Dataset Information

Automated discovery of food webs from ecological data using logic-based machine learning.

ABSTRACT: Networks of trophic links (food webs) are used to describe and understand mechanistic routes for translocation of energy (biomass) between species. However, a relatively low proportion of ecosystems have been studied using food web approaches due to difficulties in making observations on large numbers of species. In this paper we demonstrate that Machine Learning of food webs, using a logic-based approach called A/ILP, can generate plausible and testable food webs from field sample data. Our example data come from a national-scale Vortis suction sampling of invertebrates from arable fields in Great Britain. We found that 45 invertebrate species or taxa, representing approximately 25% of the sample and about 74% of the invertebrate individuals included in the learning, were hypothesized to be linked. As might be expected, detritivore Collembola were consistently the most important prey. Generalist and omnivorous carabid beetles were hypothesized to be the dominant predators of the system. We were, however, surprised by the importance of carabid larvae suggested by the machine learning as predators of a wide variety of prey. High probability links were hypothesized for widespread, potentially destabilizing, intra-guild predation; predictions that could be experimentally tested. Many of the high probability links in the model have already been observed or suggested for this system, supporting our contention that A/ILP learning can produce plausible food webs from sample data, independent of our preconceptions about "who eats whom." Well-characterised links in the literature correspond with links ascribed with high probability through A/ILP. We believe that this very general Machine Learning approach has great power and could be used to extend and test our current theories of agricultural ecosystem dynamics and function. In particular, we believe it could be used to support the development of a wider theory of ecosystem responses to environmental change.

SUBMITTER: Bohan DA

PROVIDER: S-EPMC3248413 | biostudies-literature | 2011

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated discovery of food webs from ecological data using logic-based machine learning.

Bohan David A DA Caron-Lormier Geoffrey G Muggleton Stephen S Raybould Alan A Tamaddoni-Nezhad Alireza A

PloS one 20111229 12

Networks of trophic links (food webs) are used to describe and understand mechanistic routes for translocation of energy (biomass) between species. However, a relatively low proportion of ecosystems have been studied using food web approaches due to difficulties in making observations on large numbers of species. In this paper we demonstrate that Machine Learning of food webs, using a logic-based approach called A/ILP, can generate plausible and testable food webs from field sample data. Our exa ...[more]

PMID: 22242111

Similar Datasets

Project description:BackgroundIn recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on the discovery for potential biomarkers in the human microbiome using machine learning tools has produced positive outcomes. Despite the promising results, several issues can still be found in these studies such as datasets with small number of samples, inconsistent results, lack of uniform processing and methodologies, and other additional factors lead to lack of reproducibility in biomedical research. In this work, we propose a methodology that combines the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) in multiple datasets to increase reproducibility and obtain robust and reliable results in biomedical research.ResultsThree experiments were performed analyzing microbiome data from patients/cases in Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). In each experiment, we found a biomarker signature in one dataset and applied to 2 other as further validation. The effectiveness of the proposed methodology was compared with other feature selection methods such as K-Best with F-score and random selection as a base line. The Area Under the Curve (AUC) was employed as a measure of diagnostic accuracy and used as a metric for comparing the results of the proposed methodology with other feature selection methods. Additionally, we use the Matthews Correlation Coefficient (MCC) as a metric to evaluate the performance of the methodology as well as for comparison with other feature selection methods.ConclusionsWe developed a methodology for reproducible biomarker discovery for 16s rRNA microbiome sequence analysis, addressing the issues related with data dimensionality, inconsistent results and validation across independent datasets. The findings from the three experiments, across 9 different datasets, show that the proposed methodology achieved higher accuracy compared to other feature selection methods. This methodology is a first approach to increase reproducibility, to provide robust and reliable results.

Project description:The framework of ecological stoichiometry was developed primarily within the context of "green" autotroph-based food webs. While stoichiometric principles also apply in "brown" detritus-based systems, these systems have been historically understudied and differ from green ones in several important aspects including carbon (C) quality and the nutrient [nitrogen (N) and phosphorus (P)] contents of food resources for consumers. In this paper, we review work over the last decade that has advanced the application of ecological stoichiometry from green to brown food webs, focusing on freshwater ecosystems. We first review three focal areas where green and brown food webs differ: (1) bottom-up controls by light and nutrient availability, (2) stoichiometric constraints on consumer growth and nutritional regulation, and (3) patterns in consumer-driven nutrient dynamics. Our review highlights the need for further study of how light and nutrient availability affect autotroph-heterotroph interactions on detritus and the subsequent effects on consumer feeding and growth. To complement this conceptual review, we formally quantified differences in stoichiometric principles between green and brown food webs using a meta-analysis across feeding studies of freshwater benthic invertebrates. From 257 datasets collated across 46 publications and several unpublished studies, we compared effect sizes (Pearson's r) of resource N:C and P:C on growth, consumption, excretion, and egestion between herbivorous and detritivorous consumers. The meta-analysis revealed that both herbivore and detritivore growth are limited by resource N:C and P:C contents, but effect sizes only among detritivores were significantly above zero. Consumption effect sizes were negative among herbivores but positive for detritivores in the case of both N:C and P:C, indicating distinct compensatory feeding responses across resource stoichiometry gradients. Herbivore P excretion rates responded significantly positively to resource P:C, whereas detritivore N and P excretion did not respond; detritivore N and P egestion responded positively to resource N:C and P:C, respectively. Our meta-analysis highlights resource N and P contents as broadly limiting in brown and green benthic food webs, but indicates contrasting mechanisms of limitation owing to differing consumer regulation. We suggest that green and brown food webs share fundamental stoichiometric principles, while identifying specific differences toward applying ecological stoichiometry across ecosystems.

Dataset Information

Automated discovery of food webs from ecological data using logic-based machine learning.

Publications

Automated discovery of food webs from ecological data using logic-based machine learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets