Artificial Neural Network usually called (NN), is a computational model that is inspired by the biological nervous system. The network is composed of simple elements called artificial neurons that are interconnected and operate in parallel. In most cases the NN is an adaptive system that can change its structure depending on the internal or(and?) external information that flows into the network during the learning process. The NN can be trained to perform a particular function by adjusting the values of the connection, called weights, between the artificial neurons. Neural Networks have been employed to perform complex functions in various fields, including pattern recognition, identification, classification, speech, vision, and control systems.
During the learning process, difference between the desired output (target) and the network output is minimised. This difference is usually called cost; the cost function is the measure of how far is the network output from the desired value. A common cost function is the mean-squared error and there are several algorithms that can be used to minimise this function. The following figure displays such a loop.
Figure 1: Training of a Neural Network.
Model description
The NN model has been created with the MATLAB NN-toolbox. The input/target pairs used to train the network comprise experimental and literature data (Bartel et al. 2007). The experimental data were obtained by measuring via luciferase assay the strength of knockdown due to the interaction between the shRNA and the binding site situated on the 3’UTR of luciferase gene. Nearly 30 different rational designed binding sites were tested and the respective knockdown strength calculated with the following formula->(formula anyone???).
Input/target pairs
Each input was represented by a four elements vector. Each element corresponded to a score value related to a specific feature of the binding site. The four features used to describe the binding site were: seed type, the 3’pairing contribution the AU-content and the number of binding site. The input/target pair represented the relationship between a particular binding site and the related percentage of knockdown.
Once the network was trained than it was used to predict percentages of knockdown given certain inputs. The predictions were then validated experimentally.
Right from the beginning of our modeling project, we knew we would have to integrate our trained models into an online GUI. We realized it in the most user friendly way we could think of: The user only needs to input the desired knockdown percentage (kd%) and choose an sh/miRNA sequence, to get a binding site that satisfies the users needs.
Overview of the miRockdown script flow: The knockdown percentage (kd%) input invokes the selection of the right experimental and model binding site or binding site parameters respectively. The binding site (BS) sequence input starts the generation of on the fly generated BS sequences, which are characterized by a modified targetscan_scores algorithm. The parameters of the selected model BS are correlated with the generated BS parameters and the most similar of the generated BS is the output.
The results of both of our models and the experimentally verified binding sites are integrated in [miRockdown] (see Figure: miRockdown) on the [miBEAT] GUI. For every binding site request of a user there are the results of the three different concepts displayed. Thus the users can always choose which of the three differently generated binding to use. The binding site with the most similar experimentally observed knockdown percentage is given out, together with its properties and oligos ready to clone into the miTuner-construct.
The binding sites generated from the model results come into play, when the user wants to use his or her own sh/miRNA, or when the experimentally verified binding sites have a knockdown, that is not sufficiently similar to the desired knockdown.
A script integrated into miRockdown will correlate the desired kd% with a database file for every model. The content of the database files consists of a set of binding site parameters objects spanning the complete range of the model input binding site parameters. Additionally the database files contain the models kd% result calculated for the whole set of objects.
With the user-chosen sh/miRNA sequence as input a binding site generator script is invoked, which varies the seed-type, 3'-pairing, AU-content and bulge-size of on the fly generated binding sites. The 3'-pairing and the AU-content score of the generated BS are characterized by a modified version of the targetscan_50_context_scores – Algorithm [Rodriguez et al.]. The input and output functions were adapted to the mode of operation of miRockdown, thus no files have to be generated while running miRockdown.
Now, that the generated binding sites are completely characterized, they can be compared with the parameters of the suitable model BS. The generated BS that fits the parameters of the suitable model BS best is selected as the output BS of miRockdown.
Tissue specific miRNAs
Aastha
Integration into GUI
Aastha
References
[http://www.targetscan.org/cgi-bin/targetscan/data_download.cgi?db=vert_50 targetscan_50_context_scores.pl] Copyright(c) 2007,2008 Whitehead Institute for Biomedical Research. All Rights Reserved Joe Rodriguez, Robin Ge, Kim Walker, and George Bell
"
