That was what me previous post was about. Arguably you could still get there if you allow for enough exploration, but you'd need some way to know whether the millions of things you end up with are sensible and that currently to me seems well outside of the scope in medicine.
-
New Forum Software Installed (Still a few issues but reopening the forum) More details.
List of causation hypothesis for follow up after DecodeME
- Thread starter Kiristar
- Start date
-
- Tags
- decodeme hypothesis
Jonathan Edwards
Senior Member (Voting Rights)
Of course. I am simply pointing out that so far AI has failed to go beyond a rehash of whatever is prominent in media and reviews. And as we know, it is empty vessels that make the most noise.
I have seen some of Dr Unutmaz's comments on AI. They are mostly about what is promised, not what has been delivered as far as I can see. My way of doing science may be messy and Maverick but it got me results repeatedly where others had got nowhere.
Jonathan Edwards
Senior Member (Voting Rights)
Yes, I think this is something like it. If putting together all we know about the usual rules leads to a putative mechanism it is likely to be wrong because if it followed the rues everyone would have it. One has to hold in the back of one's head a series of leaps of faith into the near impossible and look for a way that would make them stick on the rare occasion they operated.
You also have to be very clear about what you want your hypothesis to predict. My impression is that AI cannot avoid being primed with all the false assumptions that you find in textbook and review explanations of things. The biggest problem with ME/CFS is that people have thought hypotheses should predict all sorts of things that we don't actually have any reason to think occur.
Jonathan Edwards
Senior Member (Voting Rights)
A little while back I posted a query about circulating T cell findings in things like psoriasis. I am not sure one expects to find much. There need be no obvious shifts in population numbers. In fact the bad cells are likely to be absent from circulation, doing bad things elsewhere.
My thought was that you might pick something up by looking at how circulating T cells interact with other cells in short term culture. That may still not get over the problem but if people don't find much in diseases like psoriasis where we know there are misbehaving T cells then finding nothing in ME/CFS does not rule a T cell-mediated problem.
Jonathan Edwards
Senior Member (Voting Rights)
We ought to have some more hypotheses, surely?
It can't be that simple.
It can't be that simple.
Jonathan Edwards
Senior Member (Voting Rights)
I was looking up pathogenesis of Parkinson's Disease and asked Google and also PubMed. The result is instructive. Google mentions two risk genes but presents them in a way that makes no real sense. That is presumably because review articles have given plain English summaries of the roles for these genes that do not actually reflect the complex dynamics usefully. So Google tries to be clever and compare them and comes up with something that makes no sense.
The reviews are interesting in that they focus on specific pathological findings, like accumulation of alpha synuclein in granules in dopaminergic cells. But there is very little discussion of the systems dynamics that would fit the findings into a story to explain the genetics, the age range, the rate of onset and so on. The structure of the systems dynamics seems to me to be an essential starting point for building a plausible model. That was very much what Robert Phair was arguing for his shunt and we have argued over subsequently with interferons. What sort of process would manifest as spreading appearance of misfolded protein aggregates in. particular cell type. To me it seems very much like a prion story, but linked to some intrinsic system failure that only ever occurs after several decades (there are some very rare exceptions). I suspect that the environment is a red herring.
Having a workable model of dynamic structure may not necessarily affect your choice of treatment. We got the dynamics of RA a bit wrong on plasma cell longevity initially but rituximab still worked. But I think for ME/CFS having at least a high level model of overall dynamic would make it much easier to justify candidate treatments.
The problem with writing papers about system dynamics of disease is that, by and large, referees don't understand and reject the paper. So I can see why there are so few reviews that go into it.
The reviews are interesting in that they focus on specific pathological findings, like accumulation of alpha synuclein in granules in dopaminergic cells. But there is very little discussion of the systems dynamics that would fit the findings into a story to explain the genetics, the age range, the rate of onset and so on. The structure of the systems dynamics seems to me to be an essential starting point for building a plausible model. That was very much what Robert Phair was arguing for his shunt and we have argued over subsequently with interferons. What sort of process would manifest as spreading appearance of misfolded protein aggregates in. particular cell type. To me it seems very much like a prion story, but linked to some intrinsic system failure that only ever occurs after several decades (there are some very rare exceptions). I suspect that the environment is a red herring.
Having a workable model of dynamic structure may not necessarily affect your choice of treatment. We got the dynamics of RA a bit wrong on plasma cell longevity initially but rituximab still worked. But I think for ME/CFS having at least a high level model of overall dynamic would make it much easier to justify candidate treatments.
The problem with writing papers about system dynamics of disease is that, by and large, referees don't understand and reject the paper. So I can see why there are so few reviews that go into it.
chillier
Senior Member (Voting Rights)
Talked about an idea in this thread - Could nerve damage or retrograde microtubule based transport in axons explain the delay associated with PEM? about whether the time delay associated with PEM could be linked to the amount of time it takes from nerve injury/an event at nerve terminals to the nucleus generating a transcriptional response. This was based off the possibility that organophosphates, which cause certain neurons to fire constantly and would damage synapses, seem to be able to trigger an ME like illness.
I've learnt since then that apparently some forms of synaptic plasticity - namely synaptic scaling - also occur on timescales that line up well with PEM (hours to days). This is a homeostatic mechanism to keep global firing rates of a neuron relatively stable, such that if a neuron has been firing a lot due to stimulation at any of its synapses it will begin to scale down - and vice versa (The Self-Tuning Neuron: Synaptic Scaling of Excitatory Synapses, Turrigiano 2010)
I think it's also worth considering protein degradation, which has come up in a few forms now. The proteasome in Zhang HEAL2, and autophagy is plausibly linked to at least three genes in decode (FBXL4, CCPG1, RABGAP1L). Protein degradation appears to be a key part of synapse homeostasis.
In my opinion there are a bunch of things that point to synapses, but how clear is it really that there would be amplification, rather than attenuation or something else. It does seem like it could be quite complicated - if a lot of a neuron's synapses at the dendrites were compromised for example and connections were lost, maybe the neuron could end up firing more (erratically) later anyway due to a mechanism such as synaptic scaling as above.
I've learnt since then that apparently some forms of synaptic plasticity - namely synaptic scaling - also occur on timescales that line up well with PEM (hours to days). This is a homeostatic mechanism to keep global firing rates of a neuron relatively stable, such that if a neuron has been firing a lot due to stimulation at any of its synapses it will begin to scale down - and vice versa (The Self-Tuning Neuron: Synaptic Scaling of Excitatory Synapses, Turrigiano 2010)
I think it's also worth considering protein degradation, which has come up in a few forms now. The proteasome in Zhang HEAL2, and autophagy is plausibly linked to at least three genes in decode (FBXL4, CCPG1, RABGAP1L). Protein degradation appears to be a key part of synapse homeostasis.
In my opinion there are a bunch of things that point to synapses, but how clear is it really that there would be amplification, rather than attenuation or something else. It does seem like it could be quite complicated - if a lot of a neuron's synapses at the dendrites were compromised for example and connections were lost, maybe the neuron could end up firing more (erratically) later anyway due to a mechanism such as synaptic scaling as above.
Jonathan Edwards
Senior Member (Voting Rights)
I can definitely buy that.
Amplification was probably not the best word. Something is wrong with control mechanisms but as you say, it could be quite complicated!
Last edited:
jnmaciuch
Senior Member (Voting Rights)
I’m not a neuroscience person so maybe I’m missing some important context—but if it had to do with something traveling down a neuron that wasn’t an action potential, wouldn’t you expect the progression of PEM to be more, well, progressive across the body based on shortest to longest axonal length? I definitely get whole-body muscle weakness, stiffness, and pain as part of PEM and sometimes symptoms have a temporal offset between them, but not in any way that would correspond to neuron length. For me, it’s more that pain/stiffness/weakness is the worst in the muscle groups that I was using during activity, and then everywhere else it builds at the same rate and around the same intensity.
Re: MAIT T cells being found in the meninges in Mucosal-associated invariant T cells restrict reactive oxidative damage and preserve meningeal barrier integrity and cognitive function (2022)
Yes the claim is that they're tissue-resident, as part of the barrier function of meninges. From the editorial on the Zhang paper Meningeal MAIT cells maintain meningeal and brain function (2022) —
Yes the claim is that they're tissue-resident, as part of the barrier function of meninges. From the editorial on the Zhang paper Meningeal MAIT cells maintain meningeal and brain function (2022) —
chillier
Senior Member (Voting Rights)
For that particular idea, it wouldn't be that you would feel PEM in different places over time. It would be that signals from eg just used muscles would take a while to reach the neuron nuclei and cause a transcriptional response, but once it did the whole neuron could be eg sensitised at once leading then to PEM (which is a whole body feeling, at least for me). In other words the length of the axons would correspond to how soon PEM is felt, not where it is felt.
Anyway I think the scaling idea might be a bit better.