BACKGROUND: One possible approach how to economically facilitate gene expression profiling is to use the L1000 platform which measures the expression of ∼1,000 landmark genes and uses a computational method to infer the expression of another ∼10,000 genes. One such method for the gene expression inference is a D-GEX which employs neural networks. RESULTS: We propose two novel D-GEX architectures that significantly improve the quality of the inference by increasing the capacity of a network without any increase in the number of trained parameters. The architectures partition the network into individual towers. Our best proposed architecture - a checkerboard architecture with a skip connection and five towers - together with minor changes in the training protocol improves the average mean absolute error of the inference from 0.134 to 0.128. CONCLUSIONS: Our proposed approach increases the gene expression inference accuracy without increasing the number of weights of the model and thus without increasing the memory footprint of the model that is limiting its usage.

Department of Computer Science Karlovo náměstí 13 Prague 121 35 Czech Republic

See more in PubMed

Wang Y, et al. The role of SMAD3 in the genetic predisposition to papillary thyroid carcinoma. Genet Med. 2018;20(9):927–35. doi: 10.1038/gim.2017.224. PubMed DOI PMC

Edsgärd D, et al. Identification of spatial expression trends in single-cell gene expression data. Nat Methods. 2018;15(5):339–42. doi: 10.1038/nmeth.4634. PubMed DOI PMC

Nielsen J, et al. Biobank-driven genomic discovery yields new insight into atrial fibrillation biology. Nat Genetics. 2018;50(9):1234–9. doi: 10.1038/s41588-018-0171-3. PubMed DOI PMC

Lee W-C, et al. Multiregion gene expression profiling reveals heterogeneity in molecular subtypes and immunotherapy response signatures in lung cancer. Mod Pathol. 2018;31(6):947–55. doi: 10.1038/s41379-018-0029-3. PubMed DOI

Wang Z, et al. Drug gene budger (DGB): an application for ranking drugs to modulate a specific gene based on transcriptomic signatures. Bioinformatics. 2018. 10.1093/bioinformatics/bty763. PubMed PMC

Subramanian A, et al. A next generation connectivity map: L1000 platform and the first 1, 000, 000 profiles. Cell. 2017;171(6):1437–145217. doi: 10.1016/j.cell.2017.10.049. PubMed DOI PMC

Chen Y, et al. Gene expression inference with deep learning. Bioinformatics. 2016;32(12):1832–9. doi: 10.1093/bioinformatics/btw074. PubMed DOI PMC

Kunc V, Klema J. On transformative adaptive activation functions in neural networks for gene expression inference. bioRxiv. 2019. 10.1101/587287. PubMed PMC

Lancashire L, et al. An introduction to artificial neural networks in bioinformatics–application to complex microarray and mass spectrometry datasets in cancer studies. Brief Bioinforma. 2008;10(3):315–29. doi: 10.1093/bib/bbp012. PubMed DOI

Min S, et al, Deep learning in bioinformatics. Brief Bioinforma. 2016; 068. 10.1093/bib/bbw068. PubMed

Angermueller C, et al. Deep learning for computational biology. Mol Syst Biol. 2016;12(7):878. doi: 10.15252/msb.20156651. PubMed DOI PMC

Cireşan D, Meier U, Masci J, Schmidhuber J. Multi-column deep neural network for traffic sign classification. Neural Netw. 2012;32:333–338. doi: 10.1016/j.neunet.2012.02.023. PubMed DOI

Kum S, Oh C, Nam J. Melody extraction on vocal segments using multi-column deep neural networks. In: ISMIR 2016: 2016.

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) New Jersey: IEEE; 2015. Going deeper with convolutions.

He K, Zhang X, Ren S, Sun J. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) New Jersey: IEEE; 2016. Deep residual learning for image recognition.

Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, USA: 2017. p. 4278–84. http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14806.

Huang G, Liu Z, van der Maaten L, Weinberger K. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) New Jersey: IEEE; 2017. Densely connected convolutional networks.

Phan K, Maul T, Vu T. 2015 11th International Conference on Natural Computation (ICNC) New Jersey: IEEE; 2015. A parallel circuit approach for improving the speed and generalization properties of neural networks.

Phan K, Maul T, Vu T. An empirical study on improving the speed and generalization of neural networks using a parallel circuit approach. Int J Parallel Prog. 2016;45(4):780–796. doi: 10.1007/s10766-016-0435-4. DOI

Dua D, Graff C. UCI Machine Learning Repository. Irvine: University of California, School of Information and Computer Science; 2017.

Dozat T, Incorporating nesterov momentum into adam. Technical report, Stanford University. 2015. http://cs229.stanford.edu/proj2015/054_report.pdf. Accessed 20 Aug 2019.

Chollet F, et al.Keras. 2015. https://keras.io. Accessed 20 Aug 2019.

Abadi M, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Software available from tensorflow.org. 2015. http://tensorflow.org/. Accessed 20 Aug 2019.

McKinney W. Data structures for statistical computing in python In: van der Walt S., Millman J, editors. Proceedings of the 9th Python in Science Conference: 2010. p. 51–6.

van der Walt S, et al. The NumPy array: A structure for efficient numerical computation. Comput Sci Eng. 2011;13(2):22–30. doi: 10.1109/MCSE.2011.37. DOI

Waskom M, Botvinnik O, Drewokane, Hobson P, David, Halchenko Y, Lukauskas S, Cole JB, Warmenhoven J, Ruiter JD. Seaborn: v0.7.1 (June 2016): Zenodo; 2016. 10.5281/zenodo.54844.

Hunter J. Matplotlib: A 2d graphics environment. Comput Sci Eng. 2007;9(3):90–5. doi: 10.1109/MCSE.2007.55. DOI

Ritchie M, Phipson B, Wu D, Hu Y, Law C, Shi W, Smyth G. limma powers differential expression analyses for RNA-sequencing and microarray studies. Nucleic Acids Res. 2015;43(7):47–47. doi: 10.1093/nar/gkv007. PubMed DOI PMC

Wang X, Dizaji K, Huang H. Conditional generative adversarial network for gene expression inference. Bioinformatics. 2018;34(17):603–611. doi: 10.1093/bioinformatics/bty563. PubMed DOI PMC

Dizaji K, Wang X, Huang H. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD’18. New York: ACM Press; 2018. Semi-supervised generative adversarial network for gene expression inference.