import pandas as pd
ann_rows = [{'gene': 'BRD4', 'name': 'bromodomain containing 4', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Essential", 'disease_involvement': "['Cancer-related genes', 'Disease variant', 'Intellectual disability']"}, {'gene': 'HDAC', 'name': 'SIN3-HDAC complex associated factor', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'HDAC3', 'name': 'histone deacetylase 3', 'protein_class': "['Enzymes', 'Essential proteins', 'FDA approved drug targets", 'disease_involvement': "['FDA approved drug targets']"}, {'gene': 'NAMPT', 'name': 'nicotinamide phosphoribosyltransferase', 'protein_class': "['Cancer-related genes', 'Enzymes', 'Metabolic proteins', 'P", 'disease_involvement': "['Cancer-related genes']"}, {'gene': 'OCT4', 'name': 'OCT4 hESC enhancer GRCh37_chr10:133148496-133148998', 'protein_class': '—', 'disease_involvement': '—'}, {'gene': 'SIRT1', 'name': 'sirtuin 1', 'protein_class': "['Enzymes', 'Metabolic proteins', 'Predicted intracellular p", 'disease_involvement': '—'}, {'gene': 'SIRT3', 'name': 'sirtuin 3', 'protein_class': "['Enzymes', 'Metabolic proteins', 'Predicted intracellular p", 'disease_involvement': '—'}, {'gene': 'SMARCA4', 'name': 'SWI/SNF related BAF chromatin remodeling complex subunit ATP', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Human dis", 'disease_involvement': "['Cancer-related genes', 'Deafness', 'Disease variant', 'Intellectual disability"}, {'gene': 'TET2', 'name': 'tet methylcytosine dioxygenase 2', 'protein_class': "['Cancer-related genes', 'Disease related genes', 'Enzymes',", 'disease_involvement': "['Cancer-related genes', 'Disease variant', 'Tumor suppressor']"}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Protein Deacylation (GO:0035601)', 'p_value': 7.154717101473363e-08, 'odds_ratio': 587.4705882352941, 'genes': ['HDAC3', 'SIRT1', 'SIRT3']}, {'rank': 2, 'term': 'Protein Deacetylation (GO:0006476)', 'p_value': 6.173082690121319e-07, 'odds_ratio': 269.64864864864865, 'genes': ['HDAC3', 'SIRT1', 'SIRT3']}, {'rank': 3, 'term': 'Positive Regulation Of Transcription By RNA Polymerase II (GO:0045944)', 'p_value': 7.790433066335926e-07, 'odds_ratio': 40.89914163090129, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}, {'rank': 4, 'term': 'Peptidyl-Lysine Deacetylation (GO:0034983)', 'p_value': 3.7754993322284675e-06, 'odds_ratio': 1142.057142857143, 'genes': ['SIRT1', 'SIRT3']}, {'rank': 5, 'term': 'Positive Regulation Of DNA-templated Transcription (GO:0045893)', 'p_value': 4.065006033168612e-06, 'odds_ratio': 30.321746160064674, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}, {'rank': 6, 'term': 'Negative Regulation Of Androgen Receptor Signaling Pathway (GO:0060766)', 'p_value': 1.633405632897404e-05, 'odds_ratio': 475.6904761904762, 'genes': ['SIRT1', 'SMARCA4']}, {'rank': 7, 'term': 'Regulation Of Androgen Receptor Signaling Pathway (GO:0060765)', 'p_value': 6.281272926601724e-05, 'odds_ratio': 228.18285714285713, 'genes': ['SIRT1', 'SMARCA4']}, {'rank': 8, 'term': 'Regulation Of Transcription By RNA Polymerase II (GO:0006357)', 'p_value': 6.91357556918871e-05, 'odds_ratio': 17.773491592482692, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}, {'rank': 9, 'term': 'Negative Regulation Of Intracellular Steroid Hormone Receptor Signaling Pathway (GO:0033144)', 'p_value': 8.313599120396748e-05, 'odds_ratio': 196.66995073891624, 'genes': ['SIRT1', 'SMARCA4']}, {'rank': 10, 'term': 'Histone Deacetylation (GO:0016575)', 'p_value': 0.00011250476197410829, 'odds_ratio': 167.7058823529412, 'genes': ['HDAC3', 'SIRT1']}]
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': 'Protein Deacylation (GO:0035601)', 'p_value': 7.154717101473363e-08, 'odds_ratio': 587.4705882352941, 'genes': ['HDAC3', 'SIRT1', 'SIRT3']}, {'rank': 2, 'term': 'Protein Deacetylation (GO:0006476)', 'p_value': 6.173082690121319e-07, 'odds_ratio': 269.64864864864865, 'genes': ['HDAC3', 'SIRT1', 'SIRT3']}, {'rank': 3, 'term': 'Positive Regulation Of Transcription By RNA Polymerase II (GO:0045944)', 'p_value': 7.790433066335926e-07, 'odds_ratio': 40.89914163090129, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}, {'rank': 4, 'term': 'Peptidyl-Lysine Deacetylation (GO:0034983)', 'p_value': 3.7754993322284675e-06, 'odds_ratio': 1142.057142857143, 'genes': ['SIRT1', 'SIRT3']}, {'rank': 5, 'term': 'Positive Regulation Of DNA-templated Transcription (GO:0045893)', 'p_value': 4.065006033168612e-06, 'odds_ratio': 30.321746160064674, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}, {'rank': 6, 'term': 'Negative Regulation Of Androgen Receptor Signaling Pathway (GO:0060766)', 'p_value': 1.633405632897404e-05, 'odds_ratio': 475.6904761904762, 'genes': ['SIRT1', 'SMARCA4']}, {'rank': 7, 'term': 'Regulation Of Androgen Receptor Signaling Pathway (GO:0060765)', 'p_value': 6.281272926601724e-05, 'odds_ratio': 228.18285714285713, 'genes': ['SIRT1', 'SMARCA4']}, {'rank': 8, 'term': 'Regulation Of Transcription By RNA Polymerase II (GO:0006357)', 'p_value': 6.91357556918871e-05, 'odds_ratio': 17.773491592482692, 'genes': ['HDAC3', 'NAMPT', 'TET2', 'SIRT1', 'BRD4', 'SMARCA4']}]
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': 'SIRT1', 'protein2': 'SMARCA4', 'score': 0.422, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.423}, {'protein1': 'SIRT1', 'protein2': 'BRD4', 'score': 0.578, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.255}, {'protein1': 'POU5F1', 'protein2': 'SMARCA4', 'score': 0.57, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.57}, {'protein1': 'BRD4', 'protein2': 'SMARCA4', 'score': 0.709, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.487}, {'protein1': 'HDAC3', 'protein2': 'HDAC9', 'score': 0.511, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.137}, {'protein1': 'SMARCA4', 'protein2': 'HDAC9', 'score': 0.893, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.856}]
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': 'SIRT1', 'protein2': 'SMARCA4', 'score': 0.422, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.423}, {'protein1': 'SIRT1', 'protein2': 'BRD4', 'score': 0.578, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.255}, {'protein1': 'POU5F1', 'protein2': 'SMARCA4', 'score': 0.57, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.57}, {'protein1': 'BRD4', 'protein2': 'SMARCA4', 'score': 0.709, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.487}, {'protein1': 'HDAC3', 'protein2': 'HDAC9', 'score': 0.511, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0, 'tscore': 0.137}, {'protein1': 'SMARCA4', 'protein2': 'HDAC9', 'score': 0.893, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.856}]
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': 'BRD4', 'n_pathways': 1, 'top_pathway': 'Potential therapeutics for SARS'}, {'gene': 'HDAC', 'n_pathways': 0, 'top_pathway': '—'}, {'gene': 'HDAC3', 'n_pathways': 8, 'top_pathway': 'p75NTR negatively regulates cell cycle via SC1'}, {'gene': 'NAMPT', 'n_pathways': 3, 'top_pathway': 'BMAL1:CLOCK,NPAS2 activates circadian expression'}, {'gene': 'OCT4', 'n_pathways': 7, 'top_pathway': 'POU5F1 (OCT4), SOX2, NANOG repress genes related to differentiation'}, {'gene': 'SIRT1', 'n_pathways': 8, 'top_pathway': 'Regulation of HSF1-mediated heat shock response'}, {'gene': 'SIRT3', 'n_pathways': 5, 'top_pathway': 'Transcriptional activation of mitochondrial biogenesis'}, {'gene': 'SMARCA4', 'n_pathways': 8, 'top_pathway': 'Interleukin-7 signaling'}, {'gene': 'TET2', 'n_pathways': 2, 'top_pathway': 'TET1,2,3 and TDG demethylate DNA'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Nutrient-Sensing Epigenetic Circuit Reactivation', 0.969), ('Chromatin Remodeling-Mediated Nutrient Sensing Restorat', 0.914), ('Selective HDAC3 Inhibition with Cognitive Enhancement', 0.779), ('Chromatin Accessibility Restoration via BRD4 Modulation', 0.768), ('Metabolic NAD+ Salvage Pathway Enhancement Through NAMP', 0.745), ('Astrocyte-Mediated Neuronal Epigenetic Rescue', 0.725), ('Mitochondrial-Nuclear Epigenetic Cross-Talk Restoration', 0.701), ('Partial Neuronal Reprogramming via Modified Yamanaka Co', 0.672), ('Temporal TET2-Mediated Hydroxymethylation Cycling', 0.657)]
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('Epigenetic reprogramming in aging neurons')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Nutrient-Sensing Epigenetic Circuit Reac', 'Chromatin Remodeling-Mediated Nutrient S', 'Selective HDAC3 Inhibition with Cognitiv', 'Chromatin Accessibility Restoration via ', 'Metabolic NAD+ Salvage Pathway Enhanceme', 'Astrocyte-Mediated Neuronal Epigenetic R', 'Mitochondrial-Nuclear Epigenetic Cross-T', 'Partial Neuronal Reprogramming via Modif', 'Temporal TET2-Mediated Hydroxymethylatio']
matrix = np.array([[0.7, 0.95, 0.85, 0.9, 0.115, 0.9, 0.85, 0.9, 0.8], [0.72, 0.92, 0.82, 0.9, 0.115, 0.9, 0.85, 0.9, 0.8], [0.85, 0.7, 0.8, 0.75, 0.062, 0.75, 0.7, 0.75, 0.55], [0.9, 0.6, 0.7, 0.65, 0.13, 0.7, 0.65, 0.95, 0.35], [0.68, 0.84, 0.77, 0.9, 0.115, 0.9, 0.85, 0.9, 0.8], [0.95, 0.4, 0.75, 0.7, 0.135, 0.6, 0.5, 0.3, 0.4], [0.85, 0.5, 0.65, 0.6, 0.4, 0.65, 0.55, 0.5, 0.6], [0.95, 0.2, 0.8, 0.4, 0.42, 0.55, 0.35, 0.15, 0.25], [0.95, 0.25, 0.7, 0.55, 0.26, 0.6, 0.45, 0.2, 0.45]])
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-4bb7fd8c')

print('No PubMed results for hypothesis h-var-a09491064e')

print('No PubMed results for hypothesis h-0e675a41')

lit_data = [{'year': '2025', 'journal': 'Eur J Med Chem', 'title': 'Discovery of 4,5-dihydro-benzo[g]indazole-based hydroxamic acids as HDAC3/BRD4 d', 'pmid': '39764880'}, {'year': '2019', 'journal': 'Bioorg Chem', 'title': 'Design, synthesis and biological evaluation of novel indole derivatives as poten', 'pmid': '30554080'}, {'year': '2019', 'journal': 'J Neurosci', 'title': 'Enhancement of BDNF Expression and Memory by HDAC Inhibition Requires BET Bromod', 'pmid': '30504275'}]
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-var-159030513d')

print('No PubMed results for hypothesis h-8fe389e8')

print('No PubMed results for hypothesis h-0e614ae4')

print('No PubMed results for hypothesis h-baba5269')

print('No PubMed results for hypothesis h-a90e2e89')