import pandas as pd
ann_rows = [{'gene': 'IDO1', 'name': 'indoleamine 2,3-dioxygenase 1', 'summary': 'This gene encodes indoleamine 2,3-dioxygenase (IDO) - a heme enzyme that catalyzes the first and rate-limiting step in t'}, {'gene': 'PXR', 'name': "CYP3A4 5' regulatory region", 'summary': "This record represents the 5' regulatory region of the cytochrome P450 family 3 subfamily A member 4 gene. This sequence"}, {'gene': 'REG3G', 'name': 'regenerating family member 3 gamma', 'summary': 'This gene encodes a member of the regenerating islet-derived genes (REG)3 protein family. These proteins are secreted, C'}, {'gene': 'ZONULIN', 'name': 'haptoglobin', 'summary': 'This gene encodes a preproprotein, which is processed to yield both alpha and beta chains, which subsequently combine as'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Cellular Response To Lipid (GO:0071396)', 'p_value': 0.00012939152458165337, 'odds_ratio': 39544.0, 'genes': ['SPP1', 'NLRP3']}, {'rank': 2, 'term': 'Response To Testosterone (GO:0033574)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['SPP1']}, {'rank': 3, 'term': 'Positive Regulation Of T-helper 2 Cell Differentiation (GO:0045630)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 4, 'term': 'Osmosensory Signaling Pathway (GO:0007231)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 5, 'term': 'Regulation Of Type 2 Immune Response (GO:0002828)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 6, 'term': 'Negative Regulation Of Acute Inflammatory Response (GO:0002674)', 'p_value': 0.000599909243874975, 'odds_ratio': 3998.6, 'genes': ['NLRP3']}, {'rank': 7, 'term': 'Positive Regulation Of T-helper 2 Cell Cytokine Production (GO:2000553)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['NLRP3']}, {'rank': 8, 'term': 'Regulation Of T-helper 2 Cell Differentiation (GO:0045628)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['NLRP3']}, {'rank': 9, 'term': 'Response To Vitamin (GO:0033273)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['SPP1']}, {'rank': 10, 'term': 'Response To Vitamin D (GO:0033280)', 'p_value': 0.0007998405838081707, 'odds_ratio': 2855.8571428571427, 'genes': ['SPP1']}]
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': 'Cellular Response To Lipid (GO:0071396)', 'p_value': 0.00012939152458165337, 'odds_ratio': 39544.0, 'genes': ['SPP1', 'NLRP3']}, {'rank': 2, 'term': 'Response To Testosterone (GO:0033574)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['SPP1']}, {'rank': 3, 'term': 'Positive Regulation Of T-helper 2 Cell Differentiation (GO:0045630)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 4, 'term': 'Osmosensory Signaling Pathway (GO:0007231)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 5, 'term': 'Regulation Of Type 2 Immune Response (GO:0002828)', 'p_value': 0.0004999362185987752, 'odds_ratio': 4998.5, 'genes': ['NLRP3']}, {'rank': 6, 'term': 'Negative Regulation Of Acute Inflammatory Response (GO:0002674)', 'p_value': 0.000599909243874975, 'odds_ratio': 3998.6, 'genes': ['NLRP3']}, {'rank': 7, 'term': 'Positive Regulation Of T-helper 2 Cell Cytokine Production (GO:2000553)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['NLRP3']}, {'rank': 8, 'term': 'Regulation Of T-helper 2 Cell Differentiation (GO:0045628)', 'p_value': 0.0006998773712248138, 'odds_ratio': 3332.0, 'genes': ['NLRP3']}]
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': 'IDO1', 'n_pathways': 1, 'top_pathway': 'Tryptophan catabolism'}, {'gene': 'PXR', 'n_pathways': 2, 'top_pathway': 'Nuclear Receptor transcription pathway'}, {'gene': 'REG3G', 'n_pathways': 1, 'top_pathway': 'Antimicrobial peptides'}, {'gene': 'ZONULIN', 'n_pathways': 0, 'top_pathway': '—'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('H2: Indole-3-Propionate (IPA) as the Actual Neuroprotec', 0.703), ('H7: Enteric Nervous System Alpha-Synuclein Propagation ', 0.62)]
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('How does engineered C. butyricum cross the blood-brain barrier to directly bind GLP-1 receptors?')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['H2: Indole-3-Propionate (IPA) as the Act', 'H7: Enteric Nervous System Alpha-Synucle']
matrix = np.array([[0.88, 0.8, 0.75, 0.68, 0.0, 0.7, 0.75, 0.82, 0.62], [0.58, 0.75, 0.82, 0.78, 0.0, 0.68, 0.72, 0.7, 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 — 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-66078909')

print('No PubMed results for hypothesis h-a5186bb8')