Journal of Computational Biology

Genome segmentation methods are powerful tools to obtain cell type or tissue-specific genome-wide annotations and are frequently used to discover regulatory elements. However, traditional segmentation methods show low predictive accuracy and their data-driven annotations have some undesirable properties. As an alternative, we developed ModHMM, a highly modular genome segmentation method. Inspired by the supra-Bayesian approach, it incorporates predictions from a set of classifiers. This allows to compute genome segmentations by utilizing state-of-the-art methodology. We demonstrate the method on ENCODE data and show that it outperforms traditional segmentation methods not only in terms of predictive performance, but also in qualitative aspects. Therefore, ModHMM is a valuable alternative to study the epigenetic and regulatory landscape across and within cell types or tissues.

Whole-genome bisulfite sequencing (WGBS) provides a precise measure of methylation across the genome, yet presents a challenge in identifying differentially methylated regions (DMRs) between different conditions. Many methods have been developed, which focus primarily on the setting of two-group comparison. We develop a DMR detecting method MethCP for WGBS data, which is applicable for a wide range of experimental designs beyond the two-group comparisons, such as time-course data. MethCP identifies DMRs based on change point detection, which naturally segments the genome and provides region-level differential analysis. For simple two-group comparison, we show that our method outperforms developed methods in accurately detecting the complete DMR on a simulated data set and an Arabidopsis data set. Moreover, we show that MethCP is capable of detecting wide regions with small effect sizes, which can be common in some settings, but existing techniques are poor in detecting such DMRs. We also demonstrate the use of MethCP for time-course data on another data set after methylation throughout seed germination in Arabidopsis.

Long-read sequencing of transcripts with Pacific Biosciences (PacBio) Iso-Seq and Oxford Nanopore Technologies has proven to be central to the study of complex isoform landscapes in many organisms. However, current de novo transcript reconstruction algorithms from long-read data are limited, leaving the potential of these technologies unfulfilled. A common bottleneck is the dearth of scalable and accurate algorithms for clustering long reads according to their gene family of origin. To address this challenge, we develop isONclust, a clustering algorithm that is greedy (to scale) and makes use of quality values (to handle variable error rates). We test isONclust on three simulated and five biological data sets, across a breadth of organisms, technologies, and read depths. Our results demonstrate that isONclust is a substantial improvement over previous approaches, both in terms of overall accuracy and/or scalability to large data sets.

The colored de Bruijn graph (cdbg) and its variants have become an important combinatorial structure used in numerous areas in genomics, such as population-level variation detection in metagenomic samples, large-scale sequence search, and cdbg-based reference sequence indices. As samples or genomes are added to the cdbg, the color information comes to dominate the space required to represent this data structure. In this article, we show how to represent the color information efficiently by adopting a hierarchical encoding that exploits correlations among color classes—patterns of color occurrence—present in the de Bruijn graph (dbg). A major challenge in deriving an efficient encoding of the color information that takes advantage of such correlations is determining which color classes are close to each other in the high-dimensional space of possible color patterns. We demonstrate that the dbg itself can be used as an efficient mechanism to search for approximate nearest neighbors in this space. While our approach reduces the encoding size of the color information even for relatively small cdbgs (hundreds of experiments), the gains are particularly consequential as the number of potential colors (i.e., samples or references) grows into thousands. We apply this encoding in the context of two different applications; the implicit cdbg used for a large-scale sequence search index, Mantis, as well as the encoding of color information used in population-level variation detection by tools such as Vari and Rainbowfish. Our results show significant improvements in the overall size and scalability of representation of the color information. In our experiment on 10,000 samples, we achieved >11 × better compression compared to Ramen, Ramen, Rao (RRR).

Short-read aligners predominantly use the FM-index, which is easily able to index one or a few human genomes. However, it does not scale well to indexing collections of thousands of genomes. Driving this issue are the two chief components of the index: (1) a rank data structure over the Burrows–Wheeler Transform (BWT) of the string that will allow us to find the interval in the string's suffix array (SA), and (2) a sample of the SA that—when used with the rank data structure—allows us to access the SA. The rank data structure can be kept small even for large genomic databases, by run-length compressing the BWT, but until recently there was no means known to keep the SA sample small without greatly slowing down access to the SA. Now that (SODA 2018) has defined an SA sample that takes about the same space as the run-length compressed BWT, we have the design for efficient FM-indexes of genomic databases but are faced with the problem of building them. In 2018, we showed how to build the BWT of large genomic databases efficiently (WABI 2018), but the problem of building the sample efficiently was left open. We compare our approach to state-of-the-art methods for constructing the SA sample, and demonstrate that it is the fastest and most space-efficient method on highly repetitive genomic databases. Lastly, we apply our method for indexing partial and whole human genomes and show that it improves over the FM-index-based Bowtie method with respect to both memory and time and over the hybrid index-based CHIC method with respect to query time and memory required for indexing.

The r-index is a tool for compressed indexing of genomic databases for exact pattern matching, which can be used to completely align reads that perfectly match some part of a genome in the database or to find seeds for reads that do not. This article shows how to download and install the programs ri-buildfasta and ri-align; how to call ri-buildfasta on an FASTA file to build an r-index for that file; and how to query that index with ri-align.

Due to the current limitations of sequencing technologies, de novo genome assembly is typically carried out in two stages, namely contig (sequence) assembly and scaffolding. While scaffolding is computationally easier than sequence assembly, the scaffolding problem can be challenging due to the high repetitive content of eukaryotic genomes, possible mis-joins in assembled contigs, and inaccuracies in the linkage information. Genome scaffolding tools either use paired-end/mate-pair/linked/Hi-C reads or genome-wide maps (optical, physical, or genetic) as linkage information. Optical maps (in particular Bionano Genomics maps) have been extensively used in many recent large-scale genome assembly projects (e.g., goat, apple, barley, maize, quinoa, sea bass, among others). However, the most commonly used scaffolding tools have a serious limitation: they can only deal with one optical map at a time, forcing users to alternate or iterate over multiple maps. In this article, we introduce a novel scaffolding algorithm called OMGS (Optical Map-based Genome Scaffolding) that for the first time can take advantages of multiple optical maps. OMGS solves several optimization problems to generate scaffolds with optimal contiguity and correctness. Extensive experimental results demonstrate that our tool outperforms existing methods when multiple optical maps are available and produces comparable scaffolds using a single optical map.

Estimating the abundances of all k-mers in a set of biological sequences is a fundamental and challenging problem with many applications in biological analysis. Although several methods have been designed for the exact or approximate solution of this problem, they all require to process the entire data set, which can be extremely expensive for high-throughput sequencing data sets. Although in some applications it is crucial to estimate all k-mers and their abundances, in other situations it may be sufficient to report only frequent k-mers, which appear with relatively high frequency in a data set. This is the case, for example, in the computation of k-mers' abundance-based distances among data sets of reads, commonly used in metagenomic analyses. In this study, we develop, analyze, and test a sampling-based approach, called Sampling Algorithm for K-mErs approxIMAtion (SAKEIMA), to approximate the frequent k-mers and their frequencies in a high-throughput sequencing data set while providing rigorous guarantees on the quality of the approximation. SAKEIMA employs an advanced sampling scheme and we show how the characterization of the Vapnik–Chervonenkis dimension, a core concept from statistical learning theory, of a properly defined set of functions leads to practical bounds on the sample size required for a rigorous approximation. Our experimental evaluation shows that SAKEIMA allows to rigorously approximate frequent k-mers by processing only a fraction of a data set and that the frequencies estimated by SAKEIMA lead to accurate estimates of k-mer-based distances between high-throughput sequencing data sets. Overall, SAKEIMA is an efficient and rigorous tool to estimate k-mers' abundances providing significant speedups in the analysis of large sequencing data sets.

Protein design algorithms that model continuous sidechain flexibility and conformational ensembles better approximate the in vitro and in vivo behavior of proteins. The previous state of the art, iMinDEE-A*-K*, computes provable ɛ-approximations to partition functions of protein states (e.g., bound vs. unbound) by computing provable, admissible pairwise-minimized energy lower bounds on protein conformations, and using the A* enumeration algorithm to return a gap-free list of lowest-energy conformations. iMinDEE-A*-K* runs in time sublinear in the number of conformations, but can be trapped in loosely-bounded, low-energy conformational wells containing many conformations with highly similar energies. That is, iMinDEE-A*-K* is unable to exploit the correlation between protein conformation and energy: similar conformations often have similar energy. We introduce two new concepts that exploit this correlation: Minimization-Aware Enumeration and Recursive K*. We combine these two insights into a novel algorithm, Minimization-Aware Recursive K* (MARK*), which tightens bounds not on single conformations, but instead on distinct regions of the conformation space. We compare the performance of iMinDEE-A*-K* versus MARK* by running the Branch and Bound over K* (BBK*) algorithm, which provably returns sequences in order of decreasing K* score, using either iMinDEE-A*-K* or MARK* to approximate partition functions. We show on 200 design problems that MARK* not only enumerates and minimizes vastly fewer conformations than the previous state of the art, but also runs up to 2 orders of magnitude faster. Finally, we show that MARK* not only efficiently approximates the partition function, but also provably approximates the energy landscape. To our knowledge, MARK* is the first algorithm to do so. We use MARK* to analyze the change in energy landscape of the bound and unbound states of an HIV-1 capsid protein C-terminal domain in complex with a camelid V_HH, and measure the change in conformational entropy induced by binding. Thus, MARK* both accelerates existing designs and offers new capabilities not possible with previous algorithms.

Characterizing intratumor heterogeneity (ITH) is crucial to understanding cancer development, but it is hampered by limits of available data sources. Bulk DNA sequencing is the most common technology to assess ITH, but involves the analysis of a mixture of many genetically distinct cells in each sample, which must then be computationally deconvolved. Single-cell sequencing is a promising alternative, but its limitations—for example, high noise, difficulty scaling to large populations, technical artifacts, and large data sets—have so far made it impractical for studying cohorts of sufficient size to identify statistically robust features of tumor evolution. We have developed strategies for deconvolution and tumor phylogenetics combining limited amounts of bulk and single-cell data to gain some advantages of single-cell resolution with much lower cost, with specific focus on deconvolving genomic copy number data. We developed a mixed membership model for clonal deconvolution via non-negative matrix factorization balancing deconvolution quality with similarity to single-cell samples via an associated efficient coordinate descent algorithm. We then improve on that algorithm by integrating deconvolution with clonal phylogeny inference, using a mixed integer linear programming model to incorporate a minimum evolution phylogenetic tree cost in the problem objective. We demonstrate the effectiveness of these methods on semisimulated data of known ground truth, showing improved deconvolution accuracy relative to bulk data alone.

Large-scale cohorts with combined genetic and phenotypic data, coupled with methodological advances, have produced increasingly accurate genetic predictors of complex human phenotypes called polygenic risk scores (PRSs). In addition to the potential translational impacts of identifying at-risk individuals, PRS are being utilized for a growing list of scientific applications, including causal inference, identifying pleiotropy and genetic correlation, and powerful gene-based and mixed-model association tests. Existing PRS approaches rely on external large-scale genetic cohorts that have also measured the phenotype of interest. They further require matching on ancestry and genotyping platform or imputation quality. In this work, we present a novel reference-free method to produce a PRS that does not rely on an external cohort. We show that naive implementations of reference-free PRS either result in substantial overfitting or prohibitive increases in computational time. We show that our algorithm avoids both of these issues and can produce informative in-sample PRSs over a single cohort without overfitting. We then demonstrate several novel applications of reference-free PRSs, including detection of pleiotropy across 246 metabolic traits and efficient mixed-model association testing.

Reconstruction of population histories is a central problem in population genetics. Existing coalescent-based methods, such as the seminal work of Li and Durbin, attempt to solve this problem using sequence data but have no rigorous guarantees. Determining the amount of data needed to correctly reconstruct population histories is a major challenge. Using a variety of tools from information theory, the theory of extremal polynomials, and approximation theory, we prove new sharp information-theoretic lower bounds on the problem of reconstructing population structure—the history of multiple subpopulations that merge, split, and change sizes over time. Our lower bounds are exponential in the number of subpopulations, even when reconstructing recent histories. We demonstrate the sharpness of our lower bounds by providing algorithms for distinguishing and learning population histories with matching dependence on the number of subpopulations. Along the way and of independent interest, we essentially determine the optimal number of samples needed to learn an exponential mixture distribution information-theoretically, proving the upper bound by analyzing natural (and efficient) algorithms for this problem.

High-throughput DNA sequencing data are accumulating in public repositories, and efficient approaches for storing and indexing such data are in high demand. In recent research, several graph data structures have been proposed to represent large sets of sequencing data and to allow for efficient querying of sequences. In particular, the concept of labeled de Bruijn graphs has been explored by several groups. Although there has been good progress toward representing the sequence graph in small space, methods for storing a set of labels on top of such graphs are still not sufficiently explored. It is also currently not clear how characteristics of the input data, such as the sparsity and correlations of labels, can help to inform the choice of method to compress the graph labeling. In this study, we present a new compression approach, Multi-binary relation wavelet tree (BRWT), which is adaptive to different kinds of input data. We show an up to 29% improvement in compression performance over the basic BRWT method, and up to a 68% improvement over the current state-of-the-art for de Bruijn graph label compression. To put our results into perspective, we present a systematic analysis of five different state-of-the-art annotation compression schemes, evaluate key metrics on both artificial and real-world data, and discuss how different data characteristics influence the compression performance. We show that the improvements of our new method can be robustly reproduced for different representative real-world data sets.

Availability of extensive genetic data across multiple individuals and populations is driving the growing importance of graph-based reference representations. Aligning sequences to graphs is a fundamental operation on several types of sequence graphs (variation graphs, assembly graphs, pan-genomes, etc.) and their biological applications. Although research on sequence-to-graph alignments is nascent, it can draw from related work on pattern matching in hypertext. In this article, we study sequence-to-graph alignment problems under Hamming and edit distance models, and linear and affine gap penalty functions, for multiple variants of the problem that allow changes in query alone, graph alone, or in both. We prove that when changes are permitted in graphs either standalone or in conjunction with changes in the query, the sequence-to-graph alignment problem is N P -complete under both Hamming and edit distance models for alphabets of size ≥2. For the case where only changes to the sequence are permitted, we present an O ( | V | + m | E | ) time algorithm, where m denotes the query size, and V and E denote the vertex and edge sets of the graph, respectively. Our result is generalizable to both linear and affine gap penalty functions, and improves upon the runtime complexity of existing algorithms.

AIDS is a syndrome caused by the HIV. During the progression of AIDS, a patient's immune system is weakened, which increases the patient's susceptibility to infections and diseases. Although antiretroviral drugs can effectively suppress HIV, the virus mutates very quickly and can become resistant to treatment. In addition, the virus can also become resistant to other treatments not currently being used through mutations, which is known in the clinical research community as cross-resistance. Since a single HIV strain can be resistant to multiple drugs, this problem is naturally represented as a multilabel classification problem. Given this multilabel relationship, traditional single-label classification methods often fail to effectively identify the drug resistances that may develop after a particular virus mutation. In this work, we propose a novel multilabel Robust Sample Specific Distance (RSSD) method to identify multiclass HIV drug resistance. Our method is novel in that it can illustrate the relative strength of the drug resistance of a reverse transcriptase (RT) sequence against a given drug nucleoside analog and learn the distance metrics for all the drug resistances. To learn the proposed RSSDs, we formulate a learning objective that maximizes the ratio of the summations of a number of ℓ₁-norm distances, which is difficult to solve in general. To solve this optimization problem, we derive an efficient, nongreedy iterative algorithm with rigorously proved convergence. Our new method has been verified on a public HIV type 1 drug resistance data set with over 600 RT sequences and five nucleoside analogs. We compared our method against several state-of-the-art multilabel classification methods, and the experimental results have demonstrated the effectiveness of our proposed method.