The $r$-index (Gagie et al., JACM 2020) represented a breakthrough in compressed indexing of repetitive text collections, outperforming its alternatives by orders of magnitude. Its space usage, $\mathcal{O}(r)$ where $r$ is the number of runs in the Burrows-Wheeler Transform of the text, is however larger than Lempel-Ziv and grammar-based indexes, and makes it uninteresting in various real-life scenarios of milder repetitiveness. In this paper we introduce the $sr$-index, a variant that limits the space to $\mathcal{O}(\min(r,n/s))$ for a text of length $n$ and a given parameter $s$, at the expense of multiplying by $s$ the time per occurrence reported. The $sr$-index is obtained by carefully subsampling the text positions indexed by the $r$-index, in a way that we prove is still able to support pattern matching with guaranteed performance. Our experiments demonstrate that the $sr$-index sharply outperforms virtually every other compressed index on repetitive texts, both in time and space, even matching the performance of the $r$-index while using 1.5--3.0 times less space. Only some Lempel-Ziv-based indexes achieve better compression than the $sr$-index, using about half the space, but they are an order of magnitude slower.
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；National Taiwan University（台湾大学）
Template matching is widely used for many applications in image and signal processing and usually is time-critical. Traditional methods usually focus on how to reduce the search locations by coarse-to-fine strategy or full search combined with pruning strategy. However, the computation cost of those methods is easily dominated by the size of signal N instead of that of template K. This paper proposes a probabilistic and fast matching scheme, which computation costs requires O(N) additions and O(K \log K) multiplications, based on cross-correlation. The nuclear idea is to first downsample signa…
Motivation: As a fundamental task in bioinformatics, searching for massive short patterns over a long text is widely accelerated by various compressed full-text indexes. These indexes are able to provide similar searching functionalities to classical indexes, e.g., suffix trees and suffix arrays, while requiring less space. For genomic data, a well-known family of compressed full-text index, called FM-indexes, presents unmatched performance in practice. One major drawback of FM-indexes is that their locating operations, which report all occurrence positions of patterns in a given text, are par…
We introduce a compressed suffix array representation that, on a text $T$ of length $n$ over an alphabet of size $σ$, can be built in $O(n)$ deterministic time, within $O(n\logσ)$ bits of working space, and counts the number of occurrences of any pattern $P$ in $T$ in time $O(|P| + \log\log_w σ)$ on a RAM machine of $w=Ω(\log n)$-bit words. This new index outperforms all the other compressed indexes that can be built in linear deterministic time, and some others. The only faster indexes can be built in linear time only in expectation, or require $Θ(n\log n)$ bits. We also show that, by using $…
We describe how, given a text $T [1..n]$ and a positive constant $ε$, we can build a simple $O (z \log n)$-space index, where $z$ is the number of phrases in the LZ77 parse of $T$, such that later, given a pattern $P [1..m]$, in $O (m \log \log z + \mathrm{polylog} (m + z))$ time and with high probability we can find a substring of $P$ that occurs in $T$ and whose length is at least a $(1 - ε)$-fraction of the length of a longest common substring of $P$ and $T$.
We develop the data structure PReaCH (for Pruned Reachability Contraction Hierarchies) which supports reachability queries in a directed graph, i.e., it supports queries that ask whether two nodes in the graph are connected by a directed path. PReaCH adapts the contraction hierarchy speedup techniques for shortest path queries to the reachability setting. The resulting approach is surprisingly simple and guarantees linear space and near linear preprocessing time. Orthogonally to that, we improve existing pruning techniques for the search by gathering more information from a single DFS-traversa…
Important papers have appeared recently on the problem of indexing binary strings for jumbled pattern matching, and further lowering the time bounds in terms of the input size would now be a breakthrough with broad implications. We can still make progress on the problem, however, by considering other natural parameters. Badkobeh et al.\ (IPL, 2013) and Amir et al.\ (TCS, 2016) gave algorithms that index a binary string in $O (n + ρ^2 \log ρ)$ time, where $n$ is the length and $ρ$ is the number of runs, and Giaquinta and Grabowski (IPL, 2013) gave one that runs in $O (n + ρ^2)$ time. In this pa…
Indexed pattern search in text has been studied for many decades. For small alphabets, the FM-Index provides unmatched performance, in terms of both space required and search speed. For large alphabets -- for example, when the tokens are words -- the situation is more complex, and FM-Index representations are compact, but potentially slow. In this paper we apply recent innovations from the field of inverted indexing and document retrieval to compressed pattern search, including for alphabets into the millions. Commencing with the practical compressed suffix array structure developed by Sadakan…
We present a novel compressed dynamic self-index for highly repetitive text collections. Signature encoding is a compressed dynamic self-index for highly repetitive texts and has a large disadvantage that the pattern search for short patterns is slow. We improve this disadvantage for faster pattern search by leveraging an idea behind truncated suffix tree and present the first compressed dynamic self-index named TST-index that supports not only fast pattern search but also dynamic update operation of index for highly repetitive texts. Experiments using a benchmark dataset of highly repetitive …
The FM-index is a celebrated compressed data structure for full-text pattern searching. After the first wave of interest in its theoretical developments, we can observe a surge of interest in practical FM-index variants in the last few years. These enhancements are often related to a bit-vector representation, augmented with an efficient rank-handling data structure. In this work, we propose a new, cache-friendly, implementation of the rank primitive and advocate for a very simple architecture of the FM-index, which trades compression ratio for speed. Experimental results show that our variant…
Advances in DNA sequencing technology will soon result in databases of thousands of genomes. Within a species, individuals' genomes are almost exact copies of each other; e.g., any two human genomes are 99.9% the same. Relative Lempel-Ziv (RLZ) compression takes advantage of this property: it stores the first genome uncompressed or as an FM-index, then compresses the other genomes with a variant of LZ77 that copies phrases only from the first genome. RLZ achieves good compression and supports fast random access; in this paper we show how to support fast search as well, thus obtaining an effici…
We propose two suffix array inspired full-text indexes. One, called SA-hash, augments the suffix array with a hash table to speed up pattern searches due to significantly narrowed search interval before the binary search phase. The other, called FBCSA, is a compact data structure, similar to M{ä}kinen's compact suffix array, but working on fixed sized blocks. Experiments on the Pizza~\&~Chili 200\,MB datasets show that SA-hash is about 2--3 times faster in pattern searches (counts) than the standard suffix array, for the price of requiring $0.2n-1.1n$ bytes of extra space, where $n$ is the tex…
Summary: We present a new method to incrementally construct the FM-index for both short and long sequence reads, up to the size of a genome. It is the first algorithm that can build the index while implicitly sorting the sequences in the reverse (complement) lexicographical order without a separate sorting step. The implementation is among the fastest for indexing short reads and the only one that practically works for reads of averaged kilobases in length. Availability and implementation: https://github.com/lh3/ropebwt2 Contact: hengli@broadinstitute.org
We study the problem of quickly computing point-to-point shortest paths in massive road networks with traffic predictions. Incorporating traffic predictions into routing allows, for example, to avoid commuter traffic congestions. Existing techniques follow a two-phase approach: In a preprocessing step, an index is built. The index depends on the road network and the traffic patterns but not on the path start and end. The latter are the input of the query phase, in which shortest paths are computed. All existing techniques have large index size, slow query running times or may compute suboptima…
We present a simple $q$-gram based semi-index, which allows to look for a pattern typically only in a small fraction of text blocks. Several space-time tradeoffs are presented. Experiments on Pizza & Chili datasets show that our solution is up to three orders of magnitude faster than the Claude et al. \cite{CNPSTjda10} semi-index at a comparable space usage.
The FM-index is a well-known compressed full-text index, based on the Burrows-Wheeler transform (BWT). During a pattern search, the BWT sequence is accessed at "random" locations, which is cache-unfriendly. In this paper, we are interested in speeding up the FM-index by working on $q$-grams rather than individual characters, at the cost of using more space. The first presented variant is related to an inverted index on $q$-grams, yet the occurrence lists in our solution are in the sorted suffix order rather than text order in a traditional inverted index. This variant obtains $O(m/|CL| + \log …
Order-preserving pattern matching was introduced recently but it has already attracted much attention. Given a reference sequence and a pattern, we want to locate all substrings of the reference sequence whose elements have the same relative order as the pattern elements. For this problem we consider the offline version in which we build an index for the reference sequence so that subsequent searches can be completed very efficiently. We propose a space-efficient index that works well in practice despite its lack of good worst-case time bounds. Our solution is based on the new approach of deco…
Under the word RAM model, we design three data structures that can be constructed in $O(n\sqrt{\lg n})$ time over $n$ points in an $n \times n$ grid. The first data structure is an $O(n\lg^ε n)$-word structure supporting orthogonal range reporting in $O(\lg\lg n+k)$ time, where $k$ denotes output size and $ε$ is an arbitrarily small constant. The second is an $O(n\lg\lg n)$-word structure supporting orthogonal range successor in $O(\lg\lg n)$ time, while the third is an $O(n\lg^ε n)$-word structure supporting sorted range reporting in $O(\lg\lg n+k)$ time. The query times of these data structu…
A compressed full-text self-index occupies space close to that of the compressed text and simultaneously allows fast pattern matching and random access to the underlying text. Among the best compressed self-indexes, in theory and in practice, are several members of the FM-index family. In this paper, we describe new FM-index variants that combine nice theoretical properties, simple implementation and improved practical performance. Our main result is a new technique called fixed block compression boosting, which is a simpler and faster alternative to optimal compression boosting and implicit c…
We present a new algorithm which detects the maximal possible number of matched disjoint pairs satisfying a given caliper when a bipartite matching is done with respect to a scalar index (e.g., propensity score), and constructs a corresponding matching. Variable width calipers are compatible with the technique, provided that the width of the caliper is a Lipschitz function of the index. If the observations are ordered with respect to the index then the matching needs $O(N)$ operations, where $N$ is the total number of subjects to be matched. The case of 1-to-$n$ matching is also considered. We…
Next Generation Sequencing (NGS) platforms and, more generally, high-throughput technologies are giving rise to an exponential growth in the size of nucleotide sequence databases. Moreover, many emerging applications of nucleotide datasets -- as those related to personalized medicine -- require the compliance with regulations about the storage and processing of sensitive data. We have designed and carefully engineered E2FM-index, a new full-text index in minute space which was optimized for compressing and encrypting nucleotide sequence collections in FASTA format and for performing fast patte…
In-memory data management systems, such as key-value stores, have become an essential infrastructure in today's big-data processing and cloud computing. They rely on efficient index structures to access data. While unordered indexes, such as hash tables, can perform point search with O(1) time, they cannot be used in many scenarios where range queries must be supported. Many ordered indexes, such as B+ tree and skip list, have a O(log N) lookup cost, where N is number of keys in an index. For an ordered index hosting billions of keys, it may take more than 30 key-comparisons in a lookup, which…
There is growing interest in representing image data and feature descriptors using compact binary codes for fast near neighbor search. Although binary codes are motivated by their use as direct indices (addresses) into a hash table, codes longer than 32 bits are not being used as such, as it was thought to be ineffective. We introduce a rigorous way to build multiple hash tables on binary code substrings that enables exact k-nearest neighbor search in Hamming space. The approach is storage efficient and straightforward to implement. Theoretical analysis shows that the algorithm exhibits sub-li…
We present PUFFINN, a parameterless LSH-based index for solving the $k$-nearest neighbor problem with probabilistic guarantees. By parameterless we mean that the user is only required to specify the amount of memory the index is supposed to use and the result quality that should be achieved. The index combines several heuristic ideas known in the literature. By small adaptions to the query algorithm, we make heuristics rigorous. We perform experiments on real-world and synthetic inputs to evaluate implementation choices and show that the implementation satisfies the quality guarantees while be…
An optimal index solving top-k document retrieval [Navarro and Nekrich, SODA12] takes O(m + k) time for a pattern of length m, but its space is at least 80n bytes for a collection of n symbols. We reduce it to 1.5n to 3n bytes, with O(m+(k+log log n) log log n) time, on typical texts. The index is up to 25 times faster than the best previous compressed solutions, and requires at most 5% more space in practice (and in some cases as little as one half). Apart from replacing classical by compressed data structures, our main idea is to replace suffix tree sampling by frequency thresholding to achi…
Fast multiplication by two's complement addition of numbers represented as a set of polynomial radix 2 indexes, stored as an integer list for massively parallel computation
Document listing on string collections is the task of finding all documents where a pattern appears. It is regarded as the most fundamental document retrieval problem, and is useful in various applications. Many of the fastest-growing string collections are composed of very similar documents, such as versioned code and document collections, genome repositories, etc. Plain pattern-matching indexes designed for repetitive text collections achieve orders-of-magnitude reductions in space. Instead, there are not many analogous indexes for document retrieval. In this paper we present a simple docume…
Given a large dataset of binary codes and a binary query point, we address how to efficiently find $K$ codes in the dataset that yield the largest cosine similarities to the query. The straightforward answer to this problem is to compare the query with all items in the dataset, but this is practical only for small datasets. One potential solution to enhance the search time and achieve sublinear cost is to use a hash table populated with binary codes of the dataset and then look up the nearby buckets to the query to retrieve the nearest neighbors. However, if codes are compared in terms of cosi…
Existing methods for retrieving k-nearest neighbours suffer from the curse of dimensionality. We argue this is caused in part by inherent deficiencies of space partitioning, which is the underlying strategy used by most existing methods. We devise a new strategy that avoids partitioning the vector space and present a novel randomized algorithm that runs in time linear in dimensionality of the space and sub-linear in the intrinsic dimensionality and the size of the dataset and takes space constant in dimensionality of the space and linear in the size of the dataset. The proposed algorithm allow…
