ADMET / Drug-Likeness Panel
Compute RDKit descriptors, Ro5/Veber/QED, BBB/CYP/hERG heuristics, and oral-readiness flags.
Browse ChemistryAtlas apps for molecular descriptors, fingerprints, pKa, logD, solubility, ADMET, alerts, similarity search, substructure search, scaffold analysis, library design, batch screening, and QSAR.
These apps help chemists move from individual compounds to libraries, property tradeoffs, and testable design ideas.
These apps help chemists move from individual compounds to libraries, property tradeoffs, and testable design ideas.
The Discovery and Cheminformatics hub focuses on molecular screening and design: descriptors, fingerprints, drug-likeness, ADMET, solubility, pKa, structural alerts, similarity, substructure, scaffold, matched-pair, and QSAR workflows.
Compute RDKit descriptors, Ro5/Veber/QED, BBB/CYP/hERG heuristics, and oral-readiness flags.
Run RDKit SMARTS structural-alert checks and synthetic-accessibility complexity hints.
Estimate logS with an ESOL-style RDKit descriptor heuristic and classify aqueous solubility.
Run RDKit Morgan-fingerprint similarity and SMILES/SMARTS substructure matching over a pasted or uploaded library.
Apply RDKit reaction SMARTS templates for amide, ester, and hydrogenation product prediction.
Extract Murcko scaffolds and scaffold atom counts from names or SMILES with RDKit.
Train a small Random Forest QSAR model from smiles,target CSV data and predict new molecules from RDKit descriptors.
Recommend next experiments from measured/blank CSV rows using Random Forest prediction uncertainty.
Enumerate and rank substituent designs against MW, TPSA, and target-logP constraints.
Export RDKit descriptors, drug-likeness fields, Morgan on-bit fingerprints, JSON, and ML-ready CSV features.
Build pairwise SAR delta tables with Murcko scaffold checks, Tanimoto similarity, and property changes.
Select diverse compounds by greedy max-min distance over RDKit Morgan fingerprints.
Enumerate R-group or reaction-SMARTS virtual libraries, calculate product descriptors, and export SDF/CSV.
Batch screen names, SMILES, InChI, formulas, or uploaded lists with RDKit properties, constraints, and Pareto-front ranking.
Screen molecular precursors for linker, electrolyte, chromophore, and organic-electronics motifs.
Rank salt counterions and cocrystal formers from API pKa, ionization class, solubility, stability, and pharma-style tradeoffs.
Calculate pH-dependent ionization, neutral fraction, and estimated LogD from logP plus acid/base pKa values.
Run crystal structure prediction workflows from formulas, element sets, or uploaded structures.
Predict whether candidate compounds are likely two-dimensional materials.
Compare candidate formulas side by side across selected ChemistryAtlas predictors and Materials Project summary data.
Upload measured property data, use Magpie or your own descriptor columns, and discover interpretable equations.
Predict noncentrosymmetric materials from composition or structure input.
Predict band gap values from composition or structure input.
Predict elastic moduli for candidate materials.
Estimate elastic tensors and VRH moduli from uploaded structures using fast finite-strain MLIP stress calculations.
Predict hardness-related material properties.
Predict thermal conductivity for candidate materials.
Predict room-temperature linear and volumetric thermal expansion coefficients for substrate matching and reliability screening.
Predict scalar dielectric constants for capacitor, insulator, and functional dielectric screening.
Predict composition-level piezoelectric response coefficients for sensors, actuators, and energy harvesting.
Predict refractive index, optical band gap, approximate color, absorption edge, and Shockley-Queisser photovoltaic limit.
Estimate Seebeck coefficient, electrical conductivity, thermal conductivity, power factor, and zT at 300/600/900 K.
Predict magnetic ordering, Curie temperature, or Néel temperature from composition.
Predict ionic conductivity for candidate materials.
Predict superconductivity-related properties for candidate formulas.
Paste formulas or upload a CSV, select property groups, and rank candidates with Pareto-optimal materials highlighted.
Search and screen hypothetical composition database entries.
Search superconductor CIF candidates from ICSD, Materials Project, and hypothetical libraries.
Search quantum material CIF candidates from ICSD, Materials Project, and hypothetical libraries.
Search generated lithium material candidates.
Run a combined battery-material screen for electrolytes, cathodes, or anodes.