import pandas as pd
ann_rows = [{'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'}]
pd.DataFrame(ann_rows)

go_bp = [{'rank': 1, 'term': 'Chemokine (C-X-C Motif) Ligand 12 Signaling Pathway (GO:0038146)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 2, 'term': 'Negative Regulation Of Sequestering Of Triglyceride (GO:0010891)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 3, 'term': 'Negative Regulation Of Toll-Like Receptor 2 Signaling Pathway (GO:0034136)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 4, 'term': 'Regulation Of Resting Membrane Potential (GO:0060075)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 5, 'term': 'Positive Regulation Of Lipoprotein Particle Clearance (GO:0010986)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 6, 'term': 'Regulation Of Fat Cell Proliferation (GO:0070344)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 7, 'term': 'Negative Regulation Of Astrocyte Differentiation (GO:0048712)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 8, 'term': 'Positive Regulation Of Microglial Cell Activation (GO:1903980)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 9, 'term': 'Positive Regulation Of Microglial Cell Migration (GO:1904141)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 10, 'term': 'Positive Regulation Of Amyloid-Beta Clearance (GO:1900223)', 'p_value': 0.0002999905873105514, 'odds_ratio': 19994.0, 'genes': ['TREM2']}]
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': 'Chemokine (C-X-C Motif) Ligand 12 Signaling Pathway (GO:0038146)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 2, 'term': 'Negative Regulation Of Sequestering Of Triglyceride (GO:0010891)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 3, 'term': 'Negative Regulation Of Toll-Like Receptor 2 Signaling Pathway (GO:0034136)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 4, 'term': 'Regulation Of Resting Membrane Potential (GO:0060075)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 5, 'term': 'Positive Regulation Of Lipoprotein Particle Clearance (GO:0010986)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 6, 'term': 'Regulation Of Fat Cell Proliferation (GO:0070344)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 7, 'term': 'Negative Regulation Of Astrocyte Differentiation (GO:0048712)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}, {'rank': 8, 'term': 'Positive Regulation Of Microglial Cell Activation (GO:1903980)', 'p_value': 0.0002499917995416556, 'odds_ratio': 19995.0, 'genes': ['TREM2']}]
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': 'APOE', 'protein2': 'TREM2', 'score': 0.986, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.514, 'dscore': 0, 'tscore': 0.974}, {'protein1': 'APOE', 'protein2': 'CLU', 'score': 0.991, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.72, 'tscore': 0.971}, {'protein1': 'TYROBP', 'protein2': 'SIRPA', 'score': 0.8, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.8, 'tscore': 0}, {'protein1': 'TYROBP', 'protein2': 'SIRPG', 'score': 0.8, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.8, 'tscore': 0}, {'protein1': 'TYROBP', 'protein2': 'TREM2', 'score': 0.998, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.526, 'dscore': 0.8, 'tscore': 0.982}, {'protein1': 'TYROBP', 'protein2': 'SYK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.886, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'FCER1G', 'protein2': 'IGKV1-33', 'score': 0.52, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.081}, {'protein1': 'FCER1G', 'protein2': 'IGKV1D-33', 'score': 0.52, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.081}, {'protein1': 'FCER1G', 'protein2': 'TREM2', 'score': 0.977, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.977}, {'protein1': 'FCER1G', 'protein2': 'SYK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.886, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'SIRPG', 'protein2': 'TREM2', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SIRPG', 'protein2': 'SYK', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SIRPG', 'protein2': 'SIRPA', 'score': 0.966, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.495, 'dscore': 0.9, 'tscore': 0.397}, {'protein1': 'CLU', 'protein2': 'TREM2', 'score': 0.954, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.938}, {'protein1': 'TREM2', 'protein2': 'IGHV3-16', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'protein1': 'TREM2', 'protein2': 'IGKV1-33', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'protein1': 'TREM2', 'protein2': 'IGKV1D-33', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'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': 'SYK', 'protein2': 'IGKV1-33', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.4, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'IGKV1D-33', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.4, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'SIRPA', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'IGHV3-16', 'protein2': 'IGKV1-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'IGHV3-16', 'protein2': 'IGKV1D-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'IGKV1-33', 'protein2': 'IGKV1D-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, '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': 'APOE', 'protein2': 'TREM2', 'score': 0.986, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.514, 'dscore': 0, 'tscore': 0.974}, {'protein1': 'APOE', 'protein2': 'CLU', 'score': 0.991, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.72, 'tscore': 0.971}, {'protein1': 'TYROBP', 'protein2': 'SIRPA', 'score': 0.8, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.8, 'tscore': 0}, {'protein1': 'TYROBP', 'protein2': 'SIRPG', 'score': 0.8, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.8, 'tscore': 0}, {'protein1': 'TYROBP', 'protein2': 'TREM2', 'score': 0.998, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.526, 'dscore': 0.8, 'tscore': 0.982}, {'protein1': 'TYROBP', 'protein2': 'SYK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.886, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'FCER1G', 'protein2': 'IGKV1-33', 'score': 0.52, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.081}, {'protein1': 'FCER1G', 'protein2': 'IGKV1D-33', 'score': 0.52, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.5, 'tscore': 0.081}, {'protein1': 'FCER1G', 'protein2': 'TREM2', 'score': 0.977, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0, 'tscore': 0.977}, {'protein1': 'FCER1G', 'protein2': 'SYK', 'score': 0.999, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.886, 'dscore': 0.9, 'tscore': 0.982}, {'protein1': 'SIRPG', 'protein2': 'TREM2', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SIRPG', 'protein2': 'SYK', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'SIRPG', 'protein2': 'SIRPA', 'score': 0.966, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.495, 'dscore': 0.9, 'tscore': 0.397}, {'protein1': 'CLU', 'protein2': 'TREM2', 'score': 0.954, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.292, 'dscore': 0, 'tscore': 0.938}, {'protein1': 'TREM2', 'protein2': 'IGHV3-16', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'protein1': 'TREM2', 'protein2': 'IGKV1-33', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'protein1': 'TREM2', 'protein2': 'IGKV1D-33', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0, 'tscore': 0}, {'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': 'SYK', 'protein2': 'IGKV1-33', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.4, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'IGKV1D-33', 'score': 0.4, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.4, 'tscore': 0}, {'protein1': 'SYK', 'protein2': 'SIRPA', 'score': 0.9, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0, 'dscore': 0.9, 'tscore': 0}, {'protein1': 'IGHV3-16', 'protein2': 'IGKV1-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'IGHV3-16', 'protein2': 'IGKV1D-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, 'tscore': 0}, {'protein1': 'IGKV1-33', 'protein2': 'IGKV1D-33', 'score': 0.952, 'nscore': 0, 'fscore': 0, 'pscore': 0, 'ascore': 0, 'escore': 0.9, 'dscore': 0.54, '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': 'TREM2', 'n_pathways': 4, 'top_pathway': 'Immunoregulatory interactions between a Lymphoid and a non-Lymphoid ce'}]
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)

hyp_data = [('TREM2-Mediated Microglial Checkpoint Therapy', 0.534)]
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("Cell type vulnerability in Alzheimer's Disease (SEA-AD data)")
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()

labels = ['TREM2-Mediated Microglial Checkpoint The']
matrix = np.array([[0.8, 0.7, 0.6, 0.7, 0.0, 0.7, 0.6, 0.8, 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')

lit_data = [{'year': '2021', 'journal': 'Mech Ageing Dev', 'title': "TREM2, microglia, and Alzheimer's disease.", 'pmid': '33516818'}, {'year': '2023', 'journal': 'Semin Immunol', 'title': 'TREM2: A new player in the tumor microenvironment.', 'pmid': '36989543'}, {'year': '2017', 'journal': 'Cell', 'title': "TREM2 Maintains Microglial Metabolic Fitness in Alzheimer's Disease.", 'pmid': '28802038'}, {'year': '2017', 'journal': 'Trends Mol Med', 'title': 'TREM2, Microglia, and Neurodegenerative Diseases.', 'pmid': '28442216'}, {'year': '2024', 'journal': 'Neuropharmacology', 'title': 'Microglia and TREM2.', 'pmid': '38821351'}]
if lit_data:
    df = pd.DataFrame(lit_data)
    print(f'{len(lit_data)} PubMed results')
    display(df)
else:
    print('No PubMed results')