Artificial intelligence, deep convolutional neural networks, and deep learning are all niche terms that are increasingly appearing in scientific presentations as well as in the general media. In this review, we focus on deep learning and how it is applied to microscopy image data of cells and tissue samples. Starting with an analogy to neuroscience, we aim to give the reader an overview of the key concepts of neural networks, and an understanding of how deep learning differs from more classical approaches for extracting information from image data. We aim to increase the understanding of these methods, while highlighting considerations regarding input data requirements, computational resources, challenges, and limitations. We do not provide a full manual for applying these methods to your own data, but rather review previously published articles on deep learning in image cytometry, and guide the readers toward further reading on specific networks and methods, including new methods not yet applied to cytometry data. © 2018 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.
The quantification and identification of cellular phenotypes from high-content microscopy images has proven to be very useful for understanding biological activity in response to different drug treatments. The traditional approach has been to use classical image analysis to quantify changes in cell morphology, which requires several nontrivial and independent analysis steps. Recently, convolutional neural networks have emerged as a compelling alternative, offering good predictive performance and the possibility to replace traditional workflows with a single network architecture. In this study, we applied the pretrained deep convolutional neural networks ResNet50, InceptionV3, and InceptionResnetV2 to predict cell mechanisms of action in response to chemical perturbations for two cell profiling datasets from the Broad Bioimage Benchmark Collection. These networks were pretrained on ImageNet, enabling much quicker model training. We obtain higher predictive accuracy than previously reported, between 95% and 97%. The ability to quickly and accurately distinguish between different cell morphologies from a scarce amount of labeled data illustrates the combined benefit of transfer learning and deep convolutional neural networks for interrogating cell-based images.
Summary1. Partitioning biodiversity change spatially and temporally is required for effective management, both to determine whether action is required and whether it should be applied at a regional level or targeted more locally. As biodiversity is a multifaceted concept, comparative analyses of different indices, focussing on different components of biodiversity change (evenness vs. abundance), give better information than a single headline index. 2. We model changes in the spatial and temporal distribution of British breeding birds using generalized additive models applied to count data collected between 1994 and 2011. Abundance estimates, accounting for differences in detectability, are then used in communityspecific (farmland and woodland) biodiversity indices. Temporal trends in biodiversity, and change points in those trends, are assessed at different spatial scales. The geometric mean of relative abundance, a headline indicator of biodiversity change, is assessed together with a goodness-of-fit evenness measure focussing separately on the rare and common species in the communities. 3. Our analysis reveals predominantly declining trends in biodiversity indices for farmland and woodland bird communities in southern and eastern England, perhaps signalling environmental deterioration in this part of the country. Conversely, our results also show generally more positive trends in the north of Britain, consistent with north-south gradient expectations from the effects of climate change. We also reveal predominantly positive changes in evenness for the common species and negative changes in evenness for the rarer species in the communities, consistent with previously documented homogenization in bird communities. 4. Synthesis and applications. Bird populations are seen as good indicators of ecosystem health, and trends for different communities can be indicative of wider biodiversity changes within their respective habitats. However, temporal trends in biodiversity at the national level may miss opposing trends occurring at different locations within the nation. We develop methods that allow assessment of how temporal trends vary spatially and whether these trends differ for the rare and common species in the respective communities. Our methods may be used to test hypotheses about the processes that generate the trends.
The complexity of mathematical models of ecological dynamics varies greatly, and it is often difficult to judge what would be the optimal level of complexity in a particular case. Here we compare the parameter estimates, model fits, and predictive abilities of two models of metapopulation dynamics: a detailed individual‐based model (IBM) and a population‐based stochastic patch occupancy model (SPOM) derived from the IBM. The two models were fitted to a 17‐year time series of data for the Glanville fritillary butterfly (Melitaea cinxia) inhabiting a network of 72 small meadows. The data consisted of biannual counts of larval groups (IBM) and the annual presence or absence of local populations (SPOM). The models were fitted using a Bayesian state‐space approach with a hierarchical random effect structure to account for observational, demographic, and environmental stochasticities. The detection probability of larval groups (IBM) and the probability of false zeros of local populations (SPOM) in the observation models were simultaneously estimated from the time‐series data and independent control data. Prior distributions for dispersal parameters were obtained from a separate analysis of mark–recapture data. Both models fitted the data about equally, but the results were more precise for the IBM than for the SPOM. The two models yielded similar estimates for a random effect parameter describing habitat quality in each patch, which were correlated with independent empirical measures of habitat quality. The modeling results showed that variation in habitat quality influenced patch occupancy more through the effects on movement behavior at patch edges than on carrying capacity, whereas the latter influenced the mean population size in occupied patches. The IBM and the SPOM explained 63% and 45%, respectively, of the observed variation in the fraction of occupied habitat area among 75 independent patch networks not used in parameter estimation. We conclude that, while carefully constructed, detailed models can have better predictive ability than simple models, this advantage comes with the cost of greatly increased data requirements and computational challenges. Our results illustrate how complex models can be helpful in facilitating the construction of effective simpler models.
The extensive spatial and temporal coverage of many citizen science datasets (CSD) makes them appealing for use in species distribution modeling and forecasting. However, a frequent limitation is the inability to validate results. Here, we aim to assess the reliability of CSD for forecasting species occurrence in response to national forest management projections (representing 160,366 km2) by comparison against forecasts from a model based on systematically collected colonization–extinction data. We fitted species distribution models using citizen science observations of an old‐forest indicator fungus Phellinus ferrugineofuscus. We applied five modeling approaches (generalized linear model, Poisson process model, Bayesian occupancy model, and two MaxEnt models). Models were used to forecast changes in occurrence in response to national forest management for 2020‐2110. Forecasts of species occurrence from models based on CSD were congruent with forecasts made using the colonization–extinction model based on systematically collected data, although different modeling methods indicated different levels of change. All models projected increased occurrence in set‐aside forest from 2020 to 2110: the projected increase varied between 125% and 195% among models based on CSD, in comparison with an increase of 129% according to the colonization–extinction model. All but one model based on CSD projected a decline in production forest, which varied between 11% and 49%, compared to a decline of 41% using the colonization–extinction model. All models thus highlighted the importance of protected old forest for P. ferrugineofuscus persistence. We conclude that models based on CSD can reproduce forecasts from models based on systematically collected colonization–extinction data and so lead to the same forest management conclusions. Our results show that the use of a suite of models allows CSD to be reliably applied to land management and conservation decision making, demonstrating that widely available CSD can be a valuable forecasting resource.
Evolution of dispersal is affected by context-specific costs and benefits. One example is sex-biased dispersal in mammals and birds. While many such patterns have been described, the underlying mechanisms are poorly understood. Here, we study genetic and phenotypic traits that affect butterfly flight capacity and examine how these traits are related to dispersal in male and female Glanville fritillary butterflies (Melitaea cinxia). We performed two mark-recapture experiments to examine the associations of individuals' peak flight metabolic rate (MR(peak)) and Pgi genotype with their dispersal in the field. In a third experiment, we studied tethered flight in the laboratory. MR(peak) was negatively correlated with dispersal distance in males but the trend was positive in females, and the interaction between MR(peak) and sex was significant for long-distance dispersal. A similar but nonsignificant trend was found in relation to molecular variation at Pgi, which encodes a glycolytic enzyme: the genotype associated with high MR(peak) tended to be less dispersive in males but more dispersive in females. The same pattern was repeated in the tethered flight experiment: the relationship between MR(peak) and flight duration was positive in females but negative in males. These results suggest that females with high flight capacity are superior in among-population dispersal, which facilitates the spatial spreading of their reproductive effort. In contrast, males with high flight capacity may express territorial behaviour, and thereby increase the number of matings, whereas inferior males may be forced to disperse. Thus, flight capacity has opposite associations with dispersal rate in the two sexes.
The role of competition in structuring communities of herbivorous insects is still debated. Despite this, few studies have simultaneously investigated the strength of various forms of competition and their effect on community composition. In this study, we examine the extent to which different types of competition will affect the presence and abundance of individual leaf miner species in local communities on oak trees Quercus robur. We first use a laboratory experiment to quantify the strength of intra-and interspecific competition. We then conduct a large-scale field experiment to determine whether competition occurring in one year extends to the next. Finally, we use observational field data to examine the extent to which mechanisms of competition uncovered in the two experiments actually reflect into patterns of cooccurrence in nature. In our experiment, we found direct competition at the leaf-level to be stronger among conspecific than among heterospecific individuals. Indirect competition among conspecifics lowered the survival and weight of larvae of T. ekebladella, both at the branch and the tree-level. In contrast, indirect competition among heterospecifics was only detected in one out of three species pairs examined. In the field experiment, the presence of a given moth species in one year affected the relative abundance of leaf miner species in the next year. Nevertheless, patterns of competition observed in these experiments did not translate into repulsion among free-ranging leaf miners: conspecific larvae of four leafmining species were aggregated on the same trees, shoots and leaves. In contrast, heterospecific larvae were only aggregated at the tree-level. We propose that despite the fact that leaf miners do compete and that such effects extend through time, the incidence and strength of competition is relatively small at realistic densities. Hence, competition will likely be of minor importance in shaping the distribution of leaf miners in a natural setting.
Abstract. Understanding the relative importance of different ecological processes on the metapopulation dynamics of species is the basis for accurately forecasting metapopulation size in fragmented landscapes. Successful local colonization depends on both species dispersal range and how local habitat conditions affect establishment success. Moreover, there is limited understanding of the effects of different spatiotemporal landscape properties on future meta population size. We investigate which factors drive the future metapopulation size of the epiphytic model lichen species Lobaria pulmonaria in a managed forest landscape. First, we test the importance of dispersal and local conditions on the colonization-extinction dynamics of the species using Bayesian state space modelling of a large scale data set collected over a 10 yr period. Second, we test the importance of dispersal and establishment limitation in explaining establishment probability and subsequent local population growth, based on a 10 yr propagule sowing experiment. Third, we test how future metapopulation size is affected by different meta population and spatiotemporal landscape dynamics, using simulations with the metapopula tion models fitted to the empirical data. The colonization probability increased with tree inclination and connectivity, with a mean dispersal distance of 97 m (95% credible intervals, 5-530 m). Local extinctions were mainly deterministic set by tree mortality, but also by tree cutting by forestry. No experimental establishments took place on clearcuts, and in closed forest the establishment probability was higher on trees growing on moist than on dry mesic soils. The subsequent local population growth rate increased with increasing bark roughness. The simulations showed that the restricted dispersal range estimated (compared to non restricted dispersal range), and short tree rotation length (65 yr instead of 120) had approxi mately the same negative effects on future metapopulation size, while regeneration of trees creating a random tree pattern instead of an aggregated one had only some negative effect. However, using the colonization rate obtained with the experimentally added diaspores led to a considerable increase in metapopulation size, making the dispersal limitation of the species clear. The future metapopulation size is thus set by the number of host trees located in shady conditions, not isolated from occupied trees, and by the rotation length of these host trees.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.