DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture

Alok Sharma, Edwin Vans, Daichi Shigemizu, Keith A Boroevich, Tatsuhiko Tsunoda, Alok Sharma, Edwin Vans, Daichi Shigemizu, Keith A Boroevich, Tatsuhiko Tsunoda

Abstract

It is critical, but difficult, to catch the small variation in genomic or other kinds of data that differentiates phenotypes or categories. A plethora of data is available, but the information from its genes or elements is spread over arbitrarily, making it challenging to extract relevant details for identification. However, an arrangement of similar genes into clusters makes these differences more accessible and allows for robust identification of hidden mechanisms (e.g. pathways) than dealing with elements individually. Here we propose, DeepInsight, which converts non-image samples into a well-organized image-form. Thereby, the power of convolution neural network (CNN), including GPU utilization, can be realized for non-image samples. Furthermore, DeepInsight enables feature extraction through the application of CNN for non-image samples to seize imperative information and shown promising results. To our knowledge, this is the first work to apply CNN simultaneously on different kinds of non-image datasets: RNA-seq, vowels, text, and artificial.

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
DeepInsight pipeline. (a) An illustration of transformation from feature vector to feature matrix. (b) An illustration of the DeepInsight methodology to transform a feature vector to image pixels.
Figure 2
Figure 2
DeepInsight network: an illustration. (a) Illustration of two types of tumors using the image transformation methodology of the DeepInsight method. The difference between the two types can be visualized at various points. These image samples are further processed to deep learning architecture (DLA); i.e., parallel CNN as depicted in part b of the same figure. (b) Parallel CNN architecture used in DeepInsight. This architecture consists of two parallel CNN architectures where each consists of four convolutional layers. Parameters are tuned using Bayesian Optimization technique.
Figure 3
Figure 3
Revealing patterns by DeepInsight. An illustration showing the different patterns achieved by DeepInsight on gene-expression (different kind of cancers), text (two types of text) and vowels (two types of vowels). Each plot shows a transformed sample, the difference between samples can now be noticed straightforwardly.

References

    1. Ho, T. K. In 3rd International Conference on Document Analysis and Recognition 278–282 (Montreal, QC, 1995).
    1. Ho TK. The Random Subspace Method for Constructing Decision Forests. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998;20:832–844. doi: 10.1109/34.709601.
    1. Rokach, L. & Maimon, O. Data mining with decision trees: theory and applications. (World Scientific Pub Co Inc, 2008).
    1. Habibi, A. H. & Jahani, H. E. Guide to Convolutional Neural Networks: A Practical Application to Traffic-Sign Detection and Classification. (Springer International Publishing, 2017).
    1. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. 1998;86:2278–2324. doi: 10.1109/5.726791.
    1. Krizhevsky, A., Sutskever, I. & Hinton, G. E. In Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1 1097–1105 (Lake Tahoe, Nevada, 2012).
    1. Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv. 2014;1409:1556.
    1. He, K., Zhang, X., Ren, S. & Sun, J. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (Las Vegas, NV, 2016).
    1. Yan, M. L., Chen, Q. & Shuicheng. Network In Network. CoRR abs/1312.4400 (2013).
    1. Krizhevsky, A. Learning Multiple Layers of Features from Tiny Images (2009).
    1. Szegedy, C. et al. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1–9 (Boston, MA, 2015).
    1. Sermanet, P. et al. In International Conference on Learning Representations (ICLR2014), CBLS (2014).
    1. Redmon, J., Divvala, S. K., Girshick, R. B. & Farhadi, A. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 779–788 (2016).
    1. Girshick, R., Donahue, J., Darrell, T. & Malik, J. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 779–788 (2016).
    1. Girshick, R. In IEEE International Conference on Computer Vision (ICCV) 1440–1448 (Santiago, Chile, 2015).
    1. Ren, S., He, K., Girshick, R. & Sun, J. In Advances in Neural Information Processing Systems 91–99 (2015).
    1. Singh R, Lanchantin J, Robins G, Qi Y. DeepChrome: deep-learning for predicting gene expression from histone modifications. Bioinformatics. 2016;32:639–648. doi: 10.1093/bioinformatics/btw427.
    1. Liu J, Wang X, Cheng Y, Zhang L. Tumor gene expression data classification via sample expansion-based deep learning. Oncotarget. 2017;8:109646–109660.
    1. Zeng, T., Li, R., Mukkamala, R., Ye, J. & Ji, S. Deep convolutional neural networks for annotating gene expression patterns in the mouse brain. BMC Bioinformatics16 (2014).
    1. Gao X, Zhang J, Wei Z, Hakonarson H. DeepPolyA: A Convolutional Neural Network Approach for Polyadenylation Site Prediction. IEEE Access. 2018;6:24340–24349. doi: 10.1109/ACCESS.2018.2825996.
    1. Xu, J. et al. In IJCAI′15 Proceedings of the 24th International Conference on Artificial Intelligence 1369–1375 (Argentina, 2015).
    1. Zhang, X., Zhao, J. & LeCun, Y. In NIPS′15 Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada, 2015).
    1. Lyu, B. & Haque, A. Deep Learning Based Tumor Type Classification Using Gene Expression Data, (2018).
    1. Garofolo, J. S. et al. (Philadelphia: Linguistic Data Consortium, 1993).
    1. Young, S. et al. The HTK Book (for HTK Version 3.2). (Cambridge University Engineering Department, 2002).
    1. Mitchell, T. M. Machine Learning. (McGraw-Hill, Inc., 1997).
    1. Guyon, I., Gunn, S., Nikravesh, M. & Zadeh, L. A. Feature Extraction: Foundations and Applications. (Springer-Verlag, 2006).
    1. Breiman, L. Bias, Variance, And Arcing Classifiers. (Technical Report 460, Statistics Department, University of California, 2000).
    1. Goodfellow, I., Bengio, Y., Courville, A. & Bach, F. Deep Learning (The MIT Press, 2016).
    1. Maaten LJPVD, Hinton G. Visualizing High-Dimensional Data using t-SNE. Journal of Machine Learning Research. 2008;9:2579–2605.
    1. Sharma, A. & Paliwal, K. K. A new perspective to null linear discriminant analysis method and its fast implementation using random matrix multiplication with scatter matrices. Pattern Recognition45(6), 2205–2213 (2012).
    1. Sharma, A. & Paliwal, K. K. A gradient linear discriminant analysis for small sample sized problem. Neural Processing Letters27(1), 17–24 (2008).
    1. Sharma, A. & Paliwal, K. K. Linear discriminant analysis for the small sample size problem: an overview. International Journal of Machine Learning and Cybernetics6(3), 443–454 (2015).
    1. Sharma, A. & Paliwal, K. K. Fast principal component analysis using fixed-point algorithm. Pattern Recognition Letters28(10), 1151–1155 (2007).

Source: PubMed

Patrocinadores e Colaboradores

Condições médicas

Intervenções de drogas

3
Se inscrever