Cas13 gRNA Design for Silencing MAPT (Tau) Transcripts in Alzheimer's Disease
---
Title: Targeting the Exon 10 5' Splice Site with Cas13-dCas13 to Discriminate 4R vs 3R mRNAs
Description: By designing guide RNAs complementary to the 5' splice site region of exon 10 (nucleotides -6 to +20 relative to the splice junction), Cas13 can specifically bind and cleave 4R-tau mRNA while leaving 3R-tau mRNA intact. The 4R mRNA retains the complete exon 10 splice site context; the 3R mRNA skips this region entirely. This spatial distinction allows preferential 4R knockdown without affecting 3R-tau transcripts.
Target: MAPT exon 10 5' splice site sequence (5'-GUAGGG-3' motif)
Confidence: 0.65
> Basis: Splice sites are highly conserved; off-target risk mitigated by neuron-specific delivery systems. Precedent exists for splice-site targeting in other splicing disorders (e.g., SMA).
---
Title: Selective Disruption of 4R-tau mRNA Stability via Intron 10 Branch Point Sequence Targeting
Description: The branch point adenosine and polypyrimidine tract within intron 10 are essential for the splicing reaction that retains exon 10. Targeting these sequences with Cas13 can interfere with the recognition complex on the nascent pre-mRNA. This disrupts 4R-tau processing before mature mRNA export, reducing 4R-tau load while preserving the 3R-tau splicing pathway, which uses different intronic elements.
Target: MAPT intron 10 branch point region (~30-40 nucleotides upstream of 3' splice site)
Confidence: 0.45
> Basis: Mechanistically plausible but indirect; may affect splicing efficiency rather than direct cleavage. Requires high-efficiency Cas13 delivery to nuclear-nascent RNA complexes.
---
Title: Exploiting 4R-Tau-Specific Alternative Polyadenylation Signals for Targeted mRNA Decay
Description: 4R-tau transcripts utilize a distinct polyadenylation signal (AAUAAA variant) within intron 10 that is absent in 3R-tau. Guide RNAs designed to the pre-mRNA region flanking this polyA signal can recruit Cas13 to induce co-transcriptional cleavage and cytoplasmic decay specifically in 4R-tau mRNAs. This leverages endogenous RNA degradation machinery while maintaining splice site integrity.
Target: MAPT intron 10 alternative polyadenylation signal (position ~150-200 nt into intron 10)
Confidence: 0.55
> Basis: Alternative polyA sites in MAPT have been documented (Zhang et al., JBC 2021); targeting offers high specificity but may have variable efficiency depending on 3' end processing kinetics.
---
Title: Utilizing Cas13 to Prevent Trans-splicing Events that Generate Aberrant 4R-tau Variants
Description: A subset of pathogenic 4R-tau includes minor splice variants using cryptic exon 10 donor sites. Dual guide RNAs flanking the canonical exon 10 boundaries can simultaneously block cryptic splice site usage and induce RNase-mediated decay of mis-spliced transcripts. This preserves wild-type 3R-tau while eliminating pathologically altered 4R-tau isoforms.
Target: MAPT exon 10 flanking regions (5' splice donor: chr17:44074000-44074040; 3' acceptor: chr17:44083500-44083540)
Confidence: 0.50
> *Basis: Cryptic splicing in MAPT has been reported in PSP/C
This is a scientific skepticism task where I need to critically evaluate four hypotheses about selective 4R-tau silencing via Cas13 RNA editing. Let me go through each hypothesis systematically.
Let me work through each:
---
Core claim: By targeting the 5' splice site of exon 10, Cas13 can discriminate 4R vs 3R mRNA because 3R mRNA skips exon 10 entirely.
Weaknesses:
1. Sequence overlap issue: The 5' splice site (GUAGGG) is part of exon 10. While 3R-tau excludes exon 10, the pre-mRNA still contains this sequence in the nascent transcript. Cas13 acts on nascent RNA in the nucleus, so it could potentially bind to the pre-mRNA before splicing occurs.
2. Off-target risk: The GUAGGG motif is not unique to MAPT. This is a very short 6-nucleotide target, which increases off-target potential significantly.
3. Kinetic competition: Splicing occurs co-transcriptionally very rapidly.
Cas13 cleavage might not outpace the splicing machinery before exon 10 gets excised in 3R transcripts, undermining the intended specificity. Additionally, the targeted region sits within the coding sequence of 4R-tau, so even successful cleavage could produce truncated proteins with unpredictable consequences. There's also the fundamental challenge that 3R and 4R share the majority of their sequence, making any targeting strategy that relies on differential expression inherently difficult to execute with precision.
Alternative splicing of MAPT is tightly regulated with multiple splicing factors (SR proteins, hnRNPs) binding at the exon 10 splice site, which means an RNA-targeting approach might fail to outcompete these natural mechanisms. The specific 5' splice site sequence, while somewhat distinctive, may not be unique enough to avoid targeting other transcripts with similar motifs.
Testing this hypothesis would require designing gRNAs against the exon 10 5' splice site and measuring changes in 3R:4R ratio after Cas13 expression—ideally in a cell line that naturally produces both isoforms. If 3R levels remain unchanged, that would suggest the approach lacks the necessary specificity to achieve the desired discrimination.
Beyond that, I should examine whether any transcripts unrelated to MAPT share the same 5' splice site sequence and how the efficiency of Cas13 targeting stacks up against the rate at which splicing occurs. The current evidence seems to support this concept in other diseases like SMA, though the mechanistic basis for that precedent remains unclear.
The confidence score probably needs adjustment downward given the off-target concerns with a short 6-nucleotide target and the technical difficulty of outpacing co-transcriptional splicing. Something closer to 0.45-0.55 seems more realistic than the initial estimate of 0.65.
Moving to the second hypothesis about disrupting the branch point and polypyrimidine tract in intron 10—targeting these elements could theoretically shift the 3R:4R ratio toward more 3R expression. The branch point adenosine and polypyrimidine tract are essential for splicing at the 3' splice site of exon 10, so if these sequences are disrupted or blocked, exon 10 splicing could be compromised. This would preferentially reduce 4R-tau production. The key advantage here is that these sequences are only present in 4R-tau pre-mRNA since 3R-tau excludes this region entirely, making this approach potentially more specific than targeting the splice site itself.
However, there are significant technical obstacles. The branch point is located within intron 10, which requires Cas13 to access the nascent pre-mRNA in the nucleus with high efficiency—something that's proven difficult with current delivery methods. Additionally, the branch point sequence is relatively short (around 30-40 nucleotides), limiting the gRNA design options. Even with successful targeting, disrupting this region might simply reduce 4R-tau expression rather than eliminate it, and there's a risk of interfering with normal splicing of other genes that share similar branch point consensus sequences.
The specificity concern is substantial: the branch point consensus (YNYURAY in humans) appears frequently in transcripts genome-wide, and while intron 10 is large (approximately 10kb), off-target effects remain plausible. Moreover, the splicing machinery might adapt or compensate for partial disruption of the branch point region, diminishing the effect over time. There's also the possibility that 4R-tau uses alternative branch points within intron 10, similar to what occurs in other disease contexts. The mechanistic prediction itself is problematic—disrupting the branch point could trigger exon 10 skipping across both isoforms rather than selectively reducing 4R-tau, since this branch point is used by both splicing pathways.
Splicing occurs on a tight timeline (approximately 60-90 nucleotides from the branch point to the spliceosome assembly), so Cas13 may not have sufficient time to interact with the target before splicing is complete. Current evidence for branch point targeting is largely theoretical; functional studies are limited. Testing this hypothesis would require mapping the branch point using available datasets like branch-point-seq, then designing gRNAs to match it and assessing whether splicing is disrupted in the expected manner.
One key control would be validating that off-target genes with similar branch points show no splicing changes, and testing whether the reduction is actually due to the branch point disruption or simply to RNA cleavage elsewhere in the intron. If 4R-tau expression doesn't change despite successful Cas13 delivery, or if the effect persists even when the branch point is restored, that would suggest the mechanism isn't working as proposed. This hypothesis is more speculative than the first, making it harder to execute but potentially offering higher specificity if successful. I'm estimating around 0.35-0.45 confidence given the technical demands and mechanistic uncertainty.
For the alternative polyadenylation hypothesis, there's documented support for variable polyA sites in MAPT, and this would be the most selective approach if true since polyA signals are inherently transcript-specific. The mechanism is also distinct from splicing, avoiding some complications. However, alternative polyA sites are less well-characterized in this system and the efficiency could be inconsistent. Targeting the 150-200 nucleotide region might miss the actual polyA site, and even if the site is confirmed, simply targeting nearby doesn't guarantee the signal will be disrupted. There's also the risk that 3R-tau transcripts might use overlapping polyA signals, and Cas13-mediated cleavage could trigger broader RNA degradation rather than precise silencing.
The mechanistic concern is significant: if the alternative polyA site itself is part of intron 10, Cas13 cleavage might not prevent 4R-tau export if cleavage occurs downstream of the splice point, and the cleaved mRNA fragment could still be spliced normally. More critically, polyA site choice depends heavily on
Before evaluating individual hypotheses, a critical mechanistic constraint must be established. MAPT alternative splicing is governed by a complex interplay of cis-acting elements and trans-acting factors that act with remarkable speed and precision. Splicing is predominantly co-transcriptional, occurring as RNA polymerase II progresses through the gene. This means any nuclear-acting nuclease (including Cas13) must compete with splicing kinetics on a timescale of seconds. The spliceosome assembles rapidly, and by the time Cas13-mediated cleavage could substantially reduce target RNA, splicing may have already completed.
The fundamental challenge across all four hypotheses: 4R-tau and 3R-tau arise from the same pre-mRNA molecule. Preferential reduction of 4R-tau requires either (a) acting on the pre-mRNA before the splicing decision is made, or (b) specifically recognizing the spliced 4R-tau mRNA after processing. Both approaches face inherent technical barriers.
---
1. Co-transcriptional Splicing Conflict
The spliceosome assembles on pre-mRNA within seconds of transcription. The branch-point-to-splice-site distance is typically 18-37 nucleotides, and splicing catalysis occurs rapidly thereafter. Cas13, whether catalytically active or dead with fused effectors, requires guide RNA binding and RNP formation before cleavage can occur. This kinetic barrier may result in:
- Cas13 binding after splicing completes (target already eliminated regardless of isoform)
- Incomplete discrimination if splicing outpaces editing
2. Pre-mRNA Targeting Confounds Isoform Specificity
While the claim states "3R-tau mRNA skips this region entirely," this only applies to the processed mRNA. Nascent 3R-tau pre-mRNA contains exon 10 before splicing occurs. Cas13 localizes to the nucleus and can act on pre-mRNA. Thus, both isoforms are theoretically targetable during the transcription window. The hypothesis assumes Cas13 acts exclusively on mature cytoplasmic mRNA, which contradicts the nuclear localization of splice-site-targeting strategies.
3. Off-Target Risk from Short 6-Nucleotide Motif
The GUAGGG 5' splice site is not unique. Splice sites throughout the human genome share this consensus. A 6-nucleotide exact match occurs in hundreds of human genes. Even with mismatched seed regions, partial complementarity could drive off-target cleavage. The theoretical specificity is much lower than presented.
4. Coding Sequence Consequences
Even if 4R specificity is achieved, complete cleavage within the exon 10 coding region will generate truncated tau fragments. Whether these fragments are benign or toxic is unknown. Partial knockdown (rather than knockout) might be preferable, but the hypothesis doesn't address this.
| Experiment | Expected Outcome if Hypothesis Valid | Interpretation if Contradicted |
|------------|--------------------------------------|-------------------------------|
| Reporter assay: transfect 3R-tau minigene with/without Cas13 targeting exon 10 splice site | 3R-tau remains unchanged; 4R-tau reduces | If 3R-tau also decreases → pre-mRNA targeting invalidates specificity claim |
| RNA-seq after Cas13 treatment | Specific 4R reduction; no 3R change | Global splicing changes → off-target effects |
| Nascent RNA sequencing (GRO-seq) | Reduced transcription of 4R; 3R unaffected | If transcription unchanged but protein decreases → post-transcriptional mechanism not splice-site-specific |
| Off-target PCR across transcriptome | No unintended cleavage | Cleavage at off-target sites → need longer guide or higher specificity |
Rationale: The fundamental claim of isoform discrimination based on "spatial distinction" is undermined by the fact that pre-mRNA contains both exon 10 sequences regardless of eventual splicing fate. The 6-nucleotide target is too short for practical specificity. Splicing kinetics present an unresolved competition. While precedent exists for splice-site-targeting (SMA with antisense oligonucleotides), ASOs function through steric blockade of splice sites—not through nuclease cleavage, which is irreversible and potentially more hazardous.
---
1. Non-Specific Exon Skipping Risk
This is the most serious mechanistic flaw. The branch point and polypyrimidine tract are required for exon 10 inclusion in transcripts that use this splice site. If disrupted, the default outcome may be exon 10 skipping in both 3R and 4R pathways, not selective reduction of 4R-tau. The hypothesis assumes the branch point is uniquely required for the 4R pathway, but:
- 4R-tau uses the exon 10 inclusion pathway
- 3R-tau uses the exon 10 skipping pathway
- Disrupting elements required for exon 10 inclusion will shift both toward skipping
The result would be a reduction in both isoforms (potentially preferentially 4R if 3R-tau has additional pathways), not selective 4R knockdown.
2. Deep Nuclear Localization Requirement
Intron 10 is >10kb, and the branch point region is located upstream of the 3' splice site. Cas13 must access nascent pre-mRNA deep within nuclear compartment. Current AAV and LNP delivery systems show poor nuclear delivery efficiency in neurons. Even with successful nuclear localization, the pre-mRNA may be protected within the splicing complex (spliceosome).
3. Branch Point Sequence Degeneracy
The branch point consensus in humans is YNYURAY (where Y=pyrimidine, N=any, R=purine). This is present in thousands of introns. The "30-40 nucleotides" targeting window is imprecise—branch points can be distributed throughout this region. Without precise mapping in the relevant cell type, gRNA design is speculative.
4. Compensatory Splicing Mechanisms
Splicing factors (SF2/ASF, SC35, hnRNPs) binding to exon 10 splicing enhancers/silencers can compensate for partial branch point disruption. A
{"ranked_hypotheses": [{"title": "Alternative Polyadenylation Site Redirected Degradation", "description": "Targeting 4R-tau-specific alternative polyadenylation signals within intron 10 to induce co-transcriptional cleavage and cytoplasmic decay. This leverages documented alternative polyA sites in MAPT (position ~150-200nt into intron 10) that are absent in 3R-tau transcripts. The post-transcriptional mechanism may partially avoid co-transcriptional splicing kinetics conflicts, though delivery efficiency and 3' end processing kinetics remain challenges.", "target_gene": "MAPT (4R-specific intron 10 polyadenylation signal)", "composite_score": 0.48, "evidence_for": [{"claim": "Alternative polyA sites in MAPT have been documented", "pmid": "Zhang et al., JBC 2021"}, {"claim": "PolyA signals are highly transcript-specific due to unique 3' UTR contexts", "pmid": "General molecular biology principle"}], "evidence_against": [{"claim": "Alternative polyA sites are less well-characterized than splice sites in MAPT; may have variable efficiency", "pmid": "Literature gap"}, {"claim": "Pre-mRNA still contains intron 10 sequences before processing; partial targeting risk", "pmid": "Mechanistic analysis"}]}, {"title": "Splice-Site-Adjacent mRNA Targeting", "description": "Design guide RNAs complementary to the 5' splice site region of exon 10 (nucleotides -6 to +20) to selectively cleave 4R-tau pre-mRNA. Despite fundamental concerns about pre-mRNA discrimination (both isoforms contain exon 10 before splicing), targeting mature cytoplasmic mRNA may offer partial isoform specificity. The GUAGGG motif presents off-target risks, but strategic positioning could exploit differential mRNA export or stability kinetics.", "target_gene": "MAPT exon 10 5' splice site (5'-GUAGGG-3')", "composite_score": 0.38, "evidence_for": [{"claim": "Splice-site targeting precedent exists for splicing disorders (e.g., SMA with antisense oligonucleotides)", "pmid": "Clinical precedent"}, {"claim": "Splice sites are highly conserved regulatory elements", "pmid": "General molecular biology"}], "evidence_against": [{"claim": "Nascent 3R-tau pre-mRNA contains exon 10 before splicing; Cas13 can act on pre-mRNA in nucleus, undermining specificity claim", "pmid": "Mechanistic flaw identified"}, {"claim": "GUAGGG is only 6 nucleotides; occurs in hundreds of human genes; high off-target risk", "pmid": "Genomic analysis"}, {"claim": "Co-transcriptional splicing kinetics may outpace Cas13 editing; target may be eliminated before discrimination occurs", "pmid": "Kinetic analysis"}]}, {"title": "Dual-Guide Cas13 Strategy for Exon 10-Excluded Transcripts", "description": "Use two guide RNAs flanking canonical exon 10 boundaries to simultaneously block cryptic splice site usage and induce RNase-mediated decay of mis-spliced transcripts. Addresses a subset of pathogenic 4R-tau variants arising from trans-splicing events. More complex implementation but may capture pathologically relevant variants missed by single-target approaches.", "target_gene": "MAPT exon 10 flanking regions (chr17:44074000-44074040; chr17:44083500-44083540)", "composite_score": 0.35, "evidence_for": [{"claim": "Cryptic splicing in MAPT has been reported in PSP/CBS tauopathies", "pmid": "Literature cited but incomplete"}, {"claim": "Dual targeting may increase specificity through independent validation requirements", "pmid": "Technical rationale"}], "evidence_against": [{"claim": "Addresses only a subset of pathogenic 4R-tau; may not be primary mechanism in most cases", "pmid": "Scope limitation"}, {"claim": "Higher complexity increases off-target risk and delivery challenges", "pmid": "Technical burden"}, {"claim": "Pre-mRNA presence in both isoforms still applies", "pmid": "Fundamental limitation"}]}, {"title": "Intron 10 Branch Point/Polypyrimidine Tract Disruption", "description": "Target the branch point adenosine and polypyrimidine tract within intron 10 to interfere with the splicing recognition complex, disrupting 4R-tau processing before mRNA export. This is the highest-risk hypothesis due to potential non-specific exon 10 skipping affecting both isoforms, extensive nuclear delivery requirements for a >10kb intron target, and branch point sequence degeneracy (YNYURAY consensus) across the genome.", "target_gene": "MAPT intron 10 branch point region (~30-40 nucleotides upstream of 3' splice site)", "composite_score": 0.22, "evidence_for": [{"claim": "Branch point and polypyrimidine tract are essential for exon 10 inclusion splicing", "pmid": "General splicing mechanism"}, {"claim": "Disruption could reduce 4R-tau load by interfering with recognition complex", "pmid": "Theoretical basis"}], "evidence_against": [{"claim": "Disruption required for exon 10 inclusion will cause exon 10 skipping in BOTH 3R and 4R pathways, not selective 4R reduction", "pmid": "Critical mechanistic flaw"}, {"claim": "Requires high-efficiency