Search results

All good points. I suppose I was thinking more widely than LLMs. I’m not sure if a transformer architecture itself precludes usefulness. Having an attention mechanism introduce a more relational aspect and allowing information from the input at inference time to be included could be useful...

Hope so. Interesting in the context of age of samples and costs of keeping them which was brought up recently IIRC. Hopefully it’s just the former and they want people to use them while useful rather than issues over the latter

I’ve caught up now and agree with a lot of what @jnmaciuch has said, so don’t want my post to be seen as a response to that. Perhaps all I’d add is that where I see some value is not in any AI tool giving us an answer but in being partners, tools for researchers. But instead they often seem to...

Sorry if this misses some recent posts, something I wrote before catching up with the thread.. Maybe I can provide another perspective or perhaps some new data to this conversation. I wonder, can we express new ideas if all we are using is the same words? ML/AI is often just showing patterns...

Well this looks all rather unpleasant. The mention of Leeds reminds me of when a local service seemed to be, very kindly, trying to arrange for me to be ambulanced up there. Given the impact of much shorter journeys in ambulances and a trip to a local hospital I said no. A decision I’m rather...

That’s probably why it appealed to me :) I think we’re all looking forward to your, Jo and Jackie’s paper, the DecodeME results and the influx of neurobiologists! Until then we can amuse ourselves learning things and prodding and pulling at other things.

Some papers which came up in a search, the first had general background on HLA-C which I found interesting, beyond that maybe someone wiser can decide if they’re relevant HLA-C: evolution, epigenetics, and pathological implications in the major histocompatibility complex Major...

Yeah I absolutely understand both those feelings. I share that, perhaps intellectual curiosity, to get to the bottom of things and really fully understand. And have definitely felt a need for accountability and justice at many times. I’d be surprised if there’s anyone affected who hasn’t. I’m...

All variations which could just as likely a reflection of severity and the complex pathways involved, with different bits switching on/off or interacting up or downstream. I think we discussed this more in another thread recently but forget where. The differences don’t seem to me any greater...

I can understand why some want accountability. For me it’s a waste of energy for something which will get little to nothing in return. My choice is to focus on the present and the future, try to improve things for as many people as possible. That’s still going to be a lot of work but feels...

Back on the HLA-C talk. If I’m understanding this correctly it seems interesting that this is an area involved in the heavy chain given Audrey Ryback’s paper on BCR heavy chain repertoires? The strong linkage disequilibrium may be throwing things off for HLA-C specifically though? If this is...

I’m going to try a definition since this has been coming up a lot recently… Linkage disequilibrium is when at a population scale different segments of DNA, different genetic variations, occur together in different places more or less frequently than you would expect by chance. About right?

Whatever happened to, all the heroes?

HLA imputation and its application to genetic and molecular fine-mapping of the MHC region in autoimmune diseases Tatsuhiko Naito, Yukinori Okada Abstract Variations of human leukocyte antigen (HLA) genes in the major histocompatibility complex region (MHC) significantly affect the risk of...

A couple more papers posted which I found useful understanding a bit more about HLA imputation. Possibly worth understanding a bit about as background in advance of DecodeME papers HLA imputation and its application to genetic and molecular fine-mapping of the MHC region in autoimmune diseases...

Efficient HLA imputation from sequential SNPs data by transformer Kaho Tanaka, Kosuke Kato, Naoki Nonaka & Jun Seita Abstract Human leukocyte antigen (HLA) genes are associated with a variety of diseases, yet the direct typing of HLA alleles is both time-consuming and costly. Consequently...

Tutorial: a statistical genetics guide to identifying HLA alleles driving complex disease. Saori Sakaue, Saisriram Gurajala, Michelle Curtis, Yang Luo, Wanson Choi, Kazuyoshi Ishigaki, Joyce B. Kang, Laurie Rumker, Aaron J. Deutsch, Sebastian Schönherr, Lukas Forer, Jonathon LeFaive, Christian...

Maybe it depends? We don’t all have exactly the same symptoms…

I’m jealous of your laptop :) (and have found even the smaller Gemma3 models and certainly Gemini 2.5 Flash useful for exploring topics and helping me understand roughly what papers or people are talking about at times, not sure asking them to deduce is worth much beyond a bit of fun though)...

Ah, the inappropriate questionnaires will continue until morale improves