1<!DOCTYPE html><!--FHkbQYoMnTI0_QdUfmyZC--><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/css/63c64bcc8c509764.css" data-precedence="next"/><link rel="stylesheet" href="/_next/static/css/5d7dd385fd1eee72.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/webpack-8a8327b08dd8fe13.js"/>
1<script src="/_next/static/chunks/4bd1b696-c023c6e3521b1417.js" async=""></script>
1<script src="/_next/static/chunks/255-4f84124391a7dac4.js" async=""></script>
1<script src="/_next/static/chunks/main-app-2ecc3bf42ae2d122.js" async=""></script>
1<script src="/_next/static/chunks/44530001-9f564ab55328eab5.js" async=""></script>
1<script src="/_next/static/chunks/817-576501c917c8d2f1.js" async=""></script>
1<script src="/_next/static/chunks/app/layout-0d77fadd05161323.js" async=""></script>
1<script src="/_next/static/chunks/176-14d53a9c86e31d17.js" async=""></script>
1<script src="/_next/static/chunks/779-303be24ae6ed1d4b.js" async=""></script>
1<script src="/_next/static/chunks/940-38e89157d17ef948.js" async=""></script>
1<script src="/_next/static/chunks/app/documentation/page-cfa91cc4b509df03.js" async=""></script>
1<title>Documentation · Neuralocity</title><meta name="description" content="Reference documentation for the Neuralocity molecule data platform."/>
1<script src="/_next/static/chunks/polyfills-42372ed130431b0a.js" noModule=""></script>
1</head><body><div hidden=""><!--$--><!--/$--></div><div class="gradient-surface flex min-h-screen flex-col"><header class="marketing-nav sticky top-0 z-40"><div class="marketing-nav-accent" aria-hidden="true"></div><div class="container mx-auto flex h-16 items-center justify-between px-6 md:px-12"><a class="flex items-center gap-2" href="/"><div class="flex h-8 w-8 shrink-0 items-center justify-center rounded-lg bg-emerald-500/30 ring-1 ring-emerald-400/40"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.25" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-database h-4.5 w-4.5 text-emerald-400"><ellipse cx="12" cy="5" rx="9" ry="3"></ellipse><path d="M3 5V19A9 3 0 0 0 21 19V5"></path><path d="M3 12A9 3 0 0 0 21 12"></path></svg></div><span class="text-xl font-bold tracking-tight text-white">Neuralocity</span></a><nav class="hidden items-center gap-1 md:flex"><a class="font-medium transition-colors hover:bg-white/10 hover:text-white rounded-full px-4 py-2 text-sm bg-white/10 text-white" href="/documentation">Documentation</a><a class="ml-2 marketing-btn-primary h-10 px-6 text-sm" href="/login">Sign in</a></nav><button type="button" class="rounded-lg p-2 text-white/80 hover:bg-white/10 md:hidden" aria-label="Open menu" aria-expanded="false"><svg class="h-6 w-6" fill="none" viewBox="0 0 24 24" stroke="currentColor"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 6h16M4 12h16M4 18h16"></path></svg></button></div></header><main class="flex-1 bg-background"><div class="mx-auto max-w-6xl px-4 py-12 sm:px-6 md:py-16"><div class="mb-8"><h1 class="text-2xl font-semibold tracking-tight text-text-primary">Documentation</h1><p class="mt-2 max-w-2xl text-sm leading-relaxed text-text-secondary">How to use the Neuralocity catalog, and what the drug-discovery concepts behind every field and score on this platform actually mean.</p></div><div class="flex flex-col gap-8 lg:flex-row"><nav class="shrink-0 lg:w-56"><div class="space-y-6 lg:sticky lg:top-20"><div><div class="mb-2 text-xs font-semibold uppercase tracking-wide text-muted">Using the Platform</div><ul class="space-y-1 border-l border-border"><li><a href="#overview" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-accent font-medium text-accent">Workspace Overview</a></li><li><a href="#catalog-page" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">The Catalog Page</a></li><li><a href="#molecule-detail-page" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">The Molecule Detail Page</a></li><li><a href="#cart-purchases" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Cart & Purchases</a></li><li><a href="#account-organization" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Account & Organization</a></li></ul></div><div><div class="mb-2 text-xs font-semibold uppercase tracking-wide text-muted">Drug Discovery Concepts</div><ul class="space-y-1 border-l border-border"><li><a href="#molecular-identity" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Molecular Identity</a></li><li><a href="#physicochemical-properties" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Physicochemical Properties</a></li><li><a href="#structural-characteristics" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Structural Characteristics</a></li><li><a href="#target-activity-tiers" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Target Activity & Tiers</a></li><li><a href="#model-methodology" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Model Methodology</a></li><li><a href="#safety-toxicity" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Safety & Toxicity</a></li><li><a href="#ddi-screening" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Drug-Drug Interaction Screening</a></li><li><a href="#predicted-binding-structure" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Predicted Structure & Binding Affinity</a></li><li><a href="#synthesizability-stability" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Synthesizability & Stability</a></li><li><a href="#similarity-search" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Molecular Similarity Search</a></li></ul></div><div><div class="mb-2 text-xs font-semibold uppercase tracking-wide text-muted">Reference</div><ul class="space-y-1 border-l border-border"><li><a href="#glossary" class="-ml-px block border-l-2 px-3 py-1 text-sm transition-colors border-transparent text-muted hover:text-text-primary">Glossary</a></li></ul></div></div></nav><div class="min-w-0 flex-1 space-y-10 pb-16"><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="overview" class="scroll-mt-6 text-lg font-semibold text-text-primary">Workspace Overview</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">
1The Neuralocity catalog holds several million computationally generated candidate molecules. Every molecule has been scored against a set of biological target classes and a set of safety/interaction models, so you can screen for promising candidates before any wet-lab work begins.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">The top navigation bar gives you access to the <strong class="font-semibold text-text-primary">Catalog</strong> (browse and filter molecules), your <strong class="font-semibold text-text-primary">Cart</strong> (molecules youâve selected), this<!-- --> <strong class="font-semibold text-text-primary">Documentation</strong> page, and your account settings (gear icon, top right).</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="catalog-page" class="scroll-mt-6 text-lg font-semibold text-text-primary">The Catalog Page</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">The Catalog page is a filterable, sortable table of every molecule in the current release. Each row shows a compact set of columns; the full detail for a molecule lives on its own page (see below).</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Filters</h3><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Target Class + Mechanism</strong>: choose a biological target class and whether you want antagonist or agonist activity. This is required before the Activity column has any value to show or sort by.</li><li><strong class="font-semibold text-text-primary">Activity Tier</strong>: restrict results to one or more tiers (A through E) once a target class is selected.</li><li><strong class="font-semibold text-text-primary">Safety</strong>: restrict to molecules classified Safe or Not Safe.</li><li><strong class="font-semibold text-text-primary">Drug-Drug Interaction (DDI) flags</strong>: restrict by how many CYP450 isoforms a molecule is predicted to inhibit.</li><li><strong class="font-semibold text-text-primary">Property ranges</strong>: Molecular Weight, LogP, H-Bond Donors/Acceptors, QED, and SA Score all support min/max range filters.</li><li><strong class="font-semibold text-text-primary">Text search</strong>: search by identifiers such as Molecule ID or SMILES.</li><li><strong class="font-semibold text-text-primary">Similarity search</strong>: paste a SMILES string and a similarity threshold to find structurally similar molecules already in the catalog (see<!-- --> <a href="#similarity-search" class="text-accent hover:underline">Molecular Similarity Search</a>).</li></ul><h3 class="mt-5 text-sm font-semibold text-text-primary">Reading the table</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">Columns are driven by whatâs actually available for a molecule: a column showing âNot availableâ usually means that data hasnât been populated for that row yet, or (for Activity) that no target class filter is selected. Click the column header to sort; click again to reverse direction.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Every row has a <strong class="font-semibold text-text-primary">Details</strong> link (and the Molecule ID itself is also a link) that opens the full molecule detail page, and a cart button to add that molecule directly. You can also select all molecules matching your current filters and add them to your cart in bulk.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="molecule-detail-page" class="scroll-mt-6 text-lg font-semibold text-text-primary">The Molecule Detail Page</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Clicking into a molecule shows everything known about it, organized into panels:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Structure</strong>: a rendered image of the molecule. Click it to open a larger version.</li><li><strong class="font-semibold text-text-primary">Identity</strong>: the moleculeâs identifiers: SMILES, Canonical SMILES, SMARTS, InChI, InChI Key, and Formula (see<!-- --> <a href="#molecular-identity" class="text-accent hover:underline">Molecular Identity</a>).</li><li><strong class="font-semibold text-text-primary">Properties</strong>: stored physicochemical properties plus structural characteristics computed on the fly (see<!-- --> <a href="#physicochemical-properties" class="text-accent hover:underline">Physicochemical Properties</a> <!-- -->and<!-- --> <a href="#structural-characteristics" class="text-accent hover:underline">Structural Characteristics</a>).</li><li><strong class="font-semibold text-text-primary">Activity Tiers</strong>, <strong class="font-semibold text-text-primary">Safety</strong>, and<!-- --> <strong class="font-semibold text-text-primary">Drug-Drug Interaction</strong>: the same scoring concepts as the Catalog pageâs filters, shown in full for this molecule.</li><li><strong class="font-semibold text-text-primary">Synthesizability & Stability</strong>: an AI-based assessment of how practical the molecule is to make and how well it would hold up in storage (see<!-- --> <a href="#synthesizability-stability" class="text-accent hover:underline">Synthesizability & Stability</a>).</li><li><strong class="font-semibold text-text-primary">Predict Binding Affinity For Your Target</strong>: paste your own target sequence to get a computational predicted structure for this molecule against it (see<!-- --> <a href="#predicted-binding-structure" class="text-accent hover:underline">Predicted Structure & Binding Affinity</a>).</li><li><strong class="font-semibold text-text-primary">Provenance</strong>: the moleculeâs source identifier within the catalog.</li></ul></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="cart-purchases" class="scroll-mt-6 text-lg font-semibold text-text-primary">Cart & Purchases</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Add molecules to your cart from the Catalog page or a moleculeâs detail page. Adding a molecule to your cart claims it, so it drops out of the catalog for everyone else until you remove it or purchase it. Your cart persists across sessions. From the Cart page, there are two ways to act on it:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Buy digital listing</strong>: an instant, fixed-price purchase of that moleculeâs structure identifiers, computed properties, activity tiers by target class, safety classification, and predicted solubility. Checkout is handled by Stripe, and once payment completes, purchased molecules move from your Cart to your Purchase History page under Account settings, where you can download the data as CSV.</li><li><strong class="font-semibold text-text-primary">Synthesize & deliver</strong>: request to have the physical compound synthesized and shipped to you, including the full digital listing. Pricing varies per molecule, so this doesnât go through checkout. Clicking âRequest a quoteâ emails your cart contents to our team, and we follow up directly with a firm quote and an expected delivery window.</li></ul></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="account-organization" class="scroll-mt-6 text-lg font-semibold text-text-primary">Account & Organization</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Your account settings (gear icon, top right) let you manage your profile, view your organizationâs members, send invites if your organization supports multiple users, and review your purchase history.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Some fields on the platform may be locked behind an entitlement (indicated with a lock icon), depending on your organizationâs plan.</p></section><div class="pt-4"><h2 class="text-xl font-semibold tracking-tight text-text-primary">Drug Discovery Concepts in This Platform</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Every concept below corresponds to a real field or score you can see somewhere in the product. Nothing here is generic background that isnât actually represented in the catalog.</p></div><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="molecular-identity" class="scroll-mt-6 text-lg font-semibold text-text-primary">Molecular Identity</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">A single molecule can be written down in several different, standardized ways. The Identity panel on a moleculeâs detail page shows all of them:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">SMILES</strong> (Simplified Molecular Input Line Entry System): a compact text notation for a moleculeâs structure. Itâs the format the molecule was originally generated in.</li><li><strong class="font-semibold text-text-primary">Canonical SMILES</strong>: the same molecule, rewritten into one standardized SMILES form. Two chemically identical molecules can be written as different SMILES strings; canonicalization gives every molecule one consistent representation, which is what deduplication and similarity search rely on.</li><li><strong class="font-semibold text-text-primary">SMARTS</strong>: a related notation used for describing structural<!-- --> <em>patterns</em> rather than a single specific molecule (e.g. âany aromatic ring with an attached carbonylâ). Useful for substructure searching.</li><li><strong class="font-semibold text-text-primary">InChI</strong> (International Chemical Identifier) and<!-- --> <strong class="font-semibold text-text-primary">InChI Key</strong>: a different standardized identifier format, widely used across chemistry databases. The InChI Key is a short, fixed-length hash of the full InChI, convenient for lookups and cross-referencing against other databases.</li><li><strong class="font-semibold text-text-primary">Formula</strong>: the molecular formula (e.g. CââHââ¾NâOâ), a simple c
1ount of each element present.</li></ul></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="physicochemical-properties" class="scroll-mt-6 text-lg font-semibold text-text-primary">Physicochemical Properties</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">These are computed once, when a molecule enters the catalog, and stored.</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Molecular Weight (MW)</strong>: the mass of the molecule. Most successful oral small-molecule drugs fall in a fairly narrow weight range, roughly 150 to 500 daltons, and MW is one of the first things medicinal chemists check because it touches nearly every other property that matters:<ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Absorption and permeability.</strong> Larger molecules generally cross cell membranes and the gut wall less efficiently, making it harder for an oral drug to reach the bloodstream in useful amounts.</li><li><strong class="font-semibold text-text-primary">Distribution.</strong> Once absorbed, a moleculeâs size affects how easily it moves through tissue and reaches its target, and how quickly the body clears it.</li><li><strong class="font-semibold text-text-primary">Binding specificity.</strong> Very small molecules often lack enough surface area to bind a target tightly or selectively, which can mean weaker potency or more off-target effects.</li><li><strong class="font-semibold text-text-primary">Synthesis and formulation.</strong> Heavier, more complex molecules typically take more synthetic steps to build and can be harder to formulate into a stable, dosable product.</li><li><strong class="font-semibold text-text-primary">Dosing practicality.</strong> A heavier molecule generally means more milligrams are needed per dose to reach an effective concentration in the body.</li></ul>This is why extremely large or extremely small molecules tend to make poor drug candidates, and why Molecular Weight is one of the four properties behind Lipinskiâs Rule of Five (see below).</li><li><strong class="font-semibold text-text-primary">LogP</strong>: a measure of lipophilicity, how a molecule partitions between a fat-like phase and water. This is the property on this platform most directly relevant to a moleculeâs solubility and membrane-permeability trade-off: too low (too water-loving) and a molecule struggles to cross cell membranes, while too high (too fat-loving) it tends toward poor solubility and off-target binding.</li><li><strong class="font-semibold text-text-primary">H-Bond Donors</strong> and <strong class="font-semibold text-text-primary">H-Bond Acceptors</strong>: counts of atoms that can donate or accept a hydrogen bond. Along with Molecular Weight and LogP, these are the four properties behind Lipinskiâs Rule of Five (see below).</li><li><strong class="font-semibold text-text-primary">QED</strong> (Quantitative Estimate of Drug-likeness): a single 0-to-1 score that blends several drug-likeness properties into one number. Closer to 1 means the moleculeâs overall property profile looks more like known, successful drugs.</li><li><strong class="font-semibold text-text-primary">SA Score</strong> (Synthetic Accessibility Score): a computed 1-to-10 score based purely on structural complexity, how unusual or intricate the moleculeâs substructures are compared to fragments that appear often in known, easily-made molecules. It does not reason about an actual route to make the molecule; it is a fast heuristic for how complicated the structure looks. This is different from the AI-based Synthesizability rating and description described later, which reason about a specific, plausible synthetic route (how many steps, what reagents, what could go wrong) to assess whether the molecule could actually be made. A structurally simple-looking molecule can still get a difficult Synthesizability rating if a realistic route is genuinely hard, and vice versa, so the two may disagree; both are shown because they capture different things.</li><li><strong class="font-semibold text-text-primary">Molecular Complexity (MC1)</strong> and<!-- --> <strong class="font-semibold text-text-primary">Molecular Complexity (MC2)</strong>: two measures of how intricate the moleculeâs skeleton is, based only on its shape as a graph of connected atoms. Both count <em>divalent</em> atoms, meaning atoms with exactly two connections, which are the atoms that sit in the middle of a plain chain or ring and add length
1without adding structure. MC1 is the fraction of atoms that are<!-- --> <em>not</em> divalent, on a 0-to-1 scale: a plain benzene ring scores 0.00, and a heavily branched, heavily substituted structure approaches 1. Because it is a fraction, MC1 does not grow just because a molecule is large, so it compares fairly across molecules of different sizes. MC2 is the raw count of non-divalent atoms instead of a fraction, so it does grow with size; it excludes the C=O of amide, ester, and carbamate groups, which are common, simple motifs that would otherwise inflate the count. Neither score is a verdict: complexity is not inherently good or bad, and more complexity is not worse the way a Rule of 5 violation is. They are also distinct from SA Score above, which estimates how hard a molecule is to make rather than how intricate it looks; a long unbranched chain has a low MC1 and can still be awkward to synthesize.</li><li><strong class="font-semibold text-text-primary">Spacial Score (nSPS)</strong> and <strong class="font-semibold text-text-primary">Spacial Score (SPS)</strong>: a second kind of complexity, measuring three-dimensional character rather than branching. It rewards atoms that are saturated (sp3, tetrahedral, pointing in three dimensions) over flat aromatic ones, atoms carrying defined stereochemistry, and atoms in crowded neighborhoods. nSPS is normalized per heavy atom so it compares fairly across sizes; SPS is the same quantity summed rather than averaged, so it grows with molecule size. This captures something MC1 and MC2 do not: benzene and cyclohexane both score MC1 = 0.00, because every atom in each is divalent, yet cyclohexane is a puckered three-dimensional ring and scores three times the nSPS. Across a sample of this catalog, nSPS and MC1 are essentially uncorrelated, which is why both are shown. Higher nSPS tends to mean harder to synthesize, so it moves loosely with SA Score, but three-dimensional character is often desirable in a candidate, and a high value is not a defect.</li><li><strong class="font-semibold text-text-primary">Predicted Solubility (Log S)</strong>: predicted aqueous solubility, as logââ of the moleculeâs solubility in water in moles per liter. Unlike the properties above, this is not computed directly from the structure by a fixed formula; it is predicted by a trained graph neural network (AttentiveFP) that learned the relationship between structure and measured solubility. Higher (less negative) values mean more soluble. Below <strong class="font-semibold text-text-primary">â4</strong> is a widely used rule-of-thumb cutoff in early drug discovery for compounds likely to cause problems in aqueous assays; above that, more solubility is not itself a sign of a better candidate, just an increasing degree of the same acceptable property, which is why the catalog colors it as shades of blue above the cutoff rather than a best-to-worst gradient.</li></ul><h3 class="mt-5 text-sm font-semibold text-text-primary">Attribution</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">The two molecular complexity metrics above are MC1 and MC2 as defined in<!-- --> <a href="https://doi.org/10.1021/acs.jcim.5c00334" target="_blank" rel="noreferrer" class="text-accent hover:underline">A View on Molecular Complexity from the GDB Chemical Space</a> <!-- -->(Buehler & Reymond, <em>J. Chem. Inf. Model.</em> 2025). They are computed here with the authorsâ<!-- --> <a href="https://github.com/Ye-Buehler/Molecular_Complexity" target="_blank" rel="noreferrer" class="text-accent hover:underline">reference implementation</a>, released under the MIT License. The spacial score (SPS and nSPS) is by Krzyzanowski, Pahl, Grigalunas & Waldmann (<a href="https://doi.org/10.1021/acs.jmedchem.3c00689" target="_blank" rel="noreferrer" class="text-accent hover:underline">J. Med. Chem. 2023</a>), computed with the authorsâ implementation as distributed with RDKit. The SA Score above is the synthetic accessibility score of Ertl & Schuffenhauer (<a href="https://doi.org/10.1186/1758-2946-1-8" target="_blank" rel="noreferrer" class="text-accent hover:underline">
1J. Cheminformatics 2009</a>), computed with the authorsâ fragment-contribution script distributed with<!-- --> <a href="https://www.rdkit.org/" target="_blank" rel="noreferrer" class="text-accent hover:underline">RDKit</a>. QED is the drug-likeness measure of Bickerton et al. (<a href="https://doi.org/10.1038/nchem.1243" target="_blank" rel="noreferrer" class="text-accent hover:underline">Nature Chemistry 2012</a>), as implemented in RDKit.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="structural-characteristics" class="scroll-mt-6 text-lg font-semibold text-text-primary">Structural Characteristics</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Shown on a moleculeâs detail page, computed directly from its structure each time the page loads.</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Heavy Atoms</strong>, <strong class="font-semibold text-text-primary">Hydrogens</strong>, and <strong class="font-semibold text-text-primary">Total Atoms</strong>: basic atom counts (heavy atoms are every atom except hydrogen; total atoms is heavy atoms plus hydrogens).</li><li><strong class="font-semibold text-text-primary">Heteroatoms</strong>, <strong class="font-semibold text-text-primary">O + N Atoms</strong>, <strong class="font-semibold text-text-primary">Halogen Atoms</strong>, and <strong class="font-semibold text-text-primary">Non-Organic Atoms</strong>: counts of atoms other than carbon, broken down by category. A high halogen count, for example, can be a flag for metabolic-stability or toxicity risk in medicinal chemistry.</li><li><strong class="font-semibold text-text-primary">Fragments</strong>: the number of disconnected pieces in the structure. Most drug candidates should be a single connected fragment.</li><li><strong class="font-semibold text-text-primary">Rings</strong> and <strong class="font-semibold text-text-primary">Rotatable Bonds</strong>: ring count and the number of single bonds that can freely rotate. Rotatable bond count is a common proxy for molecular flexibility, which affects both binding and oral bioavailability.</li><li><strong class="font-semibold text-text-primary">Stereocenters</strong> (defined / unspecified / unknown) and<!-- --> <strong class="font-semibold text-text-primary">Cis/Trans Bonds</strong> (defined / unspecified / unknown): a stereocenter is an atom whose spatial arrangement can produce distinct molecules (mirror-image or otherwise) with potentially very different biological activity. Because these molecules come from a generative process rather than a specific experimental synthesis, many stereocenters are left <em>unspecified</em> in the original structure. The count tells you how much stereochemical ambiguity a given molecule has.</li><li><strong class="font-semibold text-text-primary">Polar Surface Area (PSA)</strong>: the surface area of the molecule contributed by polar atoms. A widely used predictor of a moleculeâs ability to cross the blood-brain barrier and its general absorption behavior.</li><li><strong class="font-semibold text-text-primary">Molar Refractivity</strong>: a measure related to a moleculeâs size and polarizability, another property that correlates with drug-likeness.</li><li><strong class="font-semibold text-text-primary">Rule of Five Violations</strong>: Lipinskiâs Rule of Five is a widely-used rule of thumb: a molecule is more likely to be orally bioavailable if it has Molecular Weight ⤠500, LogP ⤠5, H-Bond Donors ⤠5, and H-Bond Acceptors ⤠10. This count is simply how many of those four thresholds the molecule fails, where 0 means it satisfies all four.</li></ul></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="target-activity-tiers" class="scroll-mt-6 text-lg font-semibold text-text-primary">Target Activity & Tiers</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Every molecule is scored against ten biological target classes, grouped by biological classification:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li>Kinase</li><li>GPCR</li><li>Protease</li><li>Ion Channel</li><li>
1Nuclear Receptor</li><li>Enzyme</li><li>Transporter</li><li>Epigenetic</li><li>Apoptosis Regulator</li><li>Aggregation Target</li></ul><p class="mt-2 text-sm leading-relaxed text-text-secondary">Each target class is scored separately for <strong class="font-semibold text-text-primary">antagonist</strong> activity (blocking/inhibiting the target) and <strong class="font-semibold text-text-primary">agonist</strong> activity (activating/stimulating the target), since a moleculeâs predicted behavior can differ substantially between the two mechanisms. Each target class/mechanism pair is its own <strong class="font-semibold text-text-primary">machine learning model</strong>, trained on known compound activity data for that target class. The output is a model prediction, not a measured result.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Activity is shown as a letter tier from A (best) to E (worst):</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">A</strong>: highest-confidence predicted activity.</li><li><strong class="font-semibold text-text-primary">B</strong>, <strong class="font-semibold text-text-primary">C</strong>, <strong class="font-semibold text-text-primary">D</strong>: progressively lower predicted activity.</li><li><strong class="font-semibold text-text-primary">E</strong>: lowest predicted activity, or not enough signal to place the molecule in a higher tier.</li></ul></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="model-methodology" class="scroll-mt-6 text-lg font-semibold text-text-primary">Model Methodology</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Each target class/mechanism activity model is trained on known compound activity data (drawn from ChEMBL, a public repository of experimentally measured compound-target interactions) and evaluated on a held-out test set that is deliberately hard.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Scaffold-clustered holdout</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">Before training, every compound is grouped into a cluster by its core scaffold, the ring system at the heart of the molecule, independent of whatever side chains are attached. Two molecules that differ only in a side chain end up in the same cluster. Roughly 70% of these scaffold clusters are set aside for training and 30% are held out entirely for testing. Because the split happens at the cluster level rather than the individual-molecule level, no scaffold appears in both the training set and the test set. The modelâs reported accuracy comes from scoring it against that 30%, so it reflects performance on chemically unfamiliar scaffolds, not just unseen molecules that happen to be close variants of something already seen during training.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Comparison to a random split</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">A simpler random split, holding out a random 30% of individual molecules, can let a model look better than it really is: near-identical analogs of a training molecule frequently end up in a random test set too, so the model can effectively memorize a scaffold rather than learn to recognize activity for chemistry it hasnât encountered. That inflates reported performance in a way that doesnât reflect how well the model generalizes to a genuinely new molecule. The scaffold-clustered holdout used here is a stricter, more realistic test.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">As with every score, even a well-designed holdout evaluation is still a computational estimate of performance, not a substitute for experimental validation.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Predicted Solubility (Log S) model</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">Unlike the target-class and toxicity models above, which train a separate classifier per biological question on a fixed molecular fingerprint, solubility uses a single <strong class="font-semibold text-text-primary">graph neural network</strong> (an architecture called AttentiveFP) that reads a moleculeâs atoms and bonds directly rather than reducing it to a fingerprint first, and predicts a continuous number (log S) rather than a class probability.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Training data comes from solubility datasets, built from experimentally measured aqueous solubility values (not c
1omputed or predicted). The model is first pre-trained on the larger collection for broader chemical coverage, then fine-tuned, the same benchmark used to report accuracy: on a held-out scaffold split (the same scaffold-clustered methodology described above, so unseen chemistry, not just unseen molecules) it reaches a root-mean-square error of about half a log unit and a Spearman correlation of 0.96 with the true measured values.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">This model predicts a general physicochemical property, not activity against a specific biological target, so it is shown as its predicted value directly rather than converted into a tier. As with every score on this platform, it is a computational estimate, not a lab measurement.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="safety-toxicity" class="scroll-mt-6 text-lg font-semibold text-text-primary">Safety & Toxicity</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Every molecule is screened against eight toxicity endpoints, each its own trained<!-- --> <strong class="font-semibold text-text-primary">machine learning model</strong>:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Hepatotoxicity</strong>: liver toxicity risk.</li><li><strong class="font-semibold text-text-primary">Carcinogenicity</strong>: cancer-causing potential.</li><li><strong class="font-semibold text-text-primary">Cardiotoxicity</strong>: heart toxicity risk.</li><li><strong class="font-semibold text-text-primary">Gastrotoxicity</strong>: gastrointestinal toxicity risk.</li><li><strong class="font-semibold text-text-primary">Neurotoxicity</strong>: nervous-system toxicity risk.</li><li><strong class="font-semibold text-text-primary">Psychiatric toxicity</strong>: risk of adverse psychiatric effects.</li><li><strong class="font-semibold text-text-primary">Respiratory toxicity</strong>: respiratory-system toxicity risk.</li><li><strong class="font-semibold text-text-primary">Teratogenicity</strong>: risk of causing developmental/birth defects.</li></ul><p class="mt-2 text-sm leading-relaxed text-text-secondary">These eight predictions are combined into one weighted <strong class="font-semibold text-text-primary">Safety</strong> <!-- -->indicator, shown as a simple Safe / Not Safe classification on the Catalog page (a green or red dot) and in full detail on the molecule page. Endpoints with the highest real-world consequence are weighted most heavily in that combined score. As with Activity, this is a computational prediction intended for triage, not a substitute for actual toxicology testing.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="ddi-screening" class="scroll-mt-6 text-lg font-semibold text-text-primary">Drug-Drug Interaction (DDI) Screening</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Many drugs are broken down in the body by a family of liver enzymes called<!-- --> <strong class="font-semibold text-text-primary">CYP450</strong> (cytochrome P450). If a new molecule strongly inhibits one of these enzymes, it can interfere with how other, unrelated drugs that rely on that same enzyme get metabolized. This is a common real-world cause of drug-drug interactions.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Every molecule is screened for predicted inhibition of five CYP450 isoforms:</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li>CYP1A2</li><li>CYP2C9</li><li>CYP2C19</li><li>CYP2D6</li><li>CYP3A4/5</li></ul><p class="mt-2 text-sm leading-relaxed text-text-secondary">The DDI indicator shown on a molecule is a count from 0 to 5: how many of these five isoforms the molecule is predicted to meaningfully inhibit. This is a proxy for interaction risk through shared metabolic pathways, not a lookup of specific known drug-vs-drug interactions.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">On the molecule detail page, each flagged isoform also lists the known drugs that rely on it for clearance: the specific medications that could build up to unsafe levels if co-administered with this molecule.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="predicted-binding-structure" class="scroll-mt-6 text-lg font-semibold text-text-primary">Predicted Structure & Binding Affinity</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">This panel, on the molecule detail page, is different from every other score on this platform: instead of a pre-computed result, <strong class="font-semibold text-text-primary">you</strong> supply the target. Paste a protein, DNA, or RNA sequence for a target youâre interested in, and the platform runs a computational structure prediction for this molecule against that specific target, something the rest of the catalogâs pre-computed scores donât do, since those are scored against target<!-- --> <em>classes</em>, not a target you provide yourself.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">This can take some time to run. A progress indicator shows while it works, and
1you can navigate away and come back later; the result will be waiting for you.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Reading the result</h3><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">3D structure</strong>: the target is shown as a cartoon ribbon, your molecule as thick orange sticks, and nearby target residues (the local binding pocket) as thin gray sticks for context. Drag to rotate, scroll to zoom, and use the button below the viewer to switch between a close-up of the binding site and the full structure.</li><li><strong class="font-semibold text-text-primary">Confidence (pLDDT)</strong>: the modelâs overall confidence in the predicted structure as a whole, on a 0-to-1 scale.</li><li><strong class="font-semibold text-text-primary">Interface Confidence</strong>: the modelâs confidence specifically in the predicted contact between your molecule and the target, shown as High, Moderate, or Low. This is separate from the overall structure confidence above, and is the closest indication currently available of whether the predicted pose looks plausible.</li><li><strong class="font-semibold text-text-primary">Predicted IC50</strong> and <strong class="font-semibold text-text-primary">Binding Affinity Likelihood</strong>: a direct measure of predicted binding strength. These only appear if you check âAlso predict binding affinityâ before submitting; this step is significantly slower than the structure prediction above, so it is opt-in rather than always run.</li></ul><p class="mt-2 text-sm leading-relaxed text-text-secondary"><strong>This is a computational prediction, not an experimentally validated result.</strong> The model always produces a predicted structure for whatever target and molecule you give it; it does not currently have a way to say âthis molecule doesnât bind.â A low Interface Confidence is the best available hint that a predicted pose may not be reliable, but it is not the same as a formal binding probability.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Refine with AutoDock Vina</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">Once a structure prediction completes, you can optionally run a second, independent check on it: AutoDock Vina, a classical physics-based docking method, searches for the best-fitting position and orientation of your molecule within the predicted pocket. This is a genuinely different approach from Boltz-2âs own deep-learning-based prediction above, not a re-run of the same method, so agreement or disagreement between the two is meaningful.</p><ul class="mt-2 list-disc space-y-1.5 pl-5 text-sm leading-relaxed text-text-secondary"><li><strong class="font-semibold text-text-primary">Vina Binding Affinity</strong>: Vinaâs own predicted binding strength, in kcal/mol. This is a different scale than Predicted IC50 above and the two are not directly comparable to each other.</li><li><strong class="font-semibold text-text-primary">Pose Agreement (RMSD vs. Boltz)</strong>: the distance, in Angstroms, between where Vina independently placed your molecule and where Boltz predicted it. A low value means the two methods agree on the binding pose; a high value means they disagree on where or how the molecule binds, worth noting either way.</li><li><strong class="font-semibold text-text-primary">3D overlay</strong>: Boltzâs predicted pose is shown in orange, and Vinaâs independently-docked pose is shown in teal, on the same structure, so the two can be compared visually rather than only as a number.</li></ul><p class="mt-2 text-sm leading-relaxed text-text-secondary"><strong>This refines a predicted structure, not a validated one.</strong> Vina is scoring the same computationally-predicted pocket Boltz produced, not a crystal structure, so agreement between the two methods means they converge given that starting point, not that either is confirmed correct.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Attribution</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">This feature is powered by<!-- --> <a href="https://github.com/jwohlwend/boltz" target="_blank" rel="noreferrer" class="text-accent hover:underline">Boltz-2</a> <!-- -->(Passaro, Corso, Wohlwend, et al.), an open-source biomolecular structure and binding-affinity prediction model released under the MIT License, and uses the<!-- --> <a href="https://github.com/sokrypton/ColabFold" target="_blank" rel="noreferrer" class="text-accent hover:underline">ColabFold</a> <!-- -->server (Mirdita et al.) for sequence alignment. The refinement step above is powered by<!-- --> <a href="https://github.com/ccsb-scripps/AutoDock-Vina" target="_blank" rel="noreferrer" class="text-accent hover:underline">AutoDock Vina</a> <!-- -->(Trott & Olson, 2010), molecular docking engine.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="synthesizability-stability" class="scroll-mt-6 text-lg font-semibold text-text-primary">Synthesizability & Stability</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">Unlike every score described above, this panel (on the molecule detail page) is an<!-- --> <strong class="font-semibold text-text-primary">AI-based opinion</strong>. It gives a written assessment and a 1-to-6 rating on two independent axes:</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Synthesizability</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">How practical the molecule looks to actually make, reasoning about a plausible synthetic route: how many steps it would likely take, whether any step needs unusual or hazardous reagents, and how much stereochemical complexity needs to be controlled. 1 means the route looks impractical or unprecedented;
1 6 means a short, simple route from cheap starting materials.</p><h3 class="mt-5 text-sm font-semibold text-text-primary">Stability</h3><p class="mt-2 text-sm leading-relaxed text-text-secondary">How well the molecule would hold up in storage and handling as a bench chemical: its sensitivity to air, moisture, light, and heat, and whether it contains functional groups known to be reactive or short-lived on the shelf. 1 means the molecule would likely need special handling or wouldnât keep at all; 6 means it should be as stable as a typical, well-behaved solid compound under normal storage.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">This stability rating is specifically about physical shelf storage: it is<!-- --> <strong>not</strong> a prediction of how the molecule behaves metabolically inside a living organism, which is a separate question this rating doesnât address.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="similarity-search" class="scroll-mt-6 text-lg font-semibold text-text-primary">Molecular Similarity Search</h2><p class="mt-2 text-sm leading-relaxed text-text-secondary">The Catalog page lets you search for molecules structurally similar to one you provide, rather than identical to it. Similarity is measured using<!-- --> <strong class="font-semibold text-text-primary">Tanimoto similarity</strong>: a 0-to-1 score comparing the structural fingerprints of two molecules, where 1 means identical and lower values mean less structural overlap. This is the standard way computational chemistry tools compare âhow alikeâ two structures are, without requiring an exact match.</p><p class="mt-2 text-sm leading-relaxed text-text-secondary">Enter a SMILES string and a minimum similarity threshold, and the search returns every catalog molecule scoring at or above that threshold against your query.</p></section><section class="rounded-lg border border-border bg-surface p-5 shadow-sm"><h2 id="glossary" class="scroll-mt-6 text-lg font-semibold text-text-primary">Glossary</h2><dl class="mt-3 divide-y divide-border text-sm"><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">SMILES</dt><dd class="text-text-secondary">Text notation for a molecule's structure. See Molecular Identity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">SMARTS</dt><dd class="text-text-secondary">Text notation for a structural pattern, not one specific molecule. See Molecular Identity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">InChI / InChI Key</dt><dd class="text-text-secondary">Standardized chemical identifier and its short hashed form. See Molecular Identity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">MW</dt><dd class="text-text-secondary">Molecular Weight, the mass of a molecule. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">LogP</dt><dd class="text-text-secondary">A measure of lipophilicity (fat- vs. water-solubility). See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">HBD / HBA</dt><dd class="text-text-secondary">H-Bond Donors / H-Bond Acceptors. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">QED</dt><dd class="text-text-secondary">Quantitative Estimate of Drug-likeness, a 0-1 composite score. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">SA Score</dt><dd class="text-text-secondary">Synthetic Accessibility Score, a computed 1-10 ease-of-synthesis estimate. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Log S</dt><dd class="text-text-secondary">Predicted aqueous solubility (log10 mol/L) from a trained graph neural network. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">MC1</dt><dd class="text-text-secondary">Molecular Complexity, the 0-1 fraction of atoms that are not divalent. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">MC2</dt><dd class="text-text-secondary">Molecular Complexity, the count of non-divalent atoms excluding amide/ester/carbamate C=O. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">SPS / nSPS</dt><dd class="text-text-secondary">Spacial Score, a complexity measure based on sp3 and stereochemical character; nSPS is per heavy atom. See Physicochemical Properties.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">PSA</dt><dd class="text-text-secondary">Polar Surface Area. See Structural Characteristics.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Rule of Five</dt><dd class="text-text-secondary">Lipinski's rule of thumb for oral bioavailability, based on MW/LogP/HBD/HBA. See Structural Characteristics.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Stereocenter</dt><dd class="text-text-secondary">An atom whose spatial arrangement can produce distinct molecules with different activity. See Structural Characteristics.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Target class</dt><dd class="text-text-secondary">A biological classification of drug targets (Kinase, GPCR, etc.). See Target Activity & Tiers.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Antagonist / Agonist</dt><dd class="text-text-secondary">Blocking vs. activating a biological target. See Target Activity & Tiers.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Tier (A-E)</dt><dd class="text-text-secondary">This platform's letter-grade summary of predicted target activity or safety, in place of a raw probability. See Target Activity & Tiers.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">CYP450</dt><dd class="text-text-secondary">A family of liver enzymes responsible for metabolizing many drugs. See Drug-Drug Interaction Screening.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">DDI</dt><dd class="text-text-secondary">Drug-Drug Interaction, the risk that a molecule interferes with how other drugs are metabolized. See Drug-Drug Interaction Screening.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Tanimoto similarity</dt><dd class="text-text-secondary">A 0-1 score measuring structural similarity between two molecules' fingerprints. See Molecular Similarity Search.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">pLDDT</dt><dd class="text-text-secondary">Predicted Local Distance Difference Test â a structure prediction model's confidence in its own predicted 3D structure, 0-1. See Predicted Structure & Binding Affinity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">Interface Confidence</dt><dd class="text-text-secondary">Confidence in a predicted structure's contact between two specific molecules, separate from overall pLDDT. See Predicted Structure & Binding Affinity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">IC50</dt><dd class="text-text-secondary">The concentration of a molecule needed to inhibit a target's activity by 50% â a common measure of binding/inhibition strength. See Predicted Structure & Binding Affinity.</dd></div><div class="grid grid-cols-1 gap-1 py-2.5 sm:grid-cols-[180px_1fr] sm:gap-3"><dt class="font-medium text-text-primary">RMSD</dt><dd class="text-text-secondary">Root-Mean-Square Deviation, a distance measure between two 3D poses of the same molecule. Used to compare Vina's independently-docked pose against Boltz's predicted pose. See Predicted Structure & Binding Affinity.</dd></div></dl></section></div></div></div></main><footer class="border-t border-border bg-surface"><div class="container mx-auto px-6 py-12 md:px-12"><div class="flex flex-col gap-10 lg:flex-row lg:justify-between">
1<div class="max-w-md shrink-0"><a class="text-lg font-semibold tracking-tight text-text-primary" href="/">Neuralocity</a><p class="mt-2 text-sm leading-relaxed text-text-secondary">The intelligence layer on a generative catalog, delivering computationally prioritized molecule data for early drug discovery.</p></div><div class="grid grid-cols-2 gap-8 sm:grid-cols-3"><div><h3 class="text-sm font-semibold text-text-primary">Platform</h3><ul class="mt-3 space-y-2"><li><a class="text-sm text-text-secondary transition-colors hover:text-text-primary" href="/catalog">Inside the Catalog</a></li></ul></div><div><h3 class="text-sm font-semibold text-text-primary">Company</h3><ul class="mt-3 space-y-2"><li><a class="text-sm text-text-secondary transition-colors hover:text-text-primary" href="/about">About</a></li><li><a href="mailto:[email protected]" class="text-sm text-text-secondary transition-colors hover:text-text-primary">Contact</a></li><li><button type="button" class="text-left text-sm text-text-secondary transition-colors hover:text-text-primary">Share feedback</button></li></ul></div><div><h3 class="text-sm font-semibold text-text-primary">Legal</h3><ul class="mt-3 space-y-2"><li><a class="text-sm text-text-secondary transition-colors hover:text-text-primary" href="/privacy-policy">Privacy Policy</a></li><li><a class="text-sm text-text-secondary transition-colors hover:text-text-primary" href="/terms-of-service">Terms of Service</a></li></ul></div></div></div><div class="mt-10 border-t pt-6 border-border"><p class="text-xs text-text-secondary">© <!-- -->2026<!-- --> Neuralocity LLC.</p></div></div></footer></div><!--$--><!--/$-->
1<script src="/_next/static/chunks/webpack-8a8327b08dd8fe13.js" id="_R_" async=""></script>
1<script>(self.__next_f=self.__next_f||[]).push([0])</script>
1<script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[2000,[\"730\",\"static/chunks/44530001-9f564ab55328eab5.js\",\"817\",\"static/chunks/817-576501c917c8d2f1.js\",\"177\",\"static/chunks/app/layout-0d77fadd05161323.js\"],\"Providers\"]\n3:I[9766,[],\"\"]\n4:I[8924,[],\"\"]\n5:I[387,[\"730\",\"static/chunks/44530001-9f564ab55328eab5.js\",\"817\",\"static/chunks/817-576501c917c8d2f1.js\",\"176\",\"static/chunks/176-14d53a9c86e31d17.js\",\"779\",\"static/chunks/779-303be24ae6ed1d4b.js\",\"940\",\"static/chunks/940-38e89157d17ef948.js\",\"455\",\"static/chunks/app/documentation/page-cfa91cc4b509df03.js\"],\"MarketingHeader\"]\n6:I[8231,[\"730\",\"static/chunks/44530001-9f564ab55328eab5.js\",\"817\",\"static/chunks/817-576501c917c8d2f1.js\",\"176\",\"static/chunks/176-14d53a9c86e31d17.js\",\"779\",\"static/chunks/779-303be24ae6ed1d4b.js\",\"940\",\"static/chunks/940-38e89157d17ef948.js\",\"455\",\"static/chunks/app/documentation/page-cfa91cc4b509df03.js\"],\"DocumentationContent\"]\n7:I[2619,[\"730\",\"static/chunks/44530001-9f564ab55328eab5.js\",\"817\",\"static/chunks/817-576501c917c8d2f1.js\",\"176\",\"static/chunks/176-14d53a9c86e31d17.js\",\"779\",\"static/chunks/779-303be24ae6ed1d4b.js\",\"940\",\"static/chunks/940-38e89157d17ef948.js\",\"455\",\"static/chunks/app/documentation/page-cfa91cc4b509df03.js\"],\"\"]\n8:I[2303,[\"730\",\"static/chunks/44530001-9f564ab55328eab5.js\",\"817\",\"static/chunks/817-576501c917c8d2f1.js\",\"176\",\"static/chunks/176-14d53a9c86e31d17.js\",\"779\",\"static/chunks/779-303be24ae6ed1d4b.js\",\"940\",\"static/chunks/940-38e89157d17ef948.js\",\"455\",\"static/chunks/app/documentation/page-cfa91cc4b509df03.js\"],\"FeedbackDialog\"]\nd:I[7150,[],\"\"]\n:HL[\"/_next/static/css/63c64bcc8c509764.css\",\"style\"]\n:HL[\"/_next/static/css/5d7dd385fd1eee72.css\",\"style\"]\n"])</script>
1<script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"FHkbQYoMnTI0_QdUfmyZC\",\"p\":\"\",\"c\":[\"\",\"documentation\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"documentation\",{\"children\":[\"__PAGE__\",{}]}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/63c64bcc8c509764.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":404}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}],{\"children\":[\"documentation\",[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[\"__PAGE__\",[\"$\",\"$1\",\"c\",{\"children\":[[\"$\",\"div\",null,{\"className\":\"gradient-surface flex min-h-screen flex-col\",\"children\":[[\"$\",\"$L5\",null,{}],[\"$\",\"main\",null,{\"className\":\"flex-1 bg-background\",\"children\":[\"$\",\"$L6\",null,{}]}],[\"$\",\"footer\",null,{\"className\":\"border-t border-border bg-surface\",\"children\":[\"$\",\"div\",null,{\"className\":\"container mx-auto px-6 py-12 md:px-12\",\"children\":[[\"$\",\"div\",null,{\"className\":\"flex flex-col gap-10 lg:flex-row lg:justify-between\",\"children\":[[\"$\",\"div\",null,{\"className\":\"max-w-md shrink-0\",\"children\":[[\"$\",\"$L7\",null,{\"href\":\"/\",\"className\":\"text-lg font-semibold tracking-tight text-text-primary\",\"children\":\"Neuralocity\"}],[\"$\",\"p\",null,{\"className\":\"mt-2 text-sm leading-relaxed text-text-secondary\",\"children\":\"The intelligence layer on a generative catalog, delivering computationally prioritized molecule data for early drug discovery.\"}]]}],[\"$\",\"div\",null,{\"className\":\"grid grid-cols-2 gap-8 sm:grid-cols-3\",\"children\":[[\"$\",\"div\",\"Platform\",{\"children\":[[\"$\",\"h3\",null,{\"className\":\"text-sm font-semibold text-text-primary\",\"children\":\"Platform\"}],[\"$\",\"ul\",null,{\"className\":\"mt-3 space-y-2\",\"children\":[[\"$\",\"li\",\"Inside the Catalog\",{\"children\":[\"$\",\"$L7\",null,{\"href\":\"/catalog\",\"className\":\"text-sm text-text-secondary transition-colors hover:text-text-primary\",\"children\":\"Inside the Catalog\"}]}]]}]]}],[\"$\",\"div\",\"Company\",{\"children\":[[\"$\",\"h3\",null,{\"className\":\"text-sm font-semibold text-text-primary\",\"children\":\"Company\"}],[\"$\",\"ul\",null,{\"className\":\"mt-3 space-y-2\",\"children\":[[\"$\",\"li\",\"About\",{\"children\":[\"$\",\"$L7\",null,{\"href\":\"/about\",\"className\":\"text-sm text-text-secondary transition-colors hover:text-text-primary\",\"children\":\"About\"}]}],[\"$\",\"li\",\"Contact\",{\"children\":[\"$\",\"a\",null,{\"href\":\"mailto:[email protected]\",\"className\":\"text-sm text-text-secondary transition-colors hover:text-text-primary\",\"children\":\"Contact\"}]}],[\"$\",\"li\",\"Share feedback\",{\"children\":[\"$\",\"$L8\",null,{\"variant\":\"app\"}]}]]}]]}],[\"$\",\"div\",\"Legal\",{\"children\":[[\"$\",\"h3\",null,{\"className\":\"text-sm font-semibold text-text-primary\",\"children\":\"Legal\"}],[\"$\",\"ul\",null,{\"className\":\"mt-3 space-y-2\",\"children\":[[\"$\",\"li\",\"Privacy Policy\",{\"children\":[\"$\",\"$L7\",null,{\"href\":\"/privacy-policy\",\"className\":\"text-sm text-text-secondary transition-colors hover:text-text-primary\",\"children\":\"Privacy Policy\"}]}],[\"$\",\"li\",\"Terms of Service\",{\"children\":[\"$\",\"$L7\",null,{\"href\":\"/terms-of-service\",\"className\":\"text-sm text-text-secondary transition-colors hover:text-text-primary\",\"children\":\"Terms of Service\"}]}]]}]]}]]}]]}],\"$L9\"]}]}]]}],[\"$La\"],\"$Lb\"]}],{}
1,null,false]},null,false]},null,false],\"$Lc\",false]],\"m\":\"$undefined\",\"G\":[\"$d\",[]],\"s\":false,\"S\":true}\n"])</script>
1<script>self.__next_f.push([1,"e:I[4431,[],\"OutletBoundary\"]\n10:I[5278,[],\"AsyncMetadataOutlet\"]\n12:I[4431,[],\"ViewportBoundary\"]\n14:I[4431,[],\"MetadataBoundary\"]\n15:\"$Sreact.suspense\"\n9:[\"$\",\"div\",null,{\"className\":\"mt-10 border-t pt-6 border-border\",\"children\":[\"$\",\"p\",null,{\"className\":\"text-xs text-text-secondary\",\"children\":[\"© \",2026,\" Neuralocity LLC.\"]}]}]\na:[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/5d7dd385fd1eee72.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]\nb:[\"$\",\"$Le\",null,{\"children\":[\"$Lf\",[\"$\",\"$L10\",null,{\"promise\":\"$@11\"}]]}]\nc:[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$L12\",null,{\"children\":\"$L13\"}],null],[\"$\",\"$L14\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$15\",null,{\"fallback\":null,\"children\":\"$L16\"}]}]}]]}]\n"])</script>
1<script>self.__next_f.push([1,"13:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}]]\nf:null\n"])</script>
1<script>self.__next_f.push([1,"11:{\"metadata\":[[\"$\",\"title\",\"0\",{\"children\":\"Documentation · Neuralocity\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Reference documentation for the Neuralocity molecule data platform.\"}]],\"error\":null,\"digest\":\"$undefined\"}\n"])</script>
1<script>self.__next_f.push([1,"16:\"$11:metadata\"\n"])</script>
1</body></html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.