import pandas as pd
ann_rows = [{'gene': 'MYD88', 'name': 'MYD88 innate immune signal transduction adaptor', 'summary': 'This gene encodes a cytosolic adapter protein that plays a central role in the innate and adaptive immune response. This'}, {'gene': 'NAMPT', 'name': 'nicotinamide phosphoribosyltransferase', 'summary': 'This gene encodes a protein that catalyzes the condensation of nicotinamide with 5-phosphoribosyl-1-pyrophosphate to yie'}, {'gene': 'SIRT1', 'name': 'sirtuin 1', 'summary': 'This gene encodes a member of the sirtuin family of proteins, homologs to the yeast Sir2 protein. Members of the sirtuin'}, {'gene': 'TLR4', 'name': 'toll like receptor 4', 'summary': 'The protein encoded by this gene is a member of the Toll-like receptor (TLR) family which plays a fundamental role in pa'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Regulation Of Interleukin-23 Production (GO:0032667)', 'p_value': 8.396275896569607e-07, 'odds_ratio': 3331.6666666666665, 'genes': ['TLR4', 'MYD88']}, {'rank': 2, 'term': 'Positive Regulation Of Macromolecule Biosynthetic Process (GO:0010557)', 'p_value': 8.818172756223627e-07, 'odds_ratio': 501.10084033613447, 'genes': ['NAMPT', 'SIRT1', 'TLR4']}, {'rank': 3, 'term': 'Cellular Response To Oxidised Low-Density Lipoprotein Particle Stimulus (GO:0140052)', 'p_value': 1.0794527804927066e-06, 'odds_ratio': 2855.5714285714284, 'genes': ['TLR4', 'MYD88']}, {'rank': 4, 'term': 'Positive Regulation Of Nitric-Oxide Synthase Biosynthetic Process (GO:0051770)', 'p_value': 1.3492299001701414e-06, 'odds_ratio': 2498.5, 'genes': ['NAMPT', 'TLR4']}, {'rank': 5, 'term': 'Regulation Of Nitric-Oxide Synthase Biosynthetic Process (GO:0051769)', 'p_value': 2.338213497902388e-06, 'odds_ratio': 1816.8181818181818, 'genes': ['NAMPT', 'TLR4']}, {'rank': 6, 'term': 'Cell Surface Toll-Like Receptor Signaling Pathway (GO:0140895)', 'p_value': 3.5965506045033277e-06, 'odds_ratio': 1427.2857142857142, 'genes': ['TLR4', 'MYD88']}, {'rank': 7, 'term': 'Toll-Like Receptor 4 Signaling Pathway (GO:0034142)', 'p_value': 4.075824859400975e-06, 'odds_ratio': 1332.0666666666666, 'genes': ['TLR4', 'MYD88']}, {'rank': 8, 'term': 'Positive Regulation Of NLRP3 Inflammasome Complex Assembly (GO:1900227)', 'p_value': 4.585003458844033e-06, 'odds_ratio': 1248.75, 'genes': ['TLR4', 'MYD88']}, {'rank': 9, 'term': 'Positive Regulation Of Cytokine Production Involved In Inflammatory Response (GO:1900017)', 'p_value': 4.585003458844033e-06, 'odds_ratio': 1248.75, 'genes': ['TLR4', 'MYD88']}, {'rank': 10, 'term': 'Cellular Response To Low-Density Lipoprotein Particle Stimulus (GO:0071404)', 'p_value': 6.9206420320479584e-06, 'odds_ratio': 998.8, 'genes': ['TLR4', 'MYD88']}]
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 Interleukin-23 Production (GO:0032667)', 'p_value': 8.396275896569607e-07, 'odds_ratio': 3331.6666666666665, 'genes': ['TLR4', 'MYD88']}, {'rank': 2, 'term': 'Positive Regulation Of Macromolecule Biosynthetic Process (GO:0010557)', 'p_value': 8.818172756223627e-07, 'odds_ratio': 501.10084033613447, 'genes': ['NAMPT', 'SIRT1', 'TLR4']}, {'rank': 3, 'term': 'Cellular Response To Oxidised Low-Density Lipoprotein Particle Stimulus (GO:0140052)', 'p_value': 1.0794527804927066e-06, 'odds_ratio': 2855.5714285714284, 'genes': ['TLR4', 'MYD88']}, {'rank': 4, 'term': 'Positive Regulation Of Nitric-Oxide Synthase Biosynthetic Process (GO:0051770)', 'p_value': 1.3492299001701414e-06, 'odds_ratio': 2498.5, 'genes': ['NAMPT', 'TLR4']}, {'rank': 5, 'term': 'Regulation Of Nitric-Oxide Synthase Biosynthetic Process (GO:0051769)', 'p_value': 2.338213497902388e-06, 'odds_ratio': 1816.8181818181818, 'genes': ['NAMPT', 'TLR4']}, {'rank': 6, 'term': 'Cell Surface Toll-Like Receptor Signaling Pathway (GO:0140895)', 'p_value': 3.5965506045033277e-06, 'odds_ratio': 1427.2857142857142, 'genes': ['TLR4', 'MYD88']}, {'rank': 7, 'term': 'Toll-Like Receptor 4 Signaling Pathway (GO:0034142)', 'p_value': 4.075824859400975e-06, 'odds_ratio': 1332.0666666666666, 'genes': ['TLR4', 'MYD88']}, {'rank': 8, 'term': 'Positive Regulation Of NLRP3 Inflammasome Complex Assembly (GO:1900227)', 'p_value': 4.585003458844033e-06, 'odds_ratio': 1248.75, 'genes': ['TLR4', 'MYD88']}]
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': 'NAMPT', 'protein2': 'TLR4', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.401}, {'protein1': 'TLR4', 'protein2': 'MYD88', 'score': 0.992, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.508, 'dscore': 0, 'tscore': 0.985}]
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': 'NAMPT', 'protein2': 'TLR4', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.401}, {'protein1': 'TLR4', 'protein2': 'MYD88', 'score': 0.992, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.508, 'dscore': 0, 'tscore': 0.985}]
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': 'MYD88', 'n_pathways': 8, 'top_pathway': 'ER-Phagosome pathway'}, {'gene': 'NAMPT', 'n_pathways': 3, 'top_pathway': 'BMAL1:CLOCK,NPAS2 activates circadian expression'}, {'gene': 'SIRT1', 'n_pathways': 8, 'top_pathway': 'Regulation of HSF1-mediated heat shock response'}, {'gene': 'TLR4', 'n_pathways': 8, 'top_pathway': 'ER-Phagosome pathway'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('SIRT1/PGC-1α Axis Activation to Preserve Mitochondrial ', 0.778), ('TLR4/MyD88/NF-κB Axis Blockade to Interrupt LPS-Mediate', 0.703)]
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 do gut microbiome-derived metabolites SCFAs LPS TMAO influence alpha-synuclein aggregation and dopaminergic neuron survival via vagal nerve signaling in Parkinson disease')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['SIRT1/PGC-1α Axis Activation to Preserve', 'TLR4/MyD88/NF-κB Axis Blockade to Interr']
matrix = np.array([[0.72, 0.78, 0.82, 0.88, 0.0, 0.82, 0.78, 0.8, 0.75], [0.65, 0.55, 0.7, 0.72, 0.0, 0.7, 0.65, 0.72, 0.58]])
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-26b9f3e7')

print('No PubMed results for hypothesis h-21d25124')