Occam's Typewriter

If you google "deepmind protein folding", among zillions, you get this: https://www.future-science.com/doi/10.2144/btn-2022-0007 If, OTOH, you add "criticism" to the query, among lots, you get these: https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-has-not-sol… and https://www.lesswrong.com/posts/6vybojuDEqaHeg8aN/a-confused-chemist-s… To be clear, I'm not trying to cherry pick "bad news"; I've been following DM for years;their work is nothing short of astounding, but what the MSM does with their work seems to reach beyond the bounds of actual fact. Sad - really - to see Scientific American land at such a low level of critical thinking. It's not the SA I grew up with anymore.

Gee has written what can best be described as a "notpology" here: http://occamstypewriter.org/cromercrox/2014/01/23/reflections-on-this-… He seems particularly thin-skinned, to me.

One of the major misunderstandings even many biologists have about how a cell works is a complete misconception of how jam-packed and dynamic a living cell actually is. See the following images for a pretty simulation of what a cell actually "looks" like on the inside: http://mgl.scripps.edu/people/goodsell/books/MoL2figures/Figure8.2-red… Webpage with more info: http://occamstypewriter.org/scurry/2010/08/30/the_crowded_cell/ Physicists/chemists often make fun of biology as "blob-logy" because we tend to draw biological systems as Blob-1 interacting with Blob-2 which leads to a change in Blob-3. It's a very useful abstraction, but it's also limited. In reality all these blobs are jammed together and moving around, creating a lot of random noise in the system. This is because every component in a cell is working at nano-scale (proteins are to a 1st approximation about 5nm in diameter). The rules are different at that scale, we don't experience anything like them in our daily lives. In other words, the components of the cell aren't doing chemistry at a bench, passing the results of one reaction to the next reaction, it's more like doing chemistry in a mosh pit. Biology has developed coping mechanisms for this insanity, but analogies drawn with things like computer processors and macro-world items are going to be somewhat wrong because of the inherent differences in scale.

Ha! That’s the hype there. They made predictions, like any other model out there. Their models are better but not close to what we get out of xray crystallography which is a painstaking process. Protein folding is nowhere near a solved problem. A third of proteins don’t have high enough accuracy. https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-has-not-sol…

Good idea. Here are some URLs that have failed to archive for me in the last few months (I suspect none are close to being that large): https://news.ycombinator.com/item?id=30467597 http://occamstypewriter.org/athenedonald/2022/02/27/a-university-educa… https://news.ycombinator.com/item?id=28232660 https://en.wikipedia.org/wiki/Mason_%26_Dixon

Alphafold 2 is very very cool, but we need a little dose of reality. It's still a bit away from really solving protein folding as it was marketed. For example, multi-complex proteins are not well predicted yet and these are really important in many biological processes and drug design: https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-has-not-sol… A disturbing thing is that the architecture is much less novel than I originally thought it would be, so this shows perhaps one of the major difficulties was having the resources to try different things on a massive set of multiple alignments. This is something an industrial lab like DeepMind excels at. Whereas universities tend to suck at anything that requires a directed effort of more than a handful of people.

I believe there is a fair amount of criticism explaining why DeepMind made a tremendous improvement to protein fold prediction while not actually solving the folding problem. https://occamstypewriter.org/scurry/2020/12/02/no-deepmind-has-not-sol… https://futurism.com/the-byte/scientists-unimpressed-googles-protein-f… https://www.businessinsider.com/deepmind-google-protein-folding-ai-alp…

I've been using a somewhat related technique in my research: Principal Coordinate Analysis (PCoA) also called Multidimensional Scaling (MDS) which works on a dissimilarity matrix. See [1] for the differences. [1] http://occamstypewriter.org/boboh/2012/01/17/pca_and_pcoa_explained/