A publication-grade
AI toxicology platform.
Seven toxicity endpoints, SHAP explainability, applicability-domain confidence, real SyGMa metabolite prediction, CPIC-based pharmacogenomics, and publication-scale batch screening — one integrated, reproducible, self-hostable platform, not a single predictor behind an API key.
Platform
PLATFORM MODULES
A publication-grade toxicology platform, not a single predictor — every module below is a real, deployed capability.
Prediction Engine
Seven endpoints — hERG, hepato-, nephro-, Ames, skin sensitization, cytotoxicity, reproductive tox — from one SMILES.
Learn MoreSHAP Explainability
Per-prediction feature attribution reveals which molecular drivers pushed a score up or down.
Learn MoreSyGMa Metabolism
Real, published Phase I/II metabolite prediction with structural-alert screening on every metabolite.
Learn MorePharmacogenomics
57 real CPIC gene-drug pairs adjust toxicity context for a compound under a given phenotype scenario.
Learn MoreBatch Screening
Async, chunked, resumable screening of CSV/SDF compound sets with CSV/XLSX/JSON/PDF export.
Learn MoreValidation Hub
Live scaffold-split performance, applicability-domain artifact health, and external-validation status.
Learn MoreApplicability Domain
Leverage-based, percentile-calibrated confidence — a real reliability signal, not a hardcoded constant.
Learn MoreDeveloper API
The same OpenAPI-documented endpoints powering every page on this site — Docker-deployable, no lock-in.
Learn MorePublication Reports
Audit-ready PDF/CSV/XLSX exports from batch screening and PSI, ready for lab notebooks and manuscript supplements.
Learn MorePeer Review & Conference Acceptance
SCIENTIFIC RECOGNITION
Independent recognition of the MultiEndpointTox research platform
Pharmaceuticals
MDPI · ISSN 1424-8247
MultiEndpointTox: A Chemoinformatics Platform for Multidimensional Drug Toxicity Profiling Using Interpretable Machine Learning, Multi-Task Learning, and Integrated Risk Scoring
- Sharhabil Amgad Eltahir
- Mukhtar Ibrahim Yousef
- Accepted
- 6 August 2026
- Impact Factor
- 5.7
Peer-reviewed manuscript accepted
SETAC North America
47th Annual Meeting
Metabolism-Aware and Pharmacogenetics-Informed Toxicity Prediction: A Multi-Endpoint Machine Learning Framework With Systematic Platform Benchmarking
Advancing Molecular Tools and New Approach Methodologies for Next-Generation (Eco)Toxicology and Risk Assessment
- Location
- Montreal, Quebec
- Date
- Wednesday, 4 November 2026
- Time
- 1:30 PM EST
- Room
- 517c
Presentation ID: 20648
Research milestones
- Peer-reviewed manuscript accepted
- SETAC platform presentation selected
- Open-source computational platform
- Reproducible scientific workflow
Selected for Platform Presentation at SETAC
MultiEndpointTox will be presented at the SETAC North America 47th Annual Meeting in Montreal, highlighting metabolism-aware toxicity prediction and pharmacogenetics-informed safety assessment.
Metabolism-Aware and Pharmacogenetics-Informed Toxicity Prediction: A Multi-Endpoint Machine Learning Framework With Systematic Platform Benchmarking
- Wednesday, 4 November 2026
- 1:30 PM EST
- Room 517c
Accepted in Pharmaceuticals
The MultiEndpointTox platform has been accepted for publication in Pharmaceuticals (MDPI), documenting its chemoinformatics, interpretable machine-learning, multi-task learning, and integrated-risk framework.
- Accepted
- 6 August 2026
Who It's For
BUILT FOR MODERN TOXICOLOGY RESEARCH
From lead optimization to the classroom — one platform, six ways researchers actually use it.
Drug Discovery
Screen lead series for hepato-, cardio-, and genotoxicity liability before committing to in vitro assays.
Medicinal Chemistry
Use SHAP attribution to see which substructures drive a toxicity score, then design around them.
Academic Research
A free, reproducible, self-hostable platform for coursework, theses, and independent toxicology research.
Pharmaceutical Industry
Batch-screen compound libraries with audit-ready CSV/XLSX/PDF exports for internal safety review.
Regulatory Science
Applicability-domain confidence and scaffold-split validation reporting suited to supporting documentation.
Education
A live, explorable example of interpretable ML applied to real toxicology endpoints for teaching.
01 · Platform
PLATFORM OVERVIEW
MultiEndpointTox is an AI-powered platform that predicts 7 key toxicity endpoints and provides integrated risk assessment to support early-stage decision-making in drug discovery.
What is MultiEndpointTox?
An integrated, interpretable, and validated AI platform that predicts multiple toxicity endpoints and delivers a comprehensive risk assessment in a single solution.
AI-Powered Predictions
State-of-the-art machine learning models trained on high-quality multimodal data.
Integrated Risk Assessment
Combine multiple predictions into a robust, confidence-weighted risk score.
Interpretable Insights
Explainable AI and visual analytics reveal key molecular drivers behind each prediction.
Decision Confidence
Transparent, consistent, and reliable outputs to support safer and faster decisions.
7 Toxicity Endpoints
Comprehensive coverage of key safety liabilities.
Advanced AI/ML Models
Multi-task learning, domain adaptation, and ensemble methods.
Integrated Risk Score
Population-weighted, confidence-based risk for better prioritization.
Explainable & Transparent
SHAP-based explanations and intuitive visual analytics.
Validated & Reliable
Rigorous validation across datasets, scaffolds, and external benchmarks.
Built for Discovery
Designed for early-stage screening and lead optimization.
Save Time
Reduce experimental burden with fast, accurate predictions.
Reduce Costs
Prioritize safer compounds and avoid late-stage failures.
Improve Safety
Identify liabilities early and design safer molecules.
Boost Success Rate
Make confident, data-driven decisions at every step.
Accelerate Innovation
Enable smarter discovery with trusted AI insights.
02 · Endpoints
7 KEY TOXICITY ENDPOINTS
Comprehensive prediction of seven critical toxicity liabilities to support safer compounds and better decision-making. Hover any card for its example risk profile.
Hepatotoxicity
classification
Predicts the potential of compounds to cause liver injury or dysfunction.
Decision threshold (0.717) deliberately favors sensitivity over specificity (23.8%) — false negatives are costlier than false positives in early safety screening.
Nephrotoxicity
classification
Assesses the likelihood of kidney damage or impaired renal function.
Ames Mutagenicity
classification
Evaluates the potential of compounds to cause genetic mutations.
Skin Sensitization
classification
Predicts the potential of a compound to trigger an allergic skin reaction.
Only ~31% applicability-domain coverage — most novel-compound predictions fall outside the training distribution and should be treated as exploratory.
Reproductive Toxicity
classification
Estimates the risk of adverse effects on fertility and reproductive health.
Underpowered (n=127) — scaffold AUC=0.588, not significantly better than random on novel scaffolds. Reported for information only and excluded from the integrated risk score.
hERG Cardiotoxicity
regression
Predicts the potential to inhibit hERG potassium channels (pIC50 regression), which may lead to cardiac arrhythmias.
Scaffold-split R²=0.378 vs. 0.621 on a random split — a documented 39% generalization gap. Treat novel-scaffold predictions with caution; a graph-neural-network replacement is on the roadmap.
Cytotoxicity
classification
Assesses the potential of compounds to cause cell damage or reduce cell viability.
Comprehensive Safety Coverage
Address 7 critical toxicity liabilities in one platform.
Early Risk Identification
Detect potential liabilities at the earliest stages.
Better Prioritization
Focus resources on the most promising compounds.
Informed Decisions
Integrate toxicity insights into confident decisions.
Safer Drug Discovery
Reduce late-stage failures and improve success rates.
03 · Framework
ADVANCED AI/ML MODELS
State-of-the-art machine learning with multi-task learning and domain adaptation to deliver accurate, robust, and generalizable toxicity predictions.
Multi-Task Learning
Leverage shared molecular knowledge across 7 toxicity endpoints for more accurate and data-efficient predictions.
Shared Representation — Stronger Learning, Better Accuracy
Our AI/ML Framework
INPUT
Structure · Descriptors · Fingerprints · Graph Features
OUTPUT
7 Toxicity Predictions
Domain Adaptation
Improve model generalizability across different chemical spaces, assays, and laboratories.
- Reduces dataset bias and batch effects
- Enhances performance on unseen data
- Built for real-world applicability
High Accuracy
Scaffold-split validated performance across diverse benchmarks.
AUC up to 0.92
Across Key Endpoints
Robustness
Stable predictions across chemical space and noise.
Consistent
Across Scaffolds
Data Efficiency
Learn more with less data through inductive bias and multi-task sharing.
Multi-Task
Sharing
Scalability
Handle large datasets and complex models efficiently.
Cloud & HPC
Optimized
Continuous Learning
Models improve over time with new data and feedback.
Adaptive
Framework
Uncertainty-Aware
Quantify prediction confidence to support risk-based decisions.
Confidence
Estimates
04 · Risk Assessment
INTEGRATED RISK ASSESSMENT
From single-endpoint predictions to an integrated, confidence-weighted risk score for smarter, data-driven decision-making.
1. Endpoint Predictions
AI/ML models generate probability of liability for each endpoint.
2. Weighting & Integration
Population weights + confidence adjustment + risk aggregation.
3. Integrated Risk Score
Final score between 0 and 1 indicates overall risk level.
Endpoint Risk Matrix (Example)
| hERG | Hepato | Ames | Nephro | Skin Sens | Cyto | Repro Tox | |
|---|---|---|---|---|---|---|---|
| Drug A | 0.17 | 0.91 | 0.03 | 0.18 | 0.04 | 0.20 | 0.58 |
| Drug B | 0.23 | 0.64 | 0.05 | 0.82 | 0.97 | 0.10 | 0.58 |
| Drug C | 0.23 | 0.86 | 0.00 | 0.70 | 0.01 | 0.12 | 0.58 |
| Drug D | 0.20 | 0.93 | 0.02 | 0.67 | 0.97 | 0.18 | 0.58 |
| Drug E | 0.05 | 0.95 | 0.02 | 0.68 | 0.00 | 0.09 | 0.58 |
Integrated Risk Score
95% CI: 0.48 – 0.60
Population Weighting
Endpoints are weighted based on population-level prevalence and clinical relevance.
Risk Distribution (Example Dataset)
Risk Weighting Scenarios
The API accepts a scenario parameter that reprioritizes which endpoint drives the integrated score — useful when one liability matters more for a given program.
- BaselineManuscript Table 4 weights (default).
- EqualAll endpoint weights set to 1.0.
- Cardiac priorityhERG weight raised to 3.0.1.5 → 3.0
- Hepatic priorityHepatotoxicity weight raised to 3.0.1.5 → 3.0
- Genotoxicity priorityAmes weight raised to 3.0.1.3 → 3.0
Holistic Safety View
See the big picture across all critical toxicity endpoints.
Better Prioritization
Focus on compounds with lower overall risk.
Population Awareness
Accounts for population and metabolizer variability.
Data-Driven Confidence
Confidence-weighted approach improves decision reliability.
Faster, Smarter Decisions
Reduce attrition and accelerate safer drug discovery.
05 · Explainability
INTERPRETABILITY & TRANSPARENCY
We make every prediction explainable with state-of-the-art AI techniques and intuitive visual analytics.
Build Trust
Understand why a model made a prediction.
Ensure Reliability
Detect spurious patterns and data artifacts.
Drive Discovery
Reveal key molecular drivers of toxicity.
Support Decisions
Provide scientific rationale for safer compound selection.
Regulatory Readiness
Deliver transparent and auditable predictions.
Global Feature Importance
Example: Hepatotoxicity
Local Explanation (SHAP Beeswarm)
Each dot = one compound
Local Explanation (Waterfall Plot)
How features push the prediction from the base value to the final result.
Model Explainability Summary
Molecular Highlight
Example compound — drag to rotate
Why MultiEndpointTox
BUILT FOR SCIENTIFIC RIGOR
Not a black-box predictor — a platform designed to be checked, reproduced, and self-hosted.
Explainable AI
SHAP feature attribution on every prediction — see which molecular substructures drove the score, not just a number.
Scaffold Split Validation
Scaffold-split GroupKFold cross-validation, not a random split — the harder, more honest estimate of real-world generalization.
Applicability Domains
Every prediction ships with a leverage-based confidence signal, so you know when a compound is outside the training distribution.
Docker Deployment
A real, build-and-run-verified Dockerfile — self-host the full platform, not a hosted-only black box.
REST API
OpenAPI 3.1-documented endpoints power every page on this site — integrate directly, no scraping required.
Batch Processing
Async, chunked, resumable screening of CSV/SDF compound sets — hundreds of compounds per run, not one at a time.
Publication-Grade Reporting
Audit-ready PDF/CSV/XLSX exports from batch screening and PSI, suitable for lab notebooks and manuscript supplements.
Reproducible Pipeline
A documented, scripted reproduction pipeline — clone the repo, re-run the exact validation, get the same numbers.
07 · Workflow
SCIENTIFIC WORKFLOW
From a single SMILES string to an audit-ready report — every stage below is a real, callable API endpoint, not an aspirational pipeline.
SMILES
A single molecular structure string — the only required input.
Prediction
7 toxicity endpoints scored via /predict and /predict/integrated.
SHAP
Per-prediction feature attribution — which molecular drivers pushed the score.
Metabolism
Real SyGMa Phase I/II metabolite prediction, with structural-alert screening.
PSI
Pharmacogenomic Safety Index — CPIC gene-drug evidence adjusts toxicity context.
Integrated Risk
Confidence-weighted aggregate score across all included endpoints.
Report
Exportable PDF/CSV/XLSX (batch) or PSI PDF report — audit-ready output.
Large & Curated Toxicity Data
Diverse, high-quality datasets across endpoints.
Advanced AI/ML
State-of-the-art models with multi-task learning and domain adaptation.
Robust Validation
Rigorous internal & external validation ensures reliability.
Scalable Infrastructure
Cloud-native platform for high performance and enterprise scalability.
Secure & Compliant
Data security, privacy, and compliance by design.
Comprehensive Toxicity Profile
7-endpoint predictions in one view.
Actionable Risk Score
Confidence-weighted risk with clear interpretation.
Mechanistic Insights
Understand “why” through molecular drivers.
Data-Driven Decisions
Make informed choices faster with greater confidence.
Reports & Dashboards
Shareable, audit-ready outputs for teams and regulators.
Continuous Improvement
Models learn and improve with new data and feedback.
From Data to Discovery. From Prediction to Protection.
MultiEndpointTox empowers better science, safer compounds, and smarter decisions.
See It Live
THE REAL PLATFORM
Not mockups — live embeds of the actual pages, running the same build as everywhere else on this site.
Prediction Dashboard
Single-compound prediction across all 7 toxicity endpoints.
Batch Screening
Async CSV/SDF screening with CSV/XLSX/JSON/PDF export.
Pharmacogenomics
CPIC-based Pharmacogenomic Safety Index (PSI) scoring.
Validation Hub
Scaffold-split performance, AD health, external-validation status.
Developer Portal
Quick-start guides, SDK examples, and API rate limits.
Metabolism
Real SyGMa Phase I/II metabolite prediction.
06 · Validation
ROBUST VALIDATION & PERFORMANCE
Scaffold-split cross-validation, reported honestly — including where it's a harder story than a random split would tell.
7
Endpoints
API v1.2 · Platform v2.0.0-rc2
Model Versions
Scaffold-split GroupKFold (k=5)
Methodology
Scripted, documented reproduction pipeline
Reproducibility
Scaffold-Split GroupKFold
5-fold cross-validation with all compounds sharing a scaffold kept in the same fold.
No Leakage
SMOTE, feature selection, and scaling are fit inside each training fold only.
Temporal Split (in progress)
Methodology implemented; time-split validation on newer compounds is not yet reported.
External Benchmarks (in progress)
ClinTox and Tox21 external validation scripts exist; results are not yet published.
Train/Test Overlap Audit
Scaffold & exact-structure leakage checked between splits.
Performance Summary
Primary scaffold-split GroupKFold(k=5) AUC per classification endpoint
ROC Curves
Reconstructed from each endpoint's reported AUC (the API returns summary AUC, not raw TPR/FPR arrays) — shape is illustrative, area matches the published figure exactly.
hERG is a pIC50 regression model, so ROC/AUC doesn't apply. Scaffold-split R² = 0.38, versus R² = 0.62 on a random split — see the generalization gap chart below.
Scaffold vs. Random-Split Generalization Gap
Random splits let a model exploit scaffold-level similarity between train and test sets, inflating performance. These are the two endpoints where both numbers are published.
External Validation Status
Per the model card's TRIPOD-AI checklist: external validation is partial. Reported honestly as status, not results that don't exist yet.
| Dataset | Purpose | Status |
|---|---|---|
| ClinTox | External classification benchmark (FDA-approved vs. withdrawn-for-toxicity) | In progress |
| Tox21 | External multi-assay toxicity benchmark | In progress |
| Temporal split | Time-split validation (train on older compounds, test on newer) | Methodology implemented |
| Train/test overlap check | Scaffold & exact-structure leakage audit between splits | Implemented |
0.79 – 0.92
Classification AUC
Scaffold-split, 6 classification endpoints
0.81
Integrated Score
AUC on a withdrawn/safe compound set
R² 0.38
hERG (regression)
Scaffold-split — see generalization gap below
Excluded
Reproductive Tox
Underpowered (n=127) — informational only
Publications & Resources
READ THE SOURCE
Every claim on this site traces back to one of these — the manuscript, the live API, or the repository itself.
Research Publication
Manuscript status: Accepted in Pharmaceuticals (MDPI), 6 August 2026.
Scientific Recognition
Verified acceptance records — the Pharmaceuticals (MDPI) manuscript and the SETAC North America platform presentation.
Preprint
No preprint was posted — the manuscript proceeded directly from submission to peer-reviewed acceptance.
GitLab Repository
Full source, commit history, and CI — nothing behind a paywall.
Documentation
Model cards for every endpoint — methodology, metrics, and known limitations.
API Documentation
OpenAPI 3.1 — 107 documented paths, interactive Swagger UI.
Developer Portal
Quick-start guides, SDK examples, and rate limits for every route.
Validation Reports
Scaffold-split performance, AD health, and external-validation status.
Free for academic & individual researchers
Get unlimited access to the complete MultiEndpointTox platform — no cost, application reviewed by BioNexus Discovery. Approved requests receive a real, working API key.
Apply for Free Access- Unlimited predictions
- Batch screening
- Pharmacogenomics (PSI)
- Metabolism prediction (SyGMa)
- Developer API key
- Publication-ready PDF reports
- Validation Hub access
- Future platform updates
Access Levels
CHOOSE YOUR LEVEL OF ACCESS
From an instant no-signup demo to a fully self-hosted enterprise deployment.
Demo
Try it instantly, no signup
- Single-compound prediction
- All 7 toxicity endpoints
- No registration required
- Rate-limited request volume
Free Research Access
For academic & individual researchers
- Unlimited predictions
- Batch screening
- SHAP explainability
- SyGMa metabolism prediction
- Pharmacogenomics (PSI)
- Publication-ready PDF reports
- Validation Hub access
- Developer API key
Enterprise
For pharma & biotech teams
- Unlimited API usage
- Self-hosted Docker deployment
- Private infrastructure
- Commercial license
- Priority support
08 · Case Study
VALPROIC ACID (VPA)
Comprehensive AI-powered toxicity assessment — live prediction from the deployed MultiEndpointTox API, not a canned screenshot.
Running full 7-endpoint analysis for Valproic Acid…
Live inference + SHAP explanation on the deployed model. If the API has been idle, this includes a cold start — first requests can take up to 2–3 minutes.
CCCC(CCC)C(=O)O
Ready to accelerate your toxicology research?
Try a prediction in seconds, or apply for free research access to the complete platform.