Umetrics Suite Blog

Latest version of SIMCA focuses on improved user experience

May 7, 2019

SIMCA 16 offers improved ribbons, tours, wizards, data merging, multiblock analysis and more.

SIMCA is a multivariate data analytics tool that helps users make sense of complex data by transforming numbers and statistics into visual information for easy interpretation and understanding. Across many industries ranging from pharmaceuticals and chemicals to food and beverage manufacturers to academia, SIMCA helps production managers and researchers a like make better decisions in order to take action quickly and with confidence.

While known as an easy-to-use multivariate data analytics and visualization tool, with the latest release, SIMCA provides an even more adaptive environment. This means as a user, you’ll spend less time looking for functionality and more time learning from your data.

SIMCA 16 690x460

SIMCA 16 offers improved ribbons, tours, wizards, data merging, multiblock analysis and more. Register for the free webinar May 16 or download a free trial today.

Register today

The improved usability features include:

  • A guided and interactive getting-started tour. First-time users of SIMCA will have a step-by-step tour showing the workflow from data import to finished report using a test example.
  • Improved context-based ribbons and data explorer pane. Context-based behavior is extremely valuable for batch modeling. The new ribbons appear when needed and the data explorer pane provides quick info with visual information on models and data. A properties pane gives direct access to interaction with plots.
  • Advanced dataset merging. This eliminates the need to preprocess or align and combine data outside of SIMCA.
  • Workset wizard. Guides you through how to set up a model in SIMCA, which is useful not only for new users, but also valuable for advanced users.

Other innovative new features introduced in SIMA 16 include:

  • Model interrogations – improved tools to help answer model-related questions
  • New analytics technology – Multiblock Orthogonal Component Analysis (MOCA)
  • Python Extensions – offering flexibilityin data import and preprocessing

Model interrogation innovations

SIMCA 16 provides more functionality related to using and interpreting model. It addresses commonly asked questions such as:

  • Why are parts of my model space not populated? What would a sample (e.g. a raw material composition) look like to fill the gap seen in the score space?
  • How do I set my input parameters to get the desired output values? Can I compensate the effects of a new raw material using the process parameters?

These two new tools include:

Score space exploration. This tool lets you turn interesting model ideas into real-life factor combinations. A click in the model scatter plot converts the model into actual factor settings allowing you to directly find out what sample you are missing in your stack of observations. For example, this might be useful if you have a model of historical batches of raw materials and see an area in the score plot that is empty and you want to know what type of material is missing.

Multivariate solver. The second tool is a multivariate solver that, based on your desired output (quality attributes), finds the best factor settings to accomplish your goals, without multiple iterations. This can be useful, for example, when you have a predictive model and some of the inputs have to change (e.g. a new batch of raw material) and you need to know how to compensate to reach the same output.

New analytics technology

With SIMCA 16, we introduce Multiblock Orthogonal Component Analysis (MOCA), which is a new analysis method addressing the challenge of getting an overview of more than two blocks of data where the blocks are different measurements on the same set of observations The new MOCA algorithm provides a quick and comprehensive overview of what information is unique for each block and what is common between them.

This is a situation more and more scientists and engineers across many industries – from systems biologists working with “omics” data to manufacturing and food science – are facing as the number of data sources increase. There is no direct way of doing this type of analysis today.

Traditionally you needed to fit, and interpret, an array of models of different types to get an appreciation of the information overlap. With MOCA, you save time performing the multi-block overview and at the same time access completely new, previously overlooked, information.

Some data examples of uses for this type of analysis are:

  • Systems biology where samples are analyzed, for example, metabolomics, proteomics, lipidomics
  • Manufacturing data where process signals are complemented with spectroscopy and raw material composition
  • Sensory analytics where expert panel data are compared to chemical analysis and consumer preference
  • Spectroscopy applications where you want to compare methods for the use on a specific system



Multiblock Orthogonal Component Analysis (MOCA) is especially useful for systems biology and manufacturing data that is complemented with spectroscopy, chemical analysis or "-omics" data.

Flexibility in data import and preprocessing

With the release of SIMCA 16, Python capabilities have been extended and improved – with more functionality exposed, including report generation. Another important improvement is that you no longer need to install a separate Python instance to use external packages, such as NumPy or SciPy anymore.

You can now easily create a file plugin reader using Python from inside SIMCA allowing you to import any file type and share the plugin with other SIMCA users. With Python you can also create plugins for data preprocessing or spectral filtering. This provides you with an opportunity to use the latest preprocessing techniques together with the already installed filters inside SIMCA.

The flexibility introduced by the Python plugin functionality means that you should never have to face a situation where you cannot get the data into SIMCA and you will never lack a preprocessing technique again.

These new features and improved usability continue to help SIMCA be the most user-friendly and valuable data analytics tool on the market.

See the demo

Join us for a webinar showcasing the new features of SIMCA 16 on May 16.

Register today


Want to try the new functionality?

Download a 30 day free trial.

Get SIMCA free trial


Topics: Multivariate Data Analysis, Data Visualization, SIMCA, Omics Data Analytics

Stefan Rännar

Written by Stefan Rännar

Product Manager for SIMCA