import pandas as pd
ann_rows = [{'gene': 'ATG7', 'name': 'autophagy related 7', 'summary': 'This gene encodes an E1-like activating enzyme that is essential for autophagy and cytoplasmic to vacuole transport. The'}, {'gene': 'LRRK2', 'name': 'leucine rich repeat kinase 2', 'summary': 'This gene is a member of the leucine-rich repeat kinase family and encodes a protein with an ankryin repeat region, a le'}, {'gene': 'MCOLN1', 'name': 'mucolipin TRP cation channel 1', 'summary': 'This gene encodes a memberof the transient receptor potential (TRP) cation channel gene family. The transmembrane protei'}, {'gene': 'PARK2', 'name': 'parkin coregulated like pseudogene', 'summary': '—'}, {'gene': 'PINK1', 'name': 'PTEN induced kinase 1', 'summary': 'This gene encodes a serine/threonine protein kinase that localizes to mitochondria. It is thought to protect cells from '}, {'gene': 'TFEB', 'name': 'transcription factor EB', 'summary': 'Enables DNA-binding transcription factor activity; enzyme binding activity; and transcription cis-regulatory region bind'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Cellular Response To Nutrient Levels (GO:0031669)', 'p_value': 1.1316069188511993e-06, 'odds_ratio': 265.58666666666664, 'genes': ['LRRK2', 'TFEB', 'ATG7']}, {'rank': 2, 'term': 'Cellular Response To Chemical Stress (GO:0062197)', 'p_value': 1.6871429222139262e-06, 'odds_ratio': 231.48837209302326, 'genes': ['PINK1', 'LRRK2', 'ATG7']}, {'rank': 3, 'term': 'Positive Regulation Of Autophagy (GO:0010508)', 'p_value': 2.9427917452458996e-06, 'odds_ratio': 191.25, 'genes': ['PINK1', 'LRRK2', 'TFEB']}, {'rank': 4, 'term': 'Negative Regulation Of Autophagosome Assembly (GO:1902902)', 'p_value': 3.3713141681840526e-06, 'odds_ratio': 1249.125, 'genes': ['PINK1', 'LRRK2']}, {'rank': 5, 'term': 'Cellular Response To Starvation (GO:0009267)', 'p_value': 4.815633692564819e-06, 'odds_ratio': 161.5528455284553, 'genes': ['LRRK2', 'TFEB', 'ATG7']}, {'rank': 6, 'term': 'Protein Localization To Mitochondrion (GO:0070585)', 'p_value': 8.983080444348457e-06, 'odds_ratio': 713.5714285714286, 'genes': ['PINK1', 'LRRK2']}, {'rank': 7, 'term': 'Negative Regulation Of Macroautophagy (GO:0016242)', 'p_value': 1.7278715595310902e-05, 'odds_ratio': 499.35, 'genes': ['PINK1', 'LRRK2']}, {'rank': 8, 'term': 'Negative Regulation Of Oxidative Stress-Induced Cell Death (GO:1903202)', 'p_value': 1.8921800825806036e-05, 'odds_ratio': 475.54761904761904, 'genes': ['PINK1', 'LRRK2']}, {'rank': 9, 'term': 'Regulation Of Mitochondrial Fission (GO:0090140)', 'p_value': 2.6237275376282452e-05, 'odds_ratio': 399.38, 'genes': ['PINK1', 'LRRK2']}, {'rank': 10, 'term': 'Positive Regulation Of Protein Modification Process (GO:0031401)', 'p_value': 2.7404986673915108e-05, 'odds_ratio': 89.06306306306307, 'genes': ['PINK1', 'LRRK2', 'ATG7']}]
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 Nutrient Levels (GO:0031669)', 'p_value': 1.1316069188511993e-06, 'odds_ratio': 265.58666666666664, 'genes': ['LRRK2', 'TFEB', 'ATG7']}, {'rank': 2, 'term': 'Cellular Response To Chemical Stress (GO:0062197)', 'p_value': 1.6871429222139262e-06, 'odds_ratio': 231.48837209302326, 'genes': ['PINK1', 'LRRK2', 'ATG7']}, {'rank': 3, 'term': 'Positive Regulation Of Autophagy (GO:0010508)', 'p_value': 2.9427917452458996e-06, 'odds_ratio': 191.25, 'genes': ['PINK1', 'LRRK2', 'TFEB']}, {'rank': 4, 'term': 'Negative Regulation Of Autophagosome Assembly (GO:1902902)', 'p_value': 3.3713141681840526e-06, 'odds_ratio': 1249.125, 'genes': ['PINK1', 'LRRK2']}, {'rank': 5, 'term': 'Cellular Response To Starvation (GO:0009267)', 'p_value': 4.815633692564819e-06, 'odds_ratio': 161.5528455284553, 'genes': ['LRRK2', 'TFEB', 'ATG7']}, {'rank': 6, 'term': 'Protein Localization To Mitochondrion (GO:0070585)', 'p_value': 8.983080444348457e-06, 'odds_ratio': 713.5714285714286, 'genes': ['PINK1', 'LRRK2']}, {'rank': 7, 'term': 'Negative Regulation Of Macroautophagy (GO:0016242)', 'p_value': 1.7278715595310902e-05, 'odds_ratio': 499.35, 'genes': ['PINK1', 'LRRK2']}, {'rank': 8, 'term': 'Negative Regulation Of Oxidative Stress-Induced Cell Death (GO:1903202)', 'p_value': 1.8921800825806036e-05, 'odds_ratio': 475.54761904761904, 'genes': ['PINK1', 'LRRK2']}]
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': 'LRRK2', 'protein2': 'PRKN', 'score': 0.788, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.714}, {'protein1': 'PRKN', 'protein2': 'PINK1', 'score': 0.998, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.485, 'dscore': 0.9, 'tscore': 0.982}]
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': 'LRRK2', 'protein2': 'PRKN', 'score': 0.788, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.714}, {'protein1': 'PRKN', 'protein2': 'PINK1', 'score': 0.998, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.485, 'dscore': 0.9, 'tscore': 0.982}]
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': 'ATG7', 'n_pathways': 4, 'top_pathway': 'Macroautophagy'}, {'gene': 'LRRK2', 'n_pathways': 1, 'top_pathway': 'PTK6 promotes HIF1A stabilization'}, {'gene': 'MCOLN1', 'n_pathways': 2, 'top_pathway': 'TRP channels'}, {'gene': 'PARK2', 'n_pathways': 6, 'top_pathway': 'PINK1-PRKN Mediated Mitophagy'}, {'gene': 'PINK1', 'n_pathways': 2, 'top_pathway': 'PINK1-PRKN Mediated Mitophagy'}, {'gene': 'TFEB', 'n_pathways': 2, 'top_pathway': 'Transcriptional and post-translational regulation of MITF-M expression'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Sequential TRPML1 Activation Following Autophagy Primin', 0.575), ('TRPML1-PINK1/Parkin Axis Coordinates Mitophagy with Lys', 0.56)]
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('Does TRPML1 enhancement cause therapeutic benefit or paradoxical lysosomal dysfunction in vivo?')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Sequential TRPML1 Activation Following A', 'TRPML1-PINK1/Parkin Axis Coordinates Mit']
matrix = np.array([[0.7, 0.58, 0.72, 0.65, 0.0, 0.58, 0.65, 0.6, 0.45], [0.78, 0.55, 0.68, 0.72, 0.0, 0.48, 0.62, 0.52, 0.5]])
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-d27b354c')

print('No PubMed results for hypothesis h-6be901fb')