Admetica
Profile small-molecule ADMET properties across 22 Chemprop-based prediction models.
Related tools
ADMET-AI
Predict ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties from SMILES strings using machine learning models trained on Therapeutics Data Commons datasets.
eToxPred
Predict toxicity and synthetic accessibility of small molecules using machine learning. eToxPred combines toxicity risk assessment with synthetic accessibility scoring to help prioritize drug candidates.
Brenk filter
Identify toxic, reactive, and pharmacokinetically problematic molecular fragments using structural alert patterns
Lead-likeness filter
Screen for lead-like compounds using stricter molecular descriptor criteria than Lipinski or Veber rules for early-stage drug discovery
PAINS filter
Screen compounds for Pan-Assay INterference patterns that cause false positives in biological assays
QEPPI
Quantitative estimate for protein-protein interaction inhibitor potential. Evaluates drug-likeness for compounds targeting PPIs.
ToxPred 2.0 (Toxicity prediction)
Screen compounds for structural toxicity alerts using PAINS, Brenk, and NIH filters. For focused screening, see PAINS Filter, Brenk Filter, or Veber's Rule.
Veber's rule
Veber's Rule predicts oral bioavailability by evaluating molecular weight, LogP, hydrogen bond donors/acceptors, and rotatable bonds
Lipinski's rule of 5
Lipinski's Rule of Five predicts whether compounds will be orally bioavailable by evaluating molecular weight, LogP, hydrogen bond donors, and acceptors.
SPRINT
SPRINT (Structure-aware PRotein ligand INTeraction) predicts drug-target interactions using co-embedded protein and ligand representations. Screen thousands of compounds against a protein target in seconds.
What is Admetica?
Admetica is Datagrok's open-source ADMET prediction toolkit for small molecules. In ProteinIQ, the current wrapper follows the active upstream runtime surface exposed by the published admetica==1.4.1 package and the upstream web runtime: you can predict 22 pharmacokinetic and toxicity properties from SMILES strings.
Admetica uses Chemprop graph neural networks trained per endpoint. Each model predicts one experimentally grounded ADMET property, so the tool is useful for early compound triage, lead optimization, and comparing candidates before synthesis or assay work.
How to use Admetica online
Paste one SMILES per line, upload an .sdf, .csv, .smi, .smiles, or .txt file, or fetch structures from PubChem. Tab-delimited name<TAB>SMILES input is supported if you want to preserve your own identifiers.
Input formats
| Format | Description |
|---|---|
| Plain SMILES | One compound per line |
| Tab-delimited | compound_name<TAB>SMILES |
| SDF | Multiple structures from a structure-data file |
| CSV | Table input containing SMILES |
| PubChem fetch | Resolve a compound name or CID to SMILES |
Property selection
ProteinIQ exposes the upstream property subset selector. By default, all 22 upstream-exposed models are selected. You can deselect endpoints you do not need to reduce result columns and run only the models relevant to your screen.
Upstream-exposed properties
| Group | Property |
|---|---|
| Absorption | Caco2 |
| Absorption | Lipophilicity |
| Absorption | Solubility |
| Absorption | PGP-Inhibitor |
| Absorption | PGP-Substrate |
| Distribution | PPBR |
| Distribution | VDss |
| Metabolism | CYP1A2-Inhibitor |
| Metabolism | CYP2C9-Inhibitor |
| Metabolism | CYP2C19-Inhibitor |
| Metabolism | CYP2D6-Inhibitor |
| Metabolism | CYP3A4-Inhibitor |
| Metabolism | CYP1A2-Substrate |
| Metabolism | CYP2C9-Substrate |
| Metabolism | CYP2C19-Substrate |
| Metabolism | CYP2D6-Substrate |
| Metabolism | CYP3A4-Substrate |
| Excretion | CL-Hepa |
| Excretion | CL-Micro |
| Excretion | Half-Life |
| Toxicity | hERG |
| Toxicity | LD50 |
Output columns
Results are returned as a spreadsheet with one row per molecule. Exported columns use the original upstream property keys rather than ProteinIQ-specific aliases.
| Column | Meaning |
|---|---|
ids | ProteinIQ transport identifier for the submitted row |
smiles | Submitted SMILES string |
Caco2 | Predicted Caco-2 permeability |
Lipophilicity | Predicted lipophilicity |
Solubility | Predicted aqueous solubility |
PGP-Inhibitor | P-glycoprotein inhibitor prediction |
PGP-Substrate | P-glycoprotein substrate prediction |
PPBR | Plasma protein binding rate |
VDss | Volume of distribution at steady state |
CYP1A2-Inhibitor | CYP1A2 inhibition prediction |
CYP2C9-Inhibitor | CYP2C9 inhibition prediction |
CYP2C19-Inhibitor | CYP2C19 inhibition prediction |
CYP2D6-Inhibitor | CYP2D6 inhibition prediction |
CYP3A4-Inhibitor | CYP3A4 inhibition prediction |
CYP1A2-Substrate | CYP1A2 substrate prediction |
CYP2C9-Substrate | CYP2C9 substrate prediction |
CYP2C19-Substrate | CYP2C19 substrate prediction |
CYP2D6-Substrate | CYP2D6 substrate prediction |
CYP3A4-Substrate | CYP3A4 substrate prediction |
CL-Hepa | Hepatocyte clearance prediction |
CL-Micro | Microsome clearance prediction |
Half-Life | Half-life prediction |
hERG | hERG liability prediction |
LD50 | Acute toxicity prediction |
If you run only a subset of models, the output contains only ids, smiles, and the selected upstream property columns.
Interpreting results
Admetica mixes regression and classification endpoints. Continuous outputs such as Caco2, Solubility, CL-Hepa, CL-Micro, Half-Life, and LD50 should be interpreted in the context of the upstream training data and published endpoint definitions. Classification-style outputs such as the CYP, P-gp, and hERG endpoints indicate predicted liabilities or substrate behavior for the named target.
Use the predictions as triage signals rather than hard acceptance rules. Compounds outside the model training domain, including unusual chemotypes and larger non-drug-like structures, can produce less reliable estimates.
Upstream surface in ProteinIQ
This wrapper intentionally stays thin. ProteinIQ preserves the upstream runtime predictions and returns the currently exposed 22-model surface. The wrapper keeps ids and smiles for workflow tracking, but it does not add ProteinIQ-only descriptor columns to the exported result table.
Limitations
- The wrapper reflects the published
admetica==1.4.1runtime surface rather than every asset present in the upstream repository. - Only the 22 endpoints currently exposed by the upstream runtime are selectable here.
- Predictions are best suited to small-molecule chemical space similar to the upstream training data.
- This page does not add uncertainty estimates or re-score the upstream outputs.