$ adam-submit

       e         888~-_          e             e    e
      d8b        888   \        d8b           d8b  d8b
     /Y88b       888    |      /Y88b         d888bdY88b
    /  Y88b      888    |     /  Y88b       / Y88Y Y888b
   /____Y88b     888   /     /____Y88b     /   YY   Y888b
  /      Y88b    888_-~     /      Y88b   /          Y888b

Usage: adam-submit [<spark-args> --] <adam-args>

Choose one of the following commands:

ADAM ACTIONS
          countKmers : Counts the k-mers/q-mers from a read dataset.
    countContigKmers : Counts the k-mers/q-mers from a read dataset.
           transform : Convert SAM/BAM to ADAM format and optionally perform read pre-processing transformations
   transformFeatures : Convert a file with sequence features into corresponding ADAM format and vice versa
         mergeShards : Merges the shards of a file
      reads2coverage : Calculate the coverage from a given ADAM file

CONVERSION OPERATIONS
            vcf2adam : Convert a VCF file to the corresponding ADAM format
            adam2vcf : Convert an ADAM variant to the VCF ADAM format
          fasta2adam : Converts a text FASTA sequence file into an ADAMNucleotideContig Parquet file which represents assembled sequences.
          adam2fasta : Convert ADAM nucleotide contig fragments to FASTA files
          adam2fastq : Convert BAM to FASTQ files
     fragments2reads : Convert alignment records into fragment records.
     reads2fragments : Convert alignment records into fragment records.

PRINT
               print : Print an ADAM formatted file
            flagstat : Print statistics on reads in an ADAM file (similar to samtools flagstat)
                view : View certain reads from an alignment-record file.

$ adam-submit transform --help
 INPUT                                                           : The ADAM, BAM or SAM file to apply the transforms to
 OUTPUT                                                          : Location to write the transformed data in ADAM/Parquet format
 -add_md_tags VAL                                                : Add MD Tags to reads based on the FASTA (or equivalent) file passed to this option.
 -aligned_read_predicate                                         : Only load aligned reads. Only works for Parquet files.
 -cache                                                          : Cache data to avoid recomputing between stages.
 -coalesce N                                                     : Set the number of partitions written to the ADAM output directory
 -concat VAL                                                     : Concatenate this file with <INPUT> and write the result to <OUTPUT>
 -defer_merging                                                  : Defers merging single file output
 -dump_observations VAL                                          : Local path to dump BQSR observations to. Outputs CSV format.
 -force_load_bam                                                 : Forces Transform to load from BAM/SAM.
 -force_load_fastq                                               : Forces Transform to load from unpaired FASTQ.
 -force_load_ifastq                                              : Forces Transform to load from interleaved FASTQ.
 -force_load_parquet                                             : Forces Transform to load from Parquet.
 -force_shuffle_coalesce                                         : Even if the repartitioned RDD has fewer partitions, force a shuffle.
 -h (-help, --help, -?)                                          : Print help
 -known_indels VAL                                               : VCF file including locations of known INDELs. If none is provided, default
                                                                   consensus model will be used.
 -known_snps VAL                                                 : Sites-only VCF giving location of known SNPs
 -limit_projection                                               : Only project necessary fields. Only works for Parquet files.
 -log_odds_threshold N                                           : The log-odds threshold for accepting a realignment. Default value is 5.0.
 -mark_duplicate_reads                                           : Mark duplicate reads
 -max_consensus_number N                                         : The maximum number of consensus to try realigning a target region to. Default
                                                                   value is 30.
 -max_indel_size N                                               : The maximum length of an INDEL to realign to. Default value is 500.
 -max_target_size N                                              : The maximum length of a target region to attempt realigning. Default length is
                                                                   3000.
 -md_tag_fragment_size N                                         : When adding MD tags to reads, load the reference in fragments of this size.
 -md_tag_overwrite                                               : When adding MD tags to reads, overwrite existing incorrect tags.
 -paired_fastq VAL                                               : When converting two (paired) FASTQ files to ADAM, pass the path to the second file
                                                                   here.
 -parquet_block_size N                                           : Parquet block size (default = 128mb)
 -parquet_compression_codec [UNCOMPRESSED | SNAPPY | GZIP | LZO] : Parquet compression codec
 -parquet_disable_dictionary                                     : Disable dictionary encoding
 -parquet_logging_level VAL                                      : Parquet logging level (default = severe)
 -parquet_page_size N                                            : Parquet page size (default = 1mb)
 -print_metrics                                                  : Print metrics to the log on completion
 -realign_indels                                                 : Locally realign indels present in reads.
 -recalibrate_base_qualities                                     : Recalibrate the base quality scores (ILLUMINA only)
 -record_group VAL                                               : Set converted FASTQs' record-group names to this value; if empty-string is passed,
                                                                   use the basename of the input file, minus the extension.
 -repartition N                                                  : Set the number of partitions to map data to
 -single                                                         : Saves OUTPUT as single file
 -sort_fastq_output                                              : Sets whether to sort the FASTQ output, if saving as FASTQ. False by default.
                                                                   Ignored if not saving as FASTQ.
 -sort_lexicographically                                         : Sort the reads lexicographically by contig name, instead of by index.
 -sort_reads                                                     : Sort the reads by referenceId and read position
 -storage_level VAL                                              : Set the storage level to use for caching.
 -stringency VAL                                                 : Stringency level for various checks; can be SILENT, LENIENT, or STRICT. Defaults
                                                                   to LENIENT

...
[INFO] ------------------------------------------------------------------------
[INFO] BUILD SUCCESS
[INFO] ------------------------------------------------------------------------
[INFO] Total time: 9.647s
[INFO] Finished at: Thu May 23 15:50:42 PDT 2013
[INFO] Final Memory: 19M/81M
[INFO] ------------------------------------------------------------------------

alias adam-submit="${ADAM_HOME}/bin/adam-submit"
alias adam-shell="${ADAM_HOME}/bin/adam-shell"

adam-submit transform $ADAM_HOME/adam-core/src/test/resources/small.sam /tmp/small.adam

$ adam-submit flagstat /tmp/small.adam
20 + 0 in total (QC-passed reads + QC-failed reads)
0 + 0 primary duplicates
0 + 0 primary duplicates - both read and mate mapped
0 + 0 primary duplicates - only read mapped
0 + 0 primary duplicates - cross chromosome
0 + 0 secondary duplicates
0 + 0 secondary duplicates - both read and mate mapped
0 + 0 secondary duplicates - only read mapped
0 + 0 secondary duplicates - cross chromosome
20 + 0 mapped (100.00%:0.00%)
0 + 0 paired in sequencing
0 + 0 read1
0 + 0 read2
0 + 0 properly paired (0.00%:0.00%)
0 + 0 with itself and mate mapped
0 + 0 singletons (0.00%:0.00%)
0 + 0 with mate mapped to a different chr
0 + 0 with mate mapped to a different chr (mapQ>=5)

$ adam-shell -i kmer.scala
…
(121771,TTTTTTTTTTTTTTTTTTTTT)
(44317,ACACACACACACACACACACA)
(44023,TGTGTGTGTGTGTGTGTGTGT)
(42474,CACACACACACACACACACAC)
(42095,GTGTGTGTGTGTGTGTGTGTG)
(33797,TAATCCCAGCACTTTGGGAGG)
(33081,AATCCCAGCACTTTGGGAGGC)
(32775,TGTAATCCCAGCACTTTGGGA)
(32484,CCTCCCAAAGTGCTGGGATTA)
…

@techreport{massie13,
  title={{ADAM}: Genomics Formats and Processing Patterns for Cloud Scale Computing},
  author={Massie, Matt and Nothaft, Frank and Hartl, Christopher and Kozanitis, Christos and Schumacher, Andr{\'e} and Joseph, Anthony D and Patterson, David A},
  year={2013},
  institution={UCB/EECS-2013-207, EECS Department, University of California, Berkeley}
}

@inproceedings{nothaft15,
  title={Rethinking Data-Intensive Science Using Scalable Analytics Systems},
  author={Nothaft, Frank A and Massie, Matt and Danford, Timothy and Zhang, Zhao and Laserson, Uri and Yeksigian, Carl and Kottalam, Jey and Ahuja, Arun and Hammerbacher, Jeff and Linderman, Michael and Franklin, Michael and Joseph, Anthony D. and Patterson, David A.},
  booktitle={Proceedings of the 2015 International Conference on Management of Data (SIGMOD '15)},
  year={2015},
  organization={ACM}
}