import pandas as pd
ann_rows = [{'gene': 'HDAC6', 'name': 'histone deacetylase 6', 'summary': 'Histones play a critical role in transcriptional regulation, cell cycle progression, and developmental events. Histone a'}, {'gene': 'MGEA5', 'name': 'O-GlcNAcase', 'summary': 'The dynamic modification of cytoplasmic and nuclear proteins by O-linked N-acetylglucosamine (O-GlcNAc) addition and rem'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Cilium Disassembly (GO:0061523)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HDAC6']}, {'rank': 2, 'term': 'Inclusion Body Assembly (GO:0070841)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HDAC6']}, {'rank': 3, 'term': 'Spermidine Metabolic Process (GO:0008216)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HDAC6']}, {'rank': 4, 'term': 'Peptidyl-Lysine Deacetylation (GO:0034983)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HDAC6']}, {'rank': 5, 'term': 'Negative Regulation Of Protein-Containing Complex Disassembly (GO:0043242)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['HDAC6']}, {'rank': 6, 'term': 'Response To Misfolded Protein (GO:0051788)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['HDAC6']}, {'rank': 7, 'term': 'Negative Regulation Of Oxidoreductase Activity (GO:0051354)', 'p_value': 0.0009997522177478497, 'odds_ratio': 2221.0, 'genes': ['HDAC6']}, {'rank': 8, 'term': 'Polyamine Metabolic Process (GO:0006595)', 'p_value': 0.0010997006223853795, 'odds_ratio': 1998.8, 'genes': ['HDAC6']}, {'rank': 9, 'term': 'Regulation Of Microtubule-Based Movement (GO:0060632)', 'p_value': 0.0010997006223853795, 'odds_ratio': 1998.8, 'genes': ['HDAC6']}, {'rank': 10, 'term': 'Axonal Transport Of Mitochondrion (GO:0019896)', 'p_value': 0.0011996440770550066, 'odds_ratio': 1817.0, 'genes': ['HDAC6']}]
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': 'Cilium Disassembly (GO:0061523)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HDAC6']}, {'rank': 2, 'term': 'Inclusion Body Assembly (GO:0070841)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['HDAC6']}, {'rank': 3, 'term': 'Spermidine Metabolic Process (GO:0008216)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HDAC6']}, {'rank': 4, 'term': 'Peptidyl-Lysine Deacetylation (GO:0034983)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['HDAC6']}, {'rank': 5, 'term': 'Negative Regulation Of Protein-Containing Complex Disassembly (GO:0043242)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['HDAC6']}, {'rank': 6, 'term': 'Response To Misfolded Protein (GO:0051788)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['HDAC6']}, {'rank': 7, 'term': 'Negative Regulation Of Oxidoreductase Activity (GO:0051354)', 'p_value': 0.0009997522177478497, 'odds_ratio': 2221.0, 'genes': ['HDAC6']}, {'rank': 8, 'term': 'Polyamine Metabolic Process (GO:0006595)', 'p_value': 0.0010997006223853795, 'odds_ratio': 1998.8, 'genes': ['HDAC6']}]
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': 'HDAC6', 'n_pathways': 8, 'top_pathway': 'NOTCH1 Intracellular Domain Regulates Transcription'}, {'gene': 'MGEA5', 'n_pathways': 0, 'top_pathway': '—'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('HDAC6 Inhibition for Dual Restoration of Microtubule St', 0.484), ("Selective OGA Inhibition as 'Tau Stabilization' Strateg", 0.458)]
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('Which tau PTMs are both disease-specific and druggable with selective small molecule inhibitors?')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['HDAC6 Inhibition for Dual Restoration of', "Selective OGA Inhibition as 'Tau Stabili"]
matrix = np.array([[0.42, 0.48, 0.65, 0.58, 0.0, 0.6, 0.48, 0.62, 0.45], [0.38, 0.4, 0.52, 0.55, 0.0, 0.65, 0.5, 0.68, 0.28]])
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-f86127b5')

print('No PubMed results for hypothesis h-46e028b6')