--- Log opened Sat Sep 06 00:00:32 2025
00:46 -!- srk [~sorki@user/srk] has joined #hplusroadmap
01:19 < hprmbridge> kanzure> "Effects of gene dosage on cognitive ability: A function-based association study across brain and non-brain processes" https://pmc.ncbi.nlm.nih.gov/articles/PMC11701252/ "... a duplication at 2q12.3 associated with higher cognitive performance. [...] We identified a novel association between a duplication at 2q12.3 and positive effects on cognitive ability [...] EDAR, SH3RF3, SEPT10, SOWAHC"
01:22 < hprmbridge> kanzure> "The 865 kb duplication .. equivalent to 6.5 points of intelligence quotient (IQ). Given that the median age of our dataset is 60.7 years, it is possible that this duplication may be associated with a neuroprotective effect. We suspect that many more CNVs associated with higher cognitive ability will be identified in the future as sample sizes increase,"
01:29 < hprmbridge> kanzure> "Human restricted CHRFAM7A gene increases brain efficiency" https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1359028/full (2024)
01:29 < hprmbridge> kanzure> "CHRFAM7A direct allele carriers demonstrated an upward shift in cognitive performance including cognitive processing speed, learning and memory, reaching statistical significance in visual immediate recall (FDR corrected p = 0.018). The shift in cognitive performance was associated with smaller whole brain volume (uncorrected p = 0.046) and lower connectivity by resting state functional MRI in
01:29 < hprmbridge> kanzure> the visual network (FDR corrected p = 0.027) ... direct allele carriers harbor a more efficient brain consistent with the cellular biology of actin cytoskeleton and synaptic gain of function."
01:50 < hprmbridge> kanzure> "Reduced decision bias and more rational decision making following ventromedial prefrontal cortex damage" https://www.sciencedirect.com/science/article/pii/S0010945221000411 (2021)
01:53 < hprmbridge> kanzure> "Stimulation of the human ventral tegmental area increases strategic betting" https://academic.oup.com/brain/advance-article/doi/10.1093/brain/awaf210/8165980 (2025)
02:34 <+gnusha_> https://secure.diyhpl.us/cgit/diyhpluswiki/commit/?id=ce7498ad Bryan Bishop: more cognitive genetic modifications >> http://diyhpl.us/diyhpluswiki/neurosurgery/
03:42 < kanzure> after prolonged psychic battle, kimi k2 finally suggests: "The deubiquitination theory of cognitive ability posits that enhanced deubiquitinating enzyme activity (USP46, USP10, Usp9x) and reduced E3 ligase function (Nedd4-1, MYCBP2, FBXW8) increase synaptic information storage capacity by expanding the number of discriminable weight states per excitatory synapse. Ubiquitination of AMPA ...
03:42 < kanzure> ...receptor subunits and associated endocytic machinery normally drives activity-dependent receptor internalization during long-term depression (LTD), while deubiquitination blocks this endocytosis and stabilizes receptors at the postsynaptic membrane during long-term potentiation. By shifting the balance toward deubiquitination (either through enhanced DUB expression (as seen in human-specific ...
03:42 < kanzure> ...USP10 duplications) or reduced ligase activity (as in the MYCBP2 variant associated with superior human autobiographical memory)) synapses can maintain higher baseline receptor numbers and achieve greater conductance amplitudes without sacrificing the precision of bidirectional weight adjustments. This expanded synaptic weight resolution, multiplied across the many thousands of excitatory ...
03:42 < kanzure> ...synaptic inputs per pyramidal neuron, substantially increases per-neuron informational storage capacity and enables more precise encoding of information patterns in hippocampal and cortical circuits. The evolutionary expansion of deubiquitinating systems in human lineages may thus represent a molecular mechanism underlying enhanced cognitive performance through optimized synaptic proteostasis ...
03:42 < kanzure> ...rather than simply increased synapse number or firing rates. The deubiqituination theory's core premise is that the ratio of de-ubiquitinating activity to ubiquitinating activity at excitatory synapses is a tunable parameter that sets the number of discriminable synaptic weight states. Increasing de-ubquitination increases the information storage capacity of either neurons or synapses."
03:43 -!- stipa_ [~stipa@user/stipa] has joined #hplusroadmap
03:44 -!- raffaele [~raffaele@a120210.upc-a.chello.nl] has joined #hplusroadmap
03:45 < kanzure> more: https://diyhpl.us/~bryan/irc/chatgpt/dub.txt
03:45 < kanzure> there is also a human-specific copy number variation increase in USP10 actually.
03:47  * fenn sniffs
03:47 < fenn> smells fishy
03:49 < fenn> do copy number variations show up on GWAS?
03:50 < MuaddibLLM> fenn: Sometimes - standard SNP-only GWAS won’t see CNVs unless they’re tagged by nearby SNPs; you need explicit CNV calling from array intensities or WGS (e.g., PennCNV/QuantiSNP/GATK gCNV) and then run CNV-GWAS or burden tests, especially for rare CNVs.
03:52 -!- Netsplit *.net <-> *.split quits: rafspiny, srk, flyback, stipa
03:52 -!- stipa_ is now known as stipa
03:52 -!- srk_ [~sorki@user/srk] has joined #hplusroadmap
03:54 -!- srk_ is now known as srk
03:57 < jrayhawk> or use longer sequencing
03:58 < fenn> but they're looking for SNP markers
03:58 -!- flyback [~flyback@2601:540:c700:2380:ad21:5af9:ff04:4037] has joined #hplusroadmap
03:59 < kanzure> "The deubiquitinase USP6 affects memory and synaptic plasticity through modulating NMDA receptor stability" https://pmc.ncbi.nlm.nih.gov/articles/PMC6913916/ (2019)
03:59 < kanzure> instead of GWAS i think my preference is familial linkage studies, co-segregation studies, genomic report case study, or kindred studies.
04:00 < kanzure> much of the CNV research on cognitive phenotype has been about figuring out general broad genome CNV dosage effects on cognition, which is usually more to the debilitating side than enhancing side.
04:03 < kanzure> search " USP" and "ubiquitin" https://diyhpl.us/wiki/genetic-modifications/
04:59 < hprmbridge> kanzure> "USP8/UBPY enhances the protein levels of SHANK3 and SHANK1 and subsequently enhances dendritic spine density in primary rat neurons (Kerrisk Campbell and Sheng, 2018) "
04:59 < hprmbridge> kanzure> "USP8 deubiquitinates SHANK3 to control synapse density and SHANK3 activity-dependent protein levels" https://pmc.ncbi.nlm.nih.gov/articles/PMC6596000/
05:57 < hprmbridge> kanzure> "Memory in aged mice is rescued by enhanced expression of the GluN2B subunit of the NMDA receptor" https://pmc.ncbi.nlm.nih.gov/articles/PMC3540206/ (2014)
06:25 -!- TMM [hp@amanda.tmm.cx] has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
06:25 -!- TMM [hp@amanda.tmm.cx] has joined #hplusroadmap
07:19 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has quit [Quit: Avoid fossil fuels and animal products. Have no/fewer children. Protest, elect sane politicians. Invest ecologically.]
07:22 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has joined #hplusroadmap
08:09 < kanzure> "mnemotropic effect"
08:12 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has quit [Ping timeout: 272 seconds]
08:25 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has joined #hplusroadmap
08:39 < kanzure> dendritic mitochondria are apparently elongated and sometimes >10 microns in length; can't find a good ref for this. but this one https://pmc.ncbi.nlm.nih.gov/articles/PMC3139464/ reports axonal elongated mitochondria varying in length from 300 nm to 13 microns. my guess for mitochondria per pre-synaptic extrusion is at least 1 mitochondria, if not more throughout the dendrite or axon.
08:41 -!- L29Ah [~L29Ah@wikipedia/L29Ah] has quit [Read error: Connection timed out]
08:50 <+gnusha_> https://secure.diyhpl.us/cgit/diyhpluswiki/commit/?id=6e4464c7 Bryan Bishop: deubiquitination theory of learning >> http://diyhpl.us/diyhpluswiki/intelligence/
08:58 -!- L29Ah [~L29Ah@wikipedia/L29Ah] has joined #hplusroadmap
10:44 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has quit [Quit: Avoid fossil fuels and animal products. Have no/fewer children. Protest, elect sane politicians. Invest ecologically.]
10:45 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has joined #hplusroadmap
10:51 < kanzure> "In vivo proteomic mapping through GFP-directed proximity-dependent biotin labelling in zebrafish" https://elifesciences.org/articles/64631 (2021) using a genomically-encoded GFP antibody (nanobody) fragment "to target a biotin ligase to GFP-labelled proteins of interest".
10:53 < kanzure> "Proximity-dependent biotin labelling (BioID) using genetically engineered biotin ligases has emerged as a novel approach for studying protein-protein interactions and the subcellular proteome in living cells (Roux et al., 2012; Kim et al., 2016; Branon et al., 2018; Ramanathan et al., 2018). When fused to a protein of interest (POI) and expressed in cells, the promiscuous biotin ligases ...
10:54 < kanzure> ...covalently attach biotin to all proteins within a 10 nm radius, which can be subsequently isolated by streptavidin purification and identified by mass spectrometry."
11:00 < kanzure> can you use azobenzene to make an optically switchable proximity-dependent biotin? or can you genomically add a biotin tail to all the proteins?
11:03 < kanzure> "Optogenetic control of protein binding using light-switchable nanobodies" https://www.nature.com/articles/s41467-020-17836-8 "light-based protein purification in vitro"
11:04 < kanzure> well anyway, i didn't know about genomically encoded antibody domains or nanobodies as an option or alternative to other protein binding technologies; you get to use CDR loops, existing antibody libraries, etc.
11:05 < kanzure> oh i wonder if genomically encoded antibody domains could be expressed to a cell surface and used to pre-program mammalian immune system recognition
11:06 < MuaddibLLM> Short take: yes, optically switchable proximity biotinylation is doable by gating TurboID/BioID with light (Light-Activated BioID, or split-TurboID under optogenetic dimerizers - https://pmc.ncbi.nlm.nih.gov/articles/PMC10656424/ and foundational TurboID refs https://pmc.ncbi.nlm.nih.gov/articles/PMC6126969/), and azobenzene-biotin/streptavidin photoswitches exist for light-controlled binding 
11:06 < MuaddibLLM> (https://pubs.acs.org/doi/10.1021/bc010057q), but genome-wide “biotin tails” is impractical and likely toxic - instead target via GFP-nanobody TurboID in vivo (https://elifesciences.org/articles/64631) or light-switchable nanobodies for on-demand capture (https://www.nature.com/articles/s41467-020-17836-8).
11:07 < kanzure> "Mice like the “TAL mice” (transgenic adeno/associated locus) or the older “HuMab” strains do this with human Ig loci."
11:18 -!- stipa_ [~stipa@user/stipa] has joined #hplusroadmap
11:21 -!- stipa [~stipa@user/stipa] has quit [Ping timeout: 248 seconds]
11:21 -!- stipa_ is now known as stipa
11:28 < hprmbridge> lordkek__> @​everyone
11:28 < hprmbridge> lordkek__>
11:28 < hprmbridge> lordkek__> https://www.researchhub.com/fund/4385/cold-fusion-energy-storage-virtually-unlimited-energy-source
11:39 < hprmbridge> alonzoc> Gippity powered crackpottery strikes again.
11:53 -!- RangerMauve [m-4bpbmo@matrix.mauve.moe] has quit [Ping timeout: 248 seconds]
11:55 -!- RangerMauve [m-4bpbmo@matrix.mauve.moe] has joined #hplusroadmap
13:06 < hprmbridge> lordkek__> Human Evolution Ethics Council @​everyone
13:08 < hprmbridge> kanzure> banned
13:13 -!- stipa [~stipa@user/stipa] has quit [Quit: WeeChat 4.7.0]
13:24 -!- stipa [~stipa@user/stipa] has joined #hplusroadmap
13:45 < hprmbridge> naregon> the cherry on the cake is the mldy discord tag..
13:46 < hprmbridge> naregon> what a muppet
14:23 < hprmbridge> alonzoc> There's been a serious decline in the quality of crackpots since LLMs released. They used to be amusing and slightly concerning. Now it's just a bunch of grifters and narcissists
14:28 < jrayhawk> i am offended at the implication that i am anything other than the highest quality of crackpot
14:47 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has quit [Ping timeout: 256 seconds]
15:00 -!- stipa [~stipa@user/stipa] has quit [Read error: Connection reset by peer]
15:00 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has quit [Remote host closed the connection]
15:01 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has joined #hplusroadmap
15:01 -!- stipa [~stipa@user/stipa] has joined #hplusroadmap
15:31 < fenn> some VibeVoice 1.5b samples (the 7b model is better but i couldn't find any 1.5b examples online) https://vocaroo.com/1gVLNXcxGpfb https://vocaroo.com/1jdV55gMPN6W
15:50 -!- stipa [~stipa@user/stipa] has quit [Quit: WeeChat 4.7.0]
18:09 < hprmbridge> kanzure> "From waste to wealth: Repurposing slaughterhouse waste for xenotransplantation" https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2023.1091554/full
18:31 < hprmbridge> kanzure> "Donor MHC-specific thymus vaccination allows for immunocompatible allotransplantation" https://www.nature.com/articles/s41422-024-01049-5
18:35 < fenn> using food animals as a source of organs seems like a bad idea. they're always going to be less well cared for, higher pathogen load/probability, less healthy
18:36 < hprmbridge> kanzure> this seems like something that can be assayed or tested
18:36 < fenn> no, because there are potential zoonotic blood or tissue borne viruses that we don't know about
18:37 < fenn> did the article say anything new besides "hey remember that recellularization tech that never got off the ground"
18:38 < fenn> you don't even have to kill the animal, necessarily
18:38 < fenn> just steal its organs
18:38 < hprmbridge> kanzure> yeah about that, i don't remember ever seeing a decellularized scaffold being super useful except for small volumes
18:38 < fenn> this leaves its other organs fresh and viable for more organ harvesting :[
18:40 < hprmbridge> kanzure> in other news, i am being pitched an artificial womb venture
18:40 < hprmbridge> kanzure> focused on second trimester incubator technology (placenta preservation)
18:40 < hprmbridge> kanzure> most scalable approach seems to be pig blastocyst complementation to grow human uterus, but nobody seems to be focused on this strategy
18:40 < hprmbridge> kanzure> ex vivo uterus perfusion, or ex vivo perfusion of almost any organ, is apparently not an advanced art at this time.
18:43 < fenn> ECMO and nutrient solution? sounds like deep tech
18:43 < hprmbridge> kanzure> hello, FDA?
18:44 < fenn> i just think it will be a lot of development time and effort
18:44 < fenn> i guess this is some angel funding step
18:44 < hprmbridge> kanzure> gotta repopulate japan somehow though!
18:45 < fenn> honestly the pig thing seemed more realistic
18:45 < fenn> or capybara
18:45 < hprmbridge> kanzure> one issue with the pig surrogacy approach is, who would go first?
18:45 < fenn> i think people will have a stronger disgust reaction to pig surrogacy than to capybara surrogacy
18:46 < fenn> well you could do chimps first
18:46 < hprmbridge> kanzure> even after chimps you don't exactly want to be the first
18:46 < hprmbridge> kanzure> you would ideally want to do a hundred clones and see which one develops nicely
18:46 < fenn> ask louise brown?
18:47 < fenn> i don't understand what you mean by "do a hundred clones and see which one develops nicely"
18:47 < fenn> for great science?
18:47 < hprmbridge> kanzure> there were probably tons of rejected embryos before louise brown
18:47 < hprmbridge> kanzure> no, because you want a healthy kid
18:48 < fenn> why not just try one and see how it goes?
18:48 < fenn> are you going to raise 100 clones if they all work out?
18:49 < hprmbridge> kanzure> ask louise brown's predecessors
18:51 < hprmbridge> kanzure> was that the first attempt, or the first birth? there must have been previous human embryos.
18:51 < fenn> there were failed embryos and transfers previously
18:52 -!- TMM [hp@amanda.tmm.cx] has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
18:52 -!- TMM [hp@amanda.tmm.cx] has joined #hplusroadmap
18:52 < hprmbridge> kanzure> even normal human pregnancy has a pretty high birth defect rate
18:53 < fenn> i bet we can improve that significantly
18:54 < fenn> unlike the religio-political affair that is "nutrition", livestock feed is an actual science
18:54 < L29Ah> that's why livestock is being fed antibiotics prophylactically?
18:55 < fenn> that's probably due to the filthy crowded conditions
18:56 < fenn> you can actually do experiments with controlled diets and measure data with fine granularity
19:33 <+gnusha_> https://secure.diyhpl.us/cgit/diyhpluswiki/commit/?id=ee074102 Bryan Bishop: immune system engineering >> http://diyhpl.us/diyhpluswiki/xenotransplantation/
19:34 < kanzure> lots of very cool immune system engineering here: https://diyhpl.us/wiki/cell_therapy/#more-immune
19:34 < kanzure> the "thymus vaccination" thing seems like an obvious idea... i have not incorporated our prior references on thymus engineering.
19:43 < kanzure> 2023-09-30.log:18:48 < kanzure> "US government backs thymus rejuvenation project with $37m ARPA-H funding[..] Thymus Rejuvenation project is led by Thymmune Therapeutics, a George Church..."
19:44 < kanzure> 2020-02-13.log:10:36 < kanzure> thymus aging interventions and organoids http://gnusha.org/logs/temp/thymus.search-results.txt
19:46 < kanzure> where was the lymph node injection stuff.. there was a weird company and they were injecting an organ into lymph nodes to regenerate thymus? sorry, i'm misremembering i'm sure.
20:24 < kanzure> it's very fun throwing the intelligence/IQ section of genetic-modifications.mdwn into LLMs and seeing what they think.
20:24 < kanzure> all of this is (probably) in the training data, although not this particular combination of evidence
21:57 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has quit [Remote host closed the connection]
21:58 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has joined #hplusroadmap
22:15 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has quit [Remote host closed the connection]
22:15 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has joined #hplusroadmap
23:09 -!- darsie [~darsie@84-113-82-174.cable.dynamic.surfer.at] has joined #hplusroadmap
23:17 -!- justanot1 [~justanoth@gateway/tor-sasl/justanotheruser] has joined #hplusroadmap
23:18 -!- justanotheruser [~justanoth@gateway/tor-sasl/justanotheruser] has quit [Ping timeout: 272 seconds]
--- Log closed Sun Sep 07 00:00:32 2025