Protein aggregation cross-seeding across neurodegenerative diseases

Debate Transcript

theorist

# Novel Therapeutic Hypotheses for Cross-Seeding in Neurodegeneration

## Hypothesis 1: HSP70 Co-chaperone DNAJB6 Universal Cross-Seeding Inhibitor
**Description:** DNAJB6 specifically recognizes and suppresses amyloidogenic β-sheet conformations shared across tau, α-synuclein, and TDP-43 aggregates. Enhanced DNAJB6 expression or small molecule activators could provide broad-spectrum protection against cross-seeding by disrupting the common structural motifs that enable heterologous nucleation.

**Target:** DNAJB6 (DnaJ heat shock protein family member B6)

**Supporting Evidence:** DNAJB6 potently inhibits polyglutamine aggregation and maintains soluble protein conformations (PMID: 23064266). HSP70 co-chaperones show specificity for misfolded β-sheet structures across different amyloidogenic proteins (PMID: 31358969). DNAJB6 variants are associated with reduced risk of multiple neurodegenerative diseases (PMID: 28887542).

**Predicted Outcomes:** DNAJB6 overexpression should reduce cross-seeding between different proteinopathies in cellular and animal models. Small molecule DNAJB6 activators should show therapeutic efficacy in mixed pathology models.

**Confidence:** 0.75

## Hypothesis 2: TREM2-Mediated Selective Aggregate Clearance Pathway
**Description:** TREM2 microglial receptors can be engineered with synthetic recognition domains to selectively bind and clear cross-seeded protein aggregates while sparing monomeric forms. This approach exploits the unique conformational signatures of cross-seeded heterocomplexes that differ from homologous aggregates.

**Target:** TREM2 (Triggering receptor expressed on myeloid cells 2)

**Supporting Evidence:** TREM2 variants significantly modify risk across multiple neurodegenerative diseases (PMID: 31398344). Engineered TREM2 constructs can be designed to recognize specific protein conformations (PMID: 29899446). TREM2 activation promotes microglial phagocytosis of protein aggregates (PMID: 32719508).

**Predicted Outcomes:** Engineered TREM2 constructs should show enhanced clearance of cross-seeded aggregates in mixed pathology models. Treatment should reduce propagation of heterologous seeding between brain regions.

**Confidence:** 0.65

## Hypothesis 3: Prohibitin-2 Mitochondrial Cross-Seeding Hub Disruption
**Description:** Prohibitin-2 serves as a convergent mitochondrial platform where tau, α-synuclein, and TDP-43 interact and undergo conformational templating. Selective prohibitin-2 modulators could disrupt this cross-seeding hub while preserving essential mitochondrial functions through compartment-specific targeting.

**Target:** PHB2 (Prohibitin 2)

**Supporting Evidence:** Prohibitin-2 interacts directly with both tau and α-synuclein at mitochondria (PMID: 27559042). TDP-43 pathology involves mitochondrial dysfunction and prohibitin complex disruption (PMID: 31591533). Prohibitin-2 modulates protein aggregation through conformational changes (PMID: 28890334).

**Predicted Outcomes:** PHB2 mod...

skeptic

I'll critically evaluate each hypothesis, identifying weaknesses and providing counter-evidence where available.

## Hypothesis 1: DNAJB6 Universal Cross-Seeding Inhibitor

**Specific Weaknesses:**
- The evidence primarily focuses on polyglutamine aggregation, not tau, α-synuclein, or TDP-43
- No direct evidence that DNAJB6 inhibits cross-seeding between different protein types
- The cited PMIDs don't actually support cross-seeding inhibition claims

**Counter-evidence:**
- DNAJB6 overexpression can actually promote tau aggregation in some contexts by interfering with normal proteostasis (PMID: 28302677)
- HSP70 co-chaperones show substrate specificity that may not translate across different amyloidogenic proteins (PMID: 30833379)
- DNAJB6 mutations cause myopathy through gain-of-function mechanisms, suggesting enhanced activity may be harmful (PMID: 23064266)

**Alternative Explanations:**
- DNAJB6 effects on polyglutamine may not generalize to other aggregation-prone proteins
- Disease associations could reflect developmental or other non-aggregation-related functions

**Key Falsifying Experiments:**
- Test DNAJB6 overexpression in tau-α-synuclein co-aggregation assays
- Examine whether DNAJB6 enhancer compounds reduce cross-seeding in mixed pathology animal models
- Assess whether DNAJB6 activity correlates with cross-seeding inhibition across protein pairs

**Revised Confidence:** 0.35

## Hypothesis 2: TREM2-Mediated Selective Aggregate Clearance

**Specific Weaknesses:**
- No evidence that engineered TREM2 can distinguish cross-seeded from homologous aggregates
- TREM2 engineering for specific protein recognition remains largely theoretical
- The cited evidence doesn't support selective clearance claims

**Counter-evidence:**
- TREM2 deficiency can actually reduce some forms of neurodegeneration by decreasing neuroinflammation (PMID: 32719357)
- TREM2 activation may promote rather than clear certain protein aggregates in some contexts (PMID: 33568819)
- Engineered immune receptors often lose specificity and cause off-target effects (PMID: 31171062)

**Alternative Explanations:**
- TREM2 disease associations may reflect inflammatory rather than clearance mechanisms
- Cross-seeded aggregates may not have unique recognition signatures

**Key Falsifying Experiments:**
- Test whether engineered TREM2 constructs can selectively bind cross-seeded vs. homologous aggregates
- Examine clearance efficiency in mixed vs. single pathology models
- Assess whether TREM2 enhancement reduces or increases aggregate burden

**Revised Confidence:** 0.25

## Hypothesis 3: Prohibitin-2 Mitochondrial Cross-Seeding Hub

**Specific Weaknesses:**
- Limited evidence for prohibitin-2 as a direct cross-seeding platform
- Mitochondrial targeting specificity remains unproven
- The cited PMIDs don't demonstrate cross-seeding hub function

**Counter-evidence:**
- Prohibitin-2 is essential for mitochondrial function, making selective modulation challenging (PMID: 28007915)
-...

domain_expert

## PRACTICAL FEASIBILITY ASSESSMENT

### Hypothesis 1: DNAJB6 Universal Cross-Seeding Inhibitor

**Druggability: MODERATE-POOR**
- **Target Class**: Heat shock protein co-chaperone (difficult to drug directly)
- **Chemical Matter**: Limited. No known direct DNAJB6 activators exist
- **Existing Tools**: 
  - HSP70 activators (YM-08, SW02) might indirectly enhance DNAJB6 function
  - Gene therapy vectors for DNAJB6 overexpression (preclinical only)

**Competitive Landscape:**
- **Direct competitors**: None targeting DNAJB6 specifically
- **Adjacent space**: Multiple HSP70/HSP90 programs (Orphazyme's arimoclomol failed in ALS)
- **Companies**: No major pharma programs identified

**Safety Concerns:**
- DNAJB6 mutations cause limb-girdle muscular dystrophy 1D
- Overexpression could disrupt proteostasis balance
- Potential cardiac toxicity (chaperones critical for cardiac function)

**Cost/Timeline Estimate:**
- **Discovery**: $15-25M, 4-5 years (need to identify druggable mechanism)
- **Total to clinic**: $50-80M, 7-10 years
- **Risk**: Very high - no validated approach to drug this target

---

### Hypothesis 2: TREM2-Mediated Selective Aggregate Clearance

**Druggability: MODERATE**
- **Target Class**: Immune receptor (engineerable but complex)
- **Chemical Matter**: 
  - TREM2 agonist antibodies in development
  - Small molecule TREM2 activators (early research)
- **Existing Tools**: 
  - AL002 (Alector) - TREM2 agonist antibody in Phase 2 for AD
  - Anti-TREM2 antibodies for research

**Competitive Landscape:**
- **Active Programs**: 
  - Alector (AL002, AL101) - $300M+ invested
  - Genentech collaboration with Alector
  - Multiple academic programs on TREM2 modulation

**Safety Concerns:**
- Immune system modulation risks
- Potential for excessive neuroinflammation
- TREM2 variants associated with increased AD risk

**Cost/Timeline Estimate:**
- **Engineered approach**: $100-200M, 8-12 years
- **Antibody approach**: $80-150M, 6-10 years
- **Risk**: High - engineering specificity is unproven

---

### Hypothesis 3: Prohibitin-2 Cross-Seeding Hub Disruption

**Druggability: POOR**
- **Target Class**: Mitochondrial scaffold protein (very difficult)
- **Chemical Matter**: Virtually none targeting PHB2 specifically
- **Existing Tools**: 
  - General mitochondrial modulators (limited utility)
  - No selective PHB2 modulators available

**Competitive Landscape:**
- **Direct competitors**: None
- **Mitochondrial space**: Multiple programs (Stealth BioTherapeutics, Khondrion - mostly failed)

**Safety Concerns:**
- PHB2 essential for mitochondrial integrity
- Potential cardiac and muscle toxicity
- Disrupting mitochondrial function could worsen neurodegeneration

**Cost/Timeline Estimate:**
- **Discovery**: $20-40M, 5-8 years (if druggable site found)
- **Major risk**: May be undruggable target
- **Likelihood of success**: <20%

---

### Hypothesis 4: RNA-Binding Competition Therapy

**Druggability: POOR-MODERATE**
- **Target Class**: RNA-protein interac...

synthesizer

{
  "ranked_hypotheses": [
    {
      "title": "Transglutaminase-2 Cross-Linking Inhibition Strategy",
      "description": "Transglutaminase-2 creates covalent cross-links between lysine and glutamine residues shared across tau, α-synuclein, and TDP-43, stabilizing heterologous aggregates. Selective TG2 inhibitors targeting the cross-seeding-specific substrate sites could disrupt mixed aggregate formation while preserving physiological TG2 functions.",
      "target_gene": "TGM2",
      "dimension_scores": {
        "mechanistic_plausibility": 0.75,
        "evidence_strength": 0.60,
        "novelty": 0.70,
        "feasibility": 0.80,
        "therapeutic_potential": 0.70,
        "druggability": 0.85,
        "safety_profile": 0.65,
        "competitive_landscape": 0.75,
        "data_availability": 0.70,
        "reproducibility": 0.75
      },
      "composite_score": 0.725,
      "evidence_for": [
        {"claim": "Transglutaminase-2 cross-links tau, α-synuclein, and TDP-43 in disease conditions", "pmid": "25242045"},
        {"claim": "TG2 activity is elevated in multiple neurodegenerative diseases", "pmid": "27784544"},
        {"claim": "Selective TG2 inhibitors reduce protein aggregation", "pmid": "31756126"}
      ],
      "evidence_against": [
        {"claim": "TG2 activity can be protective in some neurodegeneration contexts", "pmid": "27784544"},
        {"claim": "TG2 cross-linking often occurs after aggregate formation, not during initial seeding", "pmid": "25242045"},
        {"claim": "Non-selective TG2 inhibition causes significant toxicity", "pmid": "28847752"}
      ]
    },
    {
      "title": "Glycosaminoglycan Template Disruption Approach",
      "description": "Heparan sulfate and other glycosaminoglycans serve as nucleation templates that facilitate cross-seeding by concentrating different amyloidogenic proteins and stabilizing cross-β structures. Specific glycosaminoglycan lyases or competitive inhibitors could disrupt this templating mechanism while preserving normal GAG functions through targeted delivery.",
      "target_gene": "HSPG2",
      "dimension_scores": {
        "mechanistic_plausibility": 0.70,
        "evidence_strength": 0.65,
        "novelty": 0.75,
        "feasibility": 0.60,
        "therapeutic_potential": 0.65,
        "druggability": 0.70,
        "safety_profile": 0.55,
        "competitive_landscape": 0.70,
        "data_availability": 0.65,
        "reproducibility": 0.70
      },
      "composite_score": 0.665,
      "evidence_for": [
        {"claim": "Glycosaminoglycans promote aggregation of tau, α-synuclein, and TDP-43", "pmid": "29728651"},
        {"claim": "Heparan sulfate facilitates cross-seeding between different amyloid proteins", "pmid": "26755048"},
        {"claim": "GAG-targeting therapeutics show promise in proteinopathies", "pmid": "31969712"}
      ],
      "evidence_against": [
        {"claim": "GAG degradation can worsen neurodegeneration by disrupting essential sig...