Our Materials Informatics Pipeline
An integrated computational workflow from nanostructure design to property prediction and safety assessment
Digital Nanostructure Construction
Build nanoparticles, nanotubes, nanosheets, and crystal structures in silico using our web-based tools. Specify material composition, geometry (spherical, ellipsoidal, tubular), chirality, and dimensions through intuitive interfaces — no coding required.
Energy Minimization & Stability Analysis
Optimize nanostructure geometries through molecular dynamics energy minimization using LAMMPS with configurable force fields (OPLS-AA, CHARMM, ReaxFF, AMBER). Identify stable configurations and preferential crystal growth directions.
Atomistic Descriptor Calculation
Automatically extract 30+ structural and energetic descriptors — from potential energy distributions and coordination numbers to hexatic order parameters and lattice energies — providing the feature space for machine learning models.
Machine Learning & Property Prediction
Feed atomistic descriptors into validated ML models (Random Forest, XGBoost, LightGBM) for property prediction. OECD-compliant QSAR/QSPR models with SHAP-based interpretability and applicability domain analysis.
Safety Assessment & Nanotoxicology
Predict cytotoxicity, protein corona formation, and biological interactions using nanoinformatics models. Assess nanoparticle safety before synthesis, supporting safe-by-design approaches and regulatory compliance.
Our Cloud-Based Tool Ecosystem
Purpose-built web applications on the Enalos Cloud Platform
ASCOT
Digital construction and energy minimization of Ag, CuO, and TiO₂ spherical nanoparticles with automated atomistic descriptor calculation.
- Ag, CuO, TiO₂ (Anatase & Rutile)
- LAMMPS + OpenKIM integration
- Core/shell descriptor separation
- NanoPharos database upload
NanoConstruct
Build ellipsoidal nanoparticles from any material via CIF file upload. Investigate crystal growth, stability, and hypothetical material compositions.
- Any material via CIF upload
- Ellipsoidal & spherical geometries
- Element substitution analysis
- Crystal growth investigation
NanoTube Construct
Geometric construction and energy optimization of carbon nanotubes and nanosheets with full chirality and dimension control.
- Graphene, MoS₂, and more
- Chirality & periodicity control
- 30 atomistic descriptors
- Multiple force field options
UAnanoDock
Predict protein adsorption orientations and binding energies on nanoparticle surfaces using United-Atom multiscale molecular dynamics.
- Protein-NP interaction prediction
- Proteins up to 2000 residues
- pH-dependent binding analysis
- Immunoassay optimization
Easy-MODA
Automated generation of standardized MODA documentation for complex multiscale simulation workflows, ensuring FAIR data compliance.
- CEN CWA 17284:2018 compliant
- QMRF ↔ MODA field mapping
- Physics + data model support
- Reproducibility assurance
HydroNanoConstruct
Digital construction of nanomaterials with crystal growth investigation and automated atomistic descriptor extraction for ML integration.
- Automated nanostructure building
- Energy minimization workflows
- 30+ descriptor calculations
- Web-based, no expertise needed
Coming soon
Key Research Publications
Peer-reviewed research underpinning our materials informatics capabilities
ASCOT: Digital Construction of Ag, CuO, TiO₂ Spherical Nanoparticles
Web tool for energy-minimized nanoparticle construction and atomistic descriptor calculation, integrating LAMMPS with OpenKIM database.
NanoConstruct: Ellipsoidal Nanoparticle Builder for Crystal Growth Investigation
Application builder for any material via CIF files, enabling crystal growth investigation, stability analysis, and hypothetical element substitution.
NanoTube Construct: Computational Construction of Carbon Nanostructures
Specialized tool for geometric construction and energy optimization of nanotubes and nanosheets with chirality control and 30 atomistic descriptors.
UAnanoDock: United-Atom Multiscale Nanodocking for Protein-NP Interactions
Predicts protein adsorption orientations and binding energies on nanoparticle surfaces, optimizing immunoassay design and drug delivery.
Iron Carbide NP Cytotoxicity Prediction via Enalos Cloud Platform
Atom-level descriptors and explainable AI for predicting iron carbide nanoparticle cytotoxicity, deployed as a free web service.
Inorganic Nanoparticle Cytotoxicity Modeling with Atomistic Descriptors
Machine learning models achieving R² = 0.844 for ICNP-induced cell viability prediction, with SHAP-based interpretability analysis.
HydroNanoConstruct: Crystal Growth & Atomistic Descriptor Calculation
Web application for digital construction of nanomaterials with automated energy minimization and descriptor extraction for ML workflows.
Easy-MODA: Standardised Simulation Workflow Documentation
First automated tool for generating CEN-compliant MODA documentation, improving FAIRness and reproducibility of scientific simulations.
Predictive Nanotoxicology & Safe-by-Design
Enabling safety assessment before synthesis through explainable AI
NovaMechanics has developed a comprehensive nanoinformatics workflow for predicting nanoparticle cytotoxicity. By combining atomistic-level structural descriptors with evidence-based experimental features, our OECD-compliant machine learning models achieve high predictive accuracy for cell viability outcomes.
The models incorporate explainable AI techniques (SHAP analysis, Partial Dependence Plots) to identify which structural and physicochemical properties drive toxicity — enabling researchers to make informed design decisions early in the development process.