{"id":1038,"date":"2020-12-03T17:49:15","date_gmt":"2020-12-03T17:49:15","guid":{"rendered":"http:\/\/joshmitteldorf.peachpuff-wolverine-566518.hostingersite.com\/?p=1038"},"modified":"2020-12-04T23:19:44","modified_gmt":"2020-12-04T23:19:44","slug":"deep-mind-knows-how-proteins-fold","status":"publish","type":"post","link":"https:\/\/scienceblog.com\/joshmitteldorf\/2020\/12\/03\/deep-mind-knows-how-proteins-fold\/","title":{"rendered":"Deep Mind Knows how Proteins Fold"},"content":{"rendered":"

This week, Deep Mind<\/a>, a London-based Google company, claims to have solved the number one most consequential problem in computational biochemistry: the protein-folding problem. <\/a><\/strong>\u00a0If true, this could be the start of something big<\/a>.<\/p>\r\n

\r\n

What does it mean, and why is it important?<\/strong> Let\u2019s start with signal transduction<\/a>. This is a word for the body\u2019s chemical computer. The nervous system, of course, constitutes a signal-processing and decision-making engine; and in parallel, there is a chemical computer.\u00a0The body has molecules that talk to other molecules that talk to other molecules, sending a cascade of ifs and thens down a chain of logic. The way molecules with very complex shapes fit snugly together is the language of the chemical computer. These molecules with intricate shapes are proteins, and they are not formed in 3D. Rather, DNA provides instructions for a linear peptide<\/a> chain of amino acids which are transcribed in ribosomes<\/a> (present in every cell) to create a chain of amino acids, chosen from a canonical set of 20<\/a>. Each peptide chain folds into a protein with a characteristic shape, and it is these shapes that constitute the body\u2019s signaling language. Most age-related diseases can be traced to an excess or a deficiency of these protein signal molecules.<\/p>\r\n

So signal proteins are targets of medical research. Pharmaceutical interventions may modify signal transduction, perhaps by goosing signaling at some juncture, or by siphoning off a particular signal with another chemical designed to fit perfectly into its bumps and hollows. Up until now, there has been a lot of trial and error in the lab, looking for chemicals with complementary shapes. Imagine now that the Deep Mind press release<\/a> is not exaggerating, and they really can<\/em><\/b> reliably predict the shape that a peptide will take once it is folded. Then many months of laboratory experiments can be replaced with many hours of computation. All the trial-and-error work can be done in cyberspace. An inflection point in drug development, if it\u2019s true. <\/p>\r\n\r\n

Why it\u2019s a Hard Problem<\/strong><\/p>\r\n\r\n\r\n\r\n

Computers solve large problems by breaking them down into a great many small ones. But protein folding can\u2019t be solved by looking separately at each segment of the protein molecule. Everything affects everything else, and the optimal shape is a property of the whole. Proteins are typically huge molecules, with hundreds or thousands of amino acids chained together. The peptide bonds allow for free rotation. So the number of shapes you can form with a given chain is truly humongus. The sheer number of possibilities would overwhelm any computer program that tried to deal with the different shapes one at a time.<\/p>\r\n\r\n\r\n\r\n

The thing that stabilizes a given shape is hydrogen bonding<\/a>. Nominally, each hydrogen atom can form only one bond to a carbon or oxygen, but every hydrogen is a closet bigamist, and it longs to couple with a nearby carbon or (better still) oxygen atom even as it is bound primarily to its LTR partner. Every twist and bend in the molecular chain allows some new opportunities for hydrogen bonding, while removing others. The breakthrough in computing came 1% inspiration, 99% perspiration (Edisonn\u2019s recipe<\/a>). A key input was to map the structure of 170,000 known, natural proteins, and to train the computer to be able to retrodict the known results. Then, when working with a new and unknown shape, the computer makes decisions that are based on its past success.<\/p>\r\n

How does it make the decisions? No one knows. One of the most successful techniques in artificial intelligence uses generic layers of input and output with programmable maps, and the maps are trained to give the right answer in known cases. But the fundamental logic that drives these decisions remains opaque, even to the programmers.\u00a0<\/p>\r\n