Download presentation

Presentation is loading. Please wait.

Published byAbigail McLain Modified over 3 years ago

1
**Time Series Gene Expression Prediction using Neural Networks with Hidden Layers**

Michael R. Smith, Mark Clement, Tony Martinez, and Quinn Snell Brigham Young University Department of Computer Science October 2010

2
Modeling Problem

3
Modeling Problem

4
**Previous Modeling Work**

DNA microarray technology allows for effective and efficient way to measure gene expression Model the gene regulatory network Boolean networks Bayesian networks (dynamic BN) Electrical circuit analysis Differential equations Neural networks Constraint to be interpretable

5
**Common NN Implementation**

Each node represents a gene Weights represent the effect of one gene on another Positive (activation) Negative (inhibition) Zero (no influence) Perceptron model

6
**NN Model Changes Training recurrent neural network is difficult**

Backpropagation through time Genetic algorithms Modified the node's function Fuzzy logic Still a perceptron model

7
**Challenges with Modeling a GRN**

Fundamental Issues Data scarce, noisy and high dimensional No definitive truth Models are constrained to be interpretable Perceptron Issues Chosen because it is interpretable Does not take into higher order correlations Exclusive OR (XOR) problem

8
**Revised Problem-Prediction**

9
**Significance of Prediction**

Determine the goodness of the model With a “good” model Use the model to infer the genetic regulatory network Generate additional data points for use in a simpler model Do experiments in silico rather then in vitro.

10
**Solution Data scarcity**

Create more data by combining data points Examine using multi-layer perceptron (MLPs—NN with hidden layers) for predicting gene expression levels. MLPs are capable of modeling higher order correlations

11
Data Combination

12
**Neural Network Models Perceptron— NN without hidden layer**

Multi-Layer Perceptron— NN with a hidden layer Recurrent Neural Network

13
DREAM Results

14
DREAM Results

15
DREAM Results

16
SOS Results

17
SOS Results

18
Conclusions MLPs (NNs with hidden layers) are better able to model GRNs than NNs without hidden layers Shows that higher order correlations DO exist in modeling GRNs Could be beneficial in generating synthetic data Data combination for training produces smoother gene expression predictions Noise filtering Similar to Elman nets and BPTT

19
QUESTIONS?

Similar presentations

OK

1 Copyright © 2010, Elsevier Inc. All rights Reserved Fig 2.1 Chapter 2.

1 Copyright © 2010, Elsevier Inc. All rights Reserved Fig 2.1 Chapter 2.

© 2017 SlidePlayer.com Inc.

All rights reserved.

Ads by Google

Best ppt on ozone layer Download ppt on indus valley civilization political Ppt on indian army weapons systems Ppt on you can win if you want modern Ppt on international chamber of commerce Ppt on wireless networking technology Ppt on introduction to object-oriented programming tutorial Ppt on computer languages memes Change pptx to ppt online free Ppt on solar energy generation