navigation
search
Differences
This shows you the differences between two versions of the page.
| — |
cs-142:gene-finding-via-gc-content [2015/05/12 18:26] (current) cs142ta created |
||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | =Gene Finding via GC content= | ||
| + | ==Problem== | ||
| + | * Within a long region of genomic sequence, genes are often characterised by having a higher GC-content in contrast to the background GC-content for the entire genome. | ||
| + | * Write a program to prompt the user for a string of DNA bases (ACTG) | ||
| + | * Calculate the ratio of G’s and C’s | ||
| + | * If the ratio is > .60, report that the sequence is likely a gene, otherwise report it is probably not. | ||
| + | |||
| + | A contextually-similar problem is [[Gene Finding via TATA box search]]. | ||
| + | |||
| + | ==Solution== | ||
| + | <code cpp> | ||
| + | /* | ||
| + | Test Case 1: | ||
| + | Input: A (this is an example of a string with no Gs or Cs) | ||
| + | Expected Output: 0, not a gene | ||
| + | Actual Output: 0, not a gene | ||
| + | |||
| + | Test Case 2: | ||
| + | Input: G (this is an example of a string with only Gs and Cs) | ||
| + | Expected Output: 1, probably a gene | ||
| + | Actual Output: 1, probably a gene | ||
| + | |||
| + | Test Case 3: | ||
| + | Input: ACATAGACTAG (this is an example of a string with a mix of all four bases) | ||
| + | Expected Output: .36, probably not a gene | ||
| + | Actual Output: .36, probably not a gene | ||
| + | */ | ||
| + | |||
| + | #include <iostream> | ||
| + | #include <string> | ||
| + | |||
| + | using namespace std; | ||
| + | |||
| + | int main() | ||
| + | { | ||
| + | // Inputs: DNA sequence | ||
| + | // Outputs ratio of G&C to total, and prediction of whether or not it's a gene | ||
| + | |||
| + | // Prompt the user | ||
| + | cout << "Please input a DNA sequence: "; | ||
| + | string dna_string; | ||
| + | cin >> dna_string; | ||
| + | |||
| + | int gc_count = 0; | ||
| + | // Calculate GC-content | ||
| + | for (int i = 0; i < dna_string.length(); i++) | ||
| + | { | ||
| + | // Count the number of Gs and Cs | ||
| + | string base_at_i = dna_string.substr(i, 1); | ||
| + | |||
| + | // The following statement can be uncommented to check that our loop is working correctly. | ||
| + | // cout << "base at i is " << base_at_i << endl; | ||
| + | |||
| + | if (base_at_i == "G" || base_at_i == "C") | ||
| + | { | ||
| + | gc_count++; | ||
| + | } | ||
| + | } | ||
| + | |||
| + | cout << "Total GC count was " << gc_count << endl; | ||
| + | |||
| + | // Divide by total string length to get ratio, making sure to account for integer division problems. | ||
| + | double gc_ratio = 1.0 * gc_count / dna_string.length(); | ||
| + | cout << "GC ratio for sequence was " << gc_ratio << endl; | ||
| + | |||
| + | // if ratio > .60, then report it's a gene | ||
| + | if (gc_ratio > .6) | ||
| + | { | ||
| + | cout << "You've got a gene on your hands!" << endl; | ||
| + | } | ||
| + | else | ||
| + | { | ||
| + | cout << "Probably not a gene..." << endl; | ||
| + | } | ||
| + | |||
| + | system("pause"); | ||
| + | return 0; | ||
| + | } | ||
| + | </code> | ||
