https://qtcovi.github.io/tag/symmetry-functions/Symmetry FunctionsHugo Blox Builder (https://hugoblox.com)en-usMon, 01 Jan 2024 00:00:00 +0000https://qtcovi.github.io/media/icon_hu11734318148517933569.pnghttps://qtcovi.github.io/tag/symmetry-functions/https://qtcovi.github.io/software/mm2sf/Mon, 01 Jan 2024 00:00:00 +0000https://qtcovi.github.io/software/mm2sf/<h2 id="about">About</h2> <p><strong>MM2SF</strong> automatically generates optimised Atom-Centred Symmetry Functions (ACSFs) for use as descriptors in neural network interatomic potentials. Given a molecular dynamics trajectory or normal-mode sampling, it applies a Gaussian Mixture Model (GMM) to decompose the chemical space into well-defined clusters, then selects symmetry function parameters that accurately describe each region.</p> <p>Supported symmetry function types:</p> <ul> <li><strong>Two-body (radial)</strong> — <em>G</em>^rad</li> <li><strong>Three-body (angular)</strong> — <em>G</em>^ang (modified functional form)</li> </ul> <h2 id="installation">Installation</h2> <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-bash" data-lang="bash"><span class="line"><span class="cl">pip install git+https://github.com/m-gallegos/MM2SF.git </span></span></code></pre></div><p>Or from a downloaded zip:</p> <div class="highlight"><pre tabindex="0" class="chroma"><code class="language-bash" data-lang="bash"><span class="line"><span class="cl">pip install MM2SF-main.zip </span></span></code></pre></div><h2 id="links">Links</h2> <ul> <li><a href="https://github.com/QTCOVI/MM2SF" target="_blank" rel="noopener">GitHub repository</a></li> </ul>