Biology subjects

Mock, F.

Publications and source records attributed to Mock, F..

4 recordsLinked to original sources

bioRxiv2021

BERTax: taxonomic classification of DNA sequences with Deep Neural Networks

Taxonomic classification, i.e., the identification and assignment to groups of biological organisms with the same origin and characteristics, is a common task in genetics. Nowadays, taxonomic classification is mainly based on genome similarity search to large genome databases. In this process, the classification quality depends heavily on the database since representative relatives have to be known already. Many genomic sequences cannot be classified at all or only with a high misclassification rate. Here we present BERTax, a program that uses a deep neural network to pre-cisely classify the superkingdom, phylum, and genus of DNA sequences taxonomically without the need for a known representative relative from a database. For this, BERTax uses the natural language processing model BERT trained to represent DNA. We show BERTax to be at least on par with the state-of-the-art approaches when taxonomically similar species are part of the training data. In case of an entirely novel organism, however, BERTax clearly outperforms any existing approach. Finally, we show that BERTax can also be combined with database approaches to further increase the prediction quality. Since BERTax is not based on homologous entries in databases, it allows precise taxonomic classification of a broader range of genomic sequences. This leads to a higher number of correctly classified sequences and thus increases the overall information gain.

bioinformatics↗

bioRxiv2020

EpiDope: A Deep neural network for linear B-cell epitope prediction

By binding to specific structures on antigenic proteins, the so-called epitopes, B-cell antibodies can neutralize pathogens. The identification of B-cell epitopes is of great value for the development of specific serodiagnostic assays and the optimization of medical therapy. However, identifying diagnostically or therapeutically relevant epitopes is a challenging task that usually involves extensive laboratory work. In this study, we show that the time, cost and labor-intensive process of epitope detection in the lab can be significantly shortened by using in silico prediction. Here we present EpiDope, a python tool which uses a deep neural network to detect B-cell epitope regions on individual protein sequences (github.com/mcollatz/EpiDope). With an area under the curve (AUC) between 0.67 {+/-} 0.07 in the ROC curve, EpiDope exceeds all other currently used B-cell prediction tools. Moreover, for AUC10% (AUC for a false-positive rate < 0.1), EpiDope improves the prediction accuracy in comparison to other state-of-the-art methods. Our software is shown to reliably predict linear B-cell epitopes of a given protein sequence, thus contributing to a significant reduction of laboratory experiments and costs required for the conventional approach.

bioinformatics↗

bioRxiv2019

A comprehensive annotation and differential expression analysis of short and long non-coding RNAs in 16 bat genomes

Although bats are increasingly becoming the focus of scientific studies due to their unique properties, these exceptional animals are still among the least studied mammals. Assembly quality and completeness of bat genomes vary a lot and especially non-coding RNA (ncRNA) annotations are incomplete or simply missing. Accordingly, standard bioinformatics pipelines for gene expression analysis often ignore ncRNAs such as microRNAs or long antisense RNAs. The main cause of this problem is the use of incomplete genome annotations. We present a complete screening for ncRNAs within 16 bat genomes. NcRNAs affect a remarkable variety of vital biological functions, including gene expression regulation, RNA processing, RNA interference and, as recently described, regulatory processes in viral infections. Within all investigated bat assemblies we annotated 667 ncRNA families including 162 snoRNAs and 193 miRNAs as well as rRNAs, tRNAs, several snRNAs and IncRNAs, and other structural ncRNA elements. We validated our ncRNA candidates by six RNA-Seq data sets and show significant expression patterns that have never been described before in a bat species on such a large scale. Our annotations will be usable as a resource (Electronic Supplement) for deeper studying of bat evolution, ncRNAs repertoire, gene expression and regulation, ecology, and important host-virus interactions. Supplementary informationis available at rna.uni-jena.de/supplements/bats, the Open Science Framework (doi.org/10.17605/OSF.IO/4CMDN), and GitHub (github.com/rnajena/bats_ncrna).

bioinformatics↗

bioRxiv2019

Viral host prediction with Deep Learning

MotivationZoonosis, the natural transmission of infections from animals to humans, is a far-reaching global problem. The recent outbreaks of Zika virus, Ebola virus and Corona virus are examples of viral zoonosis, which occur more frequently due to globalization. In the case of a virus outbreak, it is helpful to know which host organism was the original carrier of the virus. Once the reservoir or intermediate host is known, it can be isolated to prevent further spreading of the viral infection. Recent approaches aim to predict a viral host based on the viral genome, often in combination with the potential host genome and arbitrarily selected features. These methods have a clear limitation in either the number of different hosts they can predict or the accuracy of their prediction. ResultsHere, we present a fast and accurate deep learning approach for viral host prediction, which is based on the viral genome sequence only. To ensure a high prediction accuracy, we developed an effective selection approach for the training data to avoid biases due to a highly unbalanced number of known sequences per virus-host combinations. We tested our deep neural network on three different virus species (influenza A, rabies lyssavirus, rotavirus A). We reached for each virus species an AUG between 0.93 and 0.98, outperforming previous approaches and allowing highly accurate predictions while only using fractions (100-400 bp) of the viral genome sequences. We show that deep neural networks are suitable to predict the host of a virus, even with a limited amount of sequences and highly unbalanced available data. The deep neural networks trained for this approach build the core of the virus-host predicting tool VIDHOP (Virus Deep learning HOst Prediction). AvailabilityThe trained models for the prediction of the host for the viruses influenza A, rabies lyssavirus, rotavirus A are implemented in the tool VIDHOP. This tool is freely available under https://github.com/flomock/vidhop. Supplementary informationSupplementary data are available at DOI 10.17605/OSF.IO/UXT7N

bioinformatics↗