public virtual IEnumerable<string> WriteToFile(string outputFile, List<FeatureItemGroup> features, string removeNamePrefix)
{
Dictionary<string, Dictionary<string, SmallRNASequence>> sequences = new Dictionary<string, Dictionary<string, SmallRNASequence>>();
foreach (var fig in features)
{
foreach (var sam in fig)
{
foreach (var loc in sam.Locations)
{
foreach (var samloc in loc.SamLocations)
{
var aligned = samloc.SamLocation.Parent;
var seq = new SmallRNASequence()
{
Sample = aligned.Sample,
Sequence = aligned.Sequence,
Count = aligned.QueryCount
};
Dictionary<string, SmallRNASequence> ssList;
if (!sequences.TryGetValue(seq.Sample, out ssList))
{
ssList = new Dictionary<string, SmallRNASequence>();
sequences[seq.Sample] = ssList;
ssList[seq.Sequence] = seq;
}
else
{
if (!ssList.ContainsKey(seq.Sequence))
{
ssList[seq.Sequence] = seq;
}
}
}
}
}
}
var counts = sequences.ToDictionary(m => m.Key, m => m.Value.Values.ToList());
var samples = sequences.Keys.OrderBy(m => m).ToArray();
List<SmallRNASequenceContig> mergedSequences = SmallRNASequenceUtils.BuildContigByIdenticalSimilarity(counts, minOverlapRate, maxExtensionBase, topNumber);
new SmallRNASequenceContigFormat().WriteToFile(outputFile, mergedSequences);
new SmallRNASequenceContigDetailFormat().WriteToFile(outputFile + ".details", mergedSequences);
return new[] { outputFile };
}
public static List<SmallRNASequence> ReadCountFile(FileItem file, Func<string[], bool> accept)
{
var countList = new List<SmallRNASequence>();
using (var sr = new StreamReader(file.File))
{
var header = sr.ReadLine();
string line;
while ((line = sr.ReadLine()) != null)
{
var parts = line.Split('\t');
if (parts.Length < 3)
{
continue;
}
if (!accept(parts))
{
continue;
}
var seq = new SmallRNASequence()
{
Sample = file.Name,
Sequence = parts[2],
Count = int.Parse(parts[1])
};
countList.Add(seq);
}
}
return countList;
}
