Admet Prediction

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha c8c1fc3a2b13 · 19 Oct 2026Report an issue or request a re-scan

• PublisherGPTomics GitHub organizationOwner of the repository this skill is read from
• Source folderGPTomics/bioSkills/chemoinformatics/admet-predictionThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictc8c1fc3a2b13A new audit runs when the source changes
• Repository statusArchivedLast push 65 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR…

---
name: bio-admet-prediction
description: Predicts ADMET properties using ADMETlab 3.0 (119 platform features, including 77 prediction models with modeled-endpoint uncertainty), ADMET-AI, DeepChem MolNet, and chemprop D-MPNN with explicit handling of OECD QSAR principles, applicability domain assessment, calibration, hERG/CYP/AMES endpoints, and PAINS / Lipinski / Ro5 / Veber / BBB druglikeness filters. Use when filtering compounds for drug-likeness, prioritizing leads by predicted safety, or building an in-house ADMET QSAR model.
tool_type: python
primary_tool: ADMETlab
---

## Version Compatibility

Reference examples tested with: RDKit 2024.09+, requests 2.31+, DeepChem 2.8+, chemprop 2.0+ (note major API change from 1.x), admet-ai 1.3+, pandas 2.2+.

Before using code patterns, verify installed versions match. If versions differ:
- Python: `pip show <package>` then `help(module.function)` to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed
package and adapt the example to match the actual API rather than retrying.

# ADMET Prediction

Predict absorption, distribution, metabolism, excretion, and toxicity properties of drug candidates. ADMET prediction underpins lead selection and de-risking; calibrated, applicability-domain-aware predictions distinguish a working filter from a costly false-confidence rejection. Modern best practice combines online services (ADMETlab 3.0 with uncertainty estimates), open-source models (chemprop D-MPNN), and rule-based filters (Lipinski / Veber / BBB heuristics) -- each with known failure modes.

For PAINS / Brenk / structural alerts, see `chemoinformatics/substructure-search`. For QSAR model building from in-house data, see `chemoinformatics/qsar-modeling`.

## ADMET Model Taxonomy

| Tool | Endpoints | Architecture | Uncertainty | Access | Fails when |
|------|-----------|--------------|-------------|--------|------------|
| ADMETlab 3.0 | 119 reported features: 77 prediction models, 34 computed properties, 8 rules | Multi-task DMPNN + descriptors for modeled endpoints | Evidential uncertainty for modeled endpoints | Web service; hosted API documented by the authors | Outside training distribution; metals; macrocycles |
| ADMET-AI | TDC-derived ADMET tasks; inspect installed model metadata | Chemprop D-MPNN | Inspect version-specific outputs; do not assume calibrated uncertainty | Python package | v2 package predictions differ from the v1 paper/server |
| DeepChem MolNet | Dataset-dependent tasks including Tox21, ToxCast, and ClinTox | Model-dependent | Model-dependent | Python package | Coverage and uncertainty depend on the selected dataset/model |
| pkCSM | Service-defined ADMET endpoints | Graph signatures + ML | Inspect current service output | Web service | Applicability domain and service contract must be checked |
| SwissADME | Physchem, pharmacokinetics, drug-likeness, and medchem outputs | Published models and rules | None advertised | Web service (no public API) | Automated access is restricted by its terms |
| ProTox-3.0 | 61 toxicity models/endpoints | RF/DNN + fingerprints, similarity, and pharmacophore methods | Confidence score | Web service / sample API | Toxicity only; reports LD50 and toxicity class |
| ADMETpredictor (Simulations Plus) | ~140 | Proprietary | Per-prediction | Commercial | License cost |
| FAF-Drugs4 | filters | Rule-based | None | Web | Static rules |
| chemprop (in-house) | User-defined | D-MPNN ± descriptors | Ensemble and other estimators; optional calibration | Python package | Requires suitable training and calibration data |

**Decision:** For batch screening with no in-house data, **ADMETlab 3.0** provides 119 reported platform features and uncertainty for modeled endpoints through its web service and hosted API; verify the live API documentation before automating access. For a sufficiently large, relevant in-house endpoint dataset, benchmark a **chemprop D-MPNN**, descriptors, and simpler baselines under a deployment-relevant split rather than assuming a universal sample-size threshold. Shan et al. (2022) reported an AUC of 0.956 for a D-MPNN combined with 206 MOE descriptors on their random-split hERG benchmark.

## Decision Tree by Scenario

| Scenario | Workflow | Reasoning |
|----------|----------|-----------|
| Library triage, no in-house data | ADMETlab 3.0 API batch | Broad platform coverage plus modeled-endpoint uncertainty |
| Single endpoint, adequate in-house data | Benchmark chemprop D-MPNN, descriptors, and simpler baselines | Select by prospective or deployment-relevant validation |
| Need calibrated probabilities | chemprop with ensemble + Platt | Native deep learning rarely calibrated |
| FDA / regulatory submission | OECD-compliant QSAR with AD | See OECD principles below |
| Quick annotation for VS | Lipinski, Veber, and QED reported separately | Rank or annotate; do not impose a universal QED gate |
| BBB penetration | Simple screen: TPSA <= 90, MW <= 500, HBD <= 3 | Repository heuristic; not the six-factor CNS MPO |
| Cardiotox liability | ADMETlab hERG + ProTox-3.0 cardiotoxicity + literature check | Both hosted endpoints model hERG blockade; compare applicability domains and assay definitions |
| Drug-drug interaction (CYP) | CYP1A2/2C9/2C19/2D6/3A4 inhibitor + substrate | Standard set of 5 CYPs |

## OECD QSAR Principles (5 Pillars)

For regulatory-grade ADMET QSAR (REACH, ECHA, FDA submissions), models must satisfy:

1. **Defined endpoint** -- specific bioassay, units, conditions
2. **Unambiguous algorithm** -- reproducible model + code
3. **Defined applicability domain (AD)** -- where the model is valid
4. **Appropriate statistical validation** -- external test set, cross-validation
5. **Mechanistic interpretation** -- biological / chemical rationale

For non-regulatory work, AD assessment is still critical. The OECD's *applicability domain* is the workhorse: predictions outside the AD are unreliable, but operational AD measures (

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

pip install rdkit requests
pip install deepchem  # For ML-based predictions

git clone https://github.com/GPTomics/bioSkills
git -C bioSkills checkout c8c1fc3a2b13

Works in

1. 2026-10-19
   ✓SAFE B 89 / 100

   first audit · source c8c1fc3a2b13

Questions about Admet Prediction

• github.com/GPTomics/bioSkills/tree/main/chemoinformatics/admet-p — the audited source at commit c8c1fc3a2b13 and every finding aboveObserved · 19 Oct 2026

Spotted something wrong? Report a correction · Methodology