background network image 1
background network image 2
background network image 3

Using advanced, proprietary deep learning methods to train from incomplete data and correlate noise

Predicting expensive experimental datapoints using minimal known data combined with larger cheaper datasets

Software that can be used online or embeded within your own platforms and workflows

1
scroll down the page image

Use Cases

Use case image1
Our unique approach

We have developed a unique capability to train and predict models from incomplete data. The technology can be used to link large, easy to acquire, databases with small, hard to acquire datasets. Generated models can be used to design, predict and identify errors.

Use case image2case study 2
Suite of Tools

Our algorithms have been wrapped up into our core Alchemite™ engine, enabling a number of software solutions, allowing easy integration in internal workflows or making use of on-demand cloud compute via fully hosted version.

read more about AlchemiteMore arrow
Use case image3case study 3
Drug Discovery

Given a fragmented dataset the algorithm can learn the underlying correlations to estimate the missing knowledge of how candidate drugs act on proteins and therefore help clients to design new drug cocktails to activate the right proteins to cure disease

Use case image4case study 4
Material Design

The million commercially available materials are characterized by hundreds of properties Our technology learns the underlying correlations to estimate the missing properties and propose a material with the target properties

Products

Intellegens is developing a series of application specific AI modules, designed to address specific, high value, data analysis bottlenecks that we are uncovering through our discussions with existing and new customers.

Alchemite™

The first commercially availble product Alchemite™, has been specifically built to work with sparse data and is capable of learning from datasets as little as 0.05% complete.
The algorithm has proven commercial applications in materials design and drug discovery. Trained models can be used for predictions, error detection and parameter optimisation (design).

read more about Alchemite
Netowrk particle picture

Company

Intellegens is a spin-out from the University of Cambridge that has developed a unique Artificial Intelligence (AI) method for training neural networks from incomplete data sets. The technique, developed in the Department of Physics, has been applied in drug discovery and material design but as the technique is generic it can be applied to many domains where there is big, incomplete data.

Picture of Gareth
Dr Gareth Conduit

Gareth Conduit has a track record of applying artificial intelligence to solve real-world problems, with research contracts held with companies spanning from materials science to healthcare. Gareth holds an academic position at the University of Cambridge and is a Fellow of Gonville & Caius College.

Picture of Ben
Ben Pellegrini

Ben is an expert in big data and cloud based platforms who has delivered full-stack, commercial solutions to numerous clients in scientific, retail and health sectors. Ben has worked with several startups, large corporates and public sector clients.

Picture of Tom
Dr Tom Whitehead

Tom recently completed his PhD at the University of Cambridge. Tom is leading the application of our novel deep learning approaches to a wide variety of industrial applications, alongside the development of our internal suite of tools and algorithms.

Picture of Gerald Fux
Gerald Fux

Starting studies for a Ph. D. in Theoretical Physics at the University of St Andrews. Master of Theoretical Quantum Physics and completed various projects (Physics simulations, Nummerics) in C/C++, Python and Matlab.

Picture of Graham Snudden
Graham Snudden

Graham was co-founder and VP Engineering at BlueGnome, a specialist in the screening of genetic abnormalities associated with developmental delay, cancer and infertility, which was acquired by US giant Illumina in 2012.

Picture of Elaine Loukes
Dr Elaine Loukes

Elaine has worked as an early-stage tech investment manager since 2001. She has extensive experience in all stages of the investment process including due diligence, financial modelling, deal negotiation and investment management.

News

next image
previous image
picture of network particles

Careers

careers image
Full stack developer

Full stack developer to work closely with the founding team to develop a platform to deliver the technology. Developing a web based interface to the underlying algorithms, backed by a cloud provider allowing on demand building of neural networks that will be made available via API or downloadable, containerized packages.

More details arrow to read more arrow to read more SEND CV
Cambridge Uni logo
Enterprise europe logo
Innovate

Please get in touch to see how we can help

See how our unique AI can solve real world problems