前段时间写了个脚本抓取基因数据，在这里记录下用到的资源.

KEGG:

Kyoto Encyclopedia of Genes and Genomes

KEGG 是一个生物基因和基因组数据库。由GenomeNet网站(目前由京都大学生物信息学研究中心系维护) 继续维护和提供分析服务.

KEGG 有一点非常好，就是提供了KEGG API。方便研究人员自己写脚本定制数据. PS. KEGG提供了SOAP/REST两种方式.

TogoWS: 

Intergration of the bioinfomatics web services

由于我前面探索的时候走过了一些弯路，需要用到比较复杂的关系查询. 所以找到了 TogoWS 。

它集合了大部分的生物信息中心的数据包括 NCBI, EBI, DDBJ, KEGG, PDBj, and CBRC。提供了统一的查询接口(API). 使用起来很方便。提供了 SOAP/REST 两种调用方式. 还能返回多种数据格式

以下分别是由perl, python, ruby 编写的生物信息学编程工具库. 详细的资料请到官方网站了解.

BioPerl

BioPerl is a toolkit of perl modules useful in building bioinformatics solutions in Perl.

BioPython

Biopython is a set of freely available tools for biological computation written in Python by an international team of developers。

这个库的KEGG模块还很不完善，没有API, 没有KEGG数据格式的分析.

BioRuby

Open source bioinformatics library for Ruby。

调用电信那边的接口. 要用到 triple_des 加密算法. 整了python 和 php 两个版本的实现.

iv, key 变量指向的都是 hex 字符串.

php:

#!/usr/bin/php
<?php

function PaddingPKCS7($data) {
	$block_size = mcrypt_get_block_size("tripledes", "cbc");
	$padding_char = $block_size - (strlen($data) % $block_size);
	$data .= str_repeat(chr($padding_char),$padding_char);
	return $data;
}

function fmt3DESEx($data, $key, $iv) {
	$td = mcrypt_module_open(MCRYPT_3DES,"", MCRYPT_MODE_CBC, "");
	$key = pack("H48",$key);
	$iv = pack("H16",$iv);
	mcrypt_generic_init($td, $key, $iv);
	$data = PaddingPKCS7($data);
	$desResult = mcrypt_generic($td, $data);
	mcrypt_generic_deinit($td);
	mcrypt_module_close($td);
	return base64_encode($desResult);     
}



$data = "asdf";
$key = "313233343536373839303132333435363738393031323334";
$iv = "3132333435363738";
$code = fmt3DESEx(mhash(MHASH_SHA1,$data), $key, $iv);
echo $code;
?>

python:

#!/usr/bin/env python
# -*- coding:utf-8 -*-

import binascii
import hashlib
import base64
import pyDes

iv = '3132333435363738'
key = '313233343536373839303132333435363738393031323334'
data = "asdf"

iv = binascii.unhexlify(iv)
key = binascii.unhexlify(key)
data = hashlib.sha1(data)

k = pyDes.triple_des(key, pyDes.CBC, iv, pad=None, padmode=pyDes.PAD_PKCS5)
d = k.encrypt(data.digest())
print base64.encodestring(d)

descript: 拖拉两个xls文件到此小程序中, 自动进行比对并输出比对结果(xls)

# -*- coding: utf-8 -*-

# Import wx.Python
import wx
import xlrd,xlwt
import os.path

# Declare GUI Constants
DRAG_SOURCE    = wx.NewId()

#=====================================
def encoding(s,coding=None):
    cl = ['utf8', 'gb2312','gb18030']
    if coding:
        cl.append(coding)
    for a in cl:
        try:
            s.decode(a)
            return a
        except UnicodeEncodeError:
            pass
    return 'unknown'

def toUnicode(s,coding=None):
    if isinstance(s,unicode):
        return s
    return s.decode(encoding(s,coding))
#=================================================

# Define File Drop Target class
class FileDropTarget(wx.FileDropTarget):
    """ This object implements Drop Target functionality for Files """
    def __init__(self, obj):
        """ Initialize the Drop Target, passing in the Object Reference to
          indicate what should receive the dropped files """
        # Initialize the wxFileDropTarget Object
        wx.FileDropTarget.__init__(self)
        # Store the Object Reference for dropped files
        self.obj = obj
        self._initContent()

    def _initContent(self):
        self.content = {'same':[],'diff':[]}

    def _log(self,string):
        self.obj.WriteText(toUnicode(string))

    def _analyze(self,xls={}):

        def combine_rows(sheet):
            rows = []
            for rownum in range(sheet.nrows):
                rows.append("-".join([toUnicode(str(row) if isinstance(row,float) else row) \
                        for row in sheet.row_values(rownum)]))
            return rows

        #FIXME optime
        name = xls.keys()
        self._log(u"正在比对 "+name[0]+u" , "+name[1]+u" 中...... \n")
        rows = []
        for sheet in xls.values():
            rows.append(combine_rows(sheet))
        same_rows = list(set(rows[0]) & set(rows[1]))
        file1_rows = list(set(rows[0]) - set(rows[1]))
        file2_rows = list(set(rows[1]) - set(rows[0]))
        self.content['same'].extend(same_rows)
        self.content['diff'].extend(\
                [{'name':name[0],'rows':file1_rows},
                {'name':name[1],'rows':file2_rows}])
        self._log("比对完成 \n")
        return 1

    def _dumpToXls(self,path):
        self._log("生成比对结果中...... \n")
        xls = xlwt.Workbook()
        sheet_same = xls.add_sheet(u'相同数据',cell_overwrite_ok=True)
        same_rows = self.content['same']
        def write_rows(sheet,rows):
            for r in range(len(rows)):
                cells = rows[r].split('-')
                for c in range(len(cells)):
                    sheet.write(r,c,cells[c])
        write_rows(sheet_same,same_rows)

        sheet_diff = {}
        for diff in self.content['diff']:
            name = diff.get('name','default')
            rows = diff.get('rows',[])
            sheet_diff[name] = xls.add_sheet(name+u"独有",cell_overwrite_ok=True)
            write_rows(sheet_diff[name],rows)
        result = os.path.join(path,u" 和 ".join(sheet_diff.keys())+u'的比对结果.xls')
        xls.save(result)
        self._log(u"生成比对结果如下:\n%s\n" % (result,))
        self._initContent()

    def _compare(self,filenames):
        filenames = filenames if isinstance(filenames,list) else list(filenames)
        #for mutiple files
        xls={}
        try:
            for file in filenames:
                name = os.path.basename(file).split('.')[0]
                xls[name] = xlrd.open_workbook(file).sheets()[0]
        except xlrd.biffh.XLRDError,e:
            self._log("请载入xls格式文件")
            return False
        #filenames.sort(self._analyze)
        self._analyze(xls)
        self._dumpToXls(os.path.dirname(filenames[0]))

    def OnDropFiles(self, x, y, filenames):
        """ Implement File Drop """
        # For Demo purposes, this function appends a list of the files dropped at the end of the widget's text
        # Move Insertion Point to the end of the widget's text
        self.obj.SetInsertionPointEnd()
        # append a list of the file names dropped
        self._log("\n加载了 %d 个文件:\n" % (len(filenames)))
        if len(filenames) != 2:
            self._log("只能比对两个文件\n")
            return False
        self._compare(filenames)

class MainWindow(wx.Frame):
    """ This window displays the GUI Widgets. """
    def __init__(self,parent,id,title):
        #wx.Frame.__init__(self,parent,-4, title, size = (430,270), style=wx.DEFAULT_FRAME_STYLE|wx.NO_FULL_REPAINT_ON_RESIZE)
        wx.Frame.__init__(self,parent,-4, title, size = (430,270), \
                style=wx.MINIMIZE_BOX | wx.MAXIMIZE_BOX | wx.SYSTEM_MENU | wx.CAPTION | wx.CLOSE_BOX | wx.CLIP_CHILDREN )
        self.SetBackgroundColour(wx.WHITE)

        wx.StaticText(self, -1, u"请将要比对的EXCEL文件拖拉进下面区域进行比对",(3,0))
        self.text = wx.TextCtrl(self, -1, "", pos=(2,15),size=(418,220), style = wx.TE_MULTILINE|wx.HSCROLL|wx.TE_READONLY)

        dt = FileDropTarget(self.text)
        self.text.SetDropTarget(dt)

        # Display the Window
        self.Show(True)

    def CloseWindow(self, event):
        """ Close the Window """
        self.Close()

    def OnDragInit(self, event):
        """ Begin a Drag Operation """
        # Create a Text Data Object, which holds the text that is to be dragged
        tdo = wx.PyTextDataObject(self.text.GetStringSelection())
        # Create a Drop Source Object, which enables the Drag operation
        tds = wx.DropSource(self.text)
        # Associate the Data to be dragged with the Drop Source Object
        tds.SetData(tdo)
        # Intiate the Drag Operation
        tds.DoDragDrop(True)

class MyApp(wx.App):
    """ Define the Drag and Drop Example Application """
    def OnInit(self):
        """ Initialize the Application """
        # Declare the Main Application Window
        frame = MainWindow(None, -1, u"Excel文件比对小程序")
        # Show the Application as the top window
        self.SetTopWindow(frame)
        return True

# Declare the Application and start the Main Loop
app = MyApp(0)
app.MainLoop()

 Abstract