Deep learning is solving biology\u2019s deepest secrets at breathtaking speed.<\/p>\n\n\n\n
Just a month ago, DeepMind cracked a 50-year-old grand challenge: protein folding<\/a>. A week later, they produced a totally transformative database of more than 350,000 protein structures, including over 98 percent of known human proteins. Structure is at the heart of biological functions. The data dump, set to explode to 130 million<\/a> structures by the end of the year, allows scientists to foray into previous \u201cdark matter\u201d\u2014proteins unseen and untested\u2014of the human body\u2019s makeup.<\/p>\n\n\n\n The end result is nothing short of revolutionary. From basic life science research to developing new medications to fight our toughest disease foes like cancer, deep learning gave us a golden key to unlock<\/a> new biological mechanisms\u2014either natural or synthetic\u2014that were previously unattainable.<\/p>\n\n\n\n Now, the AI darling is set to do the same for RNA.<\/p>\n\n\n\n As the middle child of the \u201cDNA to RNA to protein\u201d central dogma, RNA didn\u2019t get much press until its Covid-19 vaccine contribution<\/a>. But the molecule is a double hero: it both carries genetic information, and\u2014depending on its structure\u2014can catalyze biological functions, regulate which genes are turned on, tweak your immune system, and even crazier, potentially pass down \u201cmemories\u201d<\/a> through generations.<\/p>\n\n\n\n It\u2019s also frustratingly difficult to understand.<\/p>\n\n\n\n Similar to proteins, RNA also folds into complicated 3D structures. The difference, according to Drs. Rhiju Das and Ron Dror at Stanford University, is that we comparatively know little about these molecules. There are 30 times as many types of RNA as there are proteins, but the number of deciphered RNA structures is less than one percent compared to proteins.<\/p>\n\n\n\n The Stanford team decided to bridge that gap. In a paper<\/a> published last week in Science<\/em>, they described a deep learning algorithm called ARES (Atomic Rotationally Equivalent Scorer) that efficiently solves RNA structures, blasting previous attempts out of the water.<\/p>\n\n\n\n The authors \u201chave achieved notable progress in a field that has proven recalcitrant to transformative advances,\u201d said Dr. Kevin Weeks at the University of North Carolina, who was not involved in the study.<\/p>\n\n\n\n Even more impressive, ARES was trained on only 18 RNA structures, yet was able to extract substantial \u201cbuilding block\u201d rules for RNA folding that\u2019ll be further tested in experimental labs. ARES is also input agnostic, in that it isn\u2019t specifically tailored to RNA.<\/p>\n\n\n\n \u201cThis approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond,\u201d the authors said.<\/p>\n\n\n\n The importance of this biomolecule for our everyday lives is probably summarized as \u201cCovid vaccine, mic drop.\u201d<\/p>\n\n\n\n But it\u2019s so much more.<\/p>\n\n\n\n Like proteins, RNA is transcribed from DNA. It also has four letters, A, U, C, and G, with A grabbing U and C tethered to G. RNA is a whole family, with the most well-known type being messenger RNA, or mRNA, which carries the genetic instructions to build proteins. But there\u2019s also transfer RNA, or tRNA\u2014I like to think of this as a transport drone\u2014that grabs onto amino acids and shuttles them to the protein factory, microRNA that controls gene expression, and even stranger cousins that we understand little about.<\/p>\n\n\n\n Bottom line: RNA is both a powerful target and inspiration for genetic medicine or vaccines. One way to shut off a gene without actually touching it, for example, is to kill its RNA messenger. Compared to gene therapy, targeting RNA could have fewer unintended effects, all the while keeping our genetic blueprint intact.<\/p>\n\n\n\n In my head, RNA often resembles tangled headphones. It starts as a string, but subsequently tangles into a loop-de-loop\u2014like twisting a rubber band. That twisty structure then twists again with surrounding loops, forming a tertiary structure.<\/p>\n\n\n\n Unlike frustratingly annoying headphones, RNA twists in semi-predictable ways. It tends to settle into one of several structures. These are kind of like the shape your body contorts into during a bunch of dance moves. Tertiary RNA structures then stitch these dance moves together into a \u201cmotif.\u201d<\/p>\n\n\n\n \u201cEvery RNA likely has a distinct structural personality,\u201d said Weeks.<\/p>\n\n\n\n This seeming simplicity is what makes researchers tear their hair out. RNA\u2019s building blocks are simple\u2014just four letters. They also fold into semi-rigid structures before turning into more complicated tertiary models. Yet \u201cdespite these simplifying features, the modeling of complex RNA structures has proven to be difficult,\u201d said Weeks.<\/p>\n\n\n\n Current deep learning solutions usually start with one requirement: a ton of training examples, so that each layer of the neural network can begin to learn how to efficiently extract features\u2014information that allows the AI<\/a> to make solid predictions.<\/p>\n\n\n\n That\u2019s a no-go for RNA. Unlike protein structures, RNA simply doesn\u2019t have enough experimentally tried and true examples.<\/p>\n\n\n\n With ARES, the authors took an eyebrow-raising approach. The algorithm doesn\u2019t care about RNA. It discards anything we already know about the molecule and its functions. Instead, it focused only on the arrangement of atoms.<\/p>\n\n\n\n ARES was first trained with a small set of motifs known from previous RNA structures. The team also added a large bunch of alternative examples of the same structure that were incorrect. Digesting these example, ARES slowly tweaked its neural network parameters so that the program began learning how each atom and its placement contributes to the overall molecule\u2019s function.<\/p>\n\n\n\n Similar to a classic computer vision algorithm that gradually extracts features\u2014from pixels to lines and shapes\u2014ARES does the same. The layers in its neural network cover both fine and coarse scales. When challenged with a new set of RNA structures, many of which are far more complex than the training ones, ARES was able to distill patterns and novel motifs, recognizing how the letters bind.<\/p>\n\n\n\n \u201cIt learns entirely from atomic structure, using no other information\u2026and it makes no assumptions about what structural features might be important,\u201d the authors said. They didn\u2019t even provide any basic information to the algorithm, such as that RNA is made up of four-letter chains.<\/p>\n\n\n\n As another benchmark, the team next challenged ARES to RNA-Puzzles. Kicked off in 2011, RNA-Puzzles<\/a> is a community challenge for structural biologists to test their prediction algorithms against known experimental RNA structures. ARES blew the competition away.<\/p>\n\n\n\n The average resolution \u201chas stayed stubbornly stuck\u201d around 10 times less than that for a protein, said Weeks. ARES improved the accuracy by roughly 30 percent. It\u2019s a seemingly small step, but a giant leap for one of biology\u2019s most intractable problems.<\/p>\n\n\n\n Compared to protein structure prediction, RNA is far harder. And for now, ARES still can\u2019t get to the level of accuracy needed for drug discovery efforts, or find new \u201chot spots\u201d on RNA molecules that can tweak our biology.<\/p>\n\n\n\n But ARES is a powerful step forward in \u201cpiercing the fog\u201d of RNA, one that\u2019s \u201cpoised to transform RNA structure and function discovery,\u201d said Weeks. One improvement to the algorithm could be to incorporate some experimental data to further model these intricate structures. What\u2019s clear is that RNA seem to have a \u201cstructural code\u201d that helps regulate gene circuits\u2014something that ARES and its next generations may help parse.<\/p>\n\n\n\n Much of RNA has been the \u201cdark matter\u201d of biology. We know it\u2019s there, but it\u2019s difficult to visualize and even harder to study. ARES represents the next telescope into that fog. \u201cAs it becomes possible to measure, (deeply) learn, and predict the details of the tertiary RNA structure-ome, diverse new discoveries in biological mechanisms await,\u201d said Weeks.<\/p>\n\n\n\n Image Credit: neo tam<\/a> \/ Pixabay<\/a><\/em><\/p>\n\n\n\n Author:<\/strong><\/p>\n\n\n\n Shelly Xuelai Fan is a neuroscientist-turned-science writer. She completed her PhD in neuroscience at the University of British Columbia, where she developed novel treatments for neurodegeneration. While studying biological brains, she became fascinated with AI and all things biotech. Following graduation, she moved to UCSF to study blood-based factors that rejuvenate aged brains. She is the…\u00a0Learn More<\/a><\/p>\n\n\n\n Original Article<\/a><\/p>","protected":false},"excerpt":{"rendered":" Deep learning is solving biology\u2019s deepest secrets at breathtaking speed. Just a month ago, DeepMind cracked a 50-year-old grand challenge: protein folding. A week later, they produced a totally transformative database of more than 350,000 protein structures, including over 98 percent of known human proteins. Structure is at the heart of biological functions. The data dump, […]\n","protected":false},"author":1,"featured_media":1408,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"episode_type":"","audio_file":"","podmotor_file_id":"","podmotor_episode_id":"","cover_image":"","cover_image_id":"","duration":"","filesize":"","filesize_raw":"","date_recorded":"","explicit":"","block":"","footnotes":""},"categories":[13],"tags":[18,26,28,29,27],"series":[],"class_list":["post-1407","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-articulos-ingles","tag-inteligencia-artificial","tag-artificial-intelligence","tag-biotechnology","tag-biotecnologia","tag-inteligencia-artificial-2"],"episode_featured_image":"https:\/\/singularityumexico.com\/wp-content\/uploads\/2021\/09\/helix-5035873_1280-RNA-mRNA-deep-learning.jpeg","episode_player_image":"https:\/\/singularityumexico.com\/wp-content\/uploads\/2023\/05\/11711533-1673157178559-89a95be153719-4-scaled.jpg","download_link":"","player_link":"","audio_player":false,"episode_data":{"playerMode":"dark","subscribeUrls":{"apple_podcasts":{"key":"apple_podcasts","url":"","label":"Apple Podcasts","class":"apple_podcasts","icon":"apple-podcasts.png"},"stitcher":{"key":"stitcher","url":"","label":"Stitcher","class":"stitcher","icon":"stitcher.png"},"google_podcasts":{"key":"google_podcasts","url":"","label":"Google Podcasts","class":"google_podcasts","icon":"google-podcasts.png"},"spotify":{"key":"spotify","url":"","label":"Spotify","class":"spotify","icon":"spotify.png"}},"rssFeedUrl":"https:\/\/singularityumexico.com\/en\/feed\/podcast\/the-feedback-loop-by-singularity","embedCode":"Meet RNA<\/h3>\n\n\n\n
The Prediction Conundrum<\/h3>\n\n\n\n
An RNA Structural Code<\/h3>\n\n\n\n
\n\n\n\nDeep Learning Is Tackling Another Core Biology Mystery: RNA Structure<\/a><\/blockquote>