rb trim-paf .test/asm_small.paf `#trims back alignments that align the same query sequence more than once` \
    | rb break-paf --max-size 100 `#breaks the alignment into smaller pieces on indels of 100 bases or more` \
    | rb orient `#orients each contig so that the majority of bases are forward aligned` \
    | rb liftover --bed <(printf "chr22\t12000000\t13000000\n") `#subsets and trims the alignment to 1 Mbp of chr22.` \
    | rb filter --paired-len 10000 `#filters for query sequences that have at least 10,000 bases aligned to a target across all alignments.` \
    | rb stats --paf `#calculates statistics from the trimmed paf file` \
    | less -S

rustybam [OPTIONS] <SUBCOMMAND>

rb [OPTIONS] <SUBCOMMAND>

SUBCOMMANDS:
    stats          Get percent identity stats from a sam/bam/cram or PAF
    bed-length     Count the number of bases in a bed file [aliases: bedlen, bl, bedlength]
    filter         Filter PAF records in various ways
    invert         Invert the target and query sequences in a PAF along with the CIGAR string
    liftover       Liftover target sequence coordinates onto query sequence using a PAF
    trim-paf       Trim paf records that overlap in query sequence [aliases: trim, tp]
    orient         Orient paf records so that most of the bases are in the forward direction
    break-paf      Break PAF records with large indels into multiple records (useful for
                   SafFire) [aliases: breakpaf, bp]
    paf-to-sam     Convert a PAF file into a SAM file. Warning, all alignments will be marked as
                   primary! [aliases: paftosam, p2s, paf2sam]
    fasta-split    Reads in a fasta from stdin and divides into files (can compress by adding
                   .gz) [aliases: fastasplit, fasplit]
    fastq-split    Reads in a fastq from stdin and divides into files (can compress by adding
                   .gz) [aliases: fastqsplit, fqsplit]
    get-fasta      Mimic bedtools getfasta but allow for bgzip in both bed and fasta inputs
                   [aliases: getfasta, gf]
    nucfreq        Get the frequencies of each bp at each position
    repeat         Report the longest exact repeat length at every position in a fasta
    suns           Extract the intervals in a genome (fasta) that are made up of SUNs
    help           Print this message or the help of the given subcommand(s)

mamba install -c bioconda rustybam

cargo install rustybam

git clone https://github.com/vollgerlab/rustybam.git
cd rustybam
cargo build --release

target/release/{rustybam,rb}

rustybam stats {input.bam} > {stats.bed}

rustybam stats --paf {input.paf} > {stats.bed}

rustybam liftover \
     --bed <(printf "chr1\t0\t250000000\n") \
     input.paf > trimmed.paf

rustybam liftover \
    --bed <(printf "chr1\t0\t250000000\n") \
    input.paf \
    | rustybam stats --paf \
    > trimmed.stats.bed

rustybam liftover \
    --bed <(bedtools makewindows -w 100000 \
        <(printf "chr1\t0\t250000000\n") \
        ) \
    input.paf \
    | rustybam stats --paf \
    > trimmed.stats.bed

rustybam breakpaf --max-size 1000 input.paf \
    | rustybam liftover \
    --bed <(printf "chr1\t0\t250000000\n") \
    | ./rustybam stats --paf \
    > trimmed.stats.bed

rb trim-paf {input.paf} > {trimmed.paf}

cat {input.fasta} | rustybam fasta-split two.fa.gz three.fa

cat {input.fastq} | rustybam fastq-split two.fq.gz three.fq

samtools faidx {seq.fa(.gz)}
rb get-fasta --name --strand --bed {regions.of.interest.bed} --fasta {seq.fa(.gz)}