我获得了以下从excel电子表格中提取的CSV文件。只是为了提供一些可能有帮助的背景信息，它讨论了AGI编号（将其视为蛋白质标识符），未修饰的那些蛋白质标识符的肽序列，然后修饰了对未修饰序列进行修饰的肽序列，索引/缺陷那些修饰，然后是重复肽的组合光谱计数。文本文件名为MASP.GlycoModReader.txt，信息格式如下：
AGI,UnMd Peptide (M) = x,Mod Peptide (oM) = Ox,Index/Indeces of Modification,counts,Combined
Spectral count for repeated Peptides
AT1G56070.1,NMSVIAHVDHGKSTLTDSLVAAAGIIAQEVAGDVR,NoMSVIAHVDHGKSTLTDSLVAAAGIIAQEVAGDVR,2,17
AT1G56070.1,LYMEARPMEEGLAEAIDDGR,LYoMEARPoMEEGLAEAIDDGR,"3, 9",1
AT1G56070.1,EAMTPLSEFEDKL,EAoMTPLSEFEDKL,3,7
AT1G56070.1,LYMEARPMEEGLAEAIDDGR,LYoMEARPoMEEGLAEAIDDGR,"3, 9",2
AT1G56070.1,EGPLAEENMR,EGPLAEENoMR,9,2
AT1G56070.1,DLQDDFMGGAEIIK,DLQDDFoMGGAEIIK,7,1
解压缩上述内容后需要生成的输出文件格式如下：
AT1G56070.1,{"peptides": [{"sequence": "NMSVIAHVDHGKSTLTDSLVAAAGIIAQEVAGDVR", "mod_sequence":
"NoMSVIAHVDHGKSTLTDSLVAAAGIIAQEVAGDVR" , "mod_indeces": 2, "spectral_count": 17}, {"sequence":
"LYMEARPMEEGLAEAIDDGR" , "mod_sequence": "LYoMEARPoMEEGLAEAIDDGR", "mod_indeces": [3, 9],
"spectral_count": 3}, {"sequence": "EAMTPLSEFEDKL" , "mod_sequence": "EAoMTPLSEFEDKL",
"mod_indeces": [3,9], "spectral_count": 7}, {"sequence": "EGPLAEENMR", "mod_sequence":
"EGPLAEENoMR", "mod_indeces": 9, "spectral_count": 2}, {"sequence": "DLQDDFMGGAEIIK",
"mod_sequence": "DLQDDFoMGGAEIIK", "mod_indeces": [7], "spectral_count": 1}]}
我在下面提供了我的解决方案：如果有人用另一种语言有更好的解决方案，或者可以分析我的，并告诉我是否有更有效的方法来解决这个问题，请在下面评论。谢谢。
#!/usr/bin/env node
var fs = require('fs');
var csv = require('csv');
var data ="proteins.csv";
/* Uses csv nodejs module to parse the proteins.csv file.
* Parses the csv file row by row and updates the peptide_arr.
* For new entries creates a peptide object, for similar entries it updates the
* counts in the peptide object with the same AGI#.
* Uses a peptide object to store protein ID AGI#, and the associated data.
* Writes all formatted peptide objects to a txt file - output.txt.
*/
// Tracks current row
var x = 0;
// An array of peptide objects stores the information from the csv file
var peptide_arr = [];
// csv module reads row by row from data
csv()
.from(data)
.to('debug.csv')
.transform(function(row, index) {
// For the first entry push a new peptide object with the AGI# (row[0])
if(x == 0) {
// cur is the current peptide read into row by csv module
Peptide cur = new Peptide( row[0] );
// Add the assoicated data from row (1-5) to cur
cur.data.peptides.push({
"sequence" : row[1];
"mod_sequence" : row[2];
if(row[5]){
"mod_indeces" : "[" + row[3] + ", " + row[4] + "]";
"spectral_count" : row[5];
} else {
"mod_indeces" : row[3];
"spectral_count" : row[4];
}
});
// Add the current peptide to the array
peptide_arr.push(cur);
}
// Move to the next row
x++;
});
// Loop through peptide_arr and append output with each peptide's AGI# and its data
String output = "";
for(var peptide in peptide_arr)
{
output = output + peptide.toString()
}
// Write the output to output.txt
fs.writeFile("output.txt", output);
/* Peptide Object :
* - id:AGI#
* - data: JSON Array associated
*/
function Peptide(id) // this is the actual function that does the ID retrieving and data
// storage
{
this.id = id;
this.data = {
peptides: []
};
}
/* Peptide methods :
* - toJson : Returns the properly formatted string
*/
Peptide.prototype = {
toString: function(){
return this.id + "," + JSON.stringify(this.data, null, " ") + "/n"
}
};
编辑说明：似乎当我运行此解决方案时，我发布了内存泄漏错误;它无限运行，而不产生任何实质，可读的输出。如果有人愿意协助评估为什么会这样，那就太好了。
答案 0 :(得分：0)
你的版本有用吗？看起来你只创建了一个Peptide对象。另外，“if（row [5]）”语句在做什么？在您的示例数据中，总共有5个元素。另外，mod_indeces总是应该是一个列表，对吗？因为在您的示例输出文件中，mod_indeces不是第一个肽中的列表。无论如何，这是我在python中提出的：
import csv
import json
data = {}
with open('proteins.csv','rb') as f:
reader = csv.reader(f)
for row in reader:
name = row[0]
sequence = row[1]
mod_sequence = row[2]
mod_indeces = map(int,row[3].split(', '))
spectral_count = int(row[4])
peptide = {'sequence':sequence,'mod_sequence':mod_sequence,
'mod_indeces':mod_indeces,'spectral_count':spectral_count}
if name in data:
data[name]['peptides'].append(peptide)
else:
data[name] = {'peptides':[peptide]}
f.close()
f = open('output.txt','wb')
for protein in data:
f.write(protein)
f.write(',')
f.write(json.dumps(data[protein]))
f.write('\n')
f.close()
如果您在Windows上并希望以纯文本格式查看文件，则可能需要将'\ n'替换为'\ r \ n'或os.linesep。
如果你想跳过某些行（如果有标题或其他内容），你可以这样做：
import csv
import json
data = {}
rows_to_skip = 1
rows_read = 0
with open('proteins.csv','rb') as f:
reader = csv.reader(f)
for row in reader:
if rows_read >= rows_to_skip:
name = row[0]
sequence = row[1]
mod_sequence = row[2]
mod_indeces = map(int,row[3].split(', '))
spectral_count = int(row[4])
peptide = {'sequence':sequence,'mod_sequence':mod_sequence,
'mod_indeces':mod_indeces,'spectral_count':spectral_count}
if name in data:
data[name]['peptides'].append(peptide)
else:
data[name] = {'peptides':[peptide]}
rows_read += 1
f.close()
f = open('output.txt','wb')
for protein in data:
f.write(protein)
f.write(',')
f.write(json.dumps(data[protein]))
f.write('\n')
f.close()
如果希望字典的键按特定顺序排列，则可以使用orderedDict而不是默认字典。只需用以下代码替换肽系列：
peptide = OrderedDict([('sequence',sequence),
('mod_sequence',mod_sequence),
('mod_indeces',mod_indeces),
('spectral_count',spectral_count)])
现在订单已保留。也就是说，sequence之后是mod_sequence，后跟mod_indeces，后跟spectral_count。要更改顺序，只需更改OrderedDict中元素的顺序。
请注意，您还必须添加from collections import OrderedDict才能使用OrderedDict。