nikhilRP

include(ExternalProject)
ExternalProject_Add(
    nvbio
    GIT_REPOSITORY https://github.com/NVlabs/nvbio.git
    GIT_TAG v0.9.7
    BUILD_COMMAND make nvbio
    INSTALL_COMMAND ""
)
# I'm successfull in generating Static library here (libnvbio.a)

nikhilRP

OVERVIEW: LLVM 'Clang' Compiler: http://clang.llvm.org
 
USAGE: clang -cc1 [options] <inputs>
 
OPTIONS:
  -###                    Print the commands to run for this compilation
  --analyze               Run the static analyzer
  --migrate               Run the migrator
  --relocatable-pch       Build a relocatable precompiled header
  --serialize-diagnostics <value>

nikhilRP

import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.projections.{ AlignmentRecordField, Projection }
import org.apache.spark.rdd.RDD

var adamFile = "/user/nikhilrp/encoded-data/ENCFF000YGV.adam"
val reads = sc.loadParquetAlignments(adamFile)

nikhilRP

import org.bdgenomics.formats.avro.Feature
import org.bdgenomics.adam.rdd.ADAMContext._
 
var adamFile = "s3n://encoded-hdfs/ENCFF001VNW.adam"
val reads = sc.adamLoad[Feature, Nothing](adamFile)

nikhilRP

import org.bdgenomics.formats.avro.{ AlignmentRecord, Contig }
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.rdd.BroadcastRegionJoin
import org.bdgenomics.adam.projections.Projection
import org.bdgenomics.adam.projections.AlignmentRecordField._
import org.bdgenomics.adam.models.{ SequenceDictionary, ReferenceRegion }
import org.bdgenomics.adam.rdd.BroadcastRegionJoin
 
import org.apache.spark.rdd.RDD

nikhilRP

# Files.txt contains URLs for the files
# Make sure you set SPARK_HOME

while read line; do
  url=$line
  filename=$(basename "$url")
  wget "$url"
  hadoop fs -put $filename /user/mapr/encoded/
  ./../adam/bin/adam-submit transform /user/mapr/encoded/$filename /user/mapr/encoded/"${filename/.bam/.adam}"
  hadoop fs -rm /user/mapr/encoded/$filename

nikhilRP

{
    "title": "Suggest",
    "@graph": [
        {
            "text": "BRCA1",
            "payload": {
                "id": 2386
            },
            "score": 1
        },

nikhilRP

import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.projections.{ AlignmentRecordField, Projection }
import org.apache.spark.rdd.RDD
import org.bdgenomics.adam.rdd.ReferencePartitioner
import org.bdgenomics.adam.models.ReferenceRegion
 
val bamFile = "/user/nikhilrp/ENCFF000QJB.bam"
val reads = sc.loadBam(bamFile)
val sd = reads.adamGetSequenceDictionary()

nikhilRP

import org.bdgenomics.formats.avro.AlignmentRecord
import org.bdgenomics.adam.rdd.ADAMContext._
import org.bdgenomics.adam.projections.Projection
import org.apache.spark.rdd.RDD
import org.apache.parquet.filter2.dsl.Dsl._
import org.apache.parquet.filter2.predicate.FilterPredicate
import org.bdgenomics.adam.projections.AlignmentRecordField._
 
val adamFile = "/user/nikhilrp/encoded-data/mm10/chr1/ENCFF891NNX.adam"
val proj = Projection(readName, contig, start, end, qual)

nikhilRP

test_data = [(50, 150), (100, 200), (150, 250), (99, 201), (100, 201), (201, 300), (98, 99)]


def main():
    # view region
    start = 100
    end = 200
    print "View region: start - " + str(start) + " end - " + str(end)

    print "Method 1 - Nikhil"