skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Learning sparse log-ratios for high-throughput sequencing data
Abstract Motivation The automatic discovery of sparse biomarkers that are associated with an outcome of interest is a central goal of bioinformatics. In the context of high-throughput sequencing (HTS) data, and compositional data (CoDa) more generally, an important class of biomarkers are the log-ratios between the input variables. However, identifying predictive log-ratio biomarkers from HTS data is a combinatorial optimization problem, which is computationally challenging. Existing methods are slow to run and scale poorly with the dimension of the input, which has limited their application to low- and moderate-dimensional metagenomic datasets. Results Building on recent advances from the field of deep learning, we present CoDaCoRe, a novel learning algorithm that identifies sparse, interpretable and predictive log-ratio biomarkers. Our algorithm exploits a continuous relaxation to approximate the underlying combinatorial optimization problem. This relaxation can then be optimized efficiently using the modern ML toolbox, in particular, gradient descent. As a result, CoDaCoRe runs several orders of magnitude faster than competing methods, all while achieving state-of-the-art performance in terms of predictive accuracy and sparsity. We verify the outperformance of CoDaCoRe across a wide range of microbiome, metabolite and microRNA benchmark datasets, as well as a particularly high-dimensional dataset that is outright computationally intractable for existing sparse log-ratio selection methods. Availability and implementation The CoDaCoRe package is available at https://github.com/egr95/R-codacore. Code and instructions for reproducing our results are available at https://github.com/cunningham-lab/codacore. Supplementary information Supplementary data are available at Bioinformatics online.  more » « less
Award ID(s):
1707398
PAR ID:
10432375
Author(s) / Creator(s):
; ;
Editor(s):
Luigi Martelli, Pier
Date Published:
Journal Name:
Bioinformatics
Volume:
38
Issue:
1
ISSN:
1367-4803
Page Range / eLocation ID:
157 to 163
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Bioinformatics)
    Abstract MotivationMultiple sequence alignment (MSA) is a basic step in many bioinformatics pipelines. However, achieving highly accurate alignments on large datasets, especially those with sequence length heterogeneity, is a challenging task. Ultra-large multiple sequence alignment using Phylogeny-aware Profiles (UPP) is a method for MSA estimation that builds an ensemble of Hidden Markov Models (eHMM) to represent an estimated alignment on the full-length sequences in the input, and then adds the remaining sequences into the alignment using selected HMMs in the ensemble. Although UPP provides good accuracy, it is computationally intensive on large datasets. ResultsWe present UPP2, a direct improvement on UPP. The main advance is a fast technique for selecting HMMs in the ensemble that allows us to achieve the same accuracy as UPP but with greatly reduced runtime. We show that UPP2 produces more accurate alignments compared to leading MSA methods on datasets exhibiting substantial sequence length heterogeneity and is among the most accurate otherwise. Availability and implementationhttps://github.com/gillichu/sepp. Supplementary informationSupplementary data are available at Bioinformatics online. 
    more » « less
  2. ; (, Bioinformatics)
    Abstract MotivationRecent experiments have provided Hi-C data at resolution as high as 1 kbp. However, 3D structural inference from high-resolution Hi-C datasets is often computationally unfeasible using existing methods. ResultsWe have developed miniMDS, an approximation of multidimensional scaling (MDS) that partitions a Hi-C dataset, performs high-resolution MDS separately on each partition, and then reassembles the partitions using low-resolution MDS. miniMDS is faster, more accurate, and uses less memory than existing methods for inferring the human genome at high resolution (10 kbp). Availability and implementationA Python implementation of miniMDS is available on GitHub: https://github.com/seqcode/miniMDS. Supplementary informationSupplementary data are available at Bioinformatics online. 
    more » « less
  3. ; ; (, Bioinformatics)
    Abstract MotivationSpecies tree inference from multi-copy gene trees has long been a challenge in phylogenomics. The recent method ASTRAL-Pro has made strides by enabling multi-copy gene family trees as input and has been quickly adopted. Yet, its scalability, especially memory usage, needs to improve to accommodate the ever-growing dataset size. ResultsWe present ASTRAL-Pro 2, an ultrafast and memory efficient version of ASTRAL-Pro that adopts a placement-based optimization algorithm for significantly better scalability without sacrificing accuracy. Availability and implementationThe source code and binary files are publicly available at https://github.com/chaoszhang/ASTER; data are available at https://github.com/chaoszhang/A-Pro2_data. Supplementary informationSupplementary data are available at Bioinformatics online. 
    more » « less
  4. ; ; (, Bioinformatics)
    Boeva, Valentina (Ed.)
    Abstract Summary Multiple sequence alignment is an initial step in many bioinformatics pipelines, including phylogeny estimation, protein structure prediction and taxonomic identification of reads produced in amplicon or metagenomic datasets, etc. Yet, alignment estimation is challenging on datasets that exhibit substantial sequence length heterogeneity, and especially when the datasets have fragmentary sequences as a result of including reads or contigs generated by next-generation sequencing technologies. Here, we examine techniques that have been developed to improve alignment estimation when datasets contain substantial numbers of fragmentary sequences. We find that MAGUS, a recently developed MSA method, is fairly robust to fragmentary sequences under many conditions, and that using a two-stage approach where MAGUS is used to align selected ‘backbone sequences’ and the remaining sequences are added into the alignment using ensembles of Hidden Markov Models further improves alignment accuracy. The combination of MAGUS with the ensemble of eHMMs (i.e. MAGUS+eHMMs) clearly improves on UPP, the previous leading method for aligning datasets with high levels of fragmentation. Availability and implementation UPP is available on https://github.com/smirarab/sepp, and MAGUS is available on https://github.com/vlasmirnov/MAGUS. MAGUS+eHMMs can be performed by running MAGUS to obtain the backbone alignment, and then using the backbone alignment as an input to UPP. Supplementary information Supplementary data are available at Bioinformatics online. 
    more » « less
  5. ; ; (, Bioinformatics Advances)
    Abstract SummaryMultiple sequence alignment is a basic part of many bioinformatics pipelines, including in phylogeny estimation, prediction of structure for both RNAs and proteins, and metagenomic sequence analysis. Yet many sequence datasets exhibit substantial sequence length heterogeneity, both because of large insertions and deletions in the evolutionary history of the sequences and the inclusion of unassembled reads or incompletely assembled sequences in the input. A few methods have been developed that can be highly accurate in aligning datasets with sequence length heterogeneity, with UPP one of the first methods to achieve good accuracy, and WITCH a recent improvement on UPP for accuracy. In this article, we show how we can speed up WITCH. Our improvement includes replacing a critical step in WITCH (currently performed using a heuristic search) by a polynomial time exact algorithm using Smith–Waterman. Our new method, WITCH-NG (i.e. ‘next generation WITCH’) achieves the same accuracy but is substantially faster. WITCH-NG is available at https://github.com/RuneBlaze/WITCH-NG. Availability and implementationThe datasets used in this study are from prior publications and are freely available in public repositories, as indicated in the Supplementary Materials. Supplementary informationSupplementary data are available at Bioinformatics Advances online. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email