Introduction Version

Getting Started

This documentation is under construction. Please give us your feedbacks by contacting us at hub@gencovery.com.


Gencovery Artificial Intelligence and Analytics (GAIA) brick is a collection of reference ready-to-use and customizable tools for Machine Learning and Deep Learning modeling. It proposes a broad range of AI algorithms, covering among others classification, regression, clustering methods as well as neural networks, to build informative and predictive models from your data.
Machine learning approaches are traditionally divided into two broad categories:
- Supervised learning approches: in supervised learning approaches, the computer is presented with example inputs and their desired outputs, given by a ”teacher”, and the goal is to learn a general rule that maps inputs to outputs. Supervised learning can be divided into two types of methods: classifiers and regressors. In classifiers, the output variables (”target”) is discrete, whereas in regressors the output variables is continuous.
- Unsupervised learning approaches: in unsupervised learning approaches, no labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).

Deep learning is a class of machine learning algorithms that uses multiple layers to progressively extract higher-level features from the raw input. For example, in image processing, lower layers may identify edges, while higher layers may identify the concepts relevant to a human such as digits or letters or faces.


We believe in open innovation and designed our platforms to accelerate the standardisation and integration of open digital resources in biology. GAIA relies on the following open libraries:

  • Pandas, the reference Python library for Data analysis and manipulation
  • SciPy, the reference Python library for Fundamental algorithms dedicated to scientific computing
  • ScikitLearn, the reference Python library for Machine Learning
  • TensorFlow, a reference library for machine learning and artificial intelligence, with a particular focus on deep learning methods
  • Keras, a reference library that provides a Python interface for the TensorFlow library


[1] Pandas, the reference Python library for Data frame manipulation
[2] ScikitLearn, the reference Python library for Machine Learning
[3] Keras, a reference Python library for Deep Learning


Gencovery Numerical Resources (GNR) refer to the software, librairies and data provided by us through our web services. GNR may be covered by third-party licenses. Gencovery guarantees that GNR are accessible for your commercial and non-commercial use through Gencovery web services. For ad-hoc use of GNR outside Gencovery web services, please check third-party licenses to ensure you are legally authorised. Gencovery does not warrant or assume any legal liability or responsibility for the accuracy, completeness of any information disclosed through Gencovery web services. This is not a legal notice. Please refer to our terms of use for any legal notice about our web services.