Want to learn more? Book a presentation with our team
ALChemy
Automated Learning for Chemistry in a unique suite
As being part of the fields of computational chemistry and machine learning, QSAR and QSPR (Quantitative Structure–Activity/Property Relationship) modellingtakes advantage of computational techniques to derive meaningful insights from chemical and molecular data. These techniques encompass a range of methods designed to analyse, model, and predict various biological and chemical-physical activities. The ALChemy suite is designed to face every step of the modelling process, from the features selection to the predictive model deployment.
The advantages of automating the whole modelling process.
The QSAR/QSPR models focus on establishing quantitative relationships between molecular structures and properties. The predictive models obtained serve as invaluable tools for identifying potential candidates with desirable properties in the plethora of chemical compounds under consideration in a study, thus saving time, resources, and effort in experimental work.
As the fields of cheminformatics and computational chemistry continue to evolve, QSAR/QSPR modelling remains a cornerstone of innovation, enabling scientists and researchers to harness the power of data-driven insights to revolutionise drug discovery and material science.
Thanks to the suite’s capacity to handle the full range of complex and time consuming tasks involved in the QSAR modelling process, ALChemy represents a powerful support for industries and research institutions in the invaluable job of identifying potential candidates with desirable properties
ALChemy accepts as input datasets of molecular descriptors calculated by one of the many solutions available in the market by now (Dragon7, alvaDesc, any free software) with the possibility to make any kind of customisation to integrate it in your calculation pipeline.
FAST
Features Selection made easier by means of Full Search approach.
Don’t struggle with Feature Selection. With FAST (the first tool of a suite designed for creating, managing, and deploying QSAR models) you can easily extract the best subset of features for your QSAR model via a full search approach over several techniques
QUEEN
QSAR Under Effective and Efficient Neural Networks.
Discover the powerful and versatile algorithms handling QSAR modelling with QUEEN (QSAR Under Effective and Efficient Neural-Networks). This tool is a product designed to automate construction, training, and deployment of predictive models for QSAR/QSPR (Quantitative Structure–Activity/Property Relationship) applications.
Our plans
Our Chemoinformatics Business Unit distribute all the modules part of the ALChemy Suite as:
App
Application to be run locally on the user’s workstation equipped with a user interface that can be used via browser
REST API
Application that can be integrated into the existing pipeline via REST API interface
CLI
Application that can be integrated into the existing pipeline via Java Command Line Interface
Docker App
Application to run on corporate servers via Docker virtualisation and accessible via web interface
Questions about our products?
Drop us a few lines via email!
