Generating protein sequences from antibiotic resistance genes data using Generative Adversarial Networks
This addresses the need for synthetic resistant protein data in microbiology, but it is incremental as it applies an existing GAN variant to a new dataset.
The authors tackled the problem of generating synthetic protein sequences predicted to be antibiotic-resistant by using a Wasserstein GAN on 6,023 genes from the human gut, resulting in sequences similar to the original data.
We introduce a method to generate synthetic protein sequences which are predicted to be resistant to certain antibiotics. We did this using 6,023 genes that were predicted to be resistant to antibiotics in the intestinal region of the human gut and were fed as input to a Wasserstein generative adversarial network (W-GAN) model a variant to the original generative adversarial model which has been known to perform efficiently when it comes to mimicking the distribution of the real data in order to generate new data which is similar in style to the original data which was fed as the training data