Result: Deep learning for genomics using Janggu.
Eraslan, G., Avsec, Ž., Gagneur, J. & Theis, F.J. Deep learning: new computational modelling techniques for genomics. Nat. Rev. Genet. 20, 1 (2019).
Alipanahi, B., Delong, A., Weirauch, M. T. & Frey, B. J. Predicting the sequence specificities of dna-and rna-binding proteins by deep learning. Nat. Biotechnol. 33, 831 (2015). (PMID: 10.1038/nbt.3300)
Zhou, J. & Troyanskaya, O. G. Predicting effects of noncoding variants with deep learning-based sequence model. Nat. Methods 12, 931 (2015). (PMID: 10.1038/nmeth.3547)
Kelley, D. R., Snoek, J. & Rinn, J. L. Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks. Genome Res. 26, 990–999 (2016). (PMID: 10.1101/gr.200535.115)
Kelley, D. R. et al. Sequential regulatory activity prediction across chromosomes with convolutional neural networks. Genome Res. 28, 739–750 (2018). (PMID: 10.1101/gr.227819.117)
Singh, R., Lanchantin, J., Robins, G. & Qi, Y. Deepchrome: deep-learning for predicting gene expression from histone modifications. Bioinformatics 32, 639–648 (2016). (PMID: 10.1093/bioinformatics/btw427)
Angermueller, C., Lee, H. J., Reik, W. & Stegle, O. Deepcpg: accurate prediction of single-cell dna methylation states using deep learning. Genome Biol. 18, 67 (2017). (PMID: 10.1186/s13059-017-1189-z)
Budach, S. & Marsico, A. pysster: classification of biological sequences by learning sequence and structure motifs with convolutional neural networks. Bioinformatics 1, 3 (2018).
Avsec, Ž. et al. The kipoi repository accelerates community exchange and reuse of predictive models for genomics. Nat. Biotechnol. 37, 592–600 (2019). (PMID: 10.1038/s41587-019-0140-0)
Chen, K. M., Cofer, E. M., Zhou, J. & Troyanskaya, O. G. Selene: a pytorch-based deep learning library for sequence data. Nat. Methods 16, 315–318 (2019). (PMID: 10.1038/s41592-019-0360-8)
Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. 34th International Conference on Machine Learning (eds Precup, D. & Teh, Y. W.) 70, 3319–3328 (PLMR, International Convention Centre, Sydney, Australia, 2017).
Greenside, P., Shimko, T., Fordyce, P. & Kundaje, A. Discovering epistatic feature interactions from neural network models of regulatory DNA sequences. Bioinformatics 34, 629–637 (2018). (PMID: 10.1093/bioinformatics/bty575)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. & Salakhutdinov, R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learning Res. 15, 1929–1958 (2014).
Thurman, R. E. et al. The accessible chromatin landscape of the human genome. Nature 489, 75 (2012). (PMID: 10.1038/nature11232)
Simard, P. Y., Steinkraus, D. & Platt, J. C. Best practices for convolutional neural networks applied to visual document analysis. In Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2 (ICDAR ’03) (ed Werner, B.) 958 (IEEE Computer Society, USA, 2003).
Quang, D. & Xie, X. DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of dna sequences. Nucleic Acids Res. 44, 107–107 (2016). (PMID: 10.1093/nar/gkw226)
Zhou, T. et al. Quantitative modeling of transcription factor binding specificities using DNA shape. Proc. Natl Acad. Sci. 112, 4654–4659 (2015). (PMID: 10.1073/pnas.1422023112)
Keilwagen, J. & Grau, J. Varying levels of complexity in transcription factor binding motifs. Nucleic Acids Res. 43, 119–119 (2015). (PMID: 10.1093/nar/gkv577)
Reddi, S. J., Kale, S. & Kumar, S. On the convergence of adam and beyond. In International Conference on Learning Representations. https://openreview.net/forum?id=ryQu7f-RZ (2018).
Further Information
In recent years, numerous applications have demonstrated the potential of deep learning for an improved understanding of biological processes. However, most deep learning tools developed so far are designed to address a specific question on a fixed dataset and/or by a fixed model architecture. Here we present Janggu, a python library facilitates deep learning for genomics applications, aiming to ease data acquisition and model evaluation. Among its key features are special dataset objects, which form a unified and flexible data acquisition and pre-processing framework for genomics data that enables streamlining of future research applications through reusable components. Through a numpy-like interface, these dataset objects are directly compatible with popular deep learning libraries, including keras or pytorch. Janggu offers the possibility to visualize predictions as genomic tracks or by exporting them to the bigWig format as well as utilities for keras-based models. We illustrate the functionality of Janggu on several deep learning genomics applications. First, we evaluate different model topologies for the task of predicting binding sites for the transcription factor JunD. Second, we demonstrate the framework on published models for predicting chromatin effects. Third, we show that promoter usage measured by CAGE can be predicted using DNase hypersensitivity, histone modifications and DNA sequence features. We improve the performance of these models due to a novel feature in Janggu that allows us to include high-order sequence features. We believe that Janggu will help to significantly reduce repetitive programming overhead for deep learning applications in genomics, and will enable computational biologists to rapidly assess biological hypotheses.