import pandas as pd
ann_rows = [{'gene': 'APOE', 'name': 'apolipoprotein E', 'protein_class': "['Cancer-related genes', 'Candidate cardiovascular disease g", 'disease_involvement': "['Alzheimer disease', 'Amyloidosis', 'Cancer-related genes', 'Disease variant', "}, {'gene': 'ARNTL', 'name': 'clock circadian regulator', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'C1QA', 'name': 'complement C1q A chain', 'protein_class': "['Disease related genes', 'Human disease related genes', 'Pl", 'disease_involvement': '—'}, {'gene': 'C3', 'name': 'complement C3', 'protein_class': "['Candidate cardiovascular disease genes', 'Disease related ", 'disease_involvement': "['Age-related macular degeneration', 'Disease variant', 'FDA approved drug targe"}, {'gene': 'CLOCK', 'name': 'clock circadian regulator', 'protein_class': "['Enzymes', 'Metabolic proteins', 'Predicted intracellular p", 'disease_involvement': '—'}, {'gene': 'CX3CL1', 'name': 'C-X3-C motif chemokine ligand 1', 'protein_class': "['Plasma proteins', 'Predicted membrane proteins', 'Predicte", 'disease_involvement': '—'}, {'gene': 'CX3CR1', 'name': 'C-X3-C motif chemokine receptor 1', 'protein_class': "['Disease related genes', 'G-protein coupled receptors', 'Hu", 'disease_involvement': "['Age-related macular degeneration']"}, {'gene': 'DNMT3A', 'name': 'DNA methyltransferase 3 alpha', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Enzymes',", 'disease_involvement': "['Cancer-related genes', 'Disease variant', 'Dwarfism', 'Intellectual disability"}, {'gene': 'GPR109A', 'name': 'hydroxycarboxylic acid receptor 2', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'GPR43', 'name': 'free fatty acid receptor 2', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'HDAC1', 'name': 'histone deacetylase 1', 'protein_class': "['Enzymes', 'FDA approved drug targets', 'Plasma proteins', ", 'disease_involvement': "['FDA approved drug targets']"}, {'gene': 'HIF1A', 'name': 'hypoxia inducible factor 1 subunit alpha', 'protein_class': "['Cancer-related genes', 'Human disease related genes', 'Met", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'IGFBPL1', 'name': 'insulin like growth factor binding protein like 1', 'protein_class': "['Predicted secreted proteins']", 'disease_involvement': '—'}, {'gene': 'IL1B', 'name': 'interleukin 1 beta', 'protein_class': "['Cancer-related genes', 'Candidate cardiovascular disease g", 'disease_involvement': "['Cancer-related genes', 'FDA approved drug targets']"}, {'gene': 'IL6', 'name': 'interleukin 6', 'protein_class': "['Cancer-related genes', 'Candidate cardiovascular disease g", 'disease_involvement': "['Cancer-related genes', 'FDA approved drug targets']"}, {'gene': 'MULTIPLE', 'name': 'exostoses (multiple) 3', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'NFKB1', 'name': 'nuclear factor kappa B subunit 1', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'FDA appro", 'disease_involvement': "['Cancer-related genes', 'FDA approved drug targets']"}, {'gene': 'NLRP3', 'name': 'NLR family pyrin domain containing 3', 'protein_class': "['Cancer-related genes', 'Human disease related genes', 'Pre", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'TNF', 'name': 'tumor necrosis factor', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'TNFA', 'name': 'tumor necrosis factor', 'protein_class': '—', 'disease_involvement': '—'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Positive Regulation Of NF-kappaB Transcription Factor Activity (GO:0051092)', 'p_value': 9.091770008863585e-11, 'odds_ratio': 73.657824933687, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'CLOCK', 'CX3CL1']}, {'rank': 2, 'term': 'Regulation Of Smooth Muscle Cell Proliferation (GO:0048660)', 'p_value': 1.7837089378996073e-09, 'odds_ratio': 135.58503401360545, 'genes': ['IL6', 'HDAC1', 'APOE', 'TNF', 'CX3CL1']}, {'rank': 3, 'term': 'Cellular Response To Lipopolysaccharide (GO:0071222)', 'p_value': 1.8147739036301002e-09, 'odds_ratio': 72.13801452784503, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'NFKB1']}, {'rank': 4, 'term': 'Positive Regulation Of DNA-binding Transcription Factor Activity (GO:0051091)', 'p_value': 2.6448307696605873e-09, 'odds_ratio': 44.47602188606373, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'CLOCK', 'CX3CL1']}, {'rank': 5, 'term': 'Microglial Cell Activation (GO:0001774)', 'p_value': 3.4856231082538815e-09, 'odds_ratio': 311.9375, 'genes': ['CX3CR1', 'C1QA', 'TNF', 'CX3CL1']}, {'rank': 6, 'term': 'Regulation Of Lipid Storage (GO:0010883)', 'p_value': 4.303029496793e-09, 'odds_ratio': 293.5735294117647, 'genes': ['C3', 'IL6', 'TNF', 'NFKB1']}, {'rank': 7, 'term': 'Regulation Of Neurogenesis (GO:0050767)', 'p_value': 5.40302432763974e-09, 'odds_ratio': 107.08602150537635, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'TNF', 'CX3CL1']}, {'rank': 8, 'term': 'Positive Regulation Of Vascular Endothelial Growth Factor Production (GO:0010575)', 'p_value': 7.625177432915028e-09, 'odds_ratio': 249.5, 'genes': ['C3', 'IL6', 'IL1B', 'HIF1A']}, {'rank': 9, 'term': 'Positive Regulation Of I-kappaB Phosphorylation (GO:1903721)', 'p_value': 8.538975432762311e-09, 'odds_ratio': 1762.764705882353, 'genes': ['CX3CR1', 'TNF', 'CX3CL1']}, {'rank': 10, 'term': 'Regulation Of Calcidiol 1-Monooxygenase Activity (GO:0060558)', 'p_value': 8.538975432762311e-09, 'odds_ratio': 1762.764705882353, 'genes': ['IL1B', 'TNF', 'NFKB1']}]
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': 'Positive Regulation Of NF-kappaB Transcription Factor Activity (GO:0051092)', 'p_value': 9.091770008863585e-11, 'odds_ratio': 73.657824933687, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'CLOCK', 'CX3CL1']}, {'rank': 2, 'term': 'Regulation Of Smooth Muscle Cell Proliferation (GO:0048660)', 'p_value': 1.7837089378996073e-09, 'odds_ratio': 135.58503401360545, 'genes': ['IL6', 'HDAC1', 'APOE', 'TNF', 'CX3CL1']}, {'rank': 3, 'term': 'Cellular Response To Lipopolysaccharide (GO:0071222)', 'p_value': 1.8147739036301002e-09, 'odds_ratio': 72.13801452784503, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'NFKB1']}, {'rank': 4, 'term': 'Positive Regulation Of DNA-binding Transcription Factor Activity (GO:0051091)', 'p_value': 2.6448307696605873e-09, 'odds_ratio': 44.47602188606373, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'NLRP3', 'TNF', 'CLOCK', 'CX3CL1']}, {'rank': 5, 'term': 'Microglial Cell Activation (GO:0001774)', 'p_value': 3.4856231082538815e-09, 'odds_ratio': 311.9375, 'genes': ['CX3CR1', 'C1QA', 'TNF', 'CX3CL1']}, {'rank': 6, 'term': 'Regulation Of Lipid Storage (GO:0010883)', 'p_value': 4.303029496793e-09, 'odds_ratio': 293.5735294117647, 'genes': ['C3', 'IL6', 'TNF', 'NFKB1']}, {'rank': 7, 'term': 'Regulation Of Neurogenesis (GO:0050767)', 'p_value': 5.40302432763974e-09, 'odds_ratio': 107.08602150537635, 'genes': ['CX3CR1', 'IL6', 'IL1B', 'TNF', 'CX3CL1']}, {'rank': 8, 'term': 'Positive Regulation Of Vascular Endothelial Growth Factor Production (GO:0010575)', 'p_value': 7.625177432915028e-09, 'odds_ratio': 249.5, 'genes': ['C3', 'IL6', 'IL1B', 'HIF1A']}]
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': 'CX3CL1', 'protein2': 'CX3CR1', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.618, 'dscore': 0.9, 'tscore': 0.983}, {'protein1': 'NFKB1', 'protein2': 'TNF', 'score': 0.846, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.846}, {'protein1': 'NFKB1', 'protein2': 'HDAC1', 'score': 0.975, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.564, 'dscore': 0, 'tscore': 0.947}, {'protein1': 'DNMT3A', 'protein2': 'HDAC1', 'score': 0.989, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.982}, {'protein1': 'HDAC1', 'protein2': 'HIF1A', 'score': 0.912, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.845}, {'protein1': 'HCAR2', 'protein2': 'FFAR2', 'score': 0.569, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.569}, {'protein1': 'ARNTL', 'protein2': 'HIF1A', 'score': 0.922, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.552, 'dscore': 0, 'tscore': 0.834}, {'protein1': 'ARNTL', 'protein2': 'CLOCK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.965, 'dscore': 0.8, 'tscore': 0.986}]
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': 'CX3CL1', 'protein2': 'CX3CR1', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.618, 'dscore': 0.9, 'tscore': 0.983}, {'protein1': 'NFKB1', 'protein2': 'TNF', 'score': 0.846, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.846}, {'protein1': 'NFKB1', 'protein2': 'HDAC1', 'score': 0.975, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.564, 'dscore': 0, 'tscore': 0.947}, {'protein1': 'DNMT3A', 'protein2': 'HDAC1', 'score': 0.989, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.982}, {'protein1': 'HDAC1', 'protein2': 'HIF1A', 'score': 0.912, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.845}, {'protein1': 'HCAR2', 'protein2': 'FFAR2', 'score': 0.569, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.569}, {'protein1': 'ARNTL', 'protein2': 'HIF1A', 'score': 0.922, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.552, 'dscore': 0, 'tscore': 0.834}, {'protein1': 'ARNTL', 'protein2': 'CLOCK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.965, 'dscore': 0.8, 'tscore': 0.986}]
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': 'APOE', 'n_pathways': 8, 'top_pathway': 'Nuclear signaling by ERBB4'}, {'gene': 'ARNTL', 'n_pathways': 8, 'top_pathway': 'BMAL1:CLOCK,NPAS2 activates circadian expression'}, {'gene': 'C1QA', 'n_pathways': 3, 'top_pathway': 'Initial triggering of complement'}, {'gene': 'C3', 'n_pathways': 8, 'top_pathway': 'Alternative complement activation'}, {'gene': 'CLOCK', 'n_pathways': 8, 'top_pathway': 'BMAL1:CLOCK,NPAS2 activates circadian expression'}, {'gene': 'CX3CL1', 'n_pathways': 2, 'top_pathway': 'Chemokine receptors bind chemokines'}, {'gene': 'CX3CR1', 'n_pathways': 4, 'top_pathway': 'Chemokine receptors bind chemokines'}, {'gene': 'DNMT3A', 'n_pathways': 6, 'top_pathway': 'PRC2 methylates histones and DNA'}, {'gene': 'GPR109A', 'n_pathways': 3, 'top_pathway': 'Hydroxycarboxylic acid-binding receptors'}, {'gene': 'GPR43', 'n_pathways': 2, 'top_pathway': 'G alpha (q) signalling events'}, {'gene': 'HDAC1', 'n_pathways': 8, 'top_pathway': 'Transcription of E2F targets under negative control by DREAM complex'}, {'gene': 'HIF1A', 'n_pathways': 8, 'top_pathway': 'Regulation of gene expression by Hypoxia-inducible Factor'}, {'gene': 'IGFBPL1', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'IL1B', 'n_pathways': 7, 'top_pathway': 'Interleukin-1 processing'}, {'gene': 'IL6', 'n_pathways': 8, 'top_pathway': 'Interleukin-6 signaling'}, {'gene': 'MULTIPLE', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'NFKB1', 'n_pathways': 8, 'top_pathway': 'Activation of NF-kappaB in B cells'}, {'gene': 'NLRP3', 'n_pathways': 6, 'top_pathway': 'Metalloprotease DUBs'}, {'gene': 'TNF', 'n_pathways': 8, 'top_pathway': 'Transcriptional regulation of white adipocyte differentiation'}, {'gene': 'TNFA', 'n_pathways': 8, 'top_pathway': 'Transcriptional regulation of white adipocyte differentiation'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Microbiota-Microglia Axis Modulation', 0.651), ('Epigenetic Reprogramming of Microglial Memory', 0.647), ('Cardiovascular-Neuroinflammatory Dual Targeting', 0.627), ('Perinatal Immune Challenge Prevention', 0.616), ('Synaptic Pruning Precision Therapy', 0.612), ('APOE4-Lipid Metabolism Correction', 0.61), ('Cardiovascular-Neuroinflammation Crosstalk Interruption', 0.587), ('IGFBPL1-Mediated Homeostatic Restoration', 0.584), ('Complement-Mediated Synaptic Protection', 0.58), ('IGFBPL1-Mediated Microglial Reprogramming', 0.579), ('TREM2-P2RY12 Balance Restoration Therapy', 0.571), ('Temporal Gating of Microglial Responses', 0.565), ('Gut-Brain Axis Microbiome Modulation', 0.557), ('Perinatal Hypoxia-Primed Microglia Targeting', 0.548)]
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("Neuroinflammation and microglial priming in early Alzheimer's Disease")
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Microbiota-Microglia Axis Modulation', 'Epigenetic Reprogramming of Microglial M', 'Cardiovascular-Neuroinflammatory Dual Ta', 'Perinatal Immune Challenge Prevention', 'Synaptic Pruning Precision Therapy', 'APOE4-Lipid Metabolism Correction', 'Cardiovascular-Neuroinflammation Crossta', 'IGFBPL1-Mediated Homeostatic Restoration', 'Complement-Mediated Synaptic Protection', 'IGFBPL1-Mediated Microglial Reprogrammin']
matrix = np.array([[0.6, 0.6, 0.5, 0.4, 0.5, 0.4, 0.3, 0.7, 0.8], [0.8, 0.8, 0.7, 0.7, 0.785, 0.7, 0.8, 0.9, 0.6], [0.4, 0.8, 0.6, 0.6, 0.62, 0.8, 0.7, 0.9, 0.6], [0.9, 0.1, 0.4, 0.3, 0.475, 0.2, 0.1, 0.3, 0.2], [0.7, 0.6, 0.8, 0.8, 0.78, 0.8, 0.7, 0.6, 0.5], [0.7, 0.4, 0.6, 0.5, 0.695, 0.6, 0.4, 0.4, 0.7], [0.5, 0.8, 0.7, 0.6, 0.76, 0.7, 0.8, 0.9, 0.4], [0.9, 0.3, 0.8, 0.7, 0.735, 0.6, 0.6, 0.2, 0.5], [0.6, 0.5, 0.7, 0.6, 0.58, 0.5, 0.5, 0.6, 0.3], [0.9, 0.3, 0.8, 0.7, 0.555, 0.3, 0.4, 0.2, 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 — top 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-6f21f62a')

print('No PubMed results for hypothesis h-e5f1182b')

print('No PubMed results for hypothesis h-6f1e8d32')

print('No PubMed results for hypothesis h-8f9633d9')

print('No PubMed results for hypothesis h-494861d2')

print('No PubMed results for hypothesis h-69bde12f')

print('No PubMed results for hypothesis h-cc1076c1')

print('No PubMed results for hypothesis h-d4ff5555')

print('No PubMed results for hypothesis h-f19b8ac8')

print('No PubMed results for hypothesis h-6880f29b')

print('No PubMed results for hypothesis h-ea3274ff')

print('No PubMed results for hypothesis h-828b3729')

print('No PubMed results for hypothesis h-48775971')

print('No PubMed results for hypothesis h-646ae8f1')