Question

I got the following method which is used to read a txt file and return a dictionary. It takes ~7 mins to read a ~5MB file (67000 lines, 70 chars in each line).

public static Dictionary<string, string> FASTAFileReadIn(string file)
{
    Dictionary<string, string> seq = new Dictionary<string, string>();

    Regex re;
    Match m;
    GroupCollection group;
    string currentName = string.Empty;

    try
    {
        using (StreamReader sr = new StreamReader(file))
        {
            string line = string.Empty;
            while ((line = sr.ReadLine()) != null)
            {
                if (line.StartsWith(">"))
                {// Match Sequence
                    re = new Regex(@"^>(\S+)");
                    m = re.Match(line);
                    if (m.Success)
                    {
                        group = m.Groups;
                        if (!seq.ContainsKey(group[1].Value))
                        {
                            seq.Add(group[1].Value, string.Empty);
                            currentName = group[1].Value;
                        }
                    }
                }
                else if (Regex.Match(line.Trim(), @"\S+").Success &&
                            currentName != string.Empty)
                {
                    seq[currentName] += line.Trim();
                }
            }
        }
    }
    catch (IOException e)
    {
        Console.WriteLine("An IO exception has benn thrown!");
        Console.WriteLine(e.ToString());
    }
    finally { }

    return seq;
}

Which part of the code is most time consuming and how to speed it up?

Thanks

Answer 1

Cache and compile regular expressions, reorder conditionals, lessen number of trimmings, and such.

public static Dictionary<string, string> FASTAFileReadIn(string file) {
    var seq = new Dictionary<string, string>();

    Regex re = new Regex(@"^>(\S+)", RegexOptions.Compiled);
    Regex nonWhitespace = new Regex(@"\S", RegexOptions.Compiled);
    Match m;
    string currentName = string.Empty;

    try {
        foreach(string line in File.ReadLines(file)) {
            if(line[0] == '>') {
                m = re.Match(line);

                if(m.Success) {
                    if(!seq.ContainsKey(m.Groups[1].Value)) {
                        seq.Add(m.Groups[1].Value, string.Empty);
                        currentName = m.Groups[1].Value;
                    }
                }
            } else if(currentName != string.Empty) {
                if(nonWhitespace.IsMatch(line)) {
                    seq[currentName] += line.Trim();
                }
            }
        }
    } catch(IOException e) {
        Console.WriteLine("An IO exception has been thrown!");
        Console.WriteLine(e.ToString());
    }

    return seq;
}

However, that’s just a naïve optimization. Reading up on the FASTA format, I wrote this:

public static Dictionary<string, string> ReadFasta(string filename) {
    var result = new Dictionary<string, string>
    var current = new StringBuilder();
    string currentKey = null;

    foreach(string line in File.ReadLines(filename)) {
        if(line[0] == '>') {
            if(currentKey != null) {
                result.Add(currentKey, current.ToString());
                current.Clear();
            }

            int i = line.IndexOf(' ', 2);

            currentKey = i > -1 ? line.Substring(1, i - 1) : line.Substring(1);
        } else if(currentKey != null) {
            current.Append(line.TrimEnd());
        }
    }

    if(currentKey != null)
        result.Add(currentKey, current.ToString());

    return result;
}

Tell me if it works; it should be much faster.