Senior Lecturer, School of Computer Science,
   University of Lincoln, Lincoln, U.K.

Faculty, Athens International Masters Program in
Neuroscience, Dept of Biology, University of Athens, Greece

Faculty, Budapest Semester in Cognitive Science,
   Eotvos Lorand University, Budapest, Hungary

Guest Lecturer, Institute of Automation,
   Chinese Academy of Sciences, Beijing, China

Associate Editor, Cognitive Computation

Guest Associate Editor, Frontiers in Systems Neuroscience

Associate Editor, Scholarpedia

Review Editor, Frontiers in Cognitive Science
email: vcutsuridis AT lincoln DOT ac DOT uk

Brain Inspired
Systems (BICS)

Springer 2008
Hippocampal Microcircuits:
A Computational Modeler's
Resource Book, 1st ed

Springer 2010
Cycle: Models, Architectures and

Springer 2011
Hippocampal Microcircuits:
A Computational Modeler's
Resource Book, 2nd ed

Springer 2019
Multiscale Models
of Brain Disorders

Springer 2019
Book Series

Springer Series in Cognitive
& Neural Systems

Trends in Augmentation
of Human Performance


Home Page
   • Theoretical Neuroscience
   • Machine Learning
Activities, Grants
Talks, Seminars
Education, Career

Machine learning algorithms for protein function prediction from amino acid structural data  
Dramatic growth of proteomic data presents new challenges for scientists. Making sense of millions of protein sequences requires new age computational tools and databases for processing and storing their 3D structure as well as about their evolutionary and functional relationships. A 14% of all proteins in nature have been observed to contain periodic sequences of representing arrays of repeats that are directly adjacent to each other. Such tandem repeat regions have been linked to major human and animal diseases. Thus, understanding their sequence-structure-function relationship and mechanisms of their evolution promise to be a fertile direction for research leading to the identification of targets for new medicines and vaccines.

In collaboration with Mike Kokkinidis (University of Crete) we employed families of neural networks to predict the function of proteins solely from their amino acid sequences.