An official website of the United States government
Abstract MotivationNeural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet). ResultsWe evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications. Availability and implementationSource code of CFNet is available at: https://github.com/bchidest/CFNet. Supplementary informationSupplementary data are available at Bioinformatics online.
more »
« less
Analytical advances alleviate model misspecification in non-Brownian multivariate comparative methods
Abstract Adams and Collyer argue that contemporary multivariate (Gaussian) phylogenetic comparative methods are prone to favouring more complex models of evolution and sometimes rotation invariance can be an issue. Here we dissect the concept of rotation invariance and point out that, depending on the understanding, this can be an issue with any method that relies on numerical instead of analytical estimation approaches. We relate this to the ongoing discussion concerning phylogenetic principal component analysis. Contrary to what Adams and Collyer found, we do not observe a bias against the simpler Brownian motion process in simulations when we use the new, improved, likelihood evaluation algorithm employed by mvSLOUCH, which allows for studying much larger phylogenies and more complex model setups.
more »
« less
- Award ID(s):
- 2225683
- PAR ID:
- 10493217
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Evolution
- Volume:
- 78
- Issue:
- 3
- ISSN:
- 0014-3820
- Format(s):
- Medium: X Size: p. 389-400
- Size(s):
- p. 389-400
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Recent studies have revealed the presence of a complex freshwater system underlying the Aurora Subglacial Basin (ASB), a region of East Antarctica that contains ∼7 m of global sea level potential in ice mainly grounded below sea level. However, the impact that subglacial freshwater has on driving the evolution of the dynamic outlet glaciers that drain this basin has yet to be tested in a coupled ice sheet‐subglacial hydrology numerical modeling framework. Here, we project the evolution of the primary outlet glaciers draining the ASB (Moscow University Ice Shelf, Totten, Vanderford, and Adams Glaciers) in response to an evolving subglacial hydrology system and to ocean forcing through 2100, following low and high CMIP6 emission scenarios. By 2100, ice‐hydrology feedbacks enhance the ASB's 2100 sea level contribution by ∼30% (7.50–9.80 mm) in high emission scenarios and accelerate the retreat of Totten Glacier's main ice stream by 25 years. Ice‐hydrology feedbacks are particularly influential in the retreat of the Vanderford and Adams Glaciers, driving an additional 10 km of retreat in fully coupled simulations relative to uncoupled simulations. Hydrology‐driven ice shelf melt enhancements are the primary cause of domain‐wide mass loss in low emission scenarios, but are secondary to ice sheet frictional feedbacks under high emission scenarios. The results presented here demonstrate that ice‐subglacial hydrology interactions can significantly accelerate retreat of dynamic Antarctic glaciers and that future Antarctic sea level assessments that do not take these interactions into account might be severely underestimating Antarctic Ice Sheet mass loss.more » « less
-
A<sc>bstract</sc> By adapting previously known arguments concerning Ricci flow and thec-theorem, we give a direct proof that in a two-dimensional sigma-model with compact target space, scale invariance implies conformal invariance in perturbation theory. This argument, which applies to a general sigma-model constructed with a target space metric andB-field, is in accord with a more general proof in the literature that applies to arbitrary two-dimensional quantum field theories. Models with extended supersymmetry and aB-field are known to provide interesting test cases for the relation between scale invariance and conformal invariance in sigma-model perturbation theory. We give examples showing that in such models, the obstructions to conformal invariance suggested by general arguments can actually occur in models with target spaces that are not compact or complete. Thus compactness of the target space, or at least a suitable condition of completeness, is necessary as well as sufficient to ensure that scale invariance implies conformal invariance in models of this type.more » « less
-
Abstract We prove that the classical map comparing Adams’ cobar construction on the singular chains of a pointed space and the singular cubical chains on its based loop space is a quasi-isomorphism preserving explicitly defined monoidal$$E_\infty $$-coalgebra structures. This contribution extends to its ultimate conclusion a result of Baues, stating that Adams’ map preserves monoidal coalgebra structures.more » « less
-
The evolution of molecular and phenotypic traits is commonly modelled using Markov processes along a phylogeny. This phylogeny can be a tree, or a network if it includes reticulations, representing events such as hybridization or admixture. Computing the likelihood of data observed at the leaves is costly as the size and complexity of the phylogeny grows. Efficient algorithms exist for trees, but cannot be applied to networks. We show that a vast array of models for trait evolution along phylogenetic networks can be reformulated as graphical models, for which efficient belief propagation algorithms exist. We provide a brief review of belief propagation on general graphical models, then focus on linear Gaussian models for continuous traits. We show how belief propagation techniques can be applied for exact or approximate (but more scalable) likelihood and gradient calculations, and prove novel results for efficient parameter inference of some models. We highlight the possible fruitful interactions between graphical models and phylogenetic methods. For example, approximate likelihood approaches have the potential to greatly reduce computational costs for phylogenies with reticulations. This article is part of the theme issue ‘“A mathematical theory of evolution”: phylogenetic models dating back 100 years’.more » « less
