes': ['LRP1', 'TREM2']}]
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': 'Positive Regulation Of Amyloid-Beta Clearance (GO:1900223)', 'p_value': 2.0982540726248864e-06, 'odds_ratio': 1665.6666666666667, 'genes': ['LRP1', 'TREM2']}, {'rank': 2, 'term': 'Positive Regulation Of Endocytosis (GO:0045807)', 'p_value': 3.2745060493527168e-06, 'odds_ratio': 157.23157894736843, 'genes': ['NLGN1', 'LRP1', 'TREM2']}, {'rank': 3, 'term': 'Positive Regulation Of ATP Biosynthetic Process (GO:2001171)', 'p_value': 3.9152037969490335e-06, 'odds_ratio': 1110.3333333333333, 'genes': ['VCP', 'TREM2']}, {'rank': 4, 'term': 'Positive Regulation Of ATP Metabolic Process (GO:1903580)', 'p_value': 5.032841318877048e-06, 'odds_ratio': 951.6666666666666, 'genes': ['VCP', 'TREM2']}, {'rank': 5, 'term': 'Positive Regulation Of Protein Catabolic Process (GO:0045732)', 'p_value': 5.187357870686843e-06, 'odds_ratio': 134.17752808988763, 'genes': ['HSP90AA1', 'VCP', 'TREM2']}, {'rank': 6, 'term': 'Positive Regulation Of Purine Nucleotide Biosynthetic Process (GO:1900373)', 'p_value': 9.221402746009655e-06, 'odds_ratio': 666.0666666666667, 'genes': ['VCP', 'TREM2']}, {'rank': 7, 'term': 'Astrocyte Activation (GO:0048143)', 'p_value': 9.221402746009655e-06, 'odds_ratio': 666.0666666666667, 'genes': ['LRP1', 'TREM2']}, {'rank': 8, 'term': 'Positive Regulation Of Cellular Component Organization (GO:0051130)', 'p_value': 9.633449558779347e-06, 'odds_ratio': 108.44727272727273, 'genes': ['VCP', 'LRP1', 'TREM2']}]
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': 'LRP1', 'protein2': 'HSP90AA1', 'score': 0.988, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.412, 'dscore': 0, 'tscore': 0.982}, {'protein1': 'HSP90AA1', 'protein2': 'VCP', 'score': 0.803, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.423, 'dscore': 0.5, 'tscore': 0.374}]
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': 'LRP1', 'protein2': 'HSP90AA1', 'score': 0.988, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.412, 'dscore': 0, 'tscore': 0.982}, {'protein1': 'HSP90AA1', 'protein2': 'VCP', 'score': 0.803, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.423, 'dscore': 0.5, 'tscore': 0.374}]
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': 'CHMP4B', 'n_pathways': 8, 'top_pathway': 'Budding and maturation of HIV virion'}, {'gene': 'HSP90AA1', 'n_pathways': 8, 'top_pathway': 'Signaling by ERBB2'}, {'gene': 'LRP1', 'n_pathways': 2, 'top_pathway': 'Scavenging of heme from plasma'}, {'gene': 'NLGN1', 'n_pathways': 1, 'top_pathway': 'Neurexins and neuroligins'}, {'gene': 'P2RX7', 'n_pathways': 5, 'top_pathway': 'Elevation of cytosolic Ca2+ levels'}, {'gene': 'SNAP25', 'n_pathways': 8, 'top_pathway': 'Serotonin Neurotransmitter Release Cycle'}, {'gene': 'TREM2', 'n_pathways': 4, 'top_pathway': 'Immunoregulatory interactions between a Lymphoid and a non-Lymphoid ce'}, {'gene': 'VCP', 'n_pathways': 8, 'top_pathway': 'Translesion Synthesis by POLH'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Extracellular Vesicle Biogenesis Modulation', 0.814), ('LRP1-Dependent Tau Uptake Disruption', 0.808), ('VCP-Mediated Autophagy Enhancement', 0.787), ('TREM2-mediated microglial tau clearance enhancement', 0.78), ('HSP90-Tau Disaggregation Complex Enhancement', 0.634), ('TREM2-mediated microglial tau clearance enhancement', 0.618), ('LRP1-Dependent Tau Uptake Disruption', 0.6), ('VCP-Mediated Autophagy Enhancement', 0.595), ('Extracellular Vesicle Biogenesis Modulation', 0.582), ('Synaptic Vesicle Tau Capture Inhibition', 0.578), ('HSP90-Tau Disaggregation Complex Enhancement', 0.575), ('P2RX7-Mediated Exosome Secretion Blockade', 0.552), ('Synaptic Vesicle Tau Capture Inhibition', 0.547), ('Trans-Synaptic Adhesion Molecule Modulation', 0.544), ('Trans-Synaptic Adhesion Molecule Modulation', 0.503)]
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('Tau propagation mechanisms and therapeutic interception points')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Extracellular Vesicle Biogenesis Modulat', 'LRP1-Dependent Tau Uptake Disruption', 'VCP-Mediated Autophagy Enhancement', 'TREM2-mediated microglial tau clearance ', 'HSP90-Tau Disaggregation Complex Enhance', 'TREM2-mediated microglial tau clearance ', 'LRP1-Dependent Tau Uptake Disruption', 'VCP-Mediated Autophagy Enhancement', 'Extracellular Vesicle Biogenesis Modulat', 'Synaptic Vesicle Tau Capture Inhibition']
matrix = np.array([[0, 0, 0, 0, 0, 0, 0.77, 0, 0], [0, 0, 0, 0.8, 0, 0, 0.68, 0, 0], [0, 0, 0, 0, 0, 0, 0.78, 0, 0], [0, 0, 0, 0, 0, 0, 0.65, 0, 0], [0, 0, 0, 0, 0, 0, 0.697, 0, 0], [0.4, 0.49037250748841826, 0.5265052185665123, 0.7, 0.462, 0.73, 0.55, 0.6, 0.45], [0.4, 0.46067692307692304, 0.49462153846153845, 0.7, 1.0, 0.722, 0.35, 0.55, 0.45], [0.4, 0.46359999999999996, 0.49776, 0.7, 0.56, 0.723, 0.25, 0.6, 0.6], [0.4, 0.32299999999999995, 0.3468, 0.7, 0.367, 0.685, 0.35, 0.7, 0.6], [0.4, 0.32299999999999995, 0.3468, 0.7, 0.462, 0.685, 0.25, 0.49, 0.65]])
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')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H003')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H001')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H004')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H002')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H005')

print('No PubMed results for hypothesis h-b234254c')

print('No PubMed results for hypothesis h-4dd0d19b')

print('No PubMed results for hypothesis h-18a0fcc6')

print('No PubMed results for hypothesis h-55ef81c5')

print('No PubMed results for hypothesis h-73e29e3a')

print('No PubMed results for hypothesis h-0f00fd75')

print('No PubMed results for hypothesis h-1333080b')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H006')

print('No PubMed results for hypothesis h-fdaae8d9')

print('No PubMed results for hypothesis SDA-2026-04-02-gap-tau-prop-20260402003221-H007')