<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>disease gene prediction</title>
<style type="text/css">
.download {
border: 2px solid #a1a1a1;
margin: 0px auto;
padding-top: 10px;
background: #EEE9E9;
width: 50%;
border-radius: 15px;
font-size: 20px;
height: 20%;
}
#menu {
height: 30px;
margin: 0 auto;
background-color: #003366;
}
#menu table tr td a {
font-size: 18px;
color: white;
text-decoration: none;
display: block;
width: 195px;
}
</style>
<link href="css/ppgallery.css" rel="stylesheet" type="text/css" />
<link href="css/jquery-ui-1.8.6.custom.css" rel="stylesheet"
type="text/css" />
<script type="text/javascript" src="js/jquery.min.js"></script>
<script type="text/javascript" src="js/jquery-ui.min.js"></script>
<script type="text/javascript" src="js/ppgallery.js"></script>
<script type="text/javascript">
$(document).ready(function() {
$('#gallery').ppGallery();
});
function test(t) {
t.bgColor = "#A9A9A9";
}
function fuck(tt) {
tt.bgColor = "#FF7F24";
}
</script>
</head>
<body
style="padding-top: 0px; margin-top: 0px; padding-bottom: 0px; margin-bottom: 0px; background-color: #003366; font-family: arial, verdana, sans-serif;">
<br/>
<div align="center">
<div style="width: 1000px;">
<div id="logo" align="left" style="height: 150px;">
<!-- <img style="float:left; repeat-x" width="60%" height="130px;" src="resources/logor.jpg"/> -->
<img width="100%" height="150px" src="resource/log1.jpg" />
</div>
<div id="menu" style="width: 1000px; background-color: #FF7F24">
<table width="1000px">
<tr align="center" style="height: 26px;">
<td width="250px" onmouseover="test(this)" onmouseout="fuck(this)"><a
href="index.jsp"><b>Home</b></a></td>
<td width="250px" onmouseover="test(this)" onmouseout="fuck(this)">
<a href="guideline.jsp"><b>Guideline</b></a>
</td>
<td width="250px" bgcolor="#A9A9A9"><a href="download.jsp"><b>Download</b></a></td>
<td width="250px" onmouseover="test(this)" onmouseout="fuck(this)">
<a href="aboutus.jsp"><b>About Us</b></a></td>
</tr>
</table>
</div>
<div id="content" align="center"
style="padding-top: 0; margin-top: 0; height: 100%; background-color: #E8F3FE; font-size: 18px;">
<br />
<p align="left">
<strong> Data
of experiment</strong>
</p>
<table align="center" width="900px;"
style="border: 1px #DCEBFE solid; height: 120px;">
<tr>
<td align="left" colspan="3" valign="top"
style="font-size: 18px;font-family:Times New Roman; padding-left: 5px; padding-top: 10px; padding-right: 5px; padding-bottom: 10px;">
In this study, we used the datasets that were used previously by <a href="http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0058977#pone-0058977-g009">Singh-Blom et al(2013)</a>.
<br/>
<br/>
PPI network:<br/>
either the <a href="http://bioinformatics.oxfordjournals.org/content/26/14/1759.abstract">HumanNet</a>(Mostafavi S and Morris Q, 2010) or <a href="http://bioinformatics.oxfordjournals.org/content/26/14/1759.abstract">HPRD</a> network.
<br/>HumanNet contains 733,836 edges between genes with non-zero weights integrated from 21 different data sources. HPRD is an unweighted and much sparser PPI network that contains only 56,661 associations.
<br/><br/>
Gene-phenotype associations(eight non-human species):<br/>
plants,worms,fruit flies, mice, yeast, Escherichia coli, zebrafish, and chickens.
<br/><br/>
phenotype similarities for human were derived solely from <a href="http://www.nature.com/ejhg/journal/v14/n5/full/5201585a.html"> Van Driel MA (2006)</a>.
</td>
</tr>
</table>
<p align="left">
<strong> Methods
of experiment</strong>
</p>
<table align="center" width="900px;"
style="border: 1px #DCEBFE solid; height: 120px;">
<tr>
<td align="left" colspan="3" valign="top"
style="font-size: 18px; font-family:Times New Roman; padding-left: 5px; padding-top: 10px; padding-right: 5px; padding-bottom: 10px;">
Here we propose two novel multipath methods, HeteSim_MultiPath (HSMP) and HeteSim_SVM (HSSVM), based
on the HeteSim measure.
<br/><br/>HSMP uses the HeteSim measure to calculate the similarity between nodes in
heterogeneous networks. Then, the HeteSim scores of different paths are combined with a constant that
dampens contributions from longer paths.
<br/><br/>HSSVM also uses the HeteSim measure to calculate similarity.
However, HSSVM uses a machine learning method instead of a constant to combine HeteSim scores.
</td>
</tr>
</table>
<p align="left"> All datasets and methods
used in this paper can be download <a href="resource/gene_prediction.zip">here</a>.</p><p align="left"><br></p>
</div>
<div id="foot" align="center"
style="height: 30px; background-color: #003366; color: #00BFFF; padding-top: 5px; margin-top: 0; font-weight: bold;">
Developed by <a href=""
style="color: #FFFFFF;">Yuanlu Liao.</a> Copyright <a
href="http://datamining.xmu.edu.cn/main/" style="color: #FFFFFF;">DMLab@XMU</a>.
All Rights Reserved.
</div>
</div>
</div>
</body>
</html>