Skip to content

Merge origin/master in #6

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

Open
wants to merge 9 commits into
base: utils-0.2.0
Choose a base branch
from
Open

Merge origin/master in #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
3eb895c
- fixed pattern matching bug in ReferenceUtils.unionReferenceSet
tmoerman May 4, 2015
9dc6a6c
now with proper header ./scripts/format-source
tmoerman May 4, 2015
9013336
Merge pull request #671 from tmoerman/master
fnothaft May 4, 2015
6ce4ef7
[ADAM-410] add alphabet class and test to address issue https://githu…
bryanjj Apr 19, 2015
679e809
[ADAM-663] don't remove CLI jar in compute-adam-jars.sh
ryan-williams May 1, 2015
5861ef5
[ADAM-597] Move correction out of ADAM and into a downstream project.
fnothaft May 1, 2015
c0a2cc4
Merge pull request #668 from fnothaft/remove-correction
laserson May 4, 2015
1508031
Merge remote-tracking branch 'origin/master' into utils
ryan-williams May 26, 2015
2b885c4
remove a couple of unused imports
ryan-williams May 26, 2015
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
2 changes: 0 additions & 2 deletions adam-cli/src/main/scala/org/bdgenomics/adam/cli/ADAMMain.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,6 @@ import java.util.logging.Level._
import org.apache.spark.Logging
import org.bdgenomics.adam.util.ParquetLogger
import org.bdgenomics.utils.cli._
import scala.Some
import scala.collection.mutable.ListBuffer

object ADAMMain extends Logging {

Expand Down
14 changes: 2 additions & 12 deletions adam-cli/src/main/scala/org/bdgenomics/adam/cli/CountReadKmers.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,8 +44,6 @@ class CountReadKmersArgs extends Args4jBase with ParquetArgs {
var outputPath: String = null
@Argument(required = true, metaVar = "KMER_LENGTH", usage = "Length of k-mers", index = 2)
var kmerLength: Int = 0
@Args4jOption(required = false, name = "-countQmers", usage = "Counts q-mers instead of k-mers.")
var countQmers: Boolean = false
@Args4jOption(required = false, name = "-printHistogram", usage = "Prints a histogram of counts.")
var printHistogram: Boolean = false
@Args4jOption(required = false, name = "-repartition", usage = "Set the number of partitions to map data to")
Expand All @@ -71,11 +69,7 @@ class CountReadKmers(protected val args: CountReadKmersArgs) extends BDGSparkCom
}

// count kmers
val countedKmers = if (args.countQmers) {
adamRecords.adamCountQmers(args.kmerLength)
} else {
adamRecords.adamCountKmers(args.kmerLength).map(kv => (kv._1, kv._2.toDouble))
}
val countedKmers = adamRecords.adamCountKmers(args.kmerLength)

// cache counted kmers
countedKmers.cache()
Expand All @@ -90,11 +84,7 @@ class CountReadKmers(protected val args: CountReadKmersArgs) extends BDGSparkCom
}

// save as text file
if (args.countQmers) {
countedKmers.map(kv => kv._1 + ", " + kv._2)
} else {
countedKmers.map(kv => kv._1 + ", " + kv._2.toLong)
}.saveAsTextFile(args.outputPath)
countedKmers.saveAsTextFile(args.outputPath)
}

}
29 changes: 0 additions & 29 deletions adam-cli/src/main/scala/org/bdgenomics/adam/cli/Transform.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,20 +66,6 @@ class TransformArgs extends Args4jBase with ADAMSaveAnyArgs with ParquetArgs {
var lodThreshold = 5.0
@Args4jOption(required = false, name = "-max_target_size", usage = "The maximum length of a target region to attempt realigning. Default length is 3000.")
var maxTargetSize = 3000
@Args4jOption(required = false, name = "-trimReads", usage = "Apply a fixed trim to the prefix and suffix of all reads/reads in a specific read group.")
var trimReads: Boolean = false
@Args4jOption(required = false, name = "-trimFromStart", usage = "Trim to be applied to start of read.")
var trimStart: Int = 0
@Args4jOption(required = false, name = "-trimFromEnd", usage = "Trim to be applied to end of read.")
var trimEnd: Int = 0
@Args4jOption(required = false, name = "-trimReadGroup", usage = "Read group to be trimmed. If omitted, all reads are trimmed.")
var trimReadGroup: String = null
@Args4jOption(required = false, name = "-qualityBasedTrim", usage = "Trims reads based on quality scores of prefix/suffixes across read group.")
var qualityBasedTrim: Boolean = false
@Args4jOption(required = false, name = "-qualityThreshold", usage = "Phred scaled quality threshold used for trimming. If omitted, Phred 20 is used.")
var qualityThreshold: Int = 20
@Args4jOption(required = false, name = "-trimBeforeBQSR", usage = "Performs quality based trim before running BQSR. Default is to run quality based trim after BQSR.")
var trimBeforeBQSR: Boolean = false
@Args4jOption(required = false, name = "-repartition", usage = "Set the number of partitions to map data to")
var repartition: Int = -1
@Args4jOption(required = false, name = "-coalesce", usage = "Set the number of partitions written to the ADAM output directory")
Expand Down Expand Up @@ -109,16 +95,6 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
adamRecords = adamRecords.repartition(args.repartition)
}

if (args.trimReads) {
log.info("Trimming reads.")
adamRecords = adamRecords.adamTrimReads(args.trimStart, args.trimEnd, args.trimReadGroup)
}

if (args.qualityBasedTrim && args.trimBeforeBQSR) {
log.info("Applying quality based trim.")
adamRecords = adamRecords.adamTrimLowQualityReadGroups(args.qualityThreshold)
}

if (args.markDuplicates) {
log.info("Marking duplicates")
adamRecords = adamRecords.adamMarkDuplicates()
Expand All @@ -144,11 +120,6 @@ class Transform(protected val args: TransformArgs) extends BDGSparkCommand[Trans
adamRecords = adamRecords.adamBQSR(sc.broadcast(knownSnps), Option(args.observationsPath))
}

if (args.qualityBasedTrim && !args.trimBeforeBQSR) {
log.info("Applying quality based trim.")
adamRecords = adamRecords.adamTrimLowQualityReadGroups(args.qualityThreshold)
}

if (args.coalesce != -1) {
log.info("Coalescing the number of partitions to '%d'".format(args.coalesce))
adamRecords = adamRecords.coalesce(args.coalesce, shuffle = true)
Expand Down
Loading