What molecular mechanisms determine the conformational diversity and strain-like properties of pathological seeds?

arXiv Preprint NeurIPS Nature Methods PLOS ONE

---

🌐 Open in Overleaf →

Therapeutic Hypotheses: Molecular Mechanisms of Pathological Seed Conformational Diversity

Hypothesis 1: Post-Translational Modifications as Conformational Determinants

Title: PTM-mediated charge alterations drive distinct seed conformations and strain phenotypes

Mechanism: Site-specific phosphorylation, oxidation, or glycation modifies the physicochemical properties of misfolded proteins, altering their aggregation pathways and stabilizing distinct amyloid conformers. Different PTM patterns act as "epigenetic codes" that lock proteins into strain-specific folds.

Target: tau (PHF-tau at Ser202/Thr205), α-synuclein (Ser129 phosphorylation), TDP-43

Supporting Evidence:

• PMID: 28714960 - Phosphorylation at Ser129 directs α-synuclein into distinct aggregation pathways
• PMID: 24127214 - Distinct phosphorylation patterns correlate with tau strain differences
• PMID: 30242327 - Glycation modifies Aβ aggregation kinetics and toxicity profiles

Predicted Experiment: Use MS to map PTM patterns on patient-derived seeds from different strains, then recapitulate strains in vitro by engineering specific PTM-modified monomers. Test if PTM pattern transfer occurs during templated conversion.

Confidence: 0.72

Hypothesis 2: Lipid Membrane Cofactors Template Strain-Specific Conformations

Title: Membrane lipid composition determines which amyloid conformer is selected and propagated

Mechanism: Specific lipid membranes (gangliosides, phospholipids, cholesterol) act as templates that stabilize particular protein folds during initial aggregation. This "membrane-assisted conformational selection" explains how the same protein (e.g., α-synuclein) can generate strains with distinct neuronal tropism.

Target: GM1 ganglioside, phosphatidylinositol-4,5-bisphosphate, α-synuclein/lipid interaction interface

Supporting Evidence:

• PMID: 26858457 - GM1 ganglioside accelerates α-synuclein fibril formation with distinct structure
• PMID: 31586597 - Lipid rafts influence tau aggregate internalization and strain
• PMID: 28600496 - Membrane curvature controls Aβ oligomerization pathways

Predicted Experiment: Incubate monomeric proteins with membranes of varying lipid composition, then characterize resulting fibril structures via cryo-EM and test their propagation in neuronal cultures. Compare with patient-derived seeds.

Confidence: 0.68

Hypothesis 3: Early Oligomer Nucleation Determines Strain Identity

Title: Oligomer size and symmetry at the critical nucleus stage locks in strain-specific amyloid folds

Mechanism: The earliest oligomeric species (dimers, trimers, pentamers) adopt specific quaternary arrangements that are templated into mature fibrils. Inhibiting specific oligomeric "on-pathway" intermediates could redirect aggregation toward benign conformations or prevent strain formation entirely.

Target: Early oligomer interface (residues involved in nucleus formation: α-synuclein N-terminus, tau R2-R3 repeat domain)

Supporting Evidence:

• PMID: 31624385 - Different oligomeric intermediates lead to distinct amyloid strains
• PMID: 28898286 - Primary nucleation pathway determines prion strain characteristics
• PMID: 31138872 - Structural characterization of early Aβ oligomers shows strain-specific patterns

Predicted Experiment: Use single-molecule FRET and hydrogen-deuterium exchange to characterize early oligomers from different strains. Design conformation-specific antibodies or small molecules that stabilize non-pathogenic oligomers.

Confidence: 0.75

Hypothesis 4: Molecular Chaperone-Mediated Conformational Selection During Propagation

Title: Hsp90/Hsp70 chaperone system selectively amplifies specific amyloid conformers, defining strain identity

Mechanism: Molecular chaperones interact differentially with distinct amyloid conformers during cell-to-cell transmission, selectively fragmenting and amplifying certain strains while inhibiting others. This creates a "chaperone bottleneck" that maintains strain purity during propagation.

Target: Hsp90 (HSP90AA1), Hsp70 (HSPA8), Hsp40 (DNAJB6), co-chaperone BAG2

Supporting Evidence:

• PMID: 29358841 - Hsp90 regulates tau aggregation and spreading in vivo
• PMID: 32818464 - Hsp70 inhibits α-synuclein fibril fragmentation
• PMID: 29235560 - Hsp104 preferentially disaggregates specific prion strains

Predicted Experiment: knockdown/overexpression of specific chaperones in neuronal co-culture models transmitting different strains; measure changes in strain dominance via protease resistance profiling.

Confidence: 0.65

Hypothesis 5: RNA/DNA Co-Factors Create Strain-Specific Conformational Buffers

Title: Nucleic acid binding stabilizes strain-specific amyloid conformers and enables strain fidelity

Mechanism: Both DNA and RNA bind to aggregating proteins (TDP-43, FUS, α-synuclein) and act as conformational "scaffolds" that stabilize specific folds. These ribonucleoprotein complexes persist through propagation, explaining how strains maintain their identity across generations.

Target: TDP-43/RRM domain interaction with RNA; α-synuclein N-terminal nucleic acid binding; G-quadruplex sequences

Supporting Evidence:

• PMID: 32760057 - RNA promotes distinct α-synuclein aggregation pathways
• PMID: 28431797 - TDP-43 forms stable complexes with RNA in stress granules that nucleate aggregation
• PMID: 31358953 - DNA scaffolds accelerate huntingtin aggregation with altered strain properties

Predicted Experiment: Isolate nucleoprotein complexes from patient-derived seeds and characterize RNA/DNA content via sequencing. Test if removing nucleic acids alters strain conformation and transmissibility in cellular models.

Confidence: 0.58

Summary Table

| Hypothesis | Primary Target | Confidence |
|------------|----------------|------------|
| 1. PTMs as determinants | tau, α-syn S129 | 0.72 |
| 2. Lipid cofactors | GM1, membrane composition | 0.68 |
| 3. Early oligomer nucleation | Oligomer interface residues | 0.75 |
| 4. Chaperone selection | Hsp90, Hsp70, Hsp104 | 0.65 |
| 5. Nucleic acid scaffolds | RNA/DNA binding domains | 0.58 |

Key therapeutic strategies emerging: (1) PTM-modifying enzymes (kinases, phosphatases, transglutaminases), (2) lipid metabolism modifiers, (3) oligomerization inhibitors targeting nucleus formation, (4) chaperone modulators, (5) RNase/DNase treatment of seeds to destabilize conformational buffering.

Critical Evaluation of Pathological Seed Conformational Hypotheses

Hypothesis 1: PTMs as Conformational Determinants

Weak Links

• Directionality problem: PTMs are post-translational modifications—they occur on proteins already synthesized. The mechanism fails to explain how PTM patterns on the template seed would impose conformational constraints on the incoming monomer during templated conversion, unless proposing PTM transfer (chemically implausible).
• Redundancy concern: Many pathological proteins share overlapping PTM signatures (e.g., hyperphosphorylation is generic stress response). If PTMs were primary determinants, strains with identical PTM patterns should be identical, which they are not.
• Temporal disconnect: PTM patterns often change during disease progression; if they defined strain identity, strains would be unstable over time within patients.

Counter-Evidence

• Synthetic α-syn fibrils generated without defined phosphorylation still produce distinct strain-like properties in vivo (PMID: 29608179)
• Phosphatase treatment of tau seeds does not eliminate strain identity (PMID: 29100086)
• Non-pathological proteins can be heavily phosphorylated without aggregating

Falsifying Experiment

Co-incubation cross-protection assay: Dephosphorylate patient-derived seeds with broad-spectrum phosphatases/proteases, then test whether the resulting "PTM-stripped" seeds:

Lose strain identity in cellular models

Can no longer be distinguished by conformation-specific antibodies

Show altered templating efficiency for phosphorylated vs. non-phosphorylated monomers

If strain identity persists after complete PTM removal, PTMs are not determinants.

Revised confidence: 0.55 (down from 0.72)

Hypothesis 2: Lipid Membrane Cofactors

Weak Links

• Transmission barrier: Lipid bilayers are highly fragile and unlikely to survive extracellular transmission, endosomal trafficking, and lysosomal degradation during cell-to-cell propagation. How would membrane templates persist through these barriers?
• Cell-type independence: Strains maintain identity across different cell types with divergent lipid compositions. If membranes were primary determinants, strain identity should shift when seeds encounter different cellular environments.
• Unspecific lipid effects: Membrane surfaces generically catalyze protein aggregation; specific lipid-dependent conformational locking requires implausible selectivity.

Counter-Evidence

• Distinct amyloid strains are routinely generated in purely aqueous, membrane-free in vitro systems
• Pr

Feasibility Assessment: Pathological Seed Conformational Mechanisms

Hypothesis 1: PTMs as Conformational Determinants

Revised Confidence: 0.55

| Dimension | Assessment |
|-----------|------------|
| Druggability | High. Kinases (GSK3β, CDK5), phosphatases (PP2A), and transglutaminases are well-established drug targets with approved inhibitors (e.g., leflunomide, fostamatinib). Challenge: achieving substrate-specific modulation without broad toxicity. |
| Biomarkers | Moderate. Phospho-tau (p-tau 181, 217) and phospho-α-syn (pS129) have established clinical assays. PTM signatures via mass spectrometry could stratify strains. However, current assays don't capture strain-specific PTM patterns. |
| Model Systems | Mature. In vitro kinase/phosphatase treatment of seeds; cellular models with kinase inhibitors; patient-derived neurons. Cryo-EM can resolve PTM-dependent structural differences. |
| Clinical Constraints | Significant. Global PTM modulation affects thousands of substrates. PP2A agonists face autoimmune risks; kinase inhibitors have metabolic toxicities. Timing relative to disease stage unclear. |
| Safety | Concerning. Pan-kinase or pan-phosphatase approaches would disrupt essential cellular signaling. Requires exquisite selectivity for disease-relevant PTM sites. |
| Timeline/Cost | Phase II entry: 8–10 years, $300–500M. PTM enzyme modulators have established development pathways but require strain-selective optimization. |

Verdict: Mechanistically plausible for tau; less convincing for strain determination. Best suited as adjunctive therapy rather than strain-specific intervention.

Hypothesis 2: Lipid Membrane Cofactors

Revised Confidence: ~0.60

| Dimension | Assessment |
|-----------|------------|
| Druggability | Moderate. Ganglioside synthesis inhibitors (e.g., eliglustat for Gaucher's), phospholipase modulators, and membrane-curvature-targeting peptides exist. Cholesterol-lowering agents cross blood-brain barrier poorly. |
| Biomarkers | Weak. Lipidomic profiling from CSF/plasma shows disease-associated changes but lacks strain specificity. No validated membrane-composition biomarker for strain typing. |
| Model Systems | Well-established. Liposomes, supported bilayers, and neuronal membrane preparations enable controlled studies. Membrane-protein co-transmission can be monitored. |
| Clinical Constraints | Substantial. Membrane lipid composition is cell-type-specific and dynamically regulated. Chronic lipid modulation risks disrupting synaptic function, myelin integrity, and cell signaling. |
| Safety | Variable. Ganglioside depletion affects neuronal development; eliglustat has cardiac contraindications. Membrane-active compounds generally have narrow therapeutic windows. |
| Timeline/Cost | Phase I entry: 6–8 years, $200–400M. Brain-penetrant lipid modulators lacking, requiring new chemical entities. |

Verdict: Biologically compelling for templating but weak for transmission. Most relevant as prophylactic intervention before pathology is established.

Hypothesis 3: Early Oligomer Nucleation

Revised Confidence: 0.75 (highest merit)

| Dimension | Assessment |
|-----------|------------|
| Druggability | Challenging but tractable. Oligomer interface inhibitors (peptides, small molecules) can be designed using NMR/structural data. "Oligomer breakers" (e.g., CLR01) show promise. Requires distinguishing pathological from physiological oligomers. |
| Biomarkers | Emerging. Oligomer-specific antibodies (BAN2401, Aducanumab) detect pathological species in biofluids. smFRET and RT-QuIC can distinguish strain-associated oligomer signatures. |
| Model Systems | Technically mature. Single-molecule methods (FRET, TIRF, AFM) resolve early oligomers. Neuronal spreading models enable functional strain characterization. |
| Clinical Constraints | Moderate. Oligomers are transient and heterogeneous; timing of intervention critical. Strain-selective targeting would require companion diagnostics. |
| Safety | Theoretical advantage. Blocking pathological nucleation may preserve physiological oligomerization (e.g., for synaptic function). Risk if nucleation is essential for protein clearance. |
| Timeline/Cost | Phase I entry: 5–7 years, $150–300M. Structural biology advances (cryo-EM, AlphaFold) accelerate target identification. Oligomer-targeting antibodies already in trials. |

Verdict: Mechanistically strongest; addresses nucleation rather than propagation. Highest near-term clinical feasibility with existing antibody platforms.

Hypothesis 4: Chaperone-Mediated Selection

Revised Confidence: 0.65

| Dimension | Assessment |
|-----------|------------|
| Druggability | High. Hsp90 inhibitors (17-AAG, PU-H71), Hsp70 modulators (JG-98), and Hsp104 disaggregase enhancers have medicinal chemistry precedent. Geldanamycin derivatives already clinically tested. |
| Biomarkers | Moderate. Hsp90/Hsp70 client engagement measurable via proteomics; chaperone activity assays in patient-derived cells. Strain-specific chaperone binding not yet demonstrated. |
| Model Systems | Robust. Chaperone knockdown/overexpression models well-established. C. elegans and yeast prion models enable high-throughput screening. |
| Clinical Constraints | Significant. Hsp90 inhibition affects >200 clients; unfolded protein response activation limits dosing. Hsp70/Hsp104 brain penetration is poor. |
| Safety | Concerning. 17-AAG failed due to hepatotoxicity; broader chaperone modulation risks disrupting proteostasis of essential proteins. Mechanism may select for resistant strains rather than eliminate them. |
| Timeline/Cost | Phase I entry: 6–8 years, $250–400M. Chaperone modulators have oncology precedent; repurposing for neurodegeneration requires CNS optimization. |

Verdict: Best-in-class target for enhancing seed clearance; weaker as strain-specific intervention. Utility may lie in combination with strain-targeted approaches.

Hypothesis 5: Nucleic Acid Scaffolds

Revised Confidence: 0.58

| Dimension | Assessment |
|-----------|------------|
| Druggability | Low-moderate. RNase/DNase delivery to affected neurons is challenging; nucleic acid binding domain inhibitors (e.g., for TDP-43 RRM) are computationally designable. G-quadruplex stabilizers exist but lack specificity. |
| Biomarkers | Weak. RNA content of seeds has not been consistently measured in clinical specimens. No established biofluid assay for nucleoprotein seed complexes. |
| Model Systems | Feasible but underexplored. In vitro RNA/Aβ or RNA/α-syn co-assembly characterized; patient-derived seeds can be ribodepleted and tested. |
| Clinical Constraints |