BACKGROUND: The recent big data revolution in Genomics, coupled with the emergence of Deep Learning as a set of powerful machine learning methods, has shifted the standard practices of machine learning for Genomics. Even though Deep Learning methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are becoming widespread in Genomics, developing and training such models is outside the ability of most researchers in the field. RESULTS: Here we present ENNGene-Easy Neural Network model building tool for Genomics. This tool simplifies training of custom CNN or hybrid CNN-RNN models on genomic data via an easy-to-use Graphical User Interface. ENNGene allows multiple input branches, including sequence, evolutionary conservation, and secondary structure, and performs all the necessary preprocessing steps, allowing simple input such as genomic coordinates. The network architecture is selected and fully customized by the user, from the number and types of the layers to each layer's precise set-up. ENNGene then deals with all steps of training and evaluation of the model, exporting valuable metrics such as multi-class ROC and precision-recall curve plots or TensorBoard log files. To facilitate interpretation of the predicted results, we deploy Integrated Gradients, providing the user with a graphical representation of an attribution level of each input position. To showcase the usage of ENNGene, we train multiple models on the RBP24 dataset, quickly reaching the state of the art while improving the performance on more than half of the proteins by including the evolutionary conservation score and tuning the network per protein. CONCLUSIONS: As the role of DL in big data analysis in the near future is indisputable, it is important to make it available for a broader range of researchers. We believe that an easy-to-use tool such as ENNGene can allow Genomics researchers without a background in Computational Sciences to harness the power of DL to gain better insights into and extract important information from the large amounts of data available in the field.

Central European Institute of Technology Masaryk University Brno Czechia

Faculty of Informatics Masaryk University Brno Czechia

Faculty of Science National Centre for Biomolecular Research Masaryk University Brno Czechia

000      

00000naa a2200000 a 4500

001      

bmc22019081

003      

CZ-PrNML

005      

20220804135337.0

007      

ta

008      

220720s2022 xxk f 000 0|eng||

009      

AR

024    7_

$a 10.1186/s12864-022-08414-x $2 doi

035    __

$a (PubMed)35361122

040    __

$a ABA008 $b cze $d ABA008 $e AACR2

041    0_

$a eng

044    __

$a xxk

100    1_

$a Chalupová, Eliška $u Faculty of Science, National Centre for Biomolecular Research, Masaryk University, Brno, Czechia $u Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czechia

245    10

$a ENNGene: an Easy Neural Network model building tool for Genomics / $c E. Chalupová, O. Vaculík, J. Poláček, F. Jozefov, T. Majtner, P. Alexiou

520    9_

$a BACKGROUND: The recent big data revolution in Genomics, coupled with the emergence of Deep Learning as a set of powerful machine learning methods, has shifted the standard practices of machine learning for Genomics. Even though Deep Learning methods such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are becoming widespread in Genomics, developing and training such models is outside the ability of most researchers in the field. RESULTS: Here we present ENNGene-Easy Neural Network model building tool for Genomics. This tool simplifies training of custom CNN or hybrid CNN-RNN models on genomic data via an easy-to-use Graphical User Interface. ENNGene allows multiple input branches, including sequence, evolutionary conservation, and secondary structure, and performs all the necessary preprocessing steps, allowing simple input such as genomic coordinates. The network architecture is selected and fully customized by the user, from the number and types of the layers to each layer's precise set-up. ENNGene then deals with all steps of training and evaluation of the model, exporting valuable metrics such as multi-class ROC and precision-recall curve plots or TensorBoard log files. To facilitate interpretation of the predicted results, we deploy Integrated Gradients, providing the user with a graphical representation of an attribution level of each input position. To showcase the usage of ENNGene, we train multiple models on the RBP24 dataset, quickly reaching the state of the art while improving the performance on more than half of the proteins by including the evolutionary conservation score and tuning the network per protein. CONCLUSIONS: As the role of DL in big data analysis in the near future is indisputable, it is important to make it available for a broader range of researchers. We believe that an easy-to-use tool such as ENNGene can allow Genomics researchers without a background in Computational Sciences to harness the power of DL to gain better insights into and extract important information from the large amounts of data available in the field.

650    _2

$a genomika $7 D023281

650    12

$a strojové učení $7 D000069550

650    12

$a neuronové sítě (počítačové) $7 D016571

650    _2

$a sekundární struktura proteinů $7 D017433

655    _2

$a časopisecké články $7 D016428

700    1_

$a Vaculík, Ondřej $u Faculty of Science, National Centre for Biomolecular Research, Masaryk University, Brno, Czechia $u Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czechia

700    1_

$a Poláček, Jakub $u Faculty of Informatics, Masaryk University, Brno, Czechia

700    1_

$a Jozefov, Filip $u Faculty of Informatics, Masaryk University, Brno, Czechia

700    1_

$a Majtner, Tomáš $u Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czechia

700    1_

$a Alexiou, Panagiotis $u Central European Institute of Technology (CEITEC), Masaryk University, Brno, Czechia. panagiotis.alexiou@ceitec.muni.cz $1 https://orcid.org/0000000334377482

773    0_

$w MED00008181 $t BMC genomics $x 1471-2164 $g Roč. 23, č. 1 (2022), s. 248

856    41

$u https://pubmed.ncbi.nlm.nih.gov/35361122 $y Pubmed

910    __

$a ABA008 $b sig $c sign $y p $z 0

990    __

$a 20220720 $b ABA008

991    __

$a 20220804135330 $b ABA008

999    __

$a ok $b bmc $g 1822617 $s 1170324

BAS    __

$a 3

BAS    __

$a PreBMC

BMC    __

$a 2022 $b 23 $c 1 $d 248 $e 20220331 $i 1471-2164 $m BMC genomics $n BMC Genomics $x MED00008181

GRA    __

$a 867414 $p H2020 Spreading Excellence and Widening Participation

GRA    __

$a CZ.02.2.69/0.0/0.0/18 053/0016952 $p Masarykova Univerzita

LZP    __

$a Pubmed-20220720