{"id":109,"date":"2026-11-19T11:48:58","date_gmt":"2026-11-19T11:48:58","guid":{"rendered":"https:\/\/blockerlife.com\/index.php\/2026\/11\/19\/ai-designed-proteins-bound-scorpion-toxins-but-no-antivenom-was-made\/"},"modified":"2026-11-19T11:48:58","modified_gmt":"2026-11-19T11:48:58","slug":"ai-designed-proteins-bound-scorpion-toxins-but-no-antivenom-was-made","status":"publish","type":"post","link":"https:\/\/blockerlife.com\/index.php\/2026\/11\/19\/ai-designed-proteins-bound-scorpion-toxins-but-no-antivenom-was-made\/","title":{"rendered":"AI-designed proteins bound scorpion toxins, but no antivenom was made"},"content":{"rendered":"<p>As reported on October 22, 2026, investment research firm Citrini Research worked with Anthropic to test whether an unreleased version of Claude could help develop scorpion antivenom. The experiment produced proteins that bound to toxins in laboratory tests, but it did not produce a medicine\u2014or establish that the proteins could neutralize venom.<\/p>\n<p>Anthropic said Claude generated nearly 320,000 protein candidates. After filtering, the team had 180 designs and added 31 more with Claude, for a total of 211. The process took 64 hours. Citrini sent the designs to Adaptyv Bio and Twist Biosciences for testing. According to Citrini, 17 proteins bound to four of the five scorpion toxins the team targeted; none bound to more than one toxin. Citrini acknowledged that no experiment had yet tested whether the proteins stopped the toxins from working.<\/p>\n<p>Researchers interviewed by <em>The Verge<\/em> cautioned against treating binding as a drug-development breakthrough. Andreas Hougaard Laustsen-Kiel of the Technical University of Denmark said finding a binder is relatively easy compared with turning one into a medicine. His colleagues Melisa Benard Valle and Anne Ljungars called the results technically promising but said the proteins\u2019 safety, stability and behavior in the body remain unknown.<\/p>\n<p>Citrini framed the project as a glimpse of AI-enabled drug discovery\u2019s investment potential. Anthropic covered a compute and token bill of just under $50,000, while outside laboratory testing cost roughly another $150,000. Those costs, and the untested steps between toxin binding and an effective treatment, matter when assessing what the experiment achieved.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>As reported on October 22, 2026, investment research firm Citrini Research worked with Anthropic to test whether an [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-109","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/posts\/109","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/comments?post=109"}],"version-history":[{"count":0,"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/posts\/109\/revisions"}],"wp:attachment":[{"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/media?parent=109"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/categories?post=109"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blockerlife.com\/index.php\/wp-json\/wp\/v2\/tags?post=109"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}