<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/">
    <channel>
        <title>Polaris Blog</title>
        <link>https://polarishub.io</link>
        <description>Stay informed with product updates and project news.</description>
        <lastBuildDate>Fri, 10 Apr 2026 11:25:13 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <image>
            <title>Polaris Blog</title>
            <url>https://polarishub.io/favicon.ico</url>
            <link>https://polarishub.io</link>
        </image>
        <copyright>All rights reserved 2026</copyright>
        <item>
            <title><![CDATA[Dataset v2.0 - Built to scale!]]></title>
            <link>https://polarishub.io/blog/dataset-v2-built-to-scale</link>
            <guid isPermaLink="false">dataset-v2-built-to-scale</guid>
            <pubDate>Thu, 31 Oct 2024 09:51:00 GMT</pubDate>
            <content:encoded><![CDATA[With the Polaris Hub, we set out to design a universal data format for ML scientists in drug discovery. Whether you’re working with phenomics, small molecules, or protein structures, you shouldn’t have to spend time learning about domain-specific file formats, APIs, and software tools to be able to run some ML experiments.

Learn more about how we support extra-large datasets, like BELKA, in this behind-the-scenes post! ]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/8e0bdf44221c20b3f0e0da6b5fe7bd88b76ef56f-1600x1065.png?rect=1,0,1598,1065&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
        <item>
            <title><![CDATA[Introducing our Small Molecule Steering Committee]]></title>
            <link>https://polarishub.io/blog/introducing-our-small-molecule-steering-committee</link>
            <guid isPermaLink="false">introducing-our-small-molecule-steering-committee</guid>
            <pubDate>Thu, 17 Oct 2024 14:00:05 GMT</pubDate>
            <content:encoded><![CDATA[Over the past few years, the field of machine learning for drug discovery (MLDD) has experienced an unprecedented surge of innovation. But how do we know whether these innovations can truly impact the development of new drugs? It's hard to tell.]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/7f8b1a267680cc4a24f7ea53bc54367d7d9ff4a4-1800x1198.png?rect=2,0,1797,1198&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
        <item>
            <title><![CDATA[Reproducible Machine Learning in Drug Discovery: How Polaris Serves as a Single Source of Truth]]></title>
            <link>https://polarishub.io/blog/reproducible-machine-learning-in-drug-discovery-how-polaris-serves-as-a-single-source-of-truth</link>
            <guid isPermaLink="false">reproducible-machine-learning-in-drug-discovery-how-polaris-serves-as-a-single-source-of-truth</guid>
            <pubDate>Wed, 29 Jan 2025 21:00:00 GMT</pubDate>
            <content:encoded><![CDATA[One of the guiding design principles we followed when first building Polaris, was this idea of serving as a single source of truth for the machine learning community tackling drug discovery challenges. But what exactly does that mean? How does that inform the features that we're building for the platform? Read the blog to learn more! 
]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/4f8cb024631b8c4f8f46c7bc74a847375c0e79a0-3600x2396.png?rect=3,0,3594,2396&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
        <item>
            <title><![CDATA[Imagining the Future of ML Evaluation in Drug Discovery]]></title>
            <link>https://polarishub.io/blog/imagining-the-future-of-ml-evaluation-in-drug-discovery</link>
            <guid isPermaLink="false">imagining-the-future-of-ml-evaluation-in-drug-discovery</guid>
            <pubDate>Tue, 17 Dec 2024 16:02:44 GMT</pubDate>
            <content:encoded><![CDATA[Due to the scattered and inaccessible nature of evaluative insights, innovation in machine learning for drug discovery often struggle to translate into real drug discovery programs. At Polaris, we are actively re-thinking how ML methods are assessed and compared in order to bridge this gap. Let’s take a closer look at what this future of ML evaluation in drug discovery could look like!]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/a310e428303193c2b626492ca1c90d8cabf03736-1800x1198.png?rect=2,0,1797,1198&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
        <item>
            <title><![CDATA[Antiviral Competition: Advancing Open Science with ASAP Discovery and OpenADMET]]></title>
            <link>https://polarishub.io/blog/antiviral-competition</link>
            <guid isPermaLink="false">antiviral-competition</guid>
            <pubDate>Tue, 03 Dec 2024 00:45:00 GMT</pubDate>
            <content:encoded><![CDATA[Competitions are a critical tool to evaluate the current state of the art in computational molecular sciences. As par of its open science mission, the ASAP Discovery Consortium is launching an antiviral competition in collaboration with OpenADMET. Test your skills in ligand pose prediction, potency prediction, and ADMET prediction, all revolving around SARS-CoV-2 and MERS-CoV Mpro. ]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/2d872ecb441e0bd425ca452068e5bf94ed5fb0d7-1800x1198.png?rect=2,0,1797,1198&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
        <item>
            <title><![CDATA[Driving Innovation in Drug Discovery: The Role of ML Competitions]]></title>
            <link>https://polarishub.io/blog/driving-innovation-in-drug-discovery-the-role-of-ml-competitions</link>
            <guid isPermaLink="false">driving-innovation-in-drug-discovery-the-role-of-ml-competitions</guid>
            <pubDate>Fri, 22 Nov 2024 15:12:31 GMT</pubDate>
            <content:encoded><![CDATA[While fields like natural language processing (NLP) and computer vision (CV) have long benefitted from standardized benchmarks and well-organized competitions, ML for drug discovery (MLDD) faces unique challenges. What can we learn from other fields and what does the current landscape of competitions look like in MLDD? ]]></content:encoded>
            <enclosure url="https://cdn.sanity.io/images/a2i6331o/production/99b962144615ee6877b01cd3dc559f3e4f7ca7cb-1800x1198.png?rect=2,0,1797,1198&amp;w=1200&amp;h=800&amp;fm=jpg&amp;auto=format" length="0" type="image/png"/>
        </item>
    </channel>
</rss>