Of course, as usual, pro-AI people’s only argument is a hypothetical, what-if scenario.
If AI, specifically LLMs, are so great, how come it’s been 5 years and they haven’t meaningfully contributed to a cure for anything?
Fundamentally it’s the same bullshit capitalists have been repeating for the last 100 years. Capitalism is rapidly destroying the entire planet, and we’re on track to reach a mass extinction event before the end of the century, but their argument is usually among the lines of: “Well yes, but what if we innovate a groundbreaking technology that will save us all in a few years?”
It’s been 100 years and no such technology is even remotely close to being theoretically possible, just like LLMs aren’t anywhere close to being helpful in anything useful.
If AI, specifically LLMs, are so great, how come it’s been 5 years and they haven’t meaningfully contributed to a cure for anything?
Reminds me a little of cryptocurrencies. They were supposed to change everything, but all they did was enable unprecedented levels of scams and grifts and enable criminals to move money across the globe without any sensible control mechanisms.
Protein structure prediction models have contributed a lot. They are delivering much better results than the previous state of the art method of homology modeling.
Predicting structure from sequence in large scale has been a huge problem before and those attention network based models enabled in-silico screenings that were simply not possible before. This had a huge impact on pharmacologic research and especially research on binding motifs.
That said, these models work best when target proteins are one among many and don’t have very unique features. And things go downhill real fast when proteins form oligomeric structures or rely on structural features not yet resolved by empirical methods.
And things go downhill real fast when proteins form oligomeric structures or rely on structural features not yet resolved by empirical methods.
AF models oligomers just fine.
Not all proteins are structured.
Models are just models, cartoons until they are experimentally validated.
AI will generate all kinds of pathways and concepts and chemicals that are pointless without real experimental data. Done by real scientists. This is what Trump killed when he defunded the NCI via the NIH, from 1,100 funding announcements in 2024 to 11 in 2025. Apparently Americans don’t care, so that funding may never be restored, but even if it were restored, the post doc fellows who do the work have left and are not coming back, labs have closed down and will not re-open. This was a pipeline of billions that fed a US pharma industry worth trillions, now quickly relocating to China.
Ad1, yeah, maybe your proteins and at superficial investigation. But my experience with the oligomeric interfaces, when having structures that are not publicly accessible and therefore can’t be part of the training, was not so great.
Ad2, I am not talking about unstructured proteins. I am talking about structural features that have little to no precedence in public databases.
Ad3 Most models will be never validated by experimental structure elucidation. That’s the whole point of those models. To be able to get some information without having to do an undoable amoun high effort experiments. Sure, the end result will be verified but model quality matters, it is the factor that determines the success rate of the in-silico part of the experiments, ie how many candidates have to be screened on average to find sufficiently improved candidates.
Attention network based models are fine but they are not the golden calf that some are selling it either. You put it yourself, models are just models. Quality is not homogoenous though. Like I said, models for monomers are generally more credible.
Of course, as usual, pro-AI people’s only argument is a hypothetical, what-if scenario.
If AI, specifically LLMs, are so great, how come it’s been 5 years and they haven’t meaningfully contributed to a cure for anything?
Fundamentally it’s the same bullshit capitalists have been repeating for the last 100 years. Capitalism is rapidly destroying the entire planet, and we’re on track to reach a mass extinction event before the end of the century, but their argument is usually among the lines of: “Well yes, but what if we innovate a groundbreaking technology that will save us all in a few years?”
It’s been 100 years and no such technology is even remotely close to being theoretically possible, just like LLMs aren’t anywhere close to being helpful in anything useful.
Reminds me a little of cryptocurrencies. They were supposed to change everything, but all they did was enable unprecedented levels of scams and grifts and enable criminals to move money across the globe without any sensible control mechanisms.
Protein structure prediction models have contributed a lot. They are delivering much better results than the previous state of the art method of homology modeling.
Predicting structure from sequence in large scale has been a huge problem before and those attention network based models enabled in-silico screenings that were simply not possible before. This had a huge impact on pharmacologic research and especially research on binding motifs.
That said, these models work best when target proteins are one among many and don’t have very unique features. And things go downhill real fast when proteins form oligomeric structures or rely on structural features not yet resolved by empirical methods.
AF models oligomers just fine.
Not all proteins are structured.
Models are just models, cartoons until they are experimentally validated.
AI will generate all kinds of pathways and concepts and chemicals that are pointless without real experimental data. Done by real scientists. This is what Trump killed when he defunded the NCI via the NIH, from 1,100 funding announcements in 2024 to 11 in 2025. Apparently Americans don’t care, so that funding may never be restored, but even if it were restored, the post doc fellows who do the work have left and are not coming back, labs have closed down and will not re-open. This was a pipeline of billions that fed a US pharma industry worth trillions, now quickly relocating to China.
Ad1, yeah, maybe your proteins and at superficial investigation. But my experience with the oligomeric interfaces, when having structures that are not publicly accessible and therefore can’t be part of the training, was not so great.
Ad2, I am not talking about unstructured proteins. I am talking about structural features that have little to no precedence in public databases.
Ad3 Most models will be never validated by experimental structure elucidation. That’s the whole point of those models. To be able to get some information without having to do an undoable amoun high effort experiments. Sure, the end result will be verified but model quality matters, it is the factor that determines the success rate of the in-silico part of the experiments, ie how many candidates have to be screened on average to find sufficiently improved candidates.
Attention network based models are fine but they are not the golden calf that some are selling it either. You put it yourself, models are just models. Quality is not homogoenous though. Like I said, models for monomers are generally more credible.