Machine Learning & Analytics Collection

Data comes in all shapes and sizes, yet unlocking actionable insight efficiently requires deep knowledge of data science techniques. BIOVIA Pipeline Pilot Machine Learning and Analytics Collection provides a comprehensive set of machine learning and data modeling capabilities to streamline your data science initiatives.

Analyze data, train and retrain models, and deploy your automated solution to useful enterprise applications.

Developing machine learning solutions often requires complex software architectures and deep statistical knowledge. With BIOVIA Pipeline Pilot Analytics and Machine Learning Collection, developers and end users alike can incorporate the latest machine learning techniques to their workflows with just a few clicks. No coding required.

• Merge, join, characterize, and clean your data sets
• Apply any of 15+ machine learning (ML) methods to your scientific and engineering data
  • Use R-based ML methods such as support vector machines, neural networks, and XGBoost without writing R scripts
  • Use Python ML libraries including scikit-learn and TensorFlow
• Rapidly apply statistical analyses
  • Use regression and classification model evaluation viewers to assess and compare model test set performance
  • Build fast, scalable Bayesian classification models
  • Use the GFA method’s genetic algorithm for variable selection and building regression ensemble models
  • Build accurate, easy-to-use RP Forest regression and classification models
• Curate model performance
  • Deploy model applicability domain (MAD) methods and cross-validation
  • Employ the ML framework for cross-validation, hyperparameter tuning, and variable importance assessment for any type of model
• Work flexibly
  • Support for 3rd party statistic platforms and tools such as Jupyter Notebook, R, JMP and SAS
• Read in discipline-specific data
  • Purpose-built to support various numerical, chemical, biological, textual, and image data types
  • Use built-in applicability domain measures and error models to assess sample-specific prediction confidence
• Optimize predictions
  • Train multiple trial models in parallel to identify top performers or combine multiple models into a single ensemble model
• Simplify multi-objective optimization
  • Employ methods such as Pareto optimization to multi-objective optimization problems
• Visualize results in workflow
  • Generate interactive reports with ROC plots, enrichment plots and other visualization techniques
  • Perform exploratory analysis, including PCA, clustering, and multi-dimensional data visualization