生物信息学作业.docx

文档介绍：生物信息学作业
课程 生物信息学
专业 统计学
学号 201510111178
研究生姓名 赵璇
授课老师 喻祖国
1、生成长度为10万字符(A,C,G,T)程序，统计字符串长度K=3的个数并绘图。
clear all
R=rand(l,100000);
A = zeros(8,8);
%%对序列进行标记
fori = 1:100000
if (R(i)<)&&(R(i)>=0)
R(i) = 'A';
elseif (R(i) <)&&(R(i)>=)
R ⑴='C;
elseif (R(i)<)&&(R(i)>=)
R(i) =，G,;
else
R ⑴=T;
end
end
RandomSequence = sprintf('%s：R)
%%统计频数
for i = 1:99998
switch R(i)
case 'A'
m = 0;
n = 0;
case 'C
m = 0;
n = 4;
case 'G'
m = 4;
n = 0;
case T
m = 4;
n = 4;
%%产生的随机序列
%%表示生成8行8列的全零阵
%%控制格式打印
n表示列数
end
% m表示行数，
%判断3个字符的第一个字符
switch R(i+1)
case 'A'
m = m+0;
n = n+0;
case 'C
m = m+0;
n = n+2;
case 'G'
m = m+2;
n = n+0;
case T
m = m+2;
n = n+2;
%判断3个字符的第二个字符
end
switch R(i+2) %判断3个字符的第三个字符
case 'A'
m = m+1;
n = n+1;
case 'C
m = m+1;
n = n+2;
case 'G'
m = m+2;
n = n+1;
case T
m = m+2;
n = n+2;
end
A(m,n) = A(m,n) + l; % 将次数累加
end
A
%%绘图
A = flipud(A);
B = [A,zeros(8,l);zeros(l,9)];
[xx,yy]=meshgrid(0:8,0:8);
pcolorfxx^B)
colorbar
运行结果>> Demo
RandomSequence =
TIArGACGTIAITCIACrrrGArrGTGCGAGACAArGCIACCnACCGGTCGGAACrCGArCGGTrGAACrClArCACGCCTGGTCITCGAAGnAGCACArCGAGCGGGCAAIArGIA
CAIArnACCrCIACAArGGArGCGCAAAAACAITCCCrCArCACAAITGAACmAAGGGCGCGAGACGlAITCCCCGGTrGCrGCITGGGACCAmAAACCrCAITCACCGCGGAACC
CGACIATGCGACrGGACGGCCIArnACCGAGAGCrGTrCGAAGGCTGGTrGAAIACArGGCAGAAGArrGAGGTGTCCmAACnACGCGGCCAIAACACCTIAGCCGTCTCGGGGG
AAD\AGTGACCIArGCACCAGACGCCGCITGCGAnTCGACCAACAGCGGGAACGGCrGrGCAGTCACACCGCrGTGIAGCGGACAGTCrGAGCIACCCTCrCAAGCACGAGArCIAC
AGGGCGGGGIAGAAGCCGTCGCITCGGGTCCArGCGGGGGGI7\AAACCCTGTrmAGAGGTCCGGGCAGCAIACGCGCGGCACCCArcrCTCITCAITCGCnAITGTGAACGTrCGA
AAGCACAATGTGGrnArGTGCIACrGrGGAGAGGGTnurGAArCIAGGAGCACAAAAAAGCGGCGCACrrCAGGCAmAAAGGArGGArnTrGACAArCCCCGArGTCCAAGCT
ATGGTCCCnAACAGCAArGCIAGGGAGCAAmAACAmACCArCCACAGTGAArrGArCCGAAGGGGGTCGGCArCGGAAGCrrGAAAITGAGAAGCGGGGAGTIACCGGTCAAIA
CGAGCAIACAGACAATCGTCGTCGAIACTC