{"id":646,"date":"2026-10-16T20:01:28","date_gmt":"2026-10-16T20:01:28","guid":{"rendered":"https:\/\/bugleblast.com\/?p=646"},"modified":"2026-10-16T20:01:28","modified_gmt":"2026-10-16T20:01:28","slug":"ai-just-built-molecular-scissors-from-scratch-designed-proteases-that-cut-disease-proteins-and-nature-just-published-both-papers","status":"publish","type":"post","link":"https:\/\/bugleblast.com\/?p=646","title":{"rendered":"AI JUST BUILT MOLECULAR SCISSORS FROM SCRATCH! | Designed proteases that cut disease proteins \u2014 and Nature just published both papers"},"content":{"rendered":"<p>Scientists just used AI to invent molecular scissors from scratch \u2014 enzymes that find a protein sequence you choose and <strong>cut it<\/strong>.<\/p>\n<p>David Baker of the University of Washington and colleagues designed cysteine and zinc proteases de novo, Phys.org reported Oct. 16, citing two papers in <em>Nature<\/em>. The pipeline stacked an RFdiffusion2 variant called <strong>RFD2-MI<\/strong> for 3D shapes and backbones, ProteinMPNN \/ EnhancedMPNN for sequences, and AlphaFold 3 to check the folds.<\/p>\n<p>They tested the designs in bacteria: each enzyme linked to a target sequence plus a glowing marker. Success meant the enzyme cut the target and freed the marker. For cysteine proteases, <strong>13 of 69<\/strong> candidates worked. For zinc proteases, <strong>36% of 135<\/strong> candidates cut matching peptide targets. AI refinement then boosted the top zinc protease\u2019s cutting speed <strong>30\u00d7<\/strong>, and a cysteine design cut at precisely the intended site.<\/p>\n<p>Therapeutic promise \u2014 not clinical trials yet \u2014 showed up in the lab: one design cut full-length <strong>TDP-43<\/strong> (the protein that builds up in ALS and some dementias); others cut amyloid-beta fragments linked to Alzheimer\u2019s and serum amyloid A tied to systemic amyloidosis.<\/p>\n<p>The team\u2019s verdict, as reported: \u201cOur results show that de novo enzyme design has advanced well beyond model reactions on activated substrates.\u201d And: \u201cThe ability to design selective proteases for prescribed epitopes on proteins could be transformative for many potential applications.\u201d<\/p>\n<p>The papers: Anqi Chen et al., Computational design of metalloproteases (DOI 10.1038\/s41586-026-11167-2); Hojae Choi et al., De novo design of cysteine proteases (DOI 10.1038\/s41586-026-11143-w).<\/p>\n<p>Custom scissors for the proteins that make people sick. It\u2019s early, but Nature just put two stamps on it.<\/p>\n<p><strong>Sources:<\/strong> <a href=\"https:\/\/phys.org\/news\/2026-10-ai-molecular-scissors-protein.html\">Phys.org \u2014 AI molecular scissors that cut proteins<\/a> \u00b7 <a href=\"https:\/\/doi.org\/10.1038\/s41586-026-11167-2\">Nature \u2014 Chen et al., Computational design of metalloproteases<\/a> \u00b7 <a href=\"https:\/\/doi.org\/10.1038\/s41586-026-11143-w\">Nature \u2014 Choi et al., De novo design of cysteine proteases<\/a><\/p>\n<p><em>Featured image: AI-generated editorial illustration by Bugle Blast.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Designed proteases that cut disease proteins \u2014 and Nature just published both papers<\/p>\n","protected":false},"author":1,"featured_media":640,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[1],"tags":[],"class_list":["post-646","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"https:\/\/bugleblast.com\/wp-content\/uploads\/2026\/10\/bb-ai-proteases-1016.jpg","_links":{"self":[{"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/posts\/646","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/bugleblast.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=646"}],"version-history":[{"count":1,"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/posts\/646\/revisions"}],"predecessor-version":[{"id":647,"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/posts\/646\/revisions\/647"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/bugleblast.com\/index.php?rest_route=\/wp\/v2\/media\/640"}],"wp:attachment":[{"href":"https:\/\/bugleblast.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=646"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/bugleblast.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=646"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/bugleblast.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=646"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}