iDeepA

RNA-binding proteins (RBPs) play crucial roles in many biological processes, e.g. gene regulation. Computational identification of RBP binding sites on RNAs are urgently needed. In particular, RBPs bind to RNAs by recognizing sequence motifs. Thus, fast locating those motifs on RNA sequences is crucial and time-efficient for determining whether the RNAs interact with the RBPs or not. In this study, we present an attention based convolutional neural network, iDeepA, to predict RNA-protein binding sites from raw RNA sequences. We first encode RNA sequences into one-hot encoding. Next, we design a deep learning model with a convolutional neural network (CNN) and an attention mechanism, which automatically search for important positions, e.g. binding motifs, to learn discriminant high-level features for predicting RBP binding sites. We evaluate iDeepA on publicly gold-standard RBP binding sites derived from CLIP-seq data. The results demonstrate iDeepA achieves comparable performance with other state-of-the-art methods.

Dependency

keras 1.1.2 library and its backend is theano 0.9.0
sklearn

May be a bug

In attention.py, there's a statement:

config = {'init': self.init.__name__,
                  'activation': self.activation.__name__,
                  'W_constraint': self.W_constraint.get_config() if self.W_constraint else None,
                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
                  'b_regularizer': self.b_regularizer.get_config() if self.b_regularizer else None,
                  'hidden': self.hidden.get_config() if self.hidden else None}

However, in ideepa.py, decoder_x = Attention(hidden=attentionhidden_x,activation='linear') and decoder_xr = Attention(hidden=attentionhidden_xr,activation='linear') show that hidden's type is int. Undoubtedly there's no method named get_config() for int and thus when I try to save model, an error occurs.

Well, I attempt to do some changes:

config = {'init': self.init.__name__,
                  'activation': self.activation.__name__,
                  'W_constraint': self.W_constraint.get_config() if self.W_constraint else None,
                  'W_regularizer': self.W_regularizer.get_config() if self.W_regularizer else None,
                  'b_regularizer': self.b_regularizer.get_config() if self.b_regularizer else None,
                  'hidden': None}

and now I can save the model. But I'm afraid that the model will lose some information.

Would you mind illustrating the meaning of hidden, please?

xypan1232 / ideepa Goto Github PK

ideepa's Introduction

iDeepA

Dependency

ideepa's People

Contributors

Stargazers

Watchers

Forkers

ideepa's Issues

May be a bug

Batch_matmul Error

ModuleNotFoundError: No module named 'attention'

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent