You are now viewing the homepage of PIT Bioinformatics Group. We are a bioinformatics research group, established in 2005, in the Institute of Mathematics of the Eötvös Loránd University, Budapest, Hungary. We solve problems arising in life sciences by mathematical and informatical means.

During the past years we have developed several online tools for bioinformatics research. These useful pieces of software, which run on our high-performance server computers, are available on the online tools page or in the sidebar in the right.

Latest news

News coverage of our publication: SECLAF: A Webserver and Deep Neural Network Design Tool for Hierarchical Biological Sequence Classification (in Hungarian):

Television report, broadcasted on April 3, 2018, in the magazine "Tudomány minden napra":

News coverage of our publication: The Robustness and the Doubly-Preferential Attachment Simulation of the Consensus Connectome Dynamics of the Human Brain (in Hungarian):

Television report, broadcasted on December 8, 2017 on the first channel of the Hungarian Television, in the "Minden Tudás" magazine:

News coverage of our publication Comparative Connectomics

News coverage of our publication Comparative Connectomics (in Hungarian):

News coverage of our publication: Identifying Combinatorial Biomarkers by Association Rule Mining in the CAMD Alzheimer’s Database

Radio report, broadcasted on August 29, 2017 in the "Szigma" magazine of Inforadio:

Media reflections to our publication: Brain Size Bias Compensated Graph-Theoretical Parameters are Also Better in Women’s Structural Connectome

Television report, broadcasted on June 9, 2017 on the first channel of the Hungarian Television, in the "Minden Tudás" magazine:

Near Perfect Protein Multi-Label Classification with Deep Neural Networks

Our new paper "Near Perfect Protein Multi-Label Classification with Deep Neural Networks" was published on arxiv.org on 30 Mar 2017.

Artificial neural networks (ANNs) have gained a well-deserved popularity among machine learning tools upon their recent successful applications in image- and sound processing and classification problems. Here we present two new ANNs with multi-label classification ability, showing impressive accuracy when classifying protein sequences into 698 UniProt families (AUC=99.99%) and 983 Gene Ontology classes (AUC=99.45%).

See the article here: https://arxiv.org/abs/1703.10663

News coverage of our publication The “Giant Virus Finder” Discovers an Abundance of Giant Viruses in the Antarctic Dry Valleys

A 25-minute television report and a talk, first aired on June 3, 2017 on "Mindenki Akadémiája" on the Hungarian Television, on this result:

Our results on Life without dUTPase in the "Mindentudás" televison magazine

Television coverage, aired on November 11, 2016 in the "Minden tudás" magazine of the first channel of the Hungarian Television M1, on our our new publication Life without dUTPase: