LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data.

BACKGROUND: Identification of biomarkers, which are measurable characteristics of biological datasets, can be challenging. Although amplicon sequence variants (ASVs) can be considered potential biomarkers, identifying important ASVs in high-throughput sequencing datasets is challenging. Noise, algorithmic failures to account for specific distributional properties, and feature interactions can complicate the discovery of ASV biomarkers. In addition, these issues can impact the replicability of various models and elevate false-discovery rates. Contemporary machine learning approaches can be leveraged to address these issues. Ensembles of decision trees are particularly effective at classifying the types of data commonly generated in high-throughput sequencing (HTS) studies due to their robustness when the number of features in the training data is orders of magnitude larger than the number of samples. In addition, when combined with appropriate model introspection algorithms, machine learning algorithms can also be used to discover and select potential biomarkers. However, the construction of these models could introduce various biases which potentially obfuscate feature discovery. RESULTS: We developed a decision tree ensemble, LANDMark, which uses oblique and non-linear cuts at each node. In synthetic and toy tests LANDMark consistently ranked as the best classifier and often outperformed the Random Forest classifier. When trained on the full metabarcoding dataset obtained from Canada's Wood Buffalo National Park, LANDMark was able to create highly predictive models and achieved an overall balanced accuracy score of 0.96 ± 0.06. The use of recursive feature elimination did not impact LANDMark's generalization performance and, when trained on data from the BE amplicon, it was able to outperform the Linear Support Vector Machine, Logistic Regression models, and Stochastic Gradient Descent models (p ≤ 0.05). Finally, LANDMark distinguishes itself due to its ability to learn smoother non-linear decision boundaries. CONCLUSIONS: Our work introduces LANDMark, a meta-classifier which blends the characteristics of several machine learning models into a decision tree and ensemble learning framework. To our knowledge, this is the first study to apply this type of ensemble approach to amplicon sequencing data and we have shown that analyzing these datasets using LANDMark can produce highly predictive and consistent models.

Sequence signatures within the genome of SARS-CoV-2 can be used to predict host source.

We conducted an in silico analysis to better understand the potential factors impacting host adaptation of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in white-tailed deer, humans, and mink due to the strong evidence of sustained transmission within these hosts. Classification models trained on single nucleotide and amino acid differences between samples effectively identified white-tailed deer-, human-, and mink-derived SARS-CoV-2. For example, the balanced accuracy score of Extremely Randomized Trees classifiers was 0.984 ± 0.006. Eighty-eight commonly identified predictive mutations are found at sites under strong positive and negative selective pressure. A large fraction of sites under selection (86.9%) or identified by machine learning (87.1%) are found in genes other than the spike. Some locations encoded by these gene regions are predicted to be B- and T-cell epitopes or are implicated in modulating the immune response suggesting that host adaptation may involve the evasion of the host immune system, modulation of the class-I major-histocompatibility complex, and the diminished recognition of immune epitopes by CD8+ T cells. Our selection and machine learning analysis also identified that silent mutations, such as C7303T and C9430T, play an important role in discriminating deer-derived samples across multiple clades. Finally, our investigation into the origin of the B.1.641 lineage from white-tailed deer in Canada discovered an additional human sequence from Michigan related to the B.1.641 lineage sampled near the emergence of this lineage. These findings demonstrate that machine-learning approaches can be used in combination with evolutionary genomics to identify factors possibly involved in the cross-species transmission of viruses and the emergence of novel viral lineages.IMPORTANCESevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly transmissible virus capable of infecting and establishing itself in human and wildlife populations, such as white-tailed deer. This fact highlights the importance of developing novel ways to identify genetic factors that contribute to its spread and adaptation to new host species. This is especially important since these populations can serve as reservoirs that potentially facilitate the re-introduction of new variants into human populations. In this study, we apply machine learning and phylogenetic methods to uncover biomarkers of SARS-CoV-2 adaptation in mink and white-tailed deer. We find evidence demonstrating that both non-synonymous and silent mutations can be used to differentiate animal-derived sequences from human-derived ones and each other. This evidence also suggests that host adaptation involves the evasion of the immune system and the suppression of antigen presentation. Finally, the methods developed here are general and can be used to investigate host adaptation in viruses other than SARS-CoV-2.

Decision Tree Ensembles Utilizing Multivariate Splits Are Effective at Investigating Beta Diversity in Medically Relevant 16S Amplicon Sequencing Data.

Developing an understanding of how microbial communities vary across conditions is an important analytical step. We used 16S rRNA data isolated from human stool samples to investigate whether learned dissimilarities, such as those produced using unsupervised decision tree ensembles, can be used to improve the analysis of the composition of bacterial communities in patients suffering from Crohn's disease and adenomas/colorectal cancers. We also introduce a workflow capable of learning dissimilarities, projecting them into a lower dimensional space, and identifying features that impact the location of samples in the projections. For example, when used with the centered log ratio transformation, our new workflow (TreeOrdination) could identify differences in the microbial communities of Crohn's disease patients and healthy controls. Further investigation of our models elucidated the global impact amplicon sequence variants (ASVs) had on the locations of samples in the projected space and how each ASV impacted individual samples in this space. Furthermore, this approach can be used to integrate patient data easily into the model and results in models that generalize well to unseen data. Models employing multivariate splits can improve the analysis of complex high-throughput sequencing data sets because they are better able to learn about the underlying structure of the data set. IMPORTANCE There is an ever-increasing level of interest in accurately modeling and understanding the roles that commensal organisms play in human health and disease. We show that learned representations can be used to create informative ordinations. We also demonstrate that the application of modern model introspection algorithms can be used to investigate and quantify the impacts of taxa in these ordinations, and that the taxa identified by these approaches have been associated with immune-mediated inflammatory diseases and colorectal cancer.

In silico identification of multiple conserved motifs within the control region of Culicidae mitogenomes.

Mosquitoes are important vectors for human and animal diseases. Genetic markers, like the mitochondrial COI gene, can facilitate the taxonomic classification of disease vectors, vector-borne disease surveillance, and prevention. Within the control region (CR) of the mitochondrial genome, there exists a highly variable and poorly studied non-coding AT-rich area that contains the origin of replication. Although the CR hypervariable region has been used for species differentiation of some animals, few studies have investigated the mosquito CR. In this study, we analyze the mosquito mitogenome CR sequences from 125 species and 17 genera. We discovered four conserved motifs located 80 to 230 bp upstream of the 12S rRNA gene. Two of these motifs were found within all 392 Anopheles (An.) CR sequences while the other two motifs were identified in all 37 Culex (Cx.) CR sequences. However, only 3 of the 304 non-Culicidae Dipteran mitogenome CR sequences contained these motifs. Interestingly, the short motif found in all 37 Culex sequences had poly-A and poly-T stretch of similar length that is predicted to form a stable hairpin. We show that supervised learning using the frequency chaos game representation of the CR can be used to differentiate mosquito genera from their dipteran relatives.

Divergent SARS-CoV-2 variant emerges in white-tailed deer with deer-to-human transmission.

Wildlife reservoirs of broad-host-range viruses have the potential to enable evolution of viral variants that can emerge to infect humans. In North America, there is phylogenomic evidence of continual transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) from humans to white-tailed deer (Odocoileus virginianus) through unknown means, but no evidence of transmission from deer to humans. We carried out an observational surveillance study in Ontario, Canada during November and December 2021 (n = 300 deer) and identified a highly divergent lineage of SARS-CoV-2 in white-tailed deer (B.1.641). This lineage is one of the most divergent SARS-CoV-2 lineages identified so far, with 76 mutations (including 37 previously associated with non-human mammalian hosts). From a set of five complete and two partial deer-derived viral genomes we applied phylogenomic, recombination, selection and mutation spectrum analyses, which provided evidence for evolution and transmission in deer and a shared ancestry with mink-derived virus. Our analysis also revealed an epidemiologically linked human infection. Taken together, our findings provide evidence for sustained evolution of SARS-CoV-2 in white-tailed deer and of deer-to-human transmission.

COI metabarcoding primer choice affects richness and recovery of indicator taxa in freshwater systems.

Mixed community or environmental DNA marker gene sequencing has become a commonly used technique for biodiversity analyses in freshwater systems. Many cytochrome c oxidase subunit I (COI) primer sets are now available for such work. The purpose of this study is to test whether COI primer choice affects the recovery of arthropod richness, beta diversity, and recovery of target assemblages in the benthos kick-net samples typically used in freshwater biomonitoring. We examine six commonly used COI primer sets on samples collected from six freshwater sites. Biodiversity analyses show that richness is sensitive to primer choice and the combined use of multiple COI amplicons recovers higher richness. Thus, to recover maximum richness, multiple primer sets should be used with COI metabarcoding. In ordination analyses based on community dissimilarity, samples consistently cluster by site regardless of amplicon choice or PCR replicate. Thus, for broadscale community analyses, overall beta diversity patterns are robust to COI marker choice. Recovery of traditional freshwater bioindicator assemblages such as Ephemeroptera, Trichoptera, Plectoptera, and Chironomidae as well as Arthropoda site indicators were differentially detected by each amplicon tested. This work will help future biodiversity and biomonitoring studies develop not just standardized, but optimized workflows that either maximize taxon-detection or the selection of amplicons for water quality or Arthropoda site indicators.