import pandas as pd
ann_rows = [{'gene': 'ALOX15', 'name': 'arachidonate 15-lipoxygenase', 'summary': 'This gene encodes a member of the lipoxygenase family of proteins. The encoded enzyme acts on various polyunsaturated fa'}, {'gene': 'BH4', 'name': 'sepiapterin reductase', 'summary': 'This gene encodes an aldo-keto reductase that catalyzes the NADPH-dependent reduction of pteridine derivatives and is im'}, {'gene': 'GCH1', 'name': 'GTP cyclohydrolase 1', 'summary': 'This gene encodes a member of the GTP cyclohydrolase family. The encoded protein is the first and rate-limiting enzyme i'}, {'gene': 'GPX4', 'name': 'glutathione peroxidase 4', 'summary': 'The protein encoded by this gene belongs to the glutathione peroxidase family, members of which catalyze the reduction o'}, {'gene': 'HFE', 'name': 'homeostatic iron regulator', 'summary': 'The protein encoded by this gene is a membrane protein that is similar to MHC class I-type proteins and associates with '}, {'gene': 'KEAP1', 'name': 'kelch like ECH associated protein 1', 'summary': 'This gene encodes a cytoplasmic regulatory protein that plays a role in the cellular response to oxidative and electroph'}, {'gene': 'NCOA4', 'name': 'nuclear receptor coactivator 4', 'summary': 'This gene encodes an androgen receptor coactivator. The encoded protein interacts with the androgen receptor in a ligand'}, {'gene': 'NRF2', 'name': 'NRF2 regulation associated lncRNA', 'summary': '—'}, {'gene': 'SELENOP', 'name': 'selenoprotein P', 'summary': 'This gene encodes a selenoprotein that is predominantly expressed in the liver and secreted into the plasma. This seleno'}, {'gene': 'SLC7A11', 'name': 'solute carrier family 7 member 11', 'summary': 'This gene encodes a member of a heteromeric, sodium-independent, anionic amino acid transport system that is highly spec'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Lipoxygenase Pathway (GO:0019372)', 'p_value': 4.71859981396871e-06, 'odds_ratio': 999.25, 'genes': ['GPX4', 'ALOX15']}, {'rank': 2, 'term': 'Long-Chain Fatty Acid Biosynthetic Process (GO:0042759)', 'p_value': 6.70875366203682e-05, 'odds_ratio': 217.0326086956522, 'genes': ['GPX4', 'ALOX15']}, {'rank': 3, 'term': 'Unsaturated Fatty Acid Metabolic Process (GO:0033559)', 'p_value': 0.00026130779010617516, 'odds_ratio': 106.07978723404256, 'genes': ['GPX4', 'ALOX15']}, {'rank': 4, 'term': 'Icosanoid Metabolic Process (GO:0006690)', 'p_value': 0.00029440241859604355, 'odds_ratio': 99.7, 'genes': ['GPX4', 'ALOX15']}, {'rank': 5, 'term': 'Arachidonic Acid Metabolic Process (GO:0019369)', 'p_value': 0.00029440241859604355, 'odds_ratio': 99.7, 'genes': ['GPX4', 'ALOX15']}, {'rank': 6, 'term': 'Fatty Acid Biosynthetic Process (GO:0006633)', 'p_value': 0.00046021034561651085, 'odds_ratio': 79.07539682539682, 'genes': ['GPX4', 'ALOX15']}, {'rank': 7, 'term': 'Long-Chain Fatty Acid Metabolic Process (GO:0001676)', 'p_value': 0.0006621298425578926, 'odds_ratio': 65.50657894736842, 'genes': ['GPX4', 'ALOX15']}, {'rank': 8, 'term': 'Regulation Of Proteasomal Ubiquitin-Dependent Protein Catabolic Process (GO:0032434)', 'p_value': 0.0012871159553875, 'odds_ratio': 46.455607476635514, 'genes': ['HFE', 'KEAP1']}, {'rank': 9, 'term': 'Fatty Acid Metabolic Process (GO:0006631)', 'p_value': 0.0016084465825751896, 'odds_ratio': 41.395833333333336, 'genes': ['GPX4', 'ALOX15']}, {'rank': 10, 'term': 'Cellular Response To Metal Ion (GO:0071248)', 'p_value': 0.001964236966804282, 'odds_ratio': 37.32518796992481, 'genes': ['HFE', 'ALOX15']}]
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': 'Lipoxygenase Pathway (GO:0019372)', 'p_value': 4.71859981396871e-06, 'odds_ratio': 999.25, 'genes': ['GPX4', 'ALOX15']}, {'rank': 2, 'term': 'Long-Chain Fatty Acid Biosynthetic Process (GO:0042759)', 'p_value': 6.70875366203682e-05, 'odds_ratio': 217.0326086956522, 'genes': ['GPX4', 'ALOX15']}, {'rank': 3, 'term': 'Unsaturated Fatty Acid Metabolic Process (GO:0033559)', 'p_value': 0.00026130779010617516, 'odds_ratio': 106.07978723404256, 'genes': ['GPX4', 'ALOX15']}, {'rank': 4, 'term': 'Icosanoid Metabolic Process (GO:0006690)', 'p_value': 0.00029440241859604355, 'odds_ratio': 99.7, 'genes': ['GPX4', 'ALOX15']}, {'rank': 5, 'term': 'Arachidonic Acid Metabolic Process (GO:0019369)', 'p_value': 0.00029440241859604355, 'odds_ratio': 99.7, 'genes': ['GPX4', 'ALOX15']}, {'rank': 6, 'term': 'Fatty Acid Biosynthetic Process (GO:0006633)', 'p_value': 0.00046021034561651085, 'odds_ratio': 79.07539682539682, 'genes': ['GPX4', 'ALOX15']}, {'rank': 7, 'term': 'Long-Chain Fatty Acid Metabolic Process (GO:0001676)', 'p_value': 0.0006621298425578926, 'odds_ratio': 65.50657894736842, 'genes': ['GPX4', 'ALOX15']}, {'rank': 8, 'term': 'Regulation Of Proteasomal Ubiquitin-Dependent Protein Catabolic Process (GO:0032434)', 'p_value': 0.0012871159553875, 'odds_ratio': 46.455607476635514, 'genes': ['HFE', 'KEAP1']}]
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': 'GABPA', 'protein2': 'KEAP1', 'score': 0.457, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0}]
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': 'GABPA', 'protein2': 'KEAP1', 'score': 0.457, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0}]
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': 'ALOX15', 'n_pathways': 8, 'top_pathway': 'Synthesis of Leukotrienes (LT) and Eoxins (EX)'}, {'gene': 'BH4', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'GCH1', 'n_pathways': 1, 'top_pathway': 'Tetrahydrobiopterin (BH4) synthesis, recycling, salvage and regulation'}, {'gene': 'GPX4', 'n_pathways': 7, 'top_pathway': 'Synthesis of 5-eicosatetraenoic acids'}, {'gene': 'HFE', 'n_pathways': 1, 'top_pathway': 'Transferrin endocytosis and recycling'}, {'gene': 'KEAP1', 'n_pathways': 6, 'top_pathway': 'Ub-specific processing proteases'}, {'gene': 'NCOA4', 'n_pathways': 1, 'top_pathway': 'MLL4 and MLL3 complexes regulate expression of PPARG target genes in a'}, {'gene': 'NRF2', 'n_pathways': 8, 'top_pathway': 'Neddylation'}, {'gene': 'SELENOP', 'n_pathways': 1, 'top_pathway': 'Platelet degranulation'}, {'gene': 'SLC7A11', 'n_pathways': 3, 'top_pathway': 'Basigin interactions'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('GPX4 Selenopeptide Mimetics as Neuroprotective Ferropto', 0.68), ('NRF2-KEAP1 Pathway Activation to Coordinate Multi-Layer', 0.65), ('Microglial xCT/SLC7A11 Selective Inhibition to Reduce N', 0.62), ('ALOX15 Inhibition Combined with Selenium Augmentation f', 0.58), ('GCH1/BH4 Axis Stabilization for Dual Ferroptosis and Mi', 0.56), ('H63D HFE Genotype-Guided Iron Chelation Therapy for Sub', 0.55), ('FUS-ALS-Specific Ferroptosis Vulnerability Through NCOA', 0.48)]
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('Ferroptosis in ALS and motor neuron disease: GPX4, lipid peroxidation, and iron chelation therapies')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['GPX4 Selenopeptide Mimetics as Neuroprot', 'NRF2-KEAP1 Pathway Activation to Coordin', 'Microglial xCT/SLC7A11 Selective Inhibit', 'ALOX15 Inhibition Combined with Selenium', 'GCH1/BH4 Axis Stabilization for Dual Fer', 'H63D HFE Genotype-Guided Iron Chelation ', 'FUS-ALS-Specific Ferroptosis Vulnerabili']
matrix = np.array([[0.65, 0.52, 0.68, 0.82, 0.0, 0.7, 0.75, 0.48, 0.55], [0.5, 0.58, 0.65, 0.78, 0.0, 0.72, 0.68, 0.75, 0.6], [0.55, 0.42, 0.62, 0.7, 0.0, 0.68, 0.65, 0.6, 0.45], [0.7, 0.38, 0.58, 0.72, 0.0, 0.55, 0.6, 0.45, 0.5], [0.75, 0.32, 0.56, 0.65, 0.0, 0.52, 0.55, 0.35, 0.48], [0.6, 0.55, 0.55, 0.58, 0.0, 0.45, 0.42, 0.65, 0.5], [0.8, 0.25, 0.48, 0.55, 0.0, 0.38, 0.4, 0.28, 0.35]])
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')

lit_data = [{'year': '2023', 'journal': 'Cell Death Differ', 'title': 'SPY1 inhibits neuronal ferroptosis in amyotrophic lateral sclerosis by reducing ', 'pmid': '36443440'}]
if lit_data:
    df = pd.DataFrame(lit_data)
    print(f'{len(lit_data)} PubMed results')
    display(df)
else:
    print('No PubMed results')

print('No PubMed results for hypothesis h-64c36c7c')

print('No PubMed results for hypothesis h-aecdf76b')

print('No PubMed results for hypothesis h-d645402b')

lit_data = [{'year': '2023', 'journal': 'Cell Death Differ', 'title': 'SPY1 inhibits neuronal ferroptosis in amyotrophic lateral sclerosis by reducing ', 'pmid': '36443440'}]
if lit_data:
    df = pd.DataFrame(lit_data)
    print(f'{len(lit_data)} PubMed results')
    display(df)
else:
    print('No PubMed results')

print('No PubMed results for hypothesis h-25be864e')

print('No PubMed results for hypothesis h-39c4d643')

edge_data = []
if edge_data:
    pd.DataFrame(edge_data).head(25)
else:
    print('No KG edge data available')