Artificial intelligence (AI) is an interdisciplinary branch of computer science concerned with building algorithms capable of performing tasks that typically require human intelligence. Moreover, AI comprises various technologies to enable machines to perceive, understand, act and learn without manual input or data curation (deep learning). Thereby, deep learning is creating a paradigm shift in many new and emerging technologies. Thus, the use of artificial intelligence for life sciences is therefore not only indispensable but also has enormous potential to advance topics such as personalized medicine, drug discovery or basic biological research.


The German Network for Bioinformatics Infrastructure is well aware of this potential, which is reflected by the AI white paper (german) and in a large number of projects that are based on AI by de.NBI members. A query in the network led to a list of AI projects carried out by de.NBI members displayed below.


Moreover, we count over 49 projects applying AI approaches which are running in the de.NBI cloud. Currently, over 19 of those are performed by non- de.NBI members demonstrating the awareness and the benefits of the de.NBI cloud in the compute and life sciences community.


AI Website 2  

Projects by de.NBI members using Artificial Intelligence

Modelling & Phenotyping

Cardiovascular risk modelling

R. Eils, HiDiH Berlin  

Deep Learning for Analyzing Microscopy Images and Cellular Phenotyping K. Rohr, Heidelberg University HD-HuB
Identification of new antimicrobial resistance targets by high-throughput deep learning A. Goesmann, Justus Liebig University Gießen BiGi
Omni-genetic phenotype models R. Eils, HiDiH Berlin HD-HuB
REmatch – Cloud AI for drug discovery M. Boutros, DKFZ Heidelberg HD-HuB
Omics & meta-analysis

Competing Endogenous RNA Networks in Colorectal Cancer

P. Stadler, Leipzig University  

Continuous Integration of RNAz, a bioinformatical research software for de novo detection of stable, conserved and functional noncoding RNAs in comparative genomics data P. Stadler, Leipzig University   RBC

DeePSIVal - Deep Learning approach to validation of spectrum identifications

D. Benndorf, Max Planck Institute for Dynamics of Complex Technical Systems, Magdeburg BiGi
DeProVIDEO - Deep Learning for Protein Variants Detection M. Eisenacher, Ruhr University Bochum BioInfra.Prot
LAMarCK - LongitudinAl Multiomics Characterization of disease using prior Knowledge Groups of Zeller, Saez-Rodriguez, Schlesner, Bork, Korbel HD-HuB
Long non-coding RNAs in animals and plants P. Stadler, Leipzig University RBC
Machine-learning based classification of lncRNAs as ncRNA host genes P. Stadler, Leipzig University RBC
Machine-learning based hierarchical taxonomic classification of prokaryotic genes and genomes using STAG G. Zeller, EMBL Heidelberg HD-HuB
Machine-learning in translational (single-cell) omics University Hospital Tübingen, University Tübingen CiBi
SIAMCAT – a machine-learning toolbox that enables microbiome meta-analysis and cross-disease comparison G. Zeller, P. Bork, EMBL Heidelberg  HD-HuB
Database & Support
Development of an integrated, deep learning-based system to support the curation of biomedical databases W. Müller, Heidelberg Institute for Theoretical Studies, Heidelberg de.NBI-SysBio
Open Medical data R. Eils, HiDiH Berlin HD-HuB
Scalable Curation and Genome Function Prediction by the aid of Artificial Intelligence J. Overmann, Leibniz Institut DSMZ, Heidelberg BioData
The Hessian Center for Artificial Intelligence A. Goesmann, Justus Liebig University Gießen BiGi
Tool recommender system in Galaxy using deep learning R. Backofen, University of Freiburg RBC