Circuit-level neural dynamics in neurodegeneration¶
Notebook ID: nb-SDA-2026-04-03-26abc5e5f9f2 · Analysis: SDA-2026-04-03-26abc5e5f9f2 · Generated: 2026-04-10
Research question¶
Analyze circuit-level changes in neurodegeneration using Allen Institute Neural Dynamics data. Focus on: (1) hippocampal circuit disruption, (2) cortical dynamics alterations, (3) sensory processing changes. Identify circuit-based therapeutic targets connecting genes, proteins, and brain regions to neurodegeneration phenotypes.
Approach¶
This notebook is generated programmatically from real Forge tool calls and SciDEX debate data. Code cells load cached evidence bundles from data/forge_cache/seaad/*.json and query live data from scidex.db. Re-run python3 scripts/regenerate_notebooks.py --analysis SDA-2026-04-03-26abc5e5f9f2 --force to refresh.
34 hypotheses were generated and debated. The knowledge graph has 95 edges.
Debate Summary¶
Quality score: 0.59 · Rounds: 4 · Personas: Theorist, Skeptic, Domain_Expert, Synthesizer
1. Forge tool provenance¶
import json, sys, sqlite3
from pathlib import Path
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
matplotlib.rcParams['figure.dpi'] = 110
matplotlib.rcParams['figure.facecolor'] = 'white'
REPO = Path('.').resolve()
sys.path.insert(0, str(REPO))
CACHE_SUB = 'seaad'
CACHE = REPO / 'data' / 'forge_cache' / CACHE_SUB
def load(name):
p = CACHE / f'{name}.json'
if p.exists():
return json.loads(p.read_text())
return {}
db_path = Path('/home/ubuntu/scidex/scidex.db')
try:
db = sqlite3.connect(str(db_path))
prov = pd.read_sql_query('''
SELECT skill_id, status, COUNT(*) AS n_calls,
ROUND(AVG(duration_ms),0) AS mean_ms
FROM tool_calls
WHERE created_at >= date('now','-30 days')
GROUP BY skill_id, status
ORDER BY n_calls DESC
''', db)
db.close()
prov['tool'] = prov['skill_id'].str.replace('tool_', '', regex=False)
print(f'{len(prov)} tool-call aggregates (last 30 days):')
prov[['tool','status','n_calls','mean_ms']].head(20)
except Exception as e:
print(f'Provenance unavailable: {e}')
77 tool-call aggregates (last 30 days):
2. Target gene annotations¶
ann_rows = []
for g in ['BDNF', 'CHAT', 'MAPT', 'PVALB', 'SST', 'VIP']:
mg = load(f'mygene_{g}')
hpa = load(f'hpa_{g}')
if not mg and not hpa:
ann_rows.append({'gene': g, 'name': '—', 'protein_class': '—',
'disease_involvement': '—'})
continue
ann_rows.append({
'gene': g,
'name': (mg.get('name') or '')[:55],
'protein_class': ', '.join((hpa.get('protein_class') or [])[:2])[:55]
if isinstance(hpa.get('protein_class'), list)
else str(hpa.get('protein_class') or '—')[:55],
'disease_involvement': ', '.join((hpa.get('disease_involvement') or [])[:2])[:55]
if isinstance(hpa.get('disease_involvement'), list)
else str(hpa.get('disease_involvement') or '')[:55],
})
pd.DataFrame(ann_rows)
| gene | name | protein_class | disease_involvement | |
|---|---|---|---|---|
| 0 | BDNF | — | — | — |
| 1 | CHAT | — | — | — |
| 2 | MAPT | microtubule associated protein tau | — | |
| 3 | PVALB | — | — | — |
| 4 | SST | — | — | — |
| 5 | VIP | — | — | — |
3. GO Biological Process enrichment (Enrichr)¶
go_bp = load('enrichr_GO_Biological_Process')
if isinstance(go_bp, list) and go_bp:
go_df = pd.DataFrame(go_bp[:10])[['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']]
else:
print('No GO:BP enrichment data')
# Visualize top GO BP enrichment
go_bp = load('enrichr_GO_Biological_Process')
if isinstance(go_bp, list) and go_bp:
top = go_bp[:8]
terms = [t['term'][:45] for t in top][::-1]
neglogp = [-np.log10(max(t['p_value'], 1e-300)) for t in top][::-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()
else:
print('No GO:BP data to plot')
4. KEGG pathway enrichment¶
kegg = load('enrichr_KEGG_Pathways')
if isinstance(kegg, list) and kegg:
kegg_df = pd.DataFrame(kegg[:10])[['term','p_value','odds_ratio','genes']]
kegg_df['genes'] = kegg_df['genes'].apply(lambda g: ', '.join(g))
kegg_df['p_value'] = kegg_df['p_value'].apply(lambda p: f'{p:.2e}')
kegg_df['odds_ratio'] = kegg_df['odds_ratio'].round(1)
kegg_df
else:
print('No KEGG enrichment data')
No KEGG enrichment data
5. STRING protein interaction network¶
ppi = load('string_network')
if isinstance(ppi, list) and ppi:
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)
else:
print('No STRING edges returned')
11 STRING edges
# Network figure
ppi = load('string_network')
if isinstance(ppi, list) and ppi:
import math
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['score'],
linewidth=0.5+2*e['score'])
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()
else:
print('No STRING data to visualize')
6. Reactome pathway footprint¶
pw_rows = []
for g in ['BDNF', 'CHAT', 'MAPT', 'PVALB', 'SST', 'VIP']:
pws = load(f'reactome_{g}')
if isinstance(pws, list):
pw_rows.append({'gene': g, 'n_pathways': len(pws),
'top_pathway': (pws[0]['name'] if pws else '—')[:70]})
else:
pw_rows.append({'gene': g, 'n_pathways': 0, 'top_pathway': '—'})
pd.DataFrame(pw_rows).sort_values('n_pathways', ascending=False)
| gene | n_pathways | top_pathway | |
|---|---|---|---|
| 2 | MAPT | 3 | Caspase-mediated cleavage of cytoskeletal prot... |
| 0 | BDNF | 0 | — |
| 1 | CHAT | 0 | — |
| 3 | PVALB | 0 | — |
| 4 | SST | 0 | — |
| 5 | VIP | 0 | — |
7. Allen Brain Atlas ISH regional expression¶
ish_rows = []
for g in ['BDNF', 'CHAT', 'MAPT', 'PVALB', 'SST', 'VIP']:
ish = load(f'allen_ish_{g}')
regions = ish.get('regions') or [] if isinstance(ish, dict) else []
ish_rows.append({
'gene': g,
'n_ish_regions': len(regions),
'top_region': (regions[0].get('structure','') if regions else '—')[:45],
'top_energy': round(regions[0].get('expression_energy',0), 2) if regions else None,
})
pd.DataFrame(ish_rows)
| gene | n_ish_regions | top_region | top_energy | |
|---|---|---|---|---|
| 0 | BDNF | 0 | — | — |
| 1 | CHAT | 0 | — | — |
| 2 | MAPT | 0 | — | — |
| 3 | PVALB | 0 | — | — |
| 4 | SST | 0 | — | — |
| 5 | VIP | 0 | — | — |
8. Hypothesis ranking (34 hypotheses)¶
hyp_data = [('Glymphatic-Mediated Tau Clearance Dysfunction', 0.633), ('Microglial-Mediated Tau Clearance Dysfunction via TREM2', 0.628), ('Dual-Circuit Tau Vulnerability Cascade', 0.625), ('Thalamocortical Synchrony Restoration via NMDA Modulati', 0.622), ('Closed-loop transcranial focused ultrasound to restore ', 0.62), ('Locus Coeruleus-Hippocampal Circuit Protection', 0.611), ('Closed-loop focused ultrasound targeting EC-II SST inte', 0.606), ('Closed-loop tACS targeting EC-II parvalbumin interneuro', 0.598), ('Closed-loop transcranial focused ultrasound targeting E', 0.593), ('Closed-loop tACS targeting EC-II PV interneurons to sup', 0.591), ('Closed-loop focused ultrasound targeting CA1 PV interne', 0.587), ('Cholinergic Basal Forebrain-Hippocampal Circuit Protect', 0.586), ('Gamma entrainment therapy to restore hippocampal-cortic', 0.584), ('Closed-loop tACS targeting EC-II SST interneurons to bl', 0.582), ('Closed-loop transcranial alternating current stimulatio', 0.58), ('Hippocampal CA3-CA1 synaptic rescue via DHHC2-mediated ', 0.573), ('Default Mode Network Circuit Stabilization', 0.571), ('Optogenetic restoration of hippocampal gamma oscillatio', 0.567), ('Dopaminergic Ventral Tegmental-Hippocampal Circuit Prot', 0.556), ('Closed-loop focused ultrasound targeting EC-II PV inter', 0.552), ('Glymphatic-Cholinergic Tau Clearance Cascade', 0.552), ('Optogenetic restoration of hippocampal gamma oscillatio', 0.552), ('Hippocampal CA3-CA1 circuit rescue via neurogenesis and', 0.55), ('CaMKII-Dependent Synaptic Circuit Amplification', 0.549), ('Real-time gamma-guided transcranial focused ultrasound ', 0.538), ('Closed-loop tACS targeting entorhinal cortex layer II S', 0.529), ('Optogenetic viral vector delivery via tFUS-mediated blo', 0.521), ('Beta-frequency entrainment therapy targeting PV interne', 0.516), ('Closed-loop tACS targeting EC-II PV interneurons to enh', 0.513), ('Prefrontal sensory gating circuit restoration via PV in', 0.509), ('Dual-Circuit Tau Vulnerability Cascade with Glial-Media', 0.506), ('Sensory-Motor Circuit Cross-Modal Compensation', 0.5), ('Closed-loop transcranial focused ultrasound targeting C', 0.5), ('Differential Interneuron Optogenetic Restoration Therap', 0.498)]
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('Circuit-level neural dynamics in neurodegeneration')
ax.grid(axis='x', alpha=0.3)
plt.tight_layout(); plt.show()
9. Score dimension heatmap (top 10)¶
labels = ['Glymphatic-Mediated Tau Clearance Dysfun', 'Microglial-Mediated Tau Clearance Dysfun', 'Dual-Circuit Tau Vulnerability Cascade', 'Thalamocortical Synchrony Restoration vi', 'Closed-loop transcranial focused ultraso', 'Locus Coeruleus-Hippocampal Circuit Prot', 'Closed-loop focused ultrasound targeting', 'Closed-loop tACS targeting EC-II parvalb', 'Closed-loop transcranial focused ultraso', 'Closed-loop tACS targeting EC-II PV inte']
matrix = np.array([[0.85, 0.68, 0.78, 0.8, 0, 0.7, 0.63, 0.45, 0.65], [0.65, 0.7, 0.85, 0.8, 0, 0.8, 0.65, 0.6, 0.55], [0.7, 0.65, 0.72, 0.8, 0, 0.7, 0.68, 0.45, 0.6], [0.7, 0.9, 0.7, 0.75, 0, 0.7, 0.75, 0.95, 0.75], [0.8, 0.88, 0.82, 0.85, 0.322, 0.85, 0.82, 0.75, 0.9], [0.75, 0.5, 0.85, 0.8, 0, 0.65, 0.6, 0.6, 0.55], [0.79, 0.87, 0.81, 0.85, 0.322, 0.85, 0.82, 0.75, 0.9], [0.79, 0.86, 0.8, 0.85, 0.322, 0.85, 0.82, 0.75, 0.9], [0.9, 0.45, 0.8, 0.85, 0.322, 0.6, 0.55, 0.75, 0.7], [0.78, 0.87, 0.81, 0.85, 0.322, 0.85, 0.82, 0.75, 0.9]])
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')
10. PubMed evidence per hypothesis¶
Hypothesis 1: Glymphatic-Mediated Tau Clearance Dysfunction¶
Target genes: MAPT · Composite score: 0.633
Molecular Mechanism and Rationale¶
The glymphatic-mediated tau clearance dysfunction hypothesis centers on the disruption of cerebrospinal fluid-interstitial fluid exchange through impaired aquaporin-4 (AQP4) water channel function at astrocytic endfeet. Under normal conditions, polarized AQP4 distribution facilitates bulk flow clearance of soluble tau and other metabolic waste products through perivascular spaces. However, hyperphosphorylated tau species, particularly those phosphorylated at
hid = 'h-var-95b0f9a6bc'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 2: Microglial-Mediated Tau Clearance Dysfunction via TREM2 Signaling¶
Target genes: TREM2 · Composite score: 0.628
The microglial-mediated tau clearance dysfunction hypothesis proposes that MAPT-encoded tau pathology propagates through impaired microglial phagocytosis and lysosomal degradation rather than glymphatic system dysfunction. TREM2 (Triggering Receptor Expressed on Myeloid Cells 2) serves as the critical mediator, where hyperphosphorylated tau aggregates bind to TREM2 receptors on microglial surfaces, initially activating phagocytic responses but subsequently overwhelming lysosomal capacity. This l
hid = 'h-var-ce41f0efd7'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 3: Dual-Circuit Tau Vulnerability Cascade¶
Target genes: MAPT · Composite score: 0.625
Molecular Mechanism and Rationale¶
The dual-circuit tau vulnerability cascade hypothesis centers on MAPT-encoded tau protein pathology as the initiating driver of sequential circuit dysfunction in Alzheimer's disease. Hyperphosphorylated tau, particularly at Ser202/Thr205 (AT8) and Ser396/404 (PHF-1) epitopes, loses its microtubule-binding capacity and aggregates into paired helical filaments, disrupting axonal transport machinery including kinesin and dynein motors. The locus coeruleus exhib
hid = 'h-var-8412ce00a4'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 4: Thalamocortical Synchrony Restoration via NMDA Modulation¶
Target genes: GRIN2B · Composite score: 0.622
Thalamocortical Synchrony Restoration via NMDA Modulation¶
Molecular Mechanism and Rationale¶
The thalamocortical circuit represents a fundamental network architecture where reciprocal connections between thalamic relay nuclei and cortical layers generate synchronized oscillatory activity essential for cognitive function, sensory processing, and consciousness. GluN2B-containing NMDA receptors play a pivotal role in this synchronization through their unique biophysical properties, including
hid = 'h-cd60e2ec'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 5: Closed-loop transcranial focused ultrasound to restore hippocampal gam¶
Target genes: PVALB · Composite score: 0.62
Background and Rationale
Alzheimer's disease (AD) manifests early hippocampal network dysfunction characterized by the progressive loss of gamma oscillations (30-100 Hz) that are critical for memory encoding and consolidation. Gamma rhythms emerge from the precise timing of perisomatic inhibition delivered by parvalbumin-positive (PV) fast-spiking interneurons onto CA1 pyramidal cells. These interneurons, expressing the calcium-binding protein parvalbumin encoded by the PVALB gene, comprise
hid = 'h-var-6612521a02'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 6: Locus Coeruleus-Hippocampal Circuit Protection¶
Target genes: MAPT · Composite score: 0.611
Molecular Mechanism and Rationale¶
The locus coeruleus-hippocampal circuit protection hypothesis centers on the premise that tau pathology, encoded by the MAPT gene, initiates neurodegeneration through a specific anatomical vulnerability pattern. The locus coeruleus, the brain's primary noradrenergic nucleus, exhibits selective susceptibility to tau accumulation in the earliest stages of Alzheimer's disease and related tauopathies. This vulnerability stems from the unique cellular characteris
hid = 'h-23b94ed8'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 7: Closed-loop focused ultrasound targeting EC-II SST interneurons to res¶
Target genes: SST · Composite score: 0.606
Molecular Mechanism and Rationale¶
Somatostatin-positive (SST) interneurons in entorhinal cortex (EC) layer II serve as critical gamma frequency gatekeepers that regulate perforant path transmission to the hippocampus through perisomatic inhibition of stellate cells. These parvalbumin-negative interneurons express voltage-gated calcium channels and mechanosensitive ion channels that respond to low-intensity focused ultrasound (LIPUS) through sonoporation-mediated calcium influx and subsequent
hid = 'h-var-55da4f915d'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 8: Closed-loop tACS targeting EC-II parvalbumin interneurons to restore g¶
Target genes: PVALB · Composite score: 0.598
Molecular Mechanism and Rationale¶
Parvalbumin-positive (PV+) fast-spiking interneurons in entorhinal cortex layers II-III generate perisomatic gamma oscillations through precisely timed GABA release at basket cell synapses and axon initial segment (AIS) contacts via chandelier cells. In Alzheimer's disease, hyperphosphorylated tau disrupts the subcellular localization of AnkyrinG, a critical scaffolding protein that anchors voltage-gated sodium channel (VGSC) clusters at the AIS of PV intern
hid = 'h-var-4eca108177'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 9: Closed-loop transcranial focused ultrasound targeting EC-II SST intern¶
Target genes: SST · Composite score: 0.593
Molecular Mechanism and Rationale¶
The therapeutic strategy targets somatostatin-positive (SST) interneurons in entorhinal cortex layer II (EC-II), which serve as critical GABAergic regulators of tau propagation and gamma oscillatory activity. Early tau hyperphosphorylation selectively impairs SST interneuron function through disruption of microtubule-associated protein interactions and altered calcium homeostasis, leading to reduced GABA release and subsequent disinhibition of principal stel
hid = 'h-var-f110ef2e0a'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 10: Closed-loop tACS targeting EC-II PV interneurons to suppress burst fir¶
Target genes: PVALB · Composite score: 0.591
Molecular Mechanism and Rationale¶
The core mechanism involves the selective vulnerability of parvalbumin-positive (PV) fast-spiking interneurons in entorhinal cortex layer II to early tau pathology, specifically through disruption of axon initial segments (AIS) and perineuronal nets (PNNs). Hyperphosphorylated tau accumulates at the AIS of PV interneurons, disrupting voltage-gated sodium channel clustering and impairing the rapid, high-frequency firing required for effective perisomatic inhi
hid = 'h-var-14d7585dd1'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 11: Closed-loop focused ultrasound targeting CA1 PV interneurons to restor¶
Target genes: PVALB · Composite score: 0.587
Molecular Mechanism and Rationale¶
Parvalbumin-positive (PV) fast-spiking interneurons in hippocampal CA1 express mechanosensitive PIEZO1 channels that transduce low-intensity focused ultrasound into calcium-dependent membrane depolarization through activation of fast-delayed rectifier potassium channels (Kv3.1/3.2). This ultrasound-induced depolarization triggers vesicular GABA release at perisomatic basket cell synapses onto CA1 pyramidal neurons, generating precisely timed inhibitory posts
hid = 'h-var-7eaceb5a55'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 12: Cholinergic Basal Forebrain-Hippocampal Circuit Protection¶
Target genes: MAPT · Composite score: 0.586
Molecular Mechanism and Rationale¶
The cholinergic basal forebrain-hippocampal circuit protection hypothesis centers on the selective vulnerability of cholinergic neurons to tau pathology mediated by MAPT gene mutations and post-translational modifications. Hyperphosphorylated tau protein, particularly at Ser202/Thr205 and Ser396/Ser404 epitopes, disrupts microtubule stability within cholinergic projection neurons of the nucleus basalis of Meynert and medial septal complex. This disruption im
hid = 'h-var-f687d4593b'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 13: Gamma entrainment therapy to restore hippocampal-cortical synchrony¶
Target genes: SST · Composite score: 0.584
Gamma Entrainment Therapy for Alzheimer's Disease: Circuit-Level Intervention
Overview and Neurophysiological Basis
Gamma oscillations (30-100 Hz, typically 40 Hz) are fundamental rhythms of the brain, generated by synchronized firing of excitatory pyramidal neurons and inhibitory parvalbumin-positive (PV+) interneurons. These oscillations coordinate information transfer between hippocampus and prefrontal cortex, enabling memory encoding, consolidation, and retrieval. In Alzheimer's di
hid = 'h-bdbd2120'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 14: Closed-loop tACS targeting EC-II SST interneurons to block tau propaga¶
Target genes: SST · Composite score: 0.582
Molecular Mechanism and Rationale¶
Somatostatin-positive (SST+) interneurons in entorhinal cortex layer II provide critical GABAergic inhibition that regulates the excitability of stellate cells and controls the temporal dynamics of perforant path output to the hippocampus. Early tau hyperphosphorylation disrupts the intrinsic membrane properties and synaptic function of SST interneurons, leading to disinhibition of layer II stellate cells and aberrant gamma oscillations in the 30-80 Hz range
hid = 'h-var-3b982ec3d2'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 15: Closed-loop transcranial alternating current stimulation to restore hi¶
Target genes: SST · Composite score: 0.58
Molecular Mechanism and Rationale¶
The therapeutic mechanism centers on restoring the precise temporal coordination between hippocampal theta oscillations (4-8 Hz) and nested gamma bursts (30-100 Hz) through selective rescue of somatostatin-positive (SST+) interneurons in CA1 stratum oriens. SST+ interneurons provide dendritic inhibition that is critical for theta-gamma phase-amplitude coupling, where gamma power peaks at specific phases of the theta cycle to create discrete time windows for
hid = 'h-var-d749cd28cb'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 16: Hippocampal CA3-CA1 synaptic rescue via DHHC2-mediated PSD95 palmitoyl¶
Target genes: BDNF · Composite score: 0.573
Molecular Mechanism and Rationale¶
The core mechanism centers on DHHC2 palmitoyltransferase-mediated post-translational modification of PSD95, which is essential for maintaining synaptic scaffold stability at hippocampal CA3-CA1 synapses. Under normal conditions, DHHC2 catalyzes the reversible palmitoylation of PSD95 at cysteine residues 3 and 5, promoting its membrane association and preventing degradation by the ubiquitin-proteasome system. In Alzheimer's disease, amyloid-β oligomers disrup
hid = 'h-var-9c0368bb70'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 17: Default Mode Network Circuit Stabilization¶
Target genes: VIP · Composite score: 0.571
Molecular Mechanism and Rationale¶
Vasoactive intestinal peptide (VIP) interneurons regulate cortical circuit dynamics through selective disinhibition of pyramidal neurons via inhibition of parvalbumin-positive (PV+) and somatostatin-positive (SST+) interneurons. VIP neurons express G-protein coupled receptors (VPAC1 and VPAC2) that, when activated by endogenous VIP, trigger cAMP-dependent protein kinase A signaling cascades leading to enhanced GABA release and modulation of local inhibitory
hid = 'h-a635d4e5'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 18: Optogenetic restoration of hippocampal gamma oscillations via selectiv¶
Target genes: PVALB · Composite score: 0.567
Molecular Mechanism and Rationale¶
This optogenetic intervention exploits the light-sensitive channelrhodopsin-2 (ChR2) protein to restore gamma oscillations through precise activation of parvalbumin-positive (PV+) interneurons in the hippocampal CA1 region. ChR2, when expressed under the PVALB promoter via AAV vectors, integrates into the membranes of PV+ fast-spiking interneurons where it functions as a blue light-gated cation channel, allowing rapid sodium and calcium influx upon 470 nm ph
hid = 'h-var-6c90f2e594'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 19: Dopaminergic Ventral Tegmental-Hippocampal Circuit Protection¶
Target genes: MAPT · Composite score: 0.556
Molecular Mechanism and Rationale¶
The dopaminergic ventral tegmental-hippocampal circuit protection hypothesis centers on the MAPT gene's tau protein and its selective vulnerability in VTA dopaminergic neurons due to their unique metabolic and anatomical properties. Hyperphosphorylated tau accumulates preferentially in VTA neurons because dopamine metabolism generates excessive reactive oxygen species through monoamine oxidase activity, creating a pro-aggregation environment that promotes ta
hid = 'h-var-bc4357c8c5'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 20: Closed-loop focused ultrasound targeting EC-II PV interneurons to rest¶
Target genes: PVALB · Composite score: 0.552
Molecular Mechanism and Rationale¶
Parvalbumin-positive (PV) fast-spiking interneurons in entorhinal cortex layer II express high densities of mechanosensitive PIEZO1 channels that respond to focused ultrasound by inducing calcium influx and membrane depolarization. This ultrasound-triggered depolarization activates voltage-gated Kv3.1 and Kv3.2 potassium channels, which enable sustained high-frequency firing rates up to 200 Hz characteristic of chandelier and basket cell populations. The rap
hid = 'h-var-862d6a66d2'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 21: Glymphatic-Cholinergic Tau Clearance Cascade¶
Target genes: MAPT · Composite score: 0.552
Molecular Mechanism¶
The glymphatic-cholinergic tau clearance cascade begins with MAPT gene mutations or post-translational modifications that produce hyperphosphorylated tau species. These pathological tau proteins undergo conformational changes, exposing hydrophobic regions that facilitate binding to aquaporin-4 (AQP4) water channels on astrocytic endfeet. The interaction disrupts AQP4's normal polarized distribution along perivascular membranes, reducing water influx and cerebrospinal flui
hid = 'h-var-6a0893ffb6'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 22: Optogenetic restoration of hippocampal gamma oscillations via selectiv¶
Target genes: SST · Composite score: 0.552
Molecular Mechanism and Rationale¶
The therapeutic approach targets somatostatin-positive (SST) interneurons through optogenetic activation of channelrhodopsin-2 (ChR2) or similar light-gated ion channels expressed specifically in these cells via SST promoter-driven vectors. Upon blue light stimulation (470nm), ChR2 undergoes conformational changes allowing rapid sodium and calcium influx, generating action potentials that trigger GABA release from SST interneuron terminals onto pyramidal cel
hid = 'h-var-4d43a26612'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 23: Hippocampal CA3-CA1 circuit rescue via neurogenesis and synaptic prese¶
Target genes: BDNF · Composite score: 0.55
Molecular Mechanism and Rationale
The CA3-CA1 hippocampal circuit represents a fundamental neural pathway essential for episodic memory formation and consolidation, making it a critical target for Alzheimer's disease (AD) therapeutic intervention. This circuit exhibits pathological alterations early in AD progression, characterized by synaptic dysfunction, neuronal loss, and impaired plasticity mechanisms. The proposed therapeutic strategy targets the restoration of this circuit through dua
hid = 'h-856feb98'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 24: CaMKII-Dependent Synaptic Circuit Amplification¶
Target genes: CAMK2A · Composite score: 0.549
Molecular Mechanism and Rationale¶
CaMKII-dependent synaptic circuit amplification operates through enhanced calcium/calmodulin-dependent protein kinase II (CaMKII) activity, which phosphorylates critical synaptic proteins including AMPA receptors, CREB, and actin-binding proteins to promote dendritic spine formation and synaptic strength. Upon calcium influx through NMDA receptors, activated CaMKII undergoes autophosphorylation at Thr286, creating a calcium-independent kinase that persistent
hid = 'h-62c78d8b'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 25: Real-time gamma-guided transcranial focused ultrasound targeting EC-II¶
Target genes: SST · Composite score: 0.538
Molecular Mechanism and Rationale¶
The therapeutic mechanism centers on mechanotransduction-mediated activation of somatostatin-positive interneurons in entorhinal cortex layer II through ultrasound-sensitive ion channels. When low-intensity focused ultrasound (LIFUS) is applied to EC-II SST interneurons, it activates mechanosensitive PIEZO1 channels and TREK-1 potassium channels, leading to membrane depolarization and subsequent calcium influx through voltage-gated calcium channels. This cal
hid = 'h-var-d33964b962'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 26: Closed-loop tACS targeting entorhinal cortex layer II SST interneurons¶
Target genes: SST · Composite score: 0.529
Background and Rationale
Alzheimer's disease progression is fundamentally driven by the trans-synaptic propagation of pathological tau protein from the entorhinal cortex (EC) to the hippocampus, following predictable anatomical pathways that mirror clinical symptom progression. Layer II stellate neurons of the EC serve as critical nodes in this propagation network, projecting via the perforant pathway to dentate gyrus granule cells where tau pathology becomes established in early disease st
hid = 'h-var-d98a992599'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 27: Optogenetic viral vector delivery via tFUS-mediated blood-brain barrie¶
Target genes: PVALB · Composite score: 0.521
Background and Rationale
Alzheimer's disease (AD) manifests early hippocampal network dysfunction characterized by the progressive loss of gamma oscillations (30-100 Hz) critical for memory encoding. Gamma rhythms emerge from precise perisomatic inhibition by parvalbumin-positive (PV) fast-spiking interneurons onto CA1 pyramidal cells. These PVALB-expressing interneurons comprise 25% of hippocampal GABAergic cells and provide rapid, synchronous inhibition shaping gamma dynamics. In AD, amyl
hid = 'h-var-f4b4d4de63'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 28: Beta-frequency entrainment therapy targeting PV interneuron-astrocyte¶
Target genes: SST · Composite score: 0.516
Molecular Mechanism and Rationale¶
The core molecular mechanism centers on beta-frequency entrainment driving synchronized parvalbumin-positive (PV+) interneuron firing patterns that activate astrocytic gap junction networks through ATP-mediated purinergic signaling. When PV+ basket cells fire in coordinated 20 Hz bursts, they release GABA and co-transmitters including ATP, which binds to P2Y1 receptors on neighboring astrocytes, triggering IP3-dependent calcium release from endoplasmic retic
hid = 'h-var-e47f17ca3b'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 29: Closed-loop tACS targeting EC-II PV interneurons to enhance perisomati¶
Target genes: PVALB · Composite score: 0.513
Molecular Mechanism and Rationale¶
Parvalbumin-positive (PV+) fast-spiking interneurons in entorhinal cortex layer II express high levels of the calcium-binding protein parvalbumin (encoded by PVALB), which enables their characteristic rapid firing rates and precise temporal control of network activity. Early tau pathology specifically targets these interneurons, leading to downregulation of PVALB expression and consequent disruption of calcium buffering capacity, which impairs their ability
hid = 'h-var-9da3ee8550'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 30: Prefrontal sensory gating circuit restoration via PV interneuron enhan¶
Target genes: PVALB · Composite score: 0.509
Molecular Mechanism and Rationale¶
Parvalbumin-expressing (PV+) interneurons represent the most abundant class of GABAergic interneurons in the prefrontal cortex (PFC), comprising approximately 40% of all cortical inhibitory neurons. These fast-spiking interneurons are characterized by their unique molecular signature, including high expression of the calcium-binding protein parvalbumin (PVALB), the voltage-gated potassium channel subunit Kv3.1b (KCNC1), and the GABA transporter GAT-1 (SLC6A1
hid = 'h-62f9fc90'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 31: Dual-Circuit Tau Vulnerability Cascade with Glial-Mediated Amplificati¶
Target genes: MAPT · Composite score: 0.506
Molecular Mechanism¶
The dual-circuit tau vulnerability cascade with glial-mediated amplification hypothesis proposes that MAPT-encoded tau pathology initiates neurodegeneration through sequential dysfunction of the locus coeruleus-hippocampal noradrenergic circuit followed by the basal forebrain-hippocampal cholinergic circuit, with critical amplification by activated microglia and astrocytes. The locus coeruleus exhibits earliest vulnerability due to its extensive axonal arbor and high meta
hid = 'h-var-1906e102cf'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 32: Sensory-Motor Circuit Cross-Modal Compensation¶
Target genes: CHAT · Composite score: 0.5
Background and Rationale
Neurodegeneration often involves a cascade of circuit dysfunction that extends beyond primary pathological targets, with activity-dependent mechanisms playing crucial roles in disease progression. The cholinergic system, particularly neurons expressing choline acetyltransferase (CHAT), represents a vulnerable population across multiple neurodegenerative conditions including Alzheimer's disease, Parkinson's disease, and age-related cognitive decline. These cholinergi
hid = 'h-7110565d'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 33: Closed-loop transcranial focused ultrasound targeting CA1 PV interneur¶
Target genes: PVALB · Composite score: 0.5
Molecular Mechanism and Rationale¶
Parvalbumin-positive (PV+) fast-spiking interneurons in the hippocampal CA1 region express mechanosensitive ion channels including PIEZO1 and TREK-1 that respond to focused ultrasound-induced acoustic pressure waves through membrane deformation and cytoskeletal tension changes. Upon mechanostimulation, these channels facilitate calcium and potassium flux, leading to rapid depolarization that activates voltage-gated calcium channels (VGCCs) and triggers synch
hid = 'h-var-ee70969116'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
Hypothesis 34: Differential Interneuron Optogenetic Restoration Therapy¶
Target genes: PVALB/SST · Composite score: 0.498
Molecular Mechanism and Rationale¶
Amyloid-β oligomers selectively target GABAergic interneuron populations through differential expression of receptors and calcium-binding proteins, with somatostatin-positive (SST) and parvalbumin-positive (PV) interneurons showing heightened vulnerability due to their high metabolic demands and calcium buffering requirements. SST interneurons, which primarily target dendrites of pyramidal cells and regulate theta oscillations (4-8 Hz), experience compromise
hid = 'h-f8316acf'
papers = load(f'pubmed_{hid}')
if isinstance(papers, list) and papers:
lit = pd.DataFrame(papers)
cols = [c for c in ['year','journal','title','pmid'] if c in lit.columns]
if cols:
lit = lit[cols]
lit['title'] = lit['title'].str[:80]
if 'journal' in lit.columns:
lit['journal'] = lit['journal'].str[:30]
lit.sort_values('year', ascending=False, inplace=True)
display_df = lit
else:
display_df = pd.DataFrame(papers[:5])
else:
display_df = pd.DataFrame([{'note':'no PubMed results'}])
display_df
| note | |
|---|---|
| 0 | no PubMed results |
11. Knowledge graph edges (95 total)¶
edge_data = [{'source': 'BDNF', 'relation': 'activates', 'target': 'synaptic_plasticity', 'strength': 0.9}, {'source': 'amyloid-β oligomers', 'relation': 'causes (specifically disr', 'target': 'SST interneurons', 'strength': 0.82}, {'source': 'amyloid-β oligomers', 'relation': 'causes (specifically disr', 'target': 'PV interneurons', 'strength': 0.82}, {'source': 'optogenetic activation of SST ', 'relation': 'causes (optogenetic activ', 'target': 'theta oscillation restoration', 'strength': 0.82}, {'source': 'optogenetic activation of PV i', 'relation': 'causes (optogenetic activ', 'target': 'gamma oscillation restoration', 'strength': 0.82}, {'source': 'tau pathology', 'relation': 'causes (tau pathology spr', 'target': 'hippocampal circuit dysfunctio', 'strength': 0.79}, {'source': 'GluN2B modulation', 'relation': 'causes (selective modulat', 'target': 'thalamocortical synchronizatio', 'strength': 0.78}, {'source': 'SST', 'relation': 'therapeutic_target', 'target': "Alzheimer's disease", 'strength': 0.76}, {'source': 'CaMKII', 'relation': 'causes (CaMKII enhancemen', 'target': 'dendrite ramification', 'strength': 0.75}, {'source': 'CaMKII', 'relation': 'causes (CaMKII-dependent ', 'target': 'spine generation', 'strength': 0.75}, {'source': 'VIP interneuron stimulation', 'relation': 'causes (VIP interneuron-m', 'target': 'pyramidal cell disinhibition', 'strength': 0.73}, {'source': 'BDNF', 'relation': 'therapeutic_target', 'target': "Alzheimer's disease", 'strength': 0.71}, {'source': 'SST', 'relation': 'participates_in', 'target': 'GABAergic interneuron networks', 'strength': 0.7}, {'source': 'SST', 'relation': 'associated_with', 'target': "Alzheimer's disease", 'strength': 0.7}, {'source': 'SST', 'relation': 'regulates', 'target': 'gamma_oscillation', 'strength': 0.7}, {'source': 'PVALB', 'relation': 'therapeutic_target', 'target': "Alzheimer's disease", 'strength': 0.7}, {'source': 'h-f8316acf', 'relation': 'targets', 'target': 'PVALB', 'strength': 0.7}, {'source': 'h-f8316acf', 'relation': 'targets', 'target': 'SST', 'strength': 0.7}, {'source': 'h-f8316acf', 'relation': 'implicated_in', 'target': 'neuroscience', 'strength': 0.7}, {'source': 'h-23b94ed8', 'relation': 'targets', 'target': 'MAPT', 'strength': 0.7}, {'source': 'h-23b94ed8', 'relation': 'implicated_in', 'target': 'neuroscience', 'strength': 0.7}, {'source': 'PVALB', 'relation': 'participates_in', 'target': 'Prefrontal inhibitory circuits', 'strength': 0.69}, {'source': 'PVALB', 'relation': 'associated_with', 'target': "Alzheimer's disease", 'strength': 0.69}, {'source': 'natural sensory input loss', 'relation': 'causes (loss of natural s', 'target': 'cholinergic circuit degenerati', 'strength': 0.65}, {'source': 'h-62c78d8b', 'relation': 'targets', 'target': 'CAMK2A', 'strength': 0.65}]
if edge_data:
pd.DataFrame(edge_data).head(25)
else:
print('No KG edge data available')
12. Caveats¶
This notebook uses real Forge tool calls cached from live APIs, but:
- Enrichment is against curated gene-set libraries, not genome-wide screens
- STRING/Reactome/HPA/MyGene reflect curated knowledge
- PubMed literature is search-relevance ranked, not systematic review
The cached evidence bundle is the minimum viable real-data analysis for this topic.