<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Protein on AI Science Report</title>
    <link>https://aiscience.uk/tags/protein/</link>
    <description>Recent content in Protein on AI Science Report</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 09 Jul 2026 00:00:00 +0800</lastBuildDate>
    <atom:link href="https://aiscience.uk/tags/protein/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The AI That Learns From Three Experiments How to Find the Next Blockbuster Antibody</title>
      <link>https://aiscience.uk/posts/abicl-in-context-learning-antibody-affinity-ranking/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0800</pubDate>
      <guid>https://aiscience.uk/posts/abicl-in-context-learning-antibody-affinity-ranking/</guid>
      <description>&lt;p&gt;In 2023, the world spent over $200 billion on antibody drugs — treatments like Keytruda for cancer and Humira for autoimmune disease. But finding a single antibody that binds well enough to become a drug is like searching for a specific grain of sand on a beach. A typical drug discovery campaign screens thousands of candidates, each one requiring expensive lab tests to measure how tightly it grabs its target. Most fail.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
