diff options
Diffstat (limited to 'references')
| -rw-r--r-- | references/references.bib | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/references/references.bib b/references/references.bib index 8a3049f..8513701 100644 --- a/references/references.bib +++ b/references/references.bib @@ -2165,3 +2165,34 @@ keywords = {database systems, low-latency transactions, preemptive scheduling, u biburl = {https://dblp.org/rec/conf/sigmod/IdreosZHKG18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } + +@article{kd-tree, + author = {Jon Louis Bentley}, + title = {Multidimensional Binary Search Trees Used for Associative Searching}, + journal = {Commun. {ACM}}, + volume = {18}, + number = {9}, + pages = {509--517}, + year = {1975}, + url = {https://doi.org/10.1145/361002.361007}, + doi = {10.1145/361002.361007}, + timestamp = {Fri, 24 Mar 2023 16:31:07 +0100}, + biburl = {https://dblp.org/rec/journals/cacm/Bentley75.bib}, + bibsource = {dblp computer science bibliography, https://dblp.org} +} + +@article{mantis, +title = {Mantis: A Fast, Small, and Exact Large-Scale Sequence-Search Index}, +journal = {Cell Systems}, +volume = {7}, +number = {2}, +pages = {201-207.e4}, +year = {2018}, +issn = {2405-4712}, +doi = {https://doi.org/10.1016/j.cels.2018.05.021}, +url = {https://www.sciencedirect.com/science/article/pii/S2405471218302394}, +author = {Prashant Pandey and Fatemeh Almodaresi and Michael A. Bender and Michael Ferdman and Rob Johnson and Rob Patro}, +keywords = {sequence search, RNA sequencing, de Bruijn graph, color equivalence classes, Mantis, experiment discovery, counting quotient filter, sequence Bloom tree, Bloom filter}, +abstract = {Summary +Sequence-level searches on large collections of RNA sequencing experiments, such as the NCBI Sequence Read Archive (SRA), would enable one to ask many questions about the expression or variation of a given transcript in a population. Existing approaches, such as the sequence Bloom tree, suffer from fundamental limitations of the Bloom filter, resulting in slow build and query times, less-than-optimal space usage, and potentially large numbers of false-positives. This paper introduces Mantis, a space-efficient system that uses new data structures to index thousands of raw-read experiments and facilitates large-scale sequence searches. In our evaluation, index construction with Mantis is 6× faster and yields a 20% smaller index than the state-of-the-art split sequence Bloom tree (SSBT). For queries, Mantis is 6–108× faster than SSBT and has no false-positives or -negatives. For example, Mantis was able to search for all 200,400 known human transcripts in an index of 2,652 RNA sequencing experiments in 82 min; SSBT took close to 4 days.} +} |