[{"@context":"https:\/\/schema.org\/","@type":"BlogPosting","@id":"https:\/\/blog.terabox.com\/insights\/alphafold-solving-protein-folding-problem#BlogPosting","mainEntityOfPage":"https:\/\/blog.terabox.com\/insights\/alphafold-solving-protein-folding-problem","headline":"AlphaFold: Solving the Protein Folding Problem with AI","name":"AlphaFold: Solving the Protein Folding Problem with AI","description":"\ud83d\udcfa Today’s recommended deep-dive video: https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw Beyond the Bitter Lesson: How AlphaFold Solved Biology\u2019s Holy GrailThe Protein Bottleneck and the AlphaFold LeapEngineering Architecture vs. Raw ScaleFrom AlphaFold 3 to the Future of AI for ScienceKey TakeawaysQ&A Beyond the Bitter Lesson:... ","datePublished":"2026-07-17","dateModified":"2026-07-17","author":{"@type":"Person","@id":"https:\/\/blog.terabox.com\/author\/flextech-admin\/#Person","name":"flextech-admin","url":"https:\/\/blog.terabox.com\/author\/flextech-admin\/","image":{"@type":"ImageObject","@id":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","url":"https:\/\/secure.gravatar.com\/avatar\/ad516503a11cd5ca435acc9bb6523536?s=150&d=mm&r=gforcedefault=1","height":96,"width":96}},"publisher":{"@type":"Organization","name":"terabox","logo":{"@type":"ImageObject","@id":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","url":"http:\/\/blog.terabox.com\/wp-content\/uploads\/2021\/11\/logo\u4ea7\u54c1\u540d-\u7ad6\u7248.png","width":900,"height":900}},"image":{"@type":"ImageObject","@id":"https:\/\/img.youtube.com\/vi\/e3gBwLWAerw\/maxresdefault.jpg","url":"https:\/\/img.youtube.com\/vi\/e3gBwLWAerw\/maxresdefault.jpg","height":"","width":""},"url":"https:\/\/blog.terabox.com\/insights\/alphafold-solving-protein-folding-problem","video":{"@context":"http:\/\/schema.org\/","@type":"VideoObject","@id":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw#VideoObject","contentUrl":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw","name":"He won a Nobel here for AlphaFold. Then he left. - John Jumper","description":"This episode is sponsored by Notion.\u00a0Learn more about Notion's Developer Platform today at\u00a0https:\/\/notion.com\/mlst\n\nProtein folding stalled biology for fifty years. A sequence of amino acids dictates a three-dimensional shape, but reading that shape meant a year and roughly $100,000 of crystallography per structure. Then AlphaFold 2 won CASP14 so decisively the organizers called the problem essentially solved.\n\nIn this documentary cut, John Jumper, who shared the 2024 Nobel Prize in Chemistry and has since left DeepMind for Anthropic, walks Tim Scarfe through what the system did and, more interestingly, what it did not. The architecture gets a proper dissection: MSAs, the Evoformer, invariant point attention, the FAPE loss, and Jumper's correction of the equivariance story, which ablations valued at roughly 2.5 of 30 GDT points rather than the whole win. He is blunt about the limits. AlphaFold predicts one experiment extraordinarily well; it is not a model of the cell, it does not capture dynamics, and on a given drug target it is \"wrong nine times out of ten.\"\n\nFrom there: the AlphaFold Database of 200M+ predicted structures, AlphaFold 3 and ligands, Isomorphic Labs, and Jumper's quarrel with the bitter lesson, where finite data and human hypotheses still matter. Emmanuel Nji of BioStruct Africa closes the film on what changes when work that took years now takes months, and on training the next thousand structural biologists across Africa.\n\n---\nTIMESTAMPS:\n00:00:00 Cold open: predicting nature with a button press\n00:01:03 The protein folding bottleneck and CASP\n00:04:39 The Nobel, the database, and the move to Anthropic\n00:05:50 Sponsor (Notion) and framing: what AlphaFold does not claim\n00:07:39 Proteins as self-assembling nanomachines\n00:12:24 From structures to biology: drug discovery and Midnolin\n00:17:37 The humility of AlphaFold: a narrow predictor\n00:22:18 Inside the architecture: Evoformer, IPA and FAPE\n00:30:20 Ruthless empiricism: ablations and 100x in data\n00:35:20 Predict, control, understand\n00:40:00 Against the bitter lesson; AlphaFold 3 as diffusion\n00:45:07 Intelligence, representations and AGI\n00:49:23 Epilogue: AlphaFold in Africa\n00:52:16 Closing: the case for hybrid science models\n\n---\nREFERENCES:\norganization:\n[00:01:55] Critical Assessment of Structure Prediction (CASP)\nhttps:\/\/predictioncenter.org\/\n[00:04:39] The Nobel Prize in Chemistry 2024\nhttps:\/\/www.nobelprize.org\/prizes\/chemistry\/2024\/summary\/\n[00:05:18] BioStruct Africa\nhttps:\/\/www.biostructafrica.org\/\n[00:18:03] Isomorphic Labs\nhttps:\/\/www.isomorphiclabs.com\/\npaper:\n[00:03:09] AlphaFold Protein Structure Database\nhttps:\/\/doi.org\/10.1093\/nar\/gkab1061\n[00:17:25] Accurate structure prediction of biomolecular interactions with AlphaFold 3\nhttps:\/\/www.nature.com\/articles\/s41586-024-07487-w\n[00:22:18] Highly accurate protein structure prediction with AlphaFold\nhttps:\/\/www.nature.com\/articles\/s41586-021-03819-2\n[00:23:10] Midnolin promotes degradation of substrates independent of ubiquitination\nhttps:\/\/doi.org\/10.1126\/science.adh5021\n[00:27:00] Improved protein structure prediction using potentials from deep learning\nhttps:\/\/www.nature.com\/articles\/s41586-019-1923-7\ntool:\n[00:03:09] AlphaFold Protein Structure Database (EBI)\nhttps:\/\/alphafold.ebi.ac.uk\/\n[00:45:55] AlphaEvolve: a coding agent for designing advanced algorithms\nhttps:\/\/deepmind.google\/blog\/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms\/\nother:\n[00:39:40] The Bitter Lesson\nhttp:\/\/www.incompleteideas.net\/IncIdeas\/BitterLesson.html\n\n---\nReScript: https:\/\/app.rescript.info\/share\/d8cde5c221fb71e2c0f5aafe94f90dfa\n\nDisclaimer - not sponsored, editorial with us - we filmed it at GDM, London","thumbnailUrl":["https:\/\/i.ytimg.com\/vi\/e3gBwLWAerw\/default.jpg","https:\/\/i.ytimg.com\/vi\/e3gBwLWAerw\/mqdefault.jpg","https:\/\/i.ytimg.com\/vi\/e3gBwLWAerw\/hqdefault.jpg","https:\/\/i.ytimg.com\/vi\/e3gBwLWAerw\/sddefault.jpg","https:\/\/i.ytimg.com\/vi\/e3gBwLWAerw\/maxresdefault.jpg"],"uploadDate":"2026-06-22T22:43:36+00:00","duration":"PT53M6S","embedUrl":"https:\/\/www.youtube.com\/embed\/e3gBwLWAerw","publisher":{"@type":"Organization","@id":"https:\/\/www.youtube.com\/channel\/UCMLtBahI5DMrt0NPvDSoIRQ#Organization","url":"https:\/\/www.youtube.com\/channel\/UCMLtBahI5DMrt0NPvDSoIRQ","name":"Machine Learning Street Talk","description":"MLST is the leading highly technical AI podcast. Subscribe now! Welcome! We bring you the latest in advanced AI research, from the best AI experts in the world. Our approach is unrivalled in terms of scope and rigour \u2013 we believe in diversity of ideas (which is to say, not just LLMs!) and we also cover other promising alternative paths to AGI, as well as CogSci, CompSci, Neuro, Mathematics, Philosophy of Mind and Language.  \n\nSupport us on Patreon for early access, exclusive content, private Discord, biweekly calls and much more! \nhttps:\/\/www.patreon.com\/mlst \n\nDonate here: https:\/\/www.paypal.com\/donate\/?hosted_button_id=K2TYRVPBGXVNA\n\nPlease email us to learn about sponsorship packages and deals. \ntim at mlst.ai (please put your budget in the subject line)\n\nPodcast booking agencies - *don't contact us* - we wouldn't even interview anyone who needed a booking agent.\nMedia\/influence agencies - *don't contact us* - we only work directly with brands\/sponsors.\n","logo":{"url":"https:\/\/yt3.ggpht.com\/15Akj76BG8IsM5ctgqVwKXArl6IfIVFAbuGa1kOomoioRgJgXHHaLmMAW7iHTMRUoEfyjTtq8lg=s800-c-k-c0x00ffffff-no-rj","width":800,"height":800,"@type":"ImageObject","@id":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw#VideoObject_publisher_logo_ImageObject"}},"potentialAction":{"@type":"SeekToAction","@id":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw#VideoObject_potentialAction","target":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw&t={seek_to_second_number}","startOffset-input":"required name=seek_to_second_number"},"interactionStatistic":[[{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw#VideoObject_interactionStatistic_WatchAction","interactionType":{"@type":"WatchAction"},"userInteractionCount":36420}],{"@type":"InteractionCounter","@id":"https:\/\/www.youtube.com\/watch?v=e3gBwLWAerw#VideoObject_interactionStatistic_LikeAction","interactionType":{"@type":"LikeAction"},"userInteractionCount":901}]},"about":["Insights","\u300eEnglish\u300f"],"wordCount":1472,"keywords":["sync"]},{"@context":"https:\/\/schema.org\/","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Insights","item":"https:\/\/blog.terabox.com\/insights\/#breadcrumbitem"},{"@type":"ListItem","position":2,"name":"AlphaFold: Solving the Protein Folding Problem with AI","item":"https:\/\/blog.terabox.com\/insights\/alphafold-solving-protein-folding-problem#breadcrumbitem"}]}]