Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add optional validation of kept read ratio to CorrectUmis #917

Merged
merged 1 commit into from
Jun 21, 2023
Merged

Add optional validation of kept read ratio to CorrectUmis #917

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion src/main/scala/com/fulcrumgenomics/umi/CorrectUmis.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,14 +134,16 @@ class CorrectUmis
@arg(flag='U', doc="File of UMI sequences, one per line.", minElements=0) val umiFiles: Seq[FilePath] = Seq.empty,
@arg(flag='t', doc="Tag in which UMIs are stored.") val umiTag: String = ConsensusTags.UmiBases,
@arg(flag='x', doc="Don't store original UMIs upon correction.") val dontStoreOriginalUmis: Boolean = false,
@arg(doc="The number of uncorrected UMIs to cache; zero will disable the cache.") val cacheSize: Int = 100000
@arg(doc="The number of uncorrected UMIs to cache; zero will disable the cache.") val cacheSize: Int = 100000,
@arg(doc="The minimum ratio of kept UMIs to accept. A ratio below this will cause a failure (but all files will still be written).") val minCorrected: Option[Double] = None
) extends FgBioTool with LazyLogging {

validate(umis.nonEmpty || umiFiles.nonEmpty, "At least one UMI or UMI file must be provided.")
Io.assertReadable(input)
Io.assertReadable(umiFiles)
Io.assertCanWriteFile(output)
rejects.foreach(Io.assertCanWriteFile(_))
minCorrected.foreach(m => validate(m >= 0 && m <= 1, "--min-corrected must be between 0 and 1."))

// Construct the cache
private lazy val cache = new LeastRecentlyUsedCache[String,UmiMatch](maxEntries = cacheSize)
Expand Down Expand Up @@ -260,6 +262,14 @@ class CorrectUmis
if (wrongLengthRecords > 0) logger.error(s"# ${wrongLengthRecords} had unexpected UMIs of differing lengths in the BAM file!")
logger.error("###################################################################")
}

minCorrected.foreach { min =>
val ratioKept = 1.0 * kept / totalRecords
assert(ratioKept >= min,
f"# Final ratio of reads kept / total was ${ratioKept}%2.2f (user specified minimum was ${min}%2.2f) " +
"This could indicate a mismatch between library preparation and the provided UMI file."
)
}
}

/** Given a UMI sequence and a set of fixed UMIs, report the best match. */
Expand Down