TensorFlow DNNs for Predicting DNA-Transcription Factor Binding

Deep neural networks implemented in TensorFlow & Python for predicting whether transcription factors will bind to given DNA sequences. Empirical tests on the impact of hyperparameters on ROC AUC and speed with an Nvidia GeForce GTX 970 GPU are also included

Architectures Implemented:

All implemented networks are currently convolutional neural nets; RNNs are coming soon

• Lanchantin, J., Singh, R., & Qi, Y. (2016). Deep GDashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks, 1–10. Retrieved from http://arxiv.org/abs/1608.03644
• Zeng, H., Edwards, M. D., Liu, G., & Gifford, D. K. (2016). Convolutional neural network architectures for predicting DNA-protein binding. Bioinformatics, 32(12), i121–i127. https://doi.org/10.1093/bioinformatics/btw255
• A "Simple NLP CNN" as described here: http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/