#1

This new paper is from Tim Sargeant’s group out of Australia. Tims one of the leaders in autophagy research. We’ve covered Tim’s work here in the past in these threads:

here: Measuring Autophagy in Body and Brain, Comparing Autophagy Activators
here: What’s autophagy? It’s the ultimate detox that doesn’t yet live up to the hype

In 2019 we summarized work relating to the potential use of rapamycin for treating Alzheimer disease (AD). We considered the commentary necessary because use of rapamycin in people with AD is a very real prospect and we wanted to present a balanced view of the likely consequences of MTOR (mechanistic target of rapamycin kinase) inhibition in the AD brain. We concluded that use of rapamycin, an MTOR inhibitor that increases macroautophagy/autophagy, could hold promise for prevention of AD if used early enough. However, MTOR inhibition appeared ineffectual in resolving existing amyloid pathology in AD mouse models. In this View article, we update these observations with new studies that have used rapamycin in AD models and provide evidence both for and against its use in AD. We also discuss rapamycin in the light of new research that describes rapamycin-induced autophagic stress in the ageing brain and autophagic stress as the origin of the amyloid plaque itself. We conclude that rapamycin will have complex effects on the brain in AD.

Paper (paywalled):

5 Likes
Rapamycin as a preventive intervention for Alzheimer’s disease in APOE4 carriers: targeting brain metabolic and vascular restoration
Predicting Alzheimers & Dementia (and minimizing risk)
Rapamycin treatment for Alzheimer’s disease and related dementias: a pilot phase 1 clinical trial
#2

After reading the studies/trials of Rapamycin on mice and the possibility of it causing Alzheimer’s, we are not sure whether we should continue taking Rapamycin and giving it to our dog. I would like to see a study of the people who have been taking Rapam for organ rejection purposes to find out if a number of those people have Alzheimer’s. What are your thoughts ?

#3

I think most of the data suggests that rapamycin is much more likely to prevent alzheimers than cause it.

Have you seen these papers and threads?

Rapamycin and Alzheimer’s disease: Time for a clinical trial? Matt Kaeberlein and Veronica Galvan

Here: Intranasal Rapamycin Lessens Alzheimer-like Cognitive Decline in a Mouse Model of Down Syndrome

Did you listen to the podcast with Arlan Richardson: 雷帕霉素简介，老年科学家 Arlan Richardson 访谈

Here is the thread about the one mouse study suggesting increase in plaques: Rapamycin increases Alzheimer's-associated plaques in mice, study finds

3 Likes
#4

Thank you for the submissions, I think it’s safe to say Rapa is not going to cause Alzheimer’s

1 Like
#5

Evaluating the effect of rapamycin treatment in Alzheimer’s disease and aging using in vivo imaging: the ERAP phase IIa clinical study protocol

Rapamycin is an inhibitor of the mechanistic target of rapamycin (mTOR) protein kinase, and preclinical data demonstrate that it is a promising candidate for a general gero- and neuroprotective treatment in humans. Results from mouse models of Alzheimer’s disease have shown beneficial effects of rapamycin, including preventing or reversing cognitive deficits, reducing amyloid oligomers and tauopathies and normalizing synaptic plasticity and cerebral glucose uptake. The “Evaluating Rapamycin Treatment in Alzheimer’s Disease using Positron Emission Tomography” (ERAP) trial aims to test if these results translate to humans through evaluating the change in cerebral glucose uptake following six months of rapamycin treatment in participants with early-stage Alzheimer’s disease.

Discussion

The ERAP study is a clinical trial using in vivo imaging biomarkers to assess the repurposing of rapamycin for the treatment of Alzheimer’s disease. If successful, the study would provide a strong rationale for large-scale evaluation of mTOR-inhibitors as a potential disease-modifying treatment in Alzheimer’s disease.

Trial registration

ClinicalTrials.gov ID NCT06022068

3 Likes
#6

A new paper, small pilot trial, no significant results:

Rapamycin treatment for Alzheimer’s disease and related dementias: a pilot phase 1 clinical trial

The 1 mg/day dose of rapamycin is selected based on our prior data in older adults demonstrating acceptable tolerability using this dosing regimen20. The primary aim of the study is to evaluate the central nervous system (CNS) penetrance of the drug by performing mass spectrometry on cerebrospinal fluid (CSF) collected prior to treatment and within 20–60 min of the final study drug dose.

The drug rapamycin has been shown to increase longevity and reverse changes in the brain associated with Alzheimer’s disease and related dementias in animal models. However, rapamycin’s role in the clinical setting is unclear. Here we show data from a phase 1 clinical trial in ten participants with mild cognitive impairment or Alzheimer’s disease who were treated with rapamycin (1 mg/day) for eight weeks. Findings show that rapamycin levels were not detectable in cerebrospinal fluid before or after treatment. All participants knew they were receiving rapamycin and did not experience any serious negative health events due to the treatment. Additionally, several Alzheimer’s disease and inflammatory biomarkers were increased from baseline to post-treatment. These results highlight the need to better understand the impact of rapamycin on Alzheimer’s disease in humans.

Open access paper:

https://www.nature.com/articles/s43856-025-00904-9

2 Likes
mTOR activation and AD
#7

I would think it is significant that rapamycin was not detected in CSF. This is much easier to test for than in brain tissue. It also gives a mechanism for testing higher dose rapamycin and seeing if that gets into CSF although CSF flow is not that good and that needs considering.

An interesting question is whether Rapamycin in the interstitial fluid in the brain could get from there into the CSF. Whichever way this is a good route to solid testing in vivo in homo sapiens as to better understanding of Rapamycin’s links to the brain.

I asked a chatGPT question about the difference between BBB and BCSFB.

Here’s a comparison of the two CNS barriers across several key features:

1. Location & Overall Architecture

  • Blood–Brain Barrier (BBB)

    • Found at the level of brain microvessels throughout the parenchyma.
    • Endothelial cells form the vessel wall, with pericytes embedded in the basement membrane and astrocyte end-feet enveloping the vessels.

  • Blood–CSF Barrier (BCSFB)

    • Located at the choroid plexus within the ventricles.
    • Fenestrated capillaries supply the plexus stroma, but the barrier itself is the contiguous epithelium of choroid plexus epithelial (CPE) cells linked by tight junctions.

2. Cellular Components & Tight Junctions

  • BBB

    • Endothelial cells possess continuous tight junctions (claudins, occludin) and minimal pinocytotic vesicles.
    • Pericytes regulate barrier integrity and blood flow.
    • Astrocytes induce and maintain barrier properties.

  • BCSFB

    • Choroid plexus epithelial cells form the selective barrier via their tight‐junction complexes.
    • Underlying capillaries are highly permeable (fenestrated), so it’s the epithelium, not endothelium, that restricts passage.

3. Permeability & Selectivity

  • BBB

    • Extremely low paracellular permeability—only very small (<400 Da), lipophilic molecules, or those with dedicated transporters can cross.
    • Robust efflux pumps (e.g., P-glycoprotein) that eject many xenobiotics back into blood.

  • BCSFB

    • Controls composition of the CSF rather than brain interstitial fluid.
    • More permissive to metabolic waste moving from CSF into blood, and provides active secretion of electrolytes and nutrients into CSF.

4. Transport Mechanisms

Mechanism BBB BCSFB
Passive diffusion Lipid‐soluble gases and drugs Similar, but contributes to CSF levels
Carrier‐mediated Glucose (GLUT1), amino acids, etc. High activity of nutrient transporters for CSF production
Receptor‐mediated Insulin, transferrin Less prominent
Efflux pumps Very high (P-gp, BCRP, MRPs) Present but generally lower activity

5. Functional Roles

  • BBB

    • Protects neuronal environment by strictly regulating ions, neurotransmitters, and plasma proteins in the interstitial fluid.

  • BCSFB

    • Produces and maintains the ionic and protein composition of CSF (~500 mL/day turnover), providing buoyancy and waste clearance.

6. Implications in Disease & Drug Delivery

  • BBB

    • Often the primary obstacle for CNS drug delivery; its disruption is implicated in stroke, multiple sclerosis, and Alzheimer’s.

  • BCSFB

    • Altered CSF secretion/composition can contribute to hydrocephalus, meningitis, and drug clearance issues in the ventricles.

Summary

  • The BBB is a capillary‐based endothelial barrier reinforced by glia, optimized to protect the neuronal milieu.
  • The BCSFB is an epithelial barrier in the choroid plexus specialized for CSF production and maintenance.

Though both serve to shield the CNS, their distinct locations, cellular structures, and transport systems tailor them to complementary but different roles in brain homeostasis.

1 Like
#8

This is an interesting sub response from chatGPT

Efflux and clearance mechanisms
Even if rapamycin diffuses into the interstitial fluid, it is a known substrate for P-glycoprotein and other efflux transporters at both the blood–brain and blood–CSF barriers. These pumps rapidly shuttle rapamycin back into the bloodstream, preventing accumulation in the CSF or deeper into the parenchyma.

Which if we can substantiate that would
a) Indicate why Rapamycin is generally thought not to pass the BBB
b) But explains why high dose Rapamycin is thought to pass the BBB

But also indicates that what is needed for the brain is an mTOR inhibitor that is not a known substrate for P-glycoprotein and other efflux transporters (whatever the other ones are)

More from chatGPT

Research on rapamycin’s interactions with ATP-binding cassette (ABC) efflux transporters has demonstrated that it is a transport substrate for both P-glycoprotein (ABCB1) and the breast cancer resistance protein (ABCG2/BCRP), and that these transporters substantially limit its accumulation in the CNS.

  1. Substrate affinity and impact on brain penetration at the BBB
    In a concentration‐equilibrium transport assay (CETA) using LLC-PK1 cells transduced with murine Mdr1a (the rodent homolog of human ABCB1) and Bcrp1, rapamycin was actively translocated from the basolateral to the apical compartment, demonstrating significant P-gp– and BCRP-mediated efflux (DSpace). Moreover, in Abcb1a/b–/–;Abcg2–/– knockout mice lacking both transporters, brain penetration of rapamycin increased approximately 13-fold compared to wild-type animals, confirming that these pumps at the BBB “profoundly impair” rapamycin entry into the parenchyma (DSpace).

  2. Expression and function of P-gp at the blood–CSF barrier
    P-glycoprotein is not only abundant in brain capillary endothelial cells but also highly expressed on the apical membrane of choroid plexus epithelial cells, where it contributes to the blood–CSF barrier. Immunohistochemical and in vivo SPECT imaging studies using the P-gp/MRP substrate ^99mTc-sestamibi have shown a strong blood-to-CSF concentration gradient across intact choroid plexus epithelium in humans, indicating active efflux into the blood compartment (考研). General surveys of P-gp distribution further confirm its presence in the choroid plexus epithelium, functioning analogously to its role at the BBB to pump xenobiotics back into the vasculature (Wikipedia).

Taken together, these data establish that rapamycin is a bona fide substrate for P-gp (and BCRP) at both the BBB and the blood–CSF barrier, and that these transporters actively shuttle the drug from the CNS compartments back into the bloodstream, severely limiting its CNS exposure.

1 Like
#9

I think this is really important because both PD and ALS/MND appear to result from mitochondrial problems and to actually fix those means getting to CNS cells. What it does is identify what sort of mTOR inhibitor might actually do the job.

#10

We already discussed this study (CARPE_DIEM NCT04200911) as the results were published months ago on ClinicalTrials.gov but it’s even worse than I thought, not only did rapa fail to get into the CSF but several biomarkers also got worse after treatment? That’s pretty bad for rapamycin in AD…

#11

What appears to be the case is that if Rapamycin gets into the CSF it is removed really quickly. Similarly with the interstitial fluid. That explains the large dose thing. If it simply did not cross the barrier having a larger dose should not have an effect However, if it is crossing them being pumped out rapidly then a larger dose is likely to create a small result rather than a zero figure.

#12

In the MSA trial of rapamycin they did not find brain mTOR interaction at 6 mg/day over months. All the evidence points to rapa not getting into the brain.

#13

Oral rapamycin (sirolimus) exhibits low and variable penetration into the central nervous system. Direct measurement of brain levels in humans is extremely challenging, and most insights come from cerebrospinal fluid (CSF) assays, neuron-derived extracellular vesicle (NEV) biomarkers, and preclinical rodent studies.

1. Human Studies

CSF quantification limitations
– In a recent open-label pilot of weekly 7 mg rapamycin in Alzheimer’s patients, investigators attempted direct CSF measurement by LC-MS/MS but found the lower limit of quantification (LLOQ) was ~10–20 ng/mL—over an order of magnitude higher than expected free CSF levels (~0.2 ng/mL, given only ~0.17% of whole-blood rapamycin is unbound) (medRxiv). Thus, standard clinical assays cannot reliably detect rapamycin in human CSF after oral dosing.

NEV biomarker proxy for brain target engagement
– Using neuron-derived extracellular vesicles isolated from plasma, a Phase 1 trial gave healthy volunteers up to 6 mg/day oral sirolimus. NEV phospho-S6/S6 ratios (a readout of mTOR activity) showed no evidence of brain mTORC1 inhibition at these doses (考研). This suggests that, at typical immunosuppressive or anti-aging regimens, rapamycin fails to reach sufficient brain concentrations to engage its target in humans.

2. Preclinical Rodent Data

Although human CNS levels are difficult to measure, multiple rodent models demonstrate that oral rapamycin can achieve detectable—and functionally active—brain concentrations.

2.1 Mouse Alzheimer’s models

  • PDAPP (J20) mice, dietary rapamycin (2.24 mg/kg/day)
    Spilman et al. fed transgenic PDAPP mice chow containing 2.24 mg/kg/day rapamycin for 13 weeks; they observed lowered Aβ42 levels, improved cognition in Morris Water Maze, and reduced mTOR signaling in hippocampal extracts. While absolute brain concentrations were not reported, the functional mTOR inhibition indicates sufficient cerebral exposure (Frontiers).

  • 3xTg-AD mice, early intervention
    In 3xTg-AD mice (APP, PS1, tau mutations), inclusion of 2.24 mg/kg/day rapamycin in the diet from 2 months of age restored mTOR signaling to near-normal and attenuated both Aβ and tau pathologies, again implying brain penetration at this dosing level (Frontiers).

2.2 C3B6F1 hybrid lifespan study

  • Intermittent vs continuous dosing (42 mg/kg in food)
    Harrison et al. compared continuous versus weekly-intermittent 42 mg/kg rapamycin in C3B6F1 mice. Continuous dosing yielded higher tissue—including brain—concentrations, whereas intermittent dosing produced markedly lower cerebral levels (though both extended lifespan). The study did not specify ng/g values for brain but highlighted a clear dosing-concentration relationship (Alzheimer’s Drug Discovery Foundation).

2.3 Mouse cavernous malformation model

  • Oral gavage (1.6–4.8 mg/kg/day)
    In CCM-bearing mice, daily oral sirolimus (1.6–4.8 mg/kg) achieved plasma troughs of 5–15 ng/mL. Although brain tissue was not directly assayed, these plasma levels bracket typical immunosuppressive targets and set a benchmark for future CNS PK studies (PMC).

3. Rat Comparisons

  • Intranasal vs oral in rats
    Wang et al. administered rapamycin orally (dose unspecified) versus intranasally (0.04 mg/kg) in rats. Intranasal delivery led to significantly higher brain concentrations and faster absorption, whereas equivalent oral dosing produced only trace cerebral rapamycin—underscoring poor BBB passage by the oral route (考研).

4. Mechanistic Considerations

  • P-glycoprotein efflux
    Rapamycin is a P-gp substrate; strong expression of P-gp at the BBB further limits CNS uptake.
  • High protein binding
    With ~92% of drug bound in plasma, only the unbound fraction (~8%) is available to cross membranes, and only ~0.17% of total remains free in blood.
  • Lipophilicity vs size
    Although rapamycin is lipophilic, its large macrolide structure (~914 Da) falls above the ideal molecular weight for passive diffusion.

5. Summary and Outlook

  1. Human CNS levels

    • Direct CSF assays lack sensitivity; NEV biomarkers indicate negligible brain mTOR engagement at up to 6 mg/day oral dosing.

  2. Rodent evidence

    • Oral dosing in mice (2–42 mg/kg/day) yields functional brain mTOR inhibition, though quantitative brain levels (ng/g) are rarely reported.

  3. Strategies to improve delivery

    • Alternative routes (intranasal, nanoparticle carriers, molecular shuttles) are under active investigation to circumvent P-gp and tight-junction barriers.

Key takeaway: Oral rapamycin produces sub-therapeutic CNS exposure in humans—below both analytical detection and functional engagement thresholds—while rodent models demonstrate that much higher relative doses are required to achieve similar brain effects. Translating rapamycin’s neuroprotective potential into the clinic will likely demand targeted delivery strategies beyond conventional oral dosing.

2 Likes
#14

This gives another useful nugget of information that to cross a membrane requires unbound rapamycin.
(if it is true)

1 Like
#15

https://www.nature.com/articles/s43856-025-00904-9

Rapamycin is not detectable in the CSF before or after treatment, but several Alzheimer’s disease and inflammatory biomarkers increase after treatment. Our results highlight the need to better understand the biological effects and clinical impact of repurposing rapamycin for Alzheimer’s disease.

I wish they also had a study with everolimus which seems to cross the blood-brain barrier.

#16

Honestly a fairly bad/limited study IMO. Firstly, CSF isn’t a good proxy for brain penetration, so the absence of Rapa in the CSF doesn’t mean that it won’t reach the brain, nor would presence in the CSF show that it reaches brain. In fact, the authors actually cite previous studies showing that oral Rapa, in human, does reach brain tissue. So why measure CSF as your primary endpoint? I don’t really get it.

All participants received rapamycin (1 mg/day) for eight weeks.

Oops. Should have consulted this forum before starting a clinical trial, lol

Assessment of hematological studies indicated that all parameters remained within the normal range, although statistically significant reductions in red blood cell distribution width (RDW), mean corpuscular volume (MCV), and mean corpuscular hemoglobin (MCH) were observed from baseline to post-treatment. Other erythrocyte parameters, including hemoglobin, hematocrit, and red blood cell count, remained stable.

All in the Levine phenoage calculator! And this seems to be pretty reliable across most human studies.

Systolic blood pressure increased from baseline to post-treatment (baseline: 127.8 ± 19.0 mmHg; post-treatment: 138.2 ± 22.1 mmHg, t (9) = 4.226, p = 0.002).

That’s a huge increase. Not sure what to make of that. Small sample size, but it’s pretty consistent and the P value is very low. The discussion section speculates that this is simply reversion to the mean, which might be true. And there’s no placebo group, so we’ll never know.

The secondary outcomes are pretty much pointless. Nobody is going to have significant cognitive changes in 8 weeks with 9-10 patients.

As for the cytokines and AD “biomarkers”, I have little faith. As you can see, they’re all over the place, and none of them are significant once you account for multiple comparisons.

1 Like
#17

This can be done without extracting brain tissue.

There are lots of problems from measuring CSF particularly by lumbar puncture, but the patient is unlikely to suffer long term harm.

Measuring it in the brain which would give a better guide as to brain tissue levels would be much harder.

I think one reason why the importance of CSF has been downgraded (as I see it) is the difficulty of measuring it - particularly dynamic changes.