Reverting Gene Expression Pattern of Cancer into Normal-Like Using Cycle-Consistent Adversarial Network

  • Received : 2018.11.16
  • Accepted : 2018.11.25
  • Published : 2018.12.31


Cancer show distinct pattern of gene expression when it is compared to normal. This difference results malignant characteristic of cancer. Many cancer drugs are targeting this difference so that it can selectively kill cancer cells. One of the recent demand for personalized treating cancer is retrieving normal tissue from a patient so that the gene expression difference between cancer and normal be assessed. However, in most clinical situation it is hard to retrieve normal tissue from a patient. This is because biopsy of normal tissues may cause damage to the organ function or a risk of infection or side effect what a patient to take. Thus, there is a challenge to estimate normal cell's gene expression where cancers are originated from without taking additional biopsy. In this paper, we propose in-silico based prediction of normal cell's gene expression from gene expression data of a tumor sample. We call this challenge as reverting the cancer into normal. We divided this challenge into two parts. The first part is making a generator that is able to fool a pretrained discriminator. Pretrained discriminator is from the training of public data (9,601 cancers, 7,240 normals) which shows 0.997 of accuracy to discriminate if a given gene expression pattern is cancer or normal. Deceiving this pretrained discriminator means our method is capable of generating very normal-like gene expression data. The second part of the challenge is to address whether generated normal is similar to true reverse form of the input cancer data. We used, cycle-consistent adversarial networks to approach our challenges, since this network is capable of translating one domain to the other while maintaining original domain's feature and at the same time adding the new domain's feature. We evaluated that, if we put cancer data into a cycle-consistent adversarial network, it could retain most of the information from the input (cancer) and at the same time change the data into normal. We also evaluated if this generated gene expression of normal tissue would be the biological reverse form of the gene expression of cancer used as an input.


E1GMBY_2018_v6n4_275_f0001.png 이미지

Figure 1. Structure of Pretrained Discriminator

E1GMBY_2018_v6n4_275_f0002.png 이미지

Figure 2. Structure of Cycle GAN Network

E1GMBY_2018_v6n4_275_f0003.png 이미지

Figure 3. t-SNE Unpaired Test Data (700 normal samples, 700 cancer samples)

E1GMBY_2018_v6n4_275_f0004.png 이미지

Figure 4. t-SNE Paired Test Data (600 normal samples, 600 cancer samples)

Table 1. Data Description

E1GMBY_2018_v6n4_275_t0001.png 이미지

Table 2. Data Description

E1GMBY_2018_v6n4_275_t0002.png 이미지

Table 3. Unpaired Test Data (700 normal samples, 700 cancer samples)

E1GMBY_2018_v6n4_275_t0003.png 이미지

Table 4. Paired Test Data (600 normal samples, 600 cancer samples)

E1GMBY_2018_v6n4_275_t0004.png 이미지


Supported by : Handong Global University


  1. Y. LeCun, Y. Bengio, and G. J. n. Hinton, "Deep learning," vol. 521, no. 7553, p. 436, 2015.
  2. D. Wang, A. Khosla, R. Gargeya, H. Irshad, and A. H. J. a. p. a. Beck, "Deep learning for identifying metastatic breast cancer," 2016.
  3. I. Goodfellow et al., "Generative adversarial nets," in Advances in neural information processing systems, 2014, pp. 2672-2680.
  4. J.-Y. Zhu, T. Park, P. Isola, and A. A. J. a. p. Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks," 2017.
  5. K. Tomczak, P. Czerwinska, and M. J. C. o. Wiznerowicz, "The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge," vol. 19, no. 1A, p. A68, 2015.
  6. J. N. Weinstein et al., "The cancer genome atlas pan-cancer analysis project," vol. 45, no. 10, p. 1113, 2013.
  7. G. C. J. Science, "The Genotype-Tissue Expression (GTEx) pilot analysis: multitissue gene regulation in humans," vol. 348, no. 6235, pp. 648-660, 2015.