Biology subjects

Wiens, J.

Publications and source records attributed to Wiens, J..

5 recordsLinked to original sources

bioRxiv2022

Rapid Real-time Squiggle Classification for Read Until Using RawMap

ReadUntil enables Oxford Nanopore Technologys (ONT) sequencers to selectively sequence reads of target species in real-time. This enables efficient microbial enrichment for applications such as microbial abundance estimation and is particularly beneficial for metagenomic samples with a very high fraction of non-target reads (> 99% can be human reads). However, read-until requires a fast and accurate software filter that analyzes a short prefix of a read and determines if it belongs to a microbe of interest (target) or not. The baseline Read Until pipeline uses a deep neural network-based basecaller called Guppy and is slow and inaccurate for this task ([~]60% of bases sequenced are unclassified). We present RawMap, an efficient CPU-only microbial species-agnostic Read Until classifier for filtering non-target human reads in the squiggle space. RawMap uses a Support Vector Machine (SVM), which is trained to distinguish human from microbe using non-linear and non-stationary characteristics of ONTs squiggle output (continuous electrical signals). Compared to the baseline Read Until pipeline, RawMap is a 1327X faster classifier and significantly improves the sequencing time and cost, and compute time savings. We show that RawMap augmented pipelines reduce sequencing time and cost by [~]24% and computing cost by [~]22%. Additionally, since RawMap is agnostic to microbial species, it can also classify microbial species it is not trained on. We also discuss how RawMap may be used as an alternative to the RT-PCR test for viral load quantification of SARS-CoV-2. Availability and implementationSoftware is released with MIT License and available on GitHub: https://github.com/harisankarsadasivan/RawMap

bioinformatics↗

bioRxiv2022

Streamlined implementation of a machine learning model to classify screen relevant neoplasia using reference-based OTU clustering

The ability to use 16S rRNA gene sequence data to train machine learning classification models offers the opportunity diagnose patients based on the composition of their microbiome. In some applications the taxonomic resolution that provides the best models may require the use of de novo OTUs whose composition changes when new data are added. We previously developed a new reference-based approach, OptiFit, that fits new sequence data to existing de novo OTUs without changing the composition of the original OTUs. While OptiFit produces OTUs that are as high quality as de novo OTUs, it is unclear whether this method for fitting new sequence data into existing OTUs will impact the performance of classification models relative to models trained and tested only using de novo OTUs. We used OptiFit to cluster sequences into existing OTUs and evaluated model performance in classifying a dataset containing samples from patients with and without colonic screen relevant neoplasia (SRN). We compared the performance of this model to standard methods including de novo and database-reference-based clustering. We found that using OptiFit performed as well or better in classifying SRNs. OptiFit can streamline the process of classifying new samples by avoiding the need to retrain models using reclustered sequences.

microbiology↗

bioRxiv2019

Effective application of machine learning to microbiome-based classification problems

Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made towards developing ML models that predict health outcomes using bacterial abundances, but inconsistent adoption of training and evaluation methods call the validity of these models into question. Furthermore, there appears to be a preference by many researchers to favor increased model complexity over interpretability. To overcome these challenges, we trained seven models that used fecal 16S rRNA sequence data to predict the presence of colonic screen relevant neoplasias (SRNs; n=490 patients, 261 controls and 229 cases). We developed a reusable open-source pipeline to train, validate, and interpret ML models. To show the effect of model selection, we assessed the predictive performance, interpretability, and training time of L2-regularized logistic regression, L1 and L2-regularized support vector machines (SVM) with linear and radial basis function kernels, decision trees, random forest, and gradient boosted trees (XGBoost). The random forest model performed best at detecting SRNs with an AUROC of 0.695 [IQR 0.651-0.739] but was slow to train (83.2 h) and not inherently interpretable. Despite its simplicity, L2-regularized logistic regression followed random forest in predictive performance with an AUROC of 0.680 [IQR 0.625-0.735], trained faster (12 min), and was inherently interpretable. Our analysis highlights the importance of choosing an ML approach based on the goal of the study, as the choice will inform expectations of performance and interpretability. ImportanceDiagnosing diseases using machine learning (ML) is rapidly being adopted in microbiome studies. However, the estimated performance associated with these models is likely over-optimistic. Moreover, there is a trend towards using black box models without a discussion of the difficulty of interpreting such models when trying to identify microbial biomarkers of disease. This work represents a step towards developing more reproducible ML practices in applying ML to microbiome research. We implement a rigorous pipeline and emphasize the importance of selecting ML models that reflect the goal of the study. These concepts are not particular to the study of human health but can also be applied to environmental microbiology studies.

microbiology↗

bioRxiv2019

SuperCRUNCH: A toolkit for creating and manipulating supermatrices and other large phylogenetic datasets

O_LIPhylogenies with extensive taxon sampling have become indispensable for many types of ecological and evolutionary studies. Many large-scale trees are based on a "supermatrix" approach, which involves amalgamating thousands of published sequences for a group. Constructing up-to-date supermatrices can be challenging, especially as new sequences may become available almost constantly. Additionally, genomic datasets (composed of thousands of loci) are becoming common in phylogenetics and phylogeography, and present novel challenges for constructing such datasets. C_LIO_LIHere we present SuperCRUNCH, a Python toolkit for assembling large phylogenetic datasets. It can be applied to GenBank sequences, unpublished sequences, or combinations of GenBank and unpublished data. SuperCRUNCH constructs local databases and uses them to conduct rapid searches for user-specified sets of taxa and loci. Sequences are parsed into putative loci and passed through rigorous filtering steps. A post-filtering step allows for selection of one sequence per taxon (i.e. species-level supermatrix) or retention of all sequences per taxon (i.e. population-level dataset). Importantly, SuperCRUNCH can generate "vouchered" population-level datasets, in which voucher information is used to generate multi-locus phylogeographic datasets. SuperCRUNCH offers many options for taxonomy resolution, similarity filtering, sequence selection, alignment, and file manipulation. C_LIO_LIWe demonstrate the range of features available in SuperCRUNCH by generating a variety of phylogenetic datasets. Output datasets include traditional species-level supermatrices, large-scale phylogenomic matrices, and phylogeographic datasets. Finally, we briefly compare the ability of SuperCRUNCH to construct species-level supermatrices to alternative approaches. SuperCRUNCH generated a large-scale supermatrix (1,400 taxa and 66 loci) from 16GB of GenBank data in [~]1.5 hours, and generated population-level datasets (<350 samples, <10 loci) in <1 minute. It outperformed alternative methods for supermatrix construction in terms of taxa, loci, and sequences recovered. C_LIO_LISuperCRUNCH is a modular bioinformatics toolkit that can be used to assemble datasets for any taxonomic group and scale (kingdoms to individuals). It allows rapid construction of supermatrices, greatly simplifying the process of updating large phylogenies with new data. It is also designed to produce population-level datasets. SuperCRUNCH streamlines the major tasks required to process phylogenetic data, including filtering, alignment, trimming, and formatting. SuperCRUNCH is open-source, documented, and available at https://github.com/dportik/SuperCRUNCH. C_LI

bioinformatics↗

bioRxiv2019

Observing the origins of human brain development: Automated processing of fetal fMRI

AO_SCPLOWBSTRACTC_SCPLOWFetal resting-state functional magnetic resonance imaging (rs-fMRI) has emerged as a critical new approach for characterizing brain development before birth. Despite rapid and widespread growth of this approach, at present we lack neuroimaging processing pipelines suited to address the unique challenges inherent in this data type. Here, we solve the most challenging processing step, rapid and accurate isolation of the fetal brain from surrounding tissue across thousands of non-stationary 3D brain volumes. Leveraging our library of 1,241 manually traced fetal fMRI images from 207 fetuses (gestational age 24-39 weeks, M=30.9, SD=4.2), we trained a Convolutional Neural Network (CNN) that achieved excellent performance across two held-out test sets from separate scanners and populations. Furthermore, we unite the auto-masking model with additional fMRI preprocessing steps from existing software and provide insight into our adaptation of each step. This work represents an initial advancement towards a fully comprehensive, open source workflow for fetal functional MRI data preprocessing.

neuroscience↗