import pandas as pd
ann_rows = [{'gene': 'C1QA', 'name': 'complement C1q A chain', 'summary': 'This gene encodes the A-chain polypeptide of serum complement subcomponent C1q, which associates with C1r and C1s to yie'}, {'gene': 'C1QB', 'name': 'complement C1q B chain', 'summary': 'This gene encodes the B-chain polypeptide of serum complement subcomponent C1q, which associates with C1r and C1s to yie'}, {'gene': 'C3', 'name': 'complement C3', 'summary': 'Complement component C3 plays a central role in the activation of complement system. Its activation is required for both'}, {'gene': 'IL1B', 'name': 'interleukin 1 beta', 'summary': 'The protein encoded by this gene is a member of the interleukin 1 cytokine family. This cytokine is produced by activate'}, {'gene': 'NFKB1', 'name': 'nuclear factor kappa B subunit 1', 'summary': 'This gene encodes a 105 kD protein which can undergo cotranslational processing by the 26S proteasome to produce a 50 kD'}, {'gene': 'PLCG2', 'name': 'phospholipase C gamma 2', 'summary': 'The protein encoded by this gene is a transmembrane signaling enzyme that catalyzes the conversion of 1-phosphatidyl-1D-'}, {'gene': 'SYK', 'name': 'spleen associated tyrosine kinase', 'summary': 'This gene encodes a member of the family of non-receptor type Tyr protein kinases. This protein is widely expressed in h'}, {'gene': 'TREM2', 'name': 'triggering receptor expressed on myeloid cells 2', 'summary': 'This gene encodes a membrane protein that forms a receptor signaling complex with the TYRO protein tyrosine kinase bindi'}, {'gene': 'TYROBP', 'name': 'transmembrane immune signaling adaptor TYROBP', 'summary': 'This gene encodes a transmembrane signaling polypeptide which contains an immunoreceptor tyrosine-based activation motif'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Regulation Of Interleukin-6 Production (GO:0032675)', 'p_value': 1.0048399935913338e-12, 'odds_ratio': 162.55373831775702, 'genes': ['SYK', 'IL1B', 'SIRPA', 'PTPN11', 'TREM2', 'PTPN6', 'CD47']}, {'rank': 2, 'term': 'Regulation Of Phagocytosis (GO:0050764)', 'p_value': 5.048610594157601e-10, 'odds_ratio': 188.03773584905662, 'genes': ['SYK', 'IL1B', 'SIRPA', 'TREM2', 'CD47']}, {'rank': 3, 'term': 'Regulation Of ERK1 And ERK2 Cascade (GO:0070372)', 'p_value': 1.415343656859335e-08, 'odds_ratio': 55.31372549019608, 'genes': ['SYK', 'IL1B', 'SIRPA', 'PTPN11', 'TREM2', 'PTPN6']}, {'rank': 4, 'term': 'Synapse Pruning (GO:0098883)', 'p_value': 1.9067019051840425e-08, 'odds_ratio': 999.0, 'genes': ['C1QB', 'TREM2', 'C1QC']}, {'rank': 5, 'term': 'Regulation Of Tumor Necrosis Factor Production (GO:0032680)', 'p_value': 2.7217119623639505e-08, 'odds_ratio': 81.40573770491804, 'genes': ['SYK', 'SIRPA', 'PTPN11', 'PTPN6', 'CD47']}, {'rank': 6, 'term': 'Cellular Response To Cytokine Stimulus (GO:0071345)', 'p_value': 5.6575802607493816e-08, 'odds_ratio': 43.450331125827816, 'genes': ['IL1B', 'SIRPA', 'PTPN11', 'PTPN6', 'CD47', 'SIRT1']}, {'rank': 7, 'term': 'Positive Regulation Of Phagocytosis (GO:0050766)', 'p_value': 9.742769899857603e-08, 'odds_ratio': 129.4090909090909, 'genes': ['IL1B', 'SIRPA', 'TREM2', 'CD47']}, {'rank': 8, 'term': 'Positive Regulation Of Endocytosis (GO:0045807)', 'p_value': 2.9769516535686854e-07, 'odds_ratio': 96.53333333333333, 'genes': ['IL1B', 'SIRPA', 'TREM2', 'CD47']}, {'rank': 9, 'term': 'Cytokine-Mediated Signaling Pathway (GO:0019221)', 'p_value': 9.108569513553911e-07, 'odds_ratio': 39.15277777777778, 'genes': ['SYK', 'IL1B', 'PTPN11', 'PTPN6', 'SIRT1']}, {'rank': 10, 'term': 'Negative Regulation Of Inflammatory Response (GO:0050728)', 'p_value': 1.1700096460875274e-06, 'odds_ratio': 67.55480033984706, 'genes': ['SYK', 'SIRPA', 'TREM2', 'PTPN6']}]
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-6 Production (GO:0032675)', 'p_value': 1.0048399935913338e-12, 'odds_ratio': 162.55373831775702, 'genes': ['SYK', 'IL1B', 'SIRPA', 'PTPN11', 'TREM2', 'PTPN6', 'CD47']}, {'rank': 2, 'term': 'Regulation Of Phagocytosis (GO:0050764)', 'p_value': 5.048610594157601e-10, 'odds_ratio': 188.03773584905662, 'genes': ['SYK', 'IL1B', 'SIRPA', 'TREM2', 'CD47']}, {'rank': 3, 'term': 'Regulation Of ERK1 And ERK2 Cascade (GO:0070372)', 'p_value': 1.415343656859335e-08, 'odds_ratio': 55.31372549019608, 'genes': ['SYK', 'IL1B', 'SIRPA', 'PTPN11', 'TREM2', 'PTPN6']}, {'rank': 4, 'term': 'Synapse Pruning (GO:0098883)', 'p_value': 1.9067019051840425e-08, 'odds_ratio': 999.0, 'genes': ['C1QB', 'TREM2', 'C1QC']}, {'rank': 5, 'term': 'Regulation Of Tumor Necrosis Factor Production (GO:0032680)', 'p_value': 2.7217119623639505e-08, 'odds_ratio': 81.40573770491804, 'genes': ['SYK', 'SIRPA', 'PTPN11', 'PTPN6', 'CD47']}, {'rank': 6, 'term': 'Cellular Response To Cytokine Stimulus (GO:0071345)', 'p_value': 5.6575802607493816e-08, 'odds_ratio': 43.450331125827816, 'genes': ['IL1B', 'SIRPA', 'PTPN11', 'PTPN6', 'CD47', 'SIRT1']}, {'rank': 7, 'term': 'Positive Regulation Of Phagocytosis (GO:0050766)', 'p_value': 9.742769899857603e-08, 'odds_ratio': 129.4090909090909, 'genes': ['IL1B', 'SIRPA', 'TREM2', 'CD47']}, {'rank': 8, 'term': 'Positive Regulation Of Endocytosis (GO:0045807)', 'p_value': 2.9769516535686854e-07, 'odds_ratio': 96.53333333333333, 'genes': ['IL1B', 'SIRPA', 'TREM2', 'CD47']}]
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': 'CRP', 'protein2': 'FCGR1A', 'score': 0.434, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.434}, {'protein1': 'CRP', 'protein2': 'C1QC', 'score': 0.499, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CRP', 'protein2': 'C1QA', 'score': 0.63, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CRP', 'protein2': 'C1QB', 'score': 0.689, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.405, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'C1QB', 'protein2': 'C1QA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.967, 'dscore': 0.9, 'tscore': 0.981}, {'protein1': 'C1QB', 'protein2': 'C1QC', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.92, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'CD47', 'protein2': 'PTPN6', 'score': 0.499, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CD47', 'protein2': 'TREM2', 'score': 0.539, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.539}, {'protein1': 'CD47', 'protein2': 'PTPN11', 'score': 0.674, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.375}, {'protein1': 'CD47', 'protein2': 'SIRPA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.939, 'dscore': 0.9, 'tscore': 0.986}, {'protein1': 'FCGR1A', 'protein2': 'SYK', 'score': 0.964, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.4, 'dscore': 0.9, 'tscore': 0.457}, {'protein1': 'TREM2', 'protein2': 'SIRPA', 'score': 0.91, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.141}, {'protein1': 'TREM2', 'protein2': 'SYK', 'score': 0.929, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.323}, {'protein1': 'C1QC', 'protein2': 'C1QA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.96, 'dscore': 0.9, 'tscore': 0.981}, {'protein1': 'SYK', 'protein2': 'PTPN6', 'score': 0.825, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0.36, 'tscore': 0.538}, {'protein1': 'SYK', 'protein2': 'SIRPA', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'PTPN11', 'score': 0.945, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.479}, {'protein1': 'PTPN6', 'protein2': 'SIRPA', 'score': 0.845, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.618, 'dscore': 0.5, 'tscore': 0.254}, {'protein1': 'PTPN6', 'protein2': 'PTPN11', 'score': 0.947, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.079, 'dscore': 0.9, 'tscore': 0.474}, {'protein1': 'SIRPA', 'protein2': 'PTPN11', 'score': 0.996, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.677, 'dscore': 0.5, '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': 'CRP', 'protein2': 'FCGR1A', 'score': 0.434, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.434}, {'protein1': 'CRP', 'protein2': 'C1QC', 'score': 0.499, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CRP', 'protein2': 'C1QA', 'score': 0.63, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CRP', 'protein2': 'C1QB', 'score': 0.689, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.405, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'C1QB', 'protein2': 'C1QA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.967, 'dscore': 0.9, 'tscore': 0.981}, {'protein1': 'C1QB', 'protein2': 'C1QC', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.92, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'CD47', 'protein2': 'PTPN6', 'score': 0.499, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0}, {'protein1': 'CD47', 'protein2': 'TREM2', 'score': 0.539, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.539}, {'protein1': 'CD47', 'protein2': 'PTPN11', 'score': 0.674, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.375}, {'protein1': 'CD47', 'protein2': 'SIRPA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.939, 'dscore': 0.9, 'tscore': 0.986}, {'protein1': 'FCGR1A', 'protein2': 'SYK', 'score': 0.964, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.4, 'dscore': 0.9, 'tscore': 0.457}, {'protein1': 'TREM2', 'protein2': 'SIRPA', 'score': 0.91, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.141}, {'protein1': 'TREM2', 'protein2': 'SYK', 'score': 0.929, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.323}, {'protein1': 'C1QC', 'protein2': 'C1QA', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.96, 'dscore': 0.9, 'tscore': 0.981}, {'protein1': 'SYK', 'protein2': 'PTPN6', 'score': 0.825, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.457, 'dscore': 0.36, 'tscore': 0.538}, {'protein1': 'SYK', 'protein2': 'SIRPA', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'PTPN11', 'score': 0.945, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0.479}, {'protein1': 'PTPN6', 'protein2': 'SIRPA', 'score': 0.845, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.618, 'dscore': 0.5, 'tscore': 0.254}, {'protein1': 'PTPN6', 'protein2': 'PTPN11', 'score': 0.947, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.079, 'dscore': 0.9, 'tscore': 0.474}, {'protein1': 'SIRPA', 'protein2': 'PTPN11', 'score': 0.996, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.677, 'dscore': 0.5, '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': 'C1QA', 'n_pathways': 3, 'top_pathway': 'Initial triggering of complement'}, {'gene': 'C1QB', 'n_pathways': 3, 'top_pathway': 'Initial triggering of complement'}, {'gene': 'C3', 'n_pathways': 8, 'top_pathway': 'Alternative complement activation'}, {'gene': 'IL1B', 'n_pathways': 7, 'top_pathway': 'Interleukin-1 processing'}, {'gene': 'NFKB1', 'n_pathways': 8, 'top_pathway': 'Activation of NF-kappaB in B cells'}, {'gene': 'PLCG2', 'n_pathways': 8, 'top_pathway': 'GPVI-mediated activation cascade'}, {'gene': 'SYK', 'n_pathways': 8, 'top_pathway': 'GPVI-mediated activation cascade'}, {'gene': 'TREM2', 'n_pathways': 4, 'top_pathway': 'Immunoregulatory interactions between a Lymphoid and a non-Lymphoid ce'}, {'gene': 'TYROBP', 'n_pathways': 6, 'top_pathway': 'Immunoregulatory interactions between a Lymphoid and a non-Lymphoid ce'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('Complement-SASP Amplification Cascade as Mechanistic Li', 0.741), ('TREM2 Agonism to Restore Microglial Phagocytosis Across', 0.735)]
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('Why have anti-Aβ clinical trials failed despite the established role of Aβ in AD pathogenesis?')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['Complement-SASP Amplification Cascade as', 'TREM2 Agonism to Restore Microglial Phag']
matrix = np.array([[0.75, 0.55, 0.8, 0.78, 0.0, 0.6, 0.65, 0.68, 0.42], [0.8, 0.45, 0.85, 0.82, 0.0, 0.68, 0.7, 0.48, 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-f4a63646')

print('No PubMed results for hypothesis h-15a8468c')