/
CountReadKmers.scala
90 lines (76 loc) · 3.29 KB
/
CountReadKmers.scala
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
/**
* Licensed to Big Data Genomics (BDG) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The BDG licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.bdgenomics.adam.cli
import java.util.logging.Level
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.{ SparkContext, Logging }
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.projections.{ AlignmentRecordField, Projection }
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.util.ParquetLogger
import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.utils.cli._
import org.kohsuke.args4j.{ Argument, Option => Args4jOption }
object CountReadKmers extends BDGCommandCompanion {
val commandName = "count_kmers"
val commandDescription = "Counts the k-mers/q-mers from a read dataset."
def apply(cmdLine: Array[String]) = {
new CountReadKmers(Args4j[CountReadKmersArgs](cmdLine))
}
}
class CountReadKmersArgs extends Args4jBase with ParquetArgs {
@Argument(required = true, metaVar = "INPUT", usage = "The ADAM, BAM or SAM file to count kmers from", index = 0)
var inputPath: String = null
@Argument(required = true, metaVar = "OUTPUT", usage = "Location for storing k-mer counts", index = 1)
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 = "-print_histogram", 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")
var repartition: Int = -1
}
class CountReadKmers(protected val args: CountReadKmersArgs) extends BDGSparkCommand[CountReadKmersArgs] with Logging {
val companion = CountReadKmers
def run(sc: SparkContext) {
// Quiet Parquet...
ParquetLogger.hadoopLoggerLevel(Level.SEVERE)
// read from disk
var adamRecords: RDD[AlignmentRecord] = sc.loadAlignments(
args.inputPath,
projection = Some(Projection(AlignmentRecordField.sequence)))
if (args.repartition != -1) {
log.info("Repartitioning reads to '%d' partitions".format(args.repartition))
adamRecords = adamRecords.repartition(args.repartition)
}
// count kmers
val countedKmers = adamRecords.adamCountKmers(args.kmerLength)
// cache counted kmers
countedKmers.cache()
// print histogram, if requested
if (args.printHistogram) {
countedKmers.map(kv => kv._2.toLong)
.countByValue()
.toSeq
.sortBy(kv => kv._1)
.foreach(println)
}
// save as text file
countedKmers.saveAsTextFile(args.outputPath)
}
}