“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Recent advances have made it possible to analyze high-throughput marker-gene sequencing data without resorting to the customary construction of molecular operational taxonomic units (OTUs): clusters of sequencing reads that differ by less than a fixed dissimilarity threshold. New methods control errors sufficiently such that amplicon sequence variants (ASVs) can be resolved exactly, down to the level of single-nucleotide differences over the sequenced gene region. The benefits of finer resolution are immediately apparent, and arguments for ASV methods have focused on their improved resolution. Less obvious, but we believe more important, are the broad benefits that derive from the status of ASVs as consistent labels with intrinsic biological meaning identified independently from a reference database. Here we discuss how these features grant ASVs the combined advantages of closed-reference OTUs—including computational costs that scale linearly with study size, simple merging between independently processed data sets, and forward prediction—and of de novo OTUs—including accurate measurement of diversity and applicability to communities lacking deep coverage in reference databases. We argue that the improvements in reusability, reproducibility and comprehensiveness are sufficiently great that ASVs should replace OTUs as the standard unit of marker-gene analysis and reporting.

/pdf/exact-sequence-variants-should-replace-operational-taxonomic-40cukui6g2.pdf

Exact sequence variants should replace operational taxonomic units in marker-gene data analysis.

The present outbreak of lower respiratory tract infections, including respiratory distress syndrome, is the third spillover, in only two decades, of an animal coronavirus to humans resulting in a major epidemic. Here, the Coronavirus Study Group (CSG) of the International Committee on Taxonomy of Viruses, which is responsible for developing the official classification of viruses and taxa naming (taxonomy) of the Coronaviridae family, assessed the novelty of the human pathogen tentatively named 2019-nCoV. Based on phylogeny, taxonomy and established practice, the CSG formally recognizes this virus as a sister to severe acute respiratory syndrome coronaviruses (SARS-CoVs) of the species Severe acute respiratory syndrome-related coronavirus and designates it as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). To facilitate communication, the CSG further proposes to use the following naming convention for individual isolates: SARS-CoV-2/Isolate/Host/Date/Location. The spectrum of clinical manifestations associated with SARS-CoV-2 infections in humans remains to be determined. The independent zoonotic transmission of SARS-CoV and SARS-CoV-2 highlights the need for studying the entire (virus) species to complement research focused on individual pathogenic viruses of immediate significance. This research will improve our understanding of virus-host interactions in an ever-changing environment and enhance our preparedness for future outbreaks.

/pdf/severe-acute-respiratory-syndrome-related-coronavirus-the-zzxnc9b0lf.pdf

Severe acute respiratory syndrome-related coronavirus: The species and its viruses – a statement of the Coronavirus Study Group

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today’s machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this Perspective we seek to distil how many of deep learning’s failures can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in comparative psychology, education and linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications. Deep learning has resulted in impressive achievements, but under what circumstances does it fail, and why? The authors propose that its failures are a consequence of shortcut learning, a common characteristic across biological and artificial systems in which strategies that appear to have solved a problem fail unexpectedly under different circumstances.

Shortcut learning in deep neural networks

High-throughput sequencing of PCR-amplified taxonomic markers (like the 16S rRNA gene) has enabled a new level of analysis of complex bacterial communities known as microbiomes. Many tools exist to quantify and compare abundance levels or OTU composition of communities in different conditions. The sequencing reads have to be denoised and assigned to the closest taxa from a reference database. Common approaches use a notion of 97% similarity and normalize the data by subsampling to equalize library sizes. In this paper, we show that statistical models allow more accurate abundance estimates. By providing a complete workflow in R, we enable the user to do sophisticated downstream statistical analyses, whether parametric or nonparametric. We provide examples of using the R packages dada2, phyloseq, DESeq2, ggplot2 and vegan to filter, visualize and test microbiome data. We also provide examples of supervised analyses using random forests and nonparametric testing using community networks and the ggnetwork package.

/pdf/bioconductor-workflow-for-microbiome-data-analysis-from-raw-4w91jmfubl.pdf

Bioconductor workflow for microbiome data analysis: from raw reads to community analyses

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Tackling Climate Change with Machine Learning

Bioconductor workflow for microbiome data analysis: From raw reads to community analyses [version 1; referees: 3 approved]

HIV-1 protease (PR), reverse transcriptase (RT), and integrase (IN) variability presents a challenge to laboratories performing genotypic resistance testing. This challenge will grow with increased sequencing of samples enriched for proviral DNA such as dried blood spots and increased use of next-generation sequencing (NGS) to detect low-abundance HIV-1 variants. We analyzed PR and RT sequences from >100,000 individuals and IN sequences from >10,000 individuals to characterize variation at each amino acid position, identify mutations indicating APOBEC-mediated G-to-A editing, and identify mutations resulting from selective drug pressure. Forty-seven percent of PR, 37% of RT, and 34% of IN positions had one or more amino acid variants with a prevalence of ≥1%. Seventy percent of PR, 60% of RT, and 60% of IN positions had one or more variants with a prevalence of ≥0.1%. Overall 201 PR, 636 RT, and 346 IN variants had a prevalence of ≥0.1%. The median intersubtype prevalence ratios were 2.9-, 2.1-, and 1.9-fold for these PR, RT, and IN variants, respectively. Only 5.0% of PR, 3.7% of RT, and 2.0% of IN variants had a median intersubtype prevalence ratio of ≥10-fold. Variants at lower prevalences were more likely to differ biochemically and to be part of an electrophoretic mixture compared to high-prevalence variants. There were 209 mutations indicative of APOBEC-mediated G-to-A editing and 326 mutations nonpolymorphic treatment selected. Identification of viruses with a high number of APOBEC-associated mutations will facilitate the quality control of dried blood spot sequencing. Identifying sequences with a high proportion of rare mutations will facilitate the quality control of NGS. IMPORTANCE Most antiretroviral drugs target three HIV-1 proteins: PR, RT, and IN. These proteins are highly variable: many different amino acids can be present at the same position in viruses from different individuals. Some of the amino acid variants cause drug resistance and occur mainly in individuals receiving antiretroviral drugs. Some variants result from a human cellular defense mechanism called APOBEC-mediated hypermutation. Many variants result from naturally occurring mutation. Some variants may represent technical artifacts. We studied PR and RT sequences from >100,000 individuals and IN sequences from >10,000 individuals to quantify variation at each amino acid position in these three HIV-1 proteins. We performed analyses to determine which amino acid variants resulted from antiretroviral drug selection pressure, APOBEC-mediated editing, and naturally occurring variation. Our results provide information essential to clinical, research, and public health laboratories performing genotypic resistance testing by sequencing HIV-1 PR, RT, and IN.

HIV-1 Protease, Reverse Transcriptase, and Integrase Variation.

The gut microbiome has been linked to host obesity; however, sex-specific associations between microbiome and fat distribution are not well understood. Here we show sex-specific microbiome signatures contributing to obesity despite both sexes having similar gut microbiome characteristics, including overall abundance and diversity. Our comparisons of the taxa associated with the android fat ratio in men and women found that there is no widespread species-level overlap. We did observe overlap between the sexes at the genus and family levels in the gut microbiome, such as Holdemanella and Gemmiger; however, they had opposite correlations with fat distribution in men and women. Our findings support a role for fat distribution in sex-specific relationships with the composition of the microbiome. Our results suggest that studies of the gut microbiome and abdominal obesity-related disease outcomes should account for sex-specific differences.

Kris Sankaran

Papers

Bioconductor workflow for microbiome data analysis: from raw reads to community analyses

Tackling Climate Change with Machine Learning

Bioconductor workflow for microbiome data analysis: From raw reads to community analyses [version 1; referees: 3 approved]

HIV-1 Protease, Reverse Transcriptase, and Integrase Variation.

Sex-specific association between gut microbiome and fat distribution