{"id":213638,"date":"2025-05-09T13:07:01","date_gmt":"2025-05-09T18:07:01","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/05\/why-dont-machine-learning-models-extrapolate"},"modified":"2025-05-09T13:07:01","modified_gmt":"2025-05-09T18:07:01","slug":"why-dont-machine-learning-models-extrapolate","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/05\/why-dont-machine-learning-models-extrapolate","title":{"rendered":"Why Don\u2019t Machine Learning Models Extrapolate?"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/why-dont-machine-learning-models-extrapolate2.jpg\"><\/a><\/p>\n<p>Introduction One thing newcomers to machine learning (ML) and many experienced practitioners often don\u2019t realize is that ML doesn\u2019t extrapolate. After training an ML model on compounds with \u00b5M potency, people frequently ask why none of the molecules they designed were predicted to have nM potency. If you\u2019re new to drug discovery, 1nM = 0.001\u00b5M. A lower potency value is usually better. It\u2019s important to remember that a model can only predict values within the range of the training set. If we\u2019ve trained a model on compounds with IC50s between 5 and 100 \u00b5M, the model won\u2019t be able to predict an IC50 of 0.1 \u00b5M. I\u2019d like to illustrate this with a simple example. As always, all the code that accompanies this post is available on GitHub.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Introduction One thing newcomers to machine learning (ML) and many experienced practitioners often don\u2019t realize is that ML doesn\u2019t extrapolate. After training an ML model on compounds with \u00b5M potency, people frequently ask why none of the molecules they designed were predicted to have nM potency. If you\u2019re new to drug discovery, 1nM = 0.001\u00b5M. [\u2026]<\/p>\n","protected":false},"author":732,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11,6],"tags":[],"class_list":["post-213638","post","type-post","status-publish","format-standard","hentry","category-biotech-medical","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/213638","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/732"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=213638"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/213638\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=213638"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=213638"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=213638"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}