Automated and autonomous experiments in electron and scanning probe microscopy
Machine learning and artificial intelligence (ML/AI) are rapidly becoming an indispensable
part of physics research, with domain applications ranging from theory and materials …
part of physics research, with domain applications ranging from theory and materials …
CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks
Cryo-electron microscopy (cryo-EM) single-particle analysis has proven powerful in
determining the structures of rigid macromolecules. However, many imaged protein …
determining the structures of rigid macromolecules. However, many imaged protein …
Unsupervised deep learning methods for biological image reconstruction and enhancement: An overview from a signal processing perspective
Recently, deep learning (DL) approaches have become the main research frontier for
biological image reconstruction and enhancement problems thanks to their high …
biological image reconstruction and enhancement problems thanks to their high …
Adversarial generation of continuous images
In most existing learning systems, images are typically viewed as 2D pixel arrays. However,
in another paradigm gaining popularity, a 2D image is represented as an implicit neural …
in another paradigm gaining popularity, a 2D image is represented as an implicit neural …
Improved transformer for high-resolution gans
Attention-based models, exemplified by the Transformer, can effectively model long range
dependency, but suffer from the quadratic complexity of self-attention operation, making …
dependency, but suffer from the quadratic complexity of self-attention operation, making …
Learning structural heterogeneity from cryo-electron sub-tomograms with tomoDRGN
BM Powell, JH Davis - Nature Methods, 2024 - nature.com
Cryo-electron tomography (cryo-ET) enables observation of macromolecular complexes in
their native, spatially contextualized cellular environment. Cryo-ET processing software to …
their native, spatially contextualized cellular environment. Cryo-ET processing software to …
A multi-encoder variational autoencoder controls multiple transformational features in single-cell image analysis
Image-based cell phenoty** relies on quantitative measurements as encoded
representations of cells; however, defining suitable representations that capture complex …
representations of cells; however, defining suitable representations that capture complex …
Amortized inference for heterogeneous reconstruction in cryo-em
Cryo-electron microscopy (cryo-EM) is an imaging modality that provides unique insights
into the dynamics of proteins and other building blocks of life. The algorithmic challenge of …
into the dynamics of proteins and other building blocks of life. The algorithmic challenge of …
Computational methods for single-particle electron cryomicroscopy
A Singer, FJ Sigworth - Annual review of biomedical data …, 2020 - annualreviews.org
Single-particle electron cryomicroscopy (cryo-EM) is an increasingly popular technique for
elucidating the three-dimensional (3D) structure of proteins and other biologically significant …
elucidating the three-dimensional (3D) structure of proteins and other biologically significant …
Parsnip: Generative models of transient light curves with physics-enabled deep learning
K Boone - The Astronomical Journal, 2021 - iopscience.iop.org
We present a novel method to produce empirical generative models of all kinds of
astronomical transients from data sets of unlabeled light curves. Our hybrid model, which we …
astronomical transients from data sets of unlabeled light curves. Our hybrid model, which we …