Leveraging machine learning for taxonomic classification of emerging astroviruses.

Astroviruses are a family of genetically diverse viruses associated with disease in humans and birds with significant health effects and economic burdens. Astrovirus taxonomic classification includes two genera, Avastrovirus and Mamastrovirus. However, with next-generation sequencing, broader interspecies transmission has been observed necessitating a reexamination of the current host-based taxonomic classification approach. In this study, a novel taxonomic classification method is presented for emergent and as yet unclassified astroviruses, based on whole genome sequence k-mer composition in addition to host information. An optional component responsible for identifying recombinant sequences was added to the method's pipeline, to counteract the impact of genetic recombination on viral classification. The proposed three-pronged classification method consists of a supervised machine learning method, an unsupervised machine learning method, and the consideration of host species. Using this three-pronged approach, we propose genus labels for 191 as yet unclassified astrovirus genomes. Genus labels are also suggested for an additional eight as yet unclassified astrovirus genomes for which incompatibility was observed with the host species, suggesting cross-species infection. Lastly, our machine learning-based approach augmented by a principal component analysis (PCA) analysis provides evidence supporting the hypothesis of the existence of human astrovirus (HAstV) subgenus of the genus Mamastrovirus, and a goose astrovirus (GoAstV) subgenus of the genus Avastrovirus. Overall, this multipronged machine learning approach provides a fast, reliable, and scalable prediction method of taxonomic labels, able to keep pace with emerging viruses and the exponential increase in the output of modern genome sequencing technologies.

Metric learning for comparing genomic data with triplet network.

Many biological applications are essentially pairwise comparison problems, such as evolutionary relationships on genomic sequences, contigs binning on metagenomic data, cell type identification on gene expression profiles of single-cells, etc. To make pair-wise comparison, it is necessary to adopt suitable dissimilarity metric. However, not all the metrics can be fully adapted to all possible biological applications. It is necessary to employ metric learning based on data adaptive to the application of interest. Therefore, in this study, we proposed MEtric Learning with Triplet network (MELT), which learns a nonlinear mapping from original space to the embedding space in order to keep similar data closer and dissimilar data far apart. MELT is a weakly supervised and data-driven comparison framework that offers more adaptive and accurate dissimilarity learned in the absence of the label information when the supervised methods are not applicable. We applied MELT in three typical applications of genomic data comparison, including hierarchical genomic sequences, longitudinal microbiome samples and longitudinal single-cell gene expression profiles, which have no distinctive grouping information. In the experiments, MELT demonstrated its empirical utility in comparison to many widely used dissimilarity metrics. And MELT is expected to accommodate a more extensive set of applications in large-scale genomic comparisons. MELT is available at https://github.com/Ying-Lab/MELT.

DIAmeter: matching peptides to data-independent acquisition mass spectrometry data.

MOTIVATION: Tandem mass spectrometry data acquired using data independent acquisition (DIA) is challenging to interpret because the data exhibits complex structure along both the mass-to-charge (m/z) and time axes. The most common approach to analyzing this type of data makes use of a library of previously observed DIA data patterns (a 'spectral library'), but this approach is expensive because the libraries do not typically generalize well across laboratories. RESULTS: Here, we propose DIAmeter, a search engine that detects peptides in DIA data using only a peptide sequence database. Although some existing library-free DIA analysis methods (i) support data generated using both wide and narrow isolation windows, (ii) detect peptides containing post-translational modifications, (iii) analyze data from a variety of instrument platforms and (iv) are capable of detecting peptides even in the absence of detectable signal in the survey (MS1) scan, DIAmeter is the only method that offers all four capabilities in a single tool. AVAILABILITY AND IMPLEMENTATION: The open source, Apache licensed source code is available as part of the Crux mass spectrometry analysis toolkit (http://crux.ms). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CRAFT: Compact genome Representation toward large-scale Alignment-Free daTabase.

MOTIVATION: Rapid developments in sequencing technologies have boosted generating high volumes of sequence data. To archive and analyze those data, one primary step is sequence comparison. Alignment-free sequence comparison based on k-mer frequencies offers a computationally efficient solution, yet in practice, the k-mer frequency vectors for large k of practical interest lead to excessive memory and storage consumption. RESULTS: We report CRAFT, a general genomic/metagenomic search engine to learn compact representations of sequences and perform fast comparison between DNA sequences. Specifically, given genome or high throughput sequencing data as input, CRAFT maps the data into a much smaller embedding space and locates the best matching genome in the archived massive sequence repositories. With 102-104-fold reduction of storage space, CRAFT performs fast query for gigabytes of data within seconds or minutes, achieving comparable performance as six state-of-the-art alignment-free measures. AVAILABILITY AND IMPLEMENTATION: CRAFT offers a user-friendly graphical user interface with one-click installation on Windows and Linux operating systems, freely available at https://github.com/jiaxingbai/CRAFT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SolidBin: improving metagenome binning with semi-supervised normalized cut.

MOTIVATION: Metagenomic contig binning is an important computational problem in metagenomic research, which aims to cluster contigs from the same genome into the same group. Unlike classical clustering problem, contig binning can utilize known relationships among some of the contigs or the taxonomic identity of some contigs. However, the current state-of-the-art contig binning methods do not make full use of the additional biological information except the coverage and sequence composition of the contigs. RESULTS: We developed a novel contig binning method, Semi-supervised Spectral Normalized Cut for Binning (SolidBin), based on semi-supervised spectral clustering. Using sequence feature similarity and/or additional biological information, such as the reliable taxonomy assignments of some contigs, SolidBin constructs two types of prior information: must-link and cannot-link constraints. Must-link constraints mean that the pair of contigs should be clustered into the same group, while cannot-link constraints mean that the pair of contigs should be clustered in different groups. These constraints are then integrated into a classical spectral clustering approach, normalized cut, for improved contig binning. The performance of SolidBin is compared with five state-of-the-art genome binners, CONCOCT, COCACOLA, MaxBin, MetaBAT and BMC3C on five next-generation sequencing benchmark datasets including simulated multi- and single-sample datasets and real multi-sample datasets. The experimental results show that, SolidBin has achieved the best performance in terms of F-score, Adjusted Rand Index and Normalized Mutual Information, especially while using the real datasets and the single-sample dataset. AVAILABILITY AND IMPLEMENTATION: https://github.com/sufforest/SolidBin. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Joint Precursor Elution Profile Inference via Regression for Peptide Detection in Data-Independent Acquisition Mass Spectra.

In data independent acquisition (DIA) mass spectrometry, precursor scans are interleaved with wide-window fragmentation scans, resulting in complex fragmentation spectra containing multiple coeluting peptide species. In this setting, detecting the isotope distribution profiles of intact peptides in the precursor scans can be a critical initial step in accurate peptide detection and quantification. This peak detection step is particularly challenging when the isotope peaks associated with two different peptide species overlap-or interfere-with one another. We propose a regression model, called Siren, to detect isotopic peaks in precursor DIA data that can explicitly account for interference. We validate Siren's peak-calling performance on a variety of data sets by counting how many of the peaks Siren identifies are associated with confidently detected peptides. In particular, we demonstrate that substituting the Siren regression model in place of the existing peak-calling step in DIA-Umpire leads to improved overall rates of peptide detection.

Background Adjusted Alignment-Free Dissimilarity Measures Improve the Detection of Horizontal Gene Transfer.

Horizontal gene transfer (HGT) plays an important role in the evolution of microbial organisms including bacteria. Alignment-free methods based on single genome compositional information have been used to detect HGT. Currently, Manhattan and Euclidean distances based on tetranucleotide frequencies are the most commonly used alignment-free dissimilarity measures to detect HGT. By testing on simulated bacterial sequences and real data sets with known horizontal transferred genomic regions, we found that more advanced alignment-free dissimilarity measures such as CVTree and [Formula: see text] that take into account the background Markov sequences can solve HGT detection problems with significantly improved performance. We also studied the influence of different factors such as evolutionary distance between host and donor sequences, size of sliding window, and host genome composition on the performances of alignment-free methods to detect HGT. Our study showed that alignment-free methods can predict HGT accurately when host and donor genomes are in different order levels. Among all methods, CVTree with word length of 3, [Formula: see text] with word length 3, Markov order 1 and [Formula: see text] with word length 4, Markov order 1 outperform others in terms of their highest F1-score and their robustness under the influence of different factors.

Alignment-Free Sequence Analysis and Applications.

Genome and metagenome comparisons based on large amounts of next generation sequencing (NGS) data pose significant challenges for alignment-based approaches due to the huge data size and the relatively short length of the reads. Alignment-free approaches based on the counts of word patterns in NGS data do not depend on the complete genome and are generally computationally efficient. Thus, they contribute significantly to genome and metagenome comparison. Recently, novel statistical approaches have been developed for the comparison of both long and shotgun sequences. These approaches have been applied to many problems including the comparison of gene regulatory regions, genome sequences, metagenomes, binning contigs in metagenomic data, identification of virus-host interactions, and detection of horizontal gene transfers. We provide an updated review of these applications and other related developments of word-count based approaches for alignment-free sequence analysis.

Towards enhanced and interpretable clustering/classification in integrative genomics.

High-throughput technologies have led to large collections of different types of biological data that provide unprecedented opportunities to unravel molecular heterogeneity of biological processes. Nevertheless, how to jointly explore data from multiple sources into a holistic, biologically meaningful interpretation remains challenging. In this work, we propose a scalable and tuning-free preprocessing framework, Heterogeneity Rescaling Pursuit (Hetero-RP), which weighs important features more highly than less important ones in accord with implicitly existing auxiliary knowledge. Finally, we demonstrate effectiveness of Hetero-RP in diverse clustering and classification applications. More importantly, Hetero-RP offers an interpretation of feature importance, shedding light on the driving forces of the underlying biology. In metagenomic contig binning, Hetero-RP automatically weighs abundance and composition profiles according to the varying number of samples, resulting in markedly improved performance of contig binning. In RNA-binding protein (RBP) binding site prediction, Hetero-RP not only improves the prediction performance measured by the area under the receiver operating characteristic curves (AUC), but also uncovers the evidence supported by independent studies, including the distribution of the binding sites of IGF2BP and PUM2, the binding competition between hnRNPC and U2AF2, and the intron-exon boundary of U2AF2 [availability: https://github.com/younglululu/Hetero-RP].

Improving contig binning of metagenomic data using [Formula: see text] oligonucleotide frequency dissimilarity.

BACKGROUND: Metagenomics sequencing provides deep insights into microbial communities. To investigate their taxonomic structure, binning assembled contigs into discrete clusters is critical. Many binning algorithms have been developed, but their performance is not always satisfactory, especially for complex microbial communities, calling for further development. RESULTS: According to previous studies, relative sequence compositions are similar across different regions of the same genome, but they differ between distinct genomes. Generally, current tools have used the normalized frequency of k-tuples directly, but this represents an absolute, not relative, sequence composition. Therefore, we attempted to model contigs using relative k-tuple composition, followed by measuring dissimilarity between contigs using [Formula: see text]. The [Formula: see text] was designed to measure the dissimilarity between two long sequences or Next-Generation Sequencing data with the Markov models of the background genomes. This method was effective in revealing group and gradient relationships between genomes, metagenomes and metatranscriptomes. With many binning tools available, we do not try to bin contigs from scratch. Instead, we developed [Formula: see text] to adjust contigs among bins based on the output of existing binning tools for a single metagenomic sample. The tool is taxonomy-free and depends only on k-tuples. To evaluate the performance of [Formula: see text], five widely used binning tools with different strategies of sequence composition or the hybrid of sequence composition and abundance were selected to bin six synthetic and real datasets, after which [Formula: see text] was applied to adjust the binning results. Our experiments showed that [Formula: see text] consistently achieves the best performance with tuple length k = 6 under the independent identically distributed (i.i.d.) background model. Using the metrics of recall, precision and ARI (Adjusted Rand Index), [Formula: see text] improves the binning performance in 28 out of 30 testing experiments (6 datasets with 5 binning tools). The [Formula: see text] is available at https://github.com/kunWangkun/d2SBin . CONCLUSIONS: Experiments showed that [Formula: see text] accurately measures the dissimilarity between contigs of metagenomic reads and that relative sequence composition is more reasonable to bin the contigs. The [Formula: see text] can be applied to any existing contig-binning tools for single metagenomic samples to obtain better binning results.

VirFinder: a novel k-mer based tool for identifying viral sequences from assembled metagenomic data.

BACKGROUND: Identifying viral sequences in mixed metagenomes containing both viral and host contigs is a critical first step in analyzing the viral component of samples. Current tools for distinguishing prokaryotic virus and host contigs primarily use gene-based similarity approaches. Such approaches can significantly limit results especially for short contigs that have few predicted proteins or lack proteins with similarity to previously known viruses. METHODS: We have developed VirFinder, the first k-mer frequency based, machine learning method for virus contig identification that entirely avoids gene-based similarity searches. VirFinder instead identifies viral sequences based on our empirical observation that viruses and hosts have discernibly different k-mer signatures. VirFinder's performance in correctly identifying viral sequences was tested by training its machine learning model on sequences from host and viral genomes sequenced before 1 January 2014 and evaluating on sequences obtained after 1 January 2014. RESULTS: VirFinder had significantly better rates of identifying true viral contigs (true positive rates (TPRs)) than VirSorter, the current state-of-the-art gene-based virus classification tool, when evaluated with either contigs subsampled from complete genomes or assembled from a simulated human gut metagenome. For example, for contigs subsampled from complete genomes, VirFinder had 78-, 2.4-, and 1.8-fold higher TPRs than VirSorter for 1, 3, and 5 kb contigs, respectively, at the same false positive rates as VirSorter (0, 0.003, and 0.006, respectively), thus VirFinder works considerably better for small contigs than VirSorter. VirFinder furthermore identified several recently sequenced virus genomes (after 1 January 2014) that VirSorter did not and that have no nucleotide similarity to previously sequenced viruses, demonstrating VirFinder's potential advantage in identifying novel viral sequences. Application of VirFinder to a set of human gut metagenomes from healthy and liver cirrhosis patients reveals higher viral diversity in healthy individuals than cirrhosis patients. We also identified contig bins containing crAssphage-like contigs with higher abundance in healthy patients and a putative Veillonella genus prophage associated with cirrhosis patients. CONCLUSIONS: This innovative k-mer based tool complements gene-based approaches and will significantly improve prokaryotic viral sequence identification, especially for metagenomic-based studies of viral ecology.

CAFE: aCcelerated Alignment-FrEe sequence analysis.

Alignment-free genome and metagenome comparisons are increasingly important with the development of next generation sequencing (NGS) technologies. Recently developed state-of-the-art k-mer based alignment-free dissimilarity measures including CVTree, $d_2^*$ and $d_2^S$ are more computationally expensive than measures based solely on the k-mer frequencies. Here, we report a standalone software, aCcelerated Alignment-FrEe sequence analysis (CAFE), for efficient calculation of 28 alignment-free dissimilarity measures. CAFE allows for both assembled genome sequences and unassembled NGS shotgun reads as input, and wraps the output in a standard PHYLIP format. In downstream analyses, CAFE can also be used to visualize the pairwise dissimilarity measures, including dendrograms, heatmap, principal coordinate analysis and network display. CAFE serves as a general k-mer based alignment-free analysis platform for studying the relationships among genomes and metagenomes, and is freely available at https://github.com/younglululu/CAFE.

COCACOLA: binning metagenomic contigs using sequence COmposition, read CoverAge, CO-alignment and paired-end read LinkAge.

Motivation: The advent of next-generation sequencing technologies enables researchers to sequence complex microbial communities directly from the environment. Because assembly typically produces only genome fragments, also known as contigs, instead of an entire genome, it is crucial to group them into operational taxonomic units (OTUs) for further taxonomic profiling and down-streaming functional analysis. OTU clustering is also referred to as binning. We present COCACOLA, a general framework automatically bin contigs into OTUs based on sequence composition and coverage across multiple samples. Results: The effectiveness of COCACOLA is demonstrated in both simulated and real datasets in comparison with state-of-art binning approaches such as CONCOCT, GroopM, MaxBin and MetaBAT. The superior performance of COCACOLA relies on two aspects. One is using L 1 distance instead of Euclidean distance for better taxonomic identification during initialization. More importantly, COCACOLA takes advantage of both hard clustering and soft clustering by sparsity regularization. In addition, the COCACOLA framework seamlessly embraces customized knowledge to facilitate binning accuracy. In our study, we have investigated two types of additional knowledge, the co-alignment to reference genomes and linkage of contigs provided by paired-end reads, as well as the ensemble of both. We find that both co-alignment and linkage information further improve binning in the majority of cases. COCACOLA is scalable and faster than CONCOCT, GroopM, MaxBin and MetaBAT. Availability and implementation: The software is available at https://github.com/younglululu/COCACOLA . Contact: fsun@usc.edu. Supplementary information: Supplementary data are available at Bioinformatics online.

Alignment-free $d_2

Viruses and their host genomes often share similar oligonucleotide frequency (ONF) patterns, which can be used to predict the host of a given virus by finding the host with the greatest ONF similarity. We comprehensively compared 11 ONF metrics using several k-mer lengths for predicting host taxonomy from among ∼32 000 prokaryotic genomes for 1427 virus isolate genomes whose true hosts are known. The background-subtracting measure [Formula: see text] at k = 6 gave the highest host prediction accuracy (33%, genus level) with reasonable computational times. Requiring a maximum dissimilarity score for making predictions (thresholding) and taking the consensus of the 30 most similar hosts further improved accuracy. Using a previous dataset of 820 bacteriophage and 2699 bacterial genomes, [Formula: see text] host prediction accuracies with thresholding and consensus methods (genus-level: 64%) exceeded previous Euclidian distance ONF (32%) or homology-based (22-62%) methods. When applied to metagenomically-assembled marine SUP05 viruses and the human gut virus crAssphage, [Formula: see text]-based predictions overlapped (i.e. some same, some different) with the previously inferred hosts of these viruses. The extent of overlap improved when only using host genomes or metagenomic contigs from the same habitat or samples as the query viruses. The [Formula: see text] ONF method will greatly improve the characterization of novel, metagenomic viruses.