Our Training Approach
Practical, expert-led programmes that accelerate adoption and build lasting capability
Assess Skills & Infrastructure Gaps
We begin by understanding your team's existing expertise, research workflows, and technology stack — identifying where targeted training will have the highest impact.
Design a Tailored Curriculum
Each programme is built around your domain, data, and tools. We combine lecture-style theory with hands-on exercises using your own datasets and platforms whenever possible.
Deliver Expert-Led Sessions
Our trainers are active researchers and tool developers — not just instructors. They bring real-world experience from EU-funded projects, industrial collaborations, and peer-reviewed publications.
Support Sustainable Adoption
Training doesn't end with the workshop. We provide materials, documentation, and follow-up support so your teams can apply what they've learned independently and at scale.
Training Areas
Deep technical capability across the full spectrum of computational science
Machine Learning
From foundational ML concepts to advanced model development — including supervised/unsupervised learning, feature engineering, model validation, and deployment in scientific workflows.
- QSAR/QSPR modelling
- AutoML and model selection
- Explainable AI (XAI)
- Predictive modelling systems
Artificial Intelligence
Practical AI for scientific research — covering deep learning architectures, natural language processing, contrastive learning, and AI integration into computational pipelines.
- Deep learning for drug discovery
- Neural network architectures
- AI-powered risk assessment
- Read-across and consensus models
Physics-Based Simulations
Molecular dynamics, Monte Carlo methods, quantum chemistry, and multiscale modelling — bridging atomistic-level insights with macroscopic material behaviour.
- Molecular dynamics (MD) simulations
- Nanoparticle construction & analysis
- Protein–nanoparticle interactions
- Environmental fate modelling
Statistical Analytics
Rigorous statistical methods for experimental design, data analysis, and model evaluation — applicable across chemistry, biology, materials science, and regulatory frameworks.
- Design of experiments (DoE)
- Multivariate analysis
- Uncertainty quantification
- Regulatory risk assessment
FAIR Data Management
Hands-on training in FAIR data principles, metadata standards, persistent identifiers, data governance, and building interoperable scientific repositories.
- FAIR data principles & implementation
- Metadata schemas & ontologies
- Data governance & provenance
- Repository design & curation
Scientific Software & Workflows
Training on the NovaMechanics tool ecosystem — including the Enalos Cloud Platform, KNIME analytics workflows, and domain-specific web applications for research and regulatory use.
- Enalos Cloud Platform tools
- KNIME workflow integration
- Cheminformatics platforms
- Web application deployment
Delivery Formats
Flexible options to fit your team's schedule, location, and learning goals
Workshops
Intensive 1–3 day hands-on sessions combining theory with practical exercises using real datasets and tools.
Courses
Structured multi-week programmes covering a topic in depth — from foundational concepts to advanced applications.
Project-Embedded
Training delivered within the context of EU-funded or industrial projects, aligned with consortium goals and milestones.
Custom Corporate
Bespoke programmes designed for organisations adopting AI, modelling, or FAIR infrastructure across their research operations.