Learning,visualizing and exploring 16S rRNA structure using an attention-based deep neural network

Recurrent neural networks with memory and attention mechanisms are widely used in natural language processing because they can capture short and long term sequential information for diverse tasks. We propose an integrated deep learning model for microbial DNA sequence data, which exploits convolutional neural networks, recurrent neural networks, and attention mechanisms to predict taxonomic classifications and sample-associated attributes, such as the relationship between the microbiome and host phenotype, on the read/sequence level. In this paper, we develop this novel deep learning approach and evaluate its application to amplicon sequences. We apply our approach to short DNA reads and full sequences of 16S ribosomal RNA (rRNA) marker genes, which identify the heterogeneity of a microbial community sample. We demonstrate that our implementation of a novel attention-based deep network architecture, Read2Pheno, achieves read-level phenotypic prediction. Training Read2Pheno models will encode sequences (reads) into dense, meaningful representations: learned embedded vectors output from the intermediate layer of the network model, which can provide biological insight when visualized. The attention layer of Read2Pheno models can also automatically identify nucleotide regions in reads/sequences which are particularly informative for classification. As such, this novel approach can avoid pre/post-processing and manual interpretation required with conventional approaches to microbiome sequence classification. We further show, as proof-of-concept, that aggregating read-level information can robustly predict microbial community properties, host phenotype, and taxonomic classification, with performance at least comparable to conventional approaches. An implementation of the attention-based deep learning network is available at https://github.com/EESI/sequence_attention (a python package) and https://github.com/EESI/seq2att (a command line tool).     

Real-time resolution of short-read assembly graph using ONT long reads

A streaming assembly pipeline utilising real-time Oxford Nanopore Technology (ONT) sequencing data is important for saving sequencing resources and reducing time-to-result. A previous approach implemented in npScarf provided an efficient streaming algorithm for hybrid assembly but was relatively prone to mis-assemblies compared to other graph-based methods. Here we present npGraph, a streaming hybrid assembly tool using the assembly graph instead of the separated pre-assembly contigs. It is able to produce more complete genome assembly by resolving the path finding problem on the assembly graph using long reads as the traversing guide. Application to synthetic and real data from bacterial isolate genomes show improved accuracy while still maintaining a low computational cost. npGraph also provides a graphical user interface (GUI) which provides a real-time visualisation of the progress of assembly. The tool and source code is available at https://github.com/hsnguyen/assembly.     

UniqTag: Content-Derived Unique and Stable Identifiers for Gene Annotation

When working on an ongoing genome sequencing and assembly project, it is rather inconvenient when gene identifiers change from one build of the assembly to the next. The gene labelling system described here, UniqTag, addresses this common challenge. UniqTag assigns a unique identifier to each gene that is a representative k-mer, a string of length k, selected from the sequence of that gene. Unlike serial numbers, these identifiers are stable between different assemblies and annotations of the same data without requiring that previous annotations be lifted over by sequence alignment. We assign UniqTag identifiers to ten builds of the Ensembl human genome spanning eight years to demonstrate this stability. The implementation of UniqTag in Ruby and an R package are available at https://github.com/sjackman/uniqtag sjackman/uniqtag. The R package is also available from CRAN: install.packages ("uniqtag"). Supplementary material and code to reproduce it is available at https://github.com/sjackman/uniqtag-paper.     

POMAShiny: A user-friendly web-based workflow for metabolomics and proteomics data analysis

Metabolomics and proteomics, like other omics domains, usually face a data mining challenge in providing an understandable output to advance in biomarker discovery and precision medicine. Often, statistical analysis is one of the most difficult challenges and it is critical in the subsequent biological interpretation of the results. Because of this, combined with the computational programming skills needed for this type of analysis, several bioinformatic tools aimed at simplifying metabolomics and proteomics data analysis have emerged. However, sometimes the analysis is still limited to a few hidebound statistical methods and to data sets with limited flexibility. POMAShiny is a web-based tool that provides a structured, flexible and user-friendly workflow for the visualization, exploration and statistical analysis of metabolomics and proteomics data. This tool integrates several statistical methods, some of them widely used in other types of omics, and it is based on the POMA R/Bioconductor package, which increases the reproducibility and flexibility of analyses outside the web environment. POMAShiny and POMA are both freely available at https://github.com/nutrimetabolomics/POMAShiny and https://github.com/nutrimetabolomics/POMA, respectively.     

IAGS: Inferring Ancestor Genome Structure under a Wide Range of Evolutionary Scenarios

Significant improvements in genome sequencing and assembly technology have led to increasing numbers of high-quality genomes, revealing complex evolutionary scenarios such as multiple whole-genome duplication events, which hinders ancestral genome reconstruction via the currently available computational frameworks. Here, we present the Inferring Ancestor Genome Structure (IAGS) framework, a novel block/endpoint matching optimization strategy with single-cut-or-join distance, to allow ancestral genome reconstruction under both simple (single-copy ancestor) and complex (multicopy ancestor) scenarios. We evaluated IAGS with two simulated data sets and applied it to four different real evolutionary scenarios to demonstrate its performance and general applicability. IAGS is available at https://github.com/xjtu-omics/IAGS.     

Turning publicly available gene expression data into discoveries using gene set context analysis

Gene Set Context Analysis (GSCA) is an open source software package to help researchers use massive amounts of publicly available gene expression data (PED) to make discoveries. Users can interactively visualize and explore gene and gene set activities in 25,000+ consistently normalized human and mouse gene expression samples representing diverse biological contexts (e.g. different cells, tissues and disease types, etc.). By providing one or multiple genes or gene sets as input and specifying a gene set activity pattern of interest, users can query the expression compendium to systematically identify biological contexts associated with the specified gene set activity pattern. In this way, researchers with new gene sets from their own experiments may discover previously unknown contexts of gene set functions and hence increase the value of their experiments. GSCA has a graphical user interface (GUI). The GUI makes the analysis convenient and customizable. Analysis results can be conveniently exported as publication quality figures and tables. GSCA is available at https://github.com/zji90/GSCA. This software significantly lowers the bar for biomedical investigators to use PED in their daily research for generating and screening hypotheses, which was previously difficult because of the complexity, heterogeneity and size of the data.     

Recursive MAGUS: Scalable and accurate multiple sequence alignment

Multiple sequence alignment tools struggle to keep pace with rapidly growing sequence data, as few methods can handle large datasets while maintaining alignment accuracy. We recently introduced MAGUS, a new state-of-the-art method for aligning large numbers of sequences. In this paper, we present a comprehensive set of enhancements that allow MAGUS to align vastly larger datasets with greater speed. We compare MAGUS to other leading alignment methods on datasets of up to one million sequences. Our results demonstrate the advantages of MAGUS over other alignment software in both accuracy and speed. MAGUS is freely available in open-source form at https://github.com/vlasmirnov/MAGUS.     

Ensembler: Enabling High-Throughput Molecular Simulations at the Superfamily Scale

The rapidly expanding body of available genomic and protein structural data provides a rich resource for understanding protein dynamics with biomolecular simulation. While computational infrastructure has grown rapidly, simulations on an omics scale are not yet widespread, primarily because software infrastructure to enable simulations at this scale has not kept pace. It should now be possible to study protein dynamics across entire (super)families, exploiting both available structural biology data and conformational similarities across homologous proteins. Here, we present a new tool for enabling high-throughput simulation in the genomics era. Ensembler takes any set of sequences—from a single sequence to an entire superfamily—and shepherds them through various stages of modeling and refinement to produce simulation-ready structures. This includes comparative modeling to all relevant PDB structures (which may span multiple conformational states of interest), reconstruction of missing loops, addition of missing atoms, culling of nearly identical structures, assignment of appropriate protonation states, solvation in explicit solvent, and refinement and filtering with molecular simulation to ensure stable simulation. The output of this pipeline is an ensemble of structures ready for subsequent molecular simulations using computer clusters, supercomputers, or distributed computing projects like Folding@home. Ensembler thus automates much of the time-consuming process of preparing protein models suitable for simulation, while allowing scalability up to entire superfamilies. A particular advantage of this approach can be found in the construction of kinetic models of conformational dynamics—such as Markov state models (MSMs)—which benefit from a diverse array of initial configurations that span the accessible conformational states to aid sampling. We demonstrate the power of this approach by constructing models for all catalytic domains in the human tyrosine kinase family, using all available kinase catalytic domain structures from any organism as structural templates. Ensembler is free and open source software licensed under the GNU General Public License (GPL) v2. It is compatible with Linux and OS X. The latest release can be installed via the conda package manager, and the latest source can be downloaded from https://github.com/choderalab/ensembler.     

VDJtools: Unifying Post-analysis of T Cell Receptor Repertoires

Despite the growing number of immune repertoire sequencing studies, the field still lacks software for analysis and comprehension of this high-dimensional data. Here we report VDJtools, a complementary software suite that solves a wide range of T cell receptor (TCR) repertoires post-analysis tasks, provides a detailed tabular output and publication-ready graphics, and is built on top of a flexible API. Using TCR datasets for a large cohort of unrelated healthy donors, twins, and multiple sclerosis patients we demonstrate that VDJtools greatly facilitates the analysis and leads to sound biological conclusions. VDJtools software and documentation are available at https://github.com/mikessh/vdjtools.     

A Real-Time All-Atom Structural Search Engine for Proteins

Protein designers use a wide variety of software tools for de novo design, yet their repertoire still lacks a fast and interactive all-atom search engine. To solve this, we have built the Suns program: a real-time, atomic search engine integrated into the PyMOL molecular visualization system. Users build atomic-level structural search queries within PyMOL and receive a stream of search results aligned to their query within a few seconds. This instant feedback cycle enables a new “designability”-inspired approach to protein design where the designer searches for and interactively incorporates native-like fragments from proven protein structures. We demonstrate the use of Suns to interactively build protein motifs, tertiary interactions, and to identify scaffolds compatible with hot-spot residues. The official web site and installer are located at http://www.degradolab.org/suns/ and the source code is hosted at https://github.com/godotgildor/Suns (PyMOL plugin, BSD license), https://github.com/Gabriel439/suns-cmd (command line client, BSD license), and https://github.com/Gabriel439/suns-search (search engine server, GPLv2 license).

This is a PLOS Computational Biology Software Article

     

Wham: Identifying Structural Variants of Biological Consequence

Existing methods for identifying structural variants (SVs) from short read datasets are inaccurate. This complicates disease-gene identification and efforts to understand the consequences of genetic variation. In response, we have created Wham (Whole-genome Alignment Metrics) to provide a single, integrated framework for both structural variant calling and association testing, thereby bypassing many of the difficulties that currently frustrate attempts to employ SVs in association testing. Here we describe Wham, benchmark it against three other widely used SV identification tools–Lumpy, Delly and SoftSearch–and demonstrate Wham’s ability to identify and associate SVs with phenotypes using data from humans, domestic pigeons, and vaccinia virus. Wham and all associated software are covered under the MIT License and can be freely downloaded from github (https://github.com/zeeev/wham), with documentation on a wiki (http://zeeev.github.io/wham/). For community support please post questions to https://www.biostars.org/.

This is PLOS Computational Biology software paper.

     

Spectacle: fast chromatin state annotation using spectral learning

Epigenomic data from ENCODE can be used to associate specific combinations of chromatin marks with regulatory elements in the human genome. Hidden Markov models and the expectation-maximization (EM) algorithm are often used to analyze epigenomic data. However, the EM algorithm can have overfitting problems in data sets where the chromatin states show high class-imbalance and it is often slow to converge. Here we use spectral learning instead of EM and find that our software Spectacle overcame these problems. Furthermore, Spectacle is able to find enhancer subtypes not found by ChromHMM but strongly enriched in GWAS SNPs. Spectacle is available at https://github.com/jiminsong/Spectacle.

Electronic supplementary material

The online version of this article (doi:10.1186/s13059-015-0598-0) contains supplementary material, which is available to authorized users.