An official website of the United States government
Multilevel modeling and multi-task learning are two widely used approaches for modeling nested (multi-level) data, which contain observations that can be clustered into groups, characterized by their group-level features. Despite the similarity of the problems they address, the explicit relationship between multilevel modeling and multi-task learning has not been carefully examined. In this paper, we present a comparative analysis between the two methods to illustrate their strengths and limitations when applied to two-level nested data. We provide a detailed analysis demonstrating the equivalence of their formulations under a mild condition from an optimization perspective. We also demonstrate their limitations in terms of their predictive performance and especially, their difficulty in identifying potential cross-scale interactions between the local and group-level features when applied to datasets with either a small number of groups or limited training examples per group. To overcome these limitations, we propose a novel method for disaggregating the coarse-scale values of the group-level features in the nested data. Experimental results on both synthetic and real-world data show that the disaggregated group-level features can help enhance the prediction accuracy of the models significantly and identify the cross-scale interactions more effectively.
more »
« less
Centering microbes in the emerging role of integrative biology in understanding environmental change
Synopsis We argue that the current environmental changes stressing the Earth’s biological systems urgently require study from an integrated perspective to reveal unexpected, cross-scale interactions, particularly between microbes and macroscale phenomena. Such interactions are the basis of a mechanistic understanding of the important connections between deforestation and emerging infectious disease, feedback between ecosystem disturbance and the gut microbiome, and the cross-scale effects of environmental pollutants. These kinds of questions can be answered with existing techniques and data, but a concerted effort is necessary to better coordinate studies and data sets from different disciplines to fully leverage their potential.
more »
« less
- Award ID(s):
- 1754783
- PAR ID:
- 10226302
- Date Published:
- Journal Name:
- Integrative and Comparative Biology
- ISSN:
- 1540-7063
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Muscle contraction results from force-generating cross-bridge interactions between myosin and actin. Cross-bridge cycling kinetics underlie fundamental contractile properties, such as active force production and energy utilization. Factors that influence cross-bridge kinetics at the molecular level propagate through the sarcomeres, cells and tissue to modulate whole-muscle function. Conversely, movement and changes in the muscle length can influence cross-bridge kinetics on the molecular level. Reduced, single-molecule and single-fibre experiments have shown that increasing the strain on cross-bridges may slow their cycling rate and prolong their attachment duration. However, whether these strain-dependent cycling mechanisms persist in the intact muscle tissue, which encompasses more complex organization and passive elements, remains unclear. To investigate this multi-scale relationship, we adapted traditional step-stretch protocols for use with mouse soleus muscle during isometric tetanic contractions, enabling novel estimates of length-dependent cross-bridge kinetics in the intact skeletal muscle. Compared to rates at the optimal muscle length ( L o ), we found that cross-bridge detachment rates increased by approximately 20% at 90% of L o (shorter) and decreased by approximately 20% at 110% of L o (longer). These data indicate that cross-bridge kinetics vary with whole-muscle length during intact, isometric contraction, which could intrinsically modulate force generation and energetics, and suggests a multi-scale feedback pathway between whole-muscle function and cross-bridge activity.more » « less
-
We conducted a cross-ecoregion study to test the hypothesis that N-fixation and denitrification would co-occur in streams and rivers across a range of reactive N concentrations. Between 2017 and 2019, we sampled 30 streams in 13 ecoregions, using chambers to quantify N-fixation using acetylene reduction and denitrification using acetylene block. 25 of the study streams were part of the National Ecological Observatory Network or the StreamPULSE network, which provided data on water temperature, light, nutrients, discharge and metabolism. Although N-fixation and denitrification occur under contrasting environmental conditions, we found that they co-occurred in ca. 40% of stream ecosystems surveyed, and microbes capable of carrying out each process were found in all surveyed streams. This dataset includes the chamber data used to calculate nitrogen fixation and denitrification rates, stream substrate information used to scale rates from substrate to whole-reach scale, and a variety of reach-to-landscape scale covariates used to evaluate predictors of rates across the study streams.more » « less
-
Adverse clinical events related to unsafe care are among the top ten causes of death in the U.S. Accurate modeling and prediction of clinical events from electronic health records (EHRs) play a crucial role in patient safety enhancement. An example is modeling de facto care pathways that characterize common step-by-step plans for treatment or care. However, clinical event data pose several unique challenges, including the irregularity of time intervals between consecutive events, the existence of cycles, periodicity, multi-scale event interactions, and the high computational costs associated with long event sequences. Existing neural temporal point processes (TPPs) methods do not effectively capture the multi-scale nature of event interactions, which is common in many real-world clinical applications. To address these issues, we propose the cross-temporal-scale transformer (XTSFormer), specifically designed for irregularly timed event data. Our model consists of two vital components: a novel Feature-based Cycle-aware Time Positional Encoding (FCPE) that adeptly captures the cyclical nature of time, and a hierarchical multi-scale temporal attention mechanism, where different temporal scales are determined by a bottom-up clustering approach. Extensive experiments on several real-world EHR datasets show that our XTSFormer outperforms multiple baseline methods.more » « less
-
Wolfe, Benjamin E. (Ed.)ABSTRACT Coupling remote sensing with microbial omics-based approaches provides a promising new frontier for scientists to scale microbial interactions across space and time. These data-rich, interdisciplinary methods allow us to better understand interactions between microbial communities and their environments and, in turn, their impact on ecosystem structure and function. Here, we highlight current and novel examples of applying remote sensing, machine learning, spatial statistics, and omics data approaches to marine, aquatic, and terrestrial systems. We emphasize the importance of integrating biochemical and spatiotemporal environmental data to move toward a predictive framework of microbiome interactions and their ecosystem-level effects. Finally, we emphasize lessons learned from our collaborative research with recommendations to foster productive and interdisciplinary teamwork.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1093/icb/icab047
