Predict molecular properties and boost the efficiency of machine learning workflows.
Translate data to prediction
Trainer Engine makes chemical, physical and biological activity predictions available by streamlining learning from input data with high accuracy, reliability and confidence at scale. The framework simplifies sharing models, and managing the machine learning lifecycle.
Try it free
Why you need Trainer Engine
From input data to implementation of validated models.
Chemical structure normalization, high-quality and customizable descriptors.
Rich feedback and visualization for model optimization.
Central model repository to support selecting production grade models.
Access to predictions from a built-in graphical interface, Design Hub or other design platforms.
Successful models built on bio-activity, ADMET and phys-chem targets.
Trainer Engine offers automatized, high performant, and configurable descriptor generation on normalized chemical data. It provides a wide range of machine learning algorithms including Random Forest, Gradient Boosted Trees, Support Vector Machine, and Logistic Regression. Model performance is automatically evaluated, and the most important statistical parameters are calculated both for regression and classification cases.
Feature selection is supported by seamless re-training, based on feature importance in the case of Random Forest. Calibrated error is calculated using the conformal prediction framework. Applicability domain assessment is enabled by returning the most similar structures and corresponding activity data from the training set.
The collection of generated models is accessible from the central service in order to benchmark their prediction power and provide insights into their behavior. Trainer Engine stores the models in a repository to ensure reproducibility and comparison of their parameters conveniently. The configurable analysis view comes with a classification and a regression layout presets with optimized tables, charts and molecule visualizations.
Singe / batch mode
Trainer Engine provides services for novel predictions in single or batch mode (through SDF file upload).
For programmatic access, we recommend using the REST API interface to automatize the machine learning workflow and integrate predictions into design tools like Design Hub or other third-party applications.
Optimized for model building
Trainer Engine graphical user interface offers a rich set of tools to build, validate and compare models. It is loved by computational chemists.
Simple prediction interface
It comes with a lightweight prediction application optimized for end-users, the Playground.
Learn more about Trainer Engine.
Support & FAQ
Full featured chemical editor for all platforms
Convert chemical names into structures
Smart assistant for patent claim drafting and Markush analysis
Chemical Structure Representation
Standardization and correction of chemical structures
Calculate properties instantly, search chemical data, and draw molecules online
Normalize, check, validate and register chemical compounds
High performance virtual synthesis engine
JChem for Office
Chemical structure handling, data analysis, visualization and reporting capabilities within MS Office
A single platform that connects scientific rationale, compound design and computational resources
Search through tens of millions of chemical compounds and receive relevant query hits in seconds.
Calculators and Predictors
Execute high quality physico-chemical calculations and predictions.
Identify controlled substances with Compliance Checker and assign HS tariff codes with cHemTS - the easy way to comply with chemical regulations.
From clustering and diversity analysis for chemical libraries to 2D and 3D molecular screening
Create, explore and share chemical data
Computer-assisted chemical information extraction and analysis