Machine-learning model led design to experimentally test species thermal limits: the case of kissing bugs (Triatominae)

Abstract

Species Distribution Modelling (SDM) determines habitat suitability of a species across geographic areas using macro-climatic variables; however, micro-habitats can buffer or exacerbate the influence of macro-climatic variables, requiring links between physiology and species persistence. Experimental approaches linking species physiology to micro-climate are complex, time consuming and expensive. E.g., what combination of exposure time and temperature is important for a species thermal tolerance is difficult to judge a priori. We tackled this problem using an active learning approach that utilized machine learning methods to guide thermal tolerance experimental design for three kissing-bug species (Hemiptera: Reduviidae: Triatominae), vectors of the parasite causing Chagas disease. As with other pathogen vectors, triatomines are well known to utilize micro-habitats and the associated shift in microclimate to enhance survival. Using a limited literature-collected dataset, our approach showed that temperature followed by exposure time were the strongest predictors of mortality; species played a minor role, and life stage was the least important. Further, we identified complex but biologically plausible nonlinear interactions between temperature and exposure time in shaping mortality, together setting the potential thermal limits of triatomines. The results from this data led to the design of new experiments with laboratory results that produced novel insights of the effects of temperature and exposure for the triatomines. These results, in turn, can be used to better model micro-climatic envelope for the species. Here we demonstrate the power of an active learning approach to explore experimental space to design laboratory studies testing species thermal limits. Our analytical pipeline can be easily adapted to other systems and we provide code to allow practitioners to perform similar analyses. Not only does our approach have the potential to save time and money: it can also increase our understanding of the links between species physiology and climate, a topic of increasing ecological importance.Author summarySpecies Distribution Modelling determines habitat suitability of a species across geographic areas using macro-climatic variables; however, micro-habitats can buffer or exacerbate the influence of macro-climatic variables, requiring links between physiology and species persistence. We tackled the problem of the combination of exposure time and temperature (a combination difficult to judge a priori) in determining species thermal tolerance, using an active learning approach that utilized machine learning methods to guide thermal tolerance experimental design for three kissing-bug species, vectors of the parasite causing Chagas disease. These bugs are found in micro-habitats with associated shifts in microclimate to enhance survival. Using a limited literature-collected dataset, we showed that temperature followed by exposure time were the strongest predictors of mortality, that species played a minor role, that life stage was the least important, and a complex nonlinear interaction between temperature and exposure time in shaping mortality of kissing bugs. These results led to the design of new laboratory experiments to assess the effects of temperature and exposure for the triatomines. These results can be used to better model micro-climatic envelope for species. Our active learning approach to explore experimental space to design laboratory studies can also be applied to other environmental conditions or species.

Positive associations matter: microbial relationships drive tick microbiome composition

“…While our study provides insight into the drivers of I. scapularis microbiome dynamics, our findings are necessarily associative and should help guide future more mechanistic studies [36]. These studies could include the controlled examination of host seeking behaviour under varying environmental conditions using ticks that have been infected with pathogens of interest.…”

“…The MrIML approach also provides extensive autotuning capabilities to optimize algorithm performance as well as 10-fold cross validation to guard against model overfitting. Moreover, multi-algorithm performance in prediction across ASVs can be easily compared and the model with highest performance further interrogated [27, 36]. We compared the predictive performance of three different algorithms; generalized linear models (GLMs, logistic regression), random forests (RF) and extreme gradient boosting (XGB).…”

Interpretable machine learning applied to on‐farm biosecurity and porcine reproductive and respiratory syndrome virus

“…Instead, it uses only the data provided to quantify and predict risk and interpret complex and non‐linear relationships that may not be captured otherwise (Silva et al., 2019). Additionally, as further farm data is collected, our approach will continue to develop its understanding of these relationships, improving its predictive performance (Rabinovich et al., 2021).…”

“…Despite the advantages over parametric models in relation to predictive performance, there are several relevant limitations to the machine learning methodology utilized here (Elith et al., 2008; Lucas, 2020; Machado et al., 2015; Rabinovich et al., 2021) including the presence of interactions among variables that may not be identified and the lack of an independent study sample, potentially impacting model performance and leading to spurious interpretations (Boulesteix et al., 2015; Oh, 2019; Strobl et al., 2009; Wright et al., 2016). The implementation of methods such as interaction forests and pairwise importance techniques improve the identification of interactions in machine learning algorithms (Hornung & Boulesteix, 2021; Wright et al., 2016), while individual conditional expectation (ICE) plots and the iBreakDown model are capable of accounting for known interactions in their post hoc interpretations (Biecek & Burzykowski, 2021; Goldstein et al., 2015).…”