import pandas as pd
ann_rows = [{'gene': 'APOE', 'name': 'apolipoprotein E', 'summary': 'The protein encoded by this gene is a major apoprotein of the chylomicron. It binds to a specific liver and peripheral c'}, {'gene': 'GPC4', 'name': 'glypican 4', 'summary': 'Cell surface heparan sulfate proteoglycans are composed of a membrane-associated protein core substituted with a variabl'}, {'gene': 'TREM2', 'name': 'triggering receptor expressed on myeloid cells 2', 'summary': 'This gene encodes a membrane protein that forms a receptor signaling complex with the TYRO protein tyrosine kinase bindi'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Leukocyte Apoptotic Process (GO:0071887)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HCAR2']}, {'rank': 2, 'term': 'Regulation Of Adiponectin Secretion (GO:0070163)', 'p_value': 0.000599909243874975, 'odds_ratio': 3998.6, 'genes': ['HCAR2']}, {'rank': 3, 'term': 'Positive Regulation Of Myeloid Cell Apoptotic Process (GO:0033034)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HCAR2']}, {'rank': 4, 'term': 'Glucosamine-Containing Compound Catabolic Process (GO:1901072)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['CHI3L1']}, {'rank': 5, 'term': 'Positive Regulation Of Leukocyte Apoptotic Process (GO:2000108)', 'p_value': 0.0008997988691311835, 'odds_ratio': 2498.75, 'genes': ['HCAR2']}, {'rank': 6, 'term': 'Activation Of NF-kappaB-inducing Kinase Activity (GO:0007250)', 'p_value': 0.0014994446955652384, 'odds_ratio': 1427.4285714285713, 'genes': ['CHI3L1']}, {'rank': 7, 'term': 'Negative Regulation Of Lipid Catabolic Process (GO:0050995)', 'p_value': 0.0017992006270532422, 'odds_ratio': 1175.3529411764705, 'genes': ['HCAR2']}, {'rank': 8, 'term': 'Positive Regulation Of Hormone Secretion (GO:0046887)', 'p_value': 0.001899109329170248, 'odds_ratio': 1110.0, 'genes': ['HCAR2']}, {'rank': 9, 'term': 'Regulation Of Lipid Catabolic Process (GO:0050994)', 'p_value': 0.0022986943824153676, 'odds_ratio': 908.0, 'genes': ['HCAR2']}, {'rank': 10, 'term': 'Positive Regulation Of Peptidyl-Threonine Phosphorylation (GO:0010800)', 'p_value': 0.00239857819994348, 'odds_ratio': 868.4782608695652, 'genes': ['CHI3L1']}]
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': 'Leukocyte Apoptotic Process (GO:0071887)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HCAR2']}, {'rank': 2, 'term': 'Regulation Of Adiponectin Secretion (GO:0070163)', 'p_value': 0.000599909243874975, 'odds_ratio': 3998.6, 'genes': ['HCAR2']}, {'rank': 3, 'term': 'Positive Regulation Of Myeloid Cell Apoptotic Process (GO:0033034)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HCAR2']}, {'rank': 4, 'term': 'Glucosamine-Containing Compound Catabolic Process (GO:1901072)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['CHI3L1']}, {'rank': 5, 'term': 'Positive Regulation Of Leukocyte Apoptotic Process (GO:2000108)', 'p_value': 0.0008997988691311835, 'odds_ratio': 2498.75, 'genes': ['HCAR2']}, {'rank': 6, 'term': 'Activation Of NF-kappaB-inducing Kinase Activity (GO:0007250)', 'p_value': 0.0014994446955652384, 'odds_ratio': 1427.4285714285713, 'genes': ['CHI3L1']}, {'rank': 7, 'term': 'Negative Regulation Of Lipid Catabolic Process (GO:0050995)', 'p_value': 0.0017992006270532422, 'odds_ratio': 1175.3529411764705, 'genes': ['HCAR2']}, {'rank': 8, 'term': 'Positive Regulation Of Hormone Secretion (GO:0046887)', 'p_value': 0.001899109329170248, 'odds_ratio': 1110.0, 'genes': ['HCAR2']}]
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()

print('No STRING PPI data available')

pw_rows = [{'gene': 'APOE', 'n_pathways': 8, 'top_pathway': 'Nuclear signaling by ERBB4'}, {'gene': 'GPC4', 'n_pathways': 8, 'top_pathway': 'Glycosaminoglycan-protein linkage region biosynthesis'}, {'gene': 'TREM2', 'n_pathways': 4, 'top_pathway': 'Immunoregulatory interactions between a Lymphoid and a non-Lymphoid ce'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('TREM2-Dependent Microglial Phagocytosis Acts as a Strai', 0.636), ('GPC4/HSPGs Collaborate with ApoE Isoforms to Dictate Ta', 0.583)]
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('What are the specific molecular determinants that govern tau strain selection during prion-like propagation?')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['TREM2-Dependent Microglial Phagocytosis ', 'GPC4/HSPGs Collaborate with ApoE Isoform']
matrix = np.array([[0.72, 0.78, 0.8, 0.65, 0.0, 0.75, 0.7, 0.85, 0.62], [0.8, 0.55, 0.75, 0.72, 0.0, 0.68, 0.6, 0.52, 0.48]])
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 — 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 h-dca86efa')

print('No PubMed results for hypothesis h-ec79168b')