MATCH   <query index>   <row index> <staring column>    <ending column> <SMEM length>

MATCH	99	150	414	430	17

> python mem_sample.py -h
usage: mem_sample.py [-h] [-i INPUT] [-p PANEL] [-q QUERIES] [-o OUTPUT]

options:
  -h, --help            show this help message and exit
  -i INPUT, --input INPUT
                        SMEM file in Durbin's format
  -p PANEL, --panel PANEL
                        panel as VCF/BCF (optional)
  -q QUERIES, --queries QUERIES
                        queries as VCF/BCF (optional)
  -o OUTPUT, --output OUTPUT
                        output file

python mem_sample.py -i sample_data/sample_data_results -p sample_data/panel.bcf -q sample_data/query.bcf -o sample_data/sample_data_results_new

MATCH   <querySample_haplotype>   <panelSample_haplotype> <staring column>    <ending column> <SMEM length>

MATCH	1318026_1	4919834_0	414	430	17

@article{10.1093/bioinformatics/btad552,
    author = {Cozzi, Davide and Rossi, Massimiliano and Rubinacci, Simone and Gagie, Travis and Köppl, Dominik and Boucher, Christina and Bonizzoni, Paola},
    title = "{μ- PBWT: a lightweight r-indexing of the PBWT for storing and querying UK Biobank data}",
    journal = {Bioinformatics},
    volume = {39},
    number = {9},
    pages = {btad552},
    year = {2023},
    month = {09},
    abstract = "{The Positional Burrows–Wheeler Transform (PBWT) is a data structure that indexes haplotype sequences in a manner that enables finding maximal haplotype matches in h sequences containing w variation sites in O(hw) time. This represents a significant improvement over classical quadratic-time approaches. However, the original PBWT data structure does not allow for queries over Biobank panels that consist of several millions of haplotypes, if an index of the haplotypes must be kept entirely in memory.In this article, we leverage the notion of r-index proposed for the BWT to present a memory-efficient method for constructing and storing the run-length encoded PBWT, and computing set maximal matches (SMEMs) queries in haplotype sequences. We implement our method, which we refer to as μ-PBWT, and evaluate it on datasets of 1000 Genome Project and UK Biobank data. Our experiments demonstrate that the μ-PBWT reduces the memory usage up to a factor of 20\\% compared to the best current PBWT-based indexing. In particular, μ-PBWT produces an index that stores high-coverage whole genome sequencing data of chromosome 20 in about a third of the space of its BCF file. μ-PBWT is an adaptation of techniques for the run-length compressed BWT for the PBWT (RLPBWT) and it is based on keeping in memory only a succinct representation of the RLPBWT that still allows the efficient computation of set maximal matches (SMEMs) over the original panel.Our implementation is open source and available at https://github.com/dlcgold/muPBWT. The binary is available at https://bioconda.github.io/recipes/mupbwt/README.html.}",
    issn = {1367-4811},
    doi = {10.1093/bioinformatics/btad552},
    url = {https://doi.org/10.1093/bioinformatics/btad552},
    eprint = {https://academic.oup.com/bioinformatics/article-pdf/39/9/btad552/51556136/btad552.pdf},
}