DeepCEL0 for 2D Single Molecule Localization in Fluorescence Microscopy

• URL: http://arxiv.org/abs/2107.02281v1
• Date: Mon, 5 Jul 2021 21:31:46 GMT
• Title: DeepCEL0 for 2D Single Molecule Localization in Fluorescence Microscopy
• Authors: Pasquale Cascarano, Maria Colomba Comes, Andrea Sebastiani, Arianna Mencattini, Elena Loli Piccolomini, Eugenio Martinelli
• Abstract summary: In fluorescence microscopy, Single Molecule localization Microscopy techniques aim at localizing with high precision high density fluorescent molecules. Super Resolution (SR) plays an important role in this field since it allows to go beyond the intrinsic light diffraction limit. We propose a deep learning-based algorithm for precise molecule localization of high density frames acquired by SMLM techniques.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In fluorescence microscopy, Single Molecule Localization Microscopy (SMLM) techniques aim at localizing with high precision high density fluorescent molecules by stochastically activating and imaging small subsets of blinking emitters. Super Resolution (SR) plays an important role in this field since it allows to go beyond the intrinsic light diffraction limit. In this work, we propose a deep learning-based algorithm for precise molecule localization of high density frames acquired by SMLM techniques whose $\ell_{2}$-based loss function is regularized by positivity and $\ell_{0}$-based constraints. The $\ell_{0}$ is relaxed through its Continuous Exact $\ell_{0}$ (CEL0) counterpart. The arising approach, named DeepCEL0, is parameter-free, more flexible, faster and provides more precise molecule localization maps if compared to the other state-of-the-art methods. We validate our approach on both simulated and real fluorescence microscopy data.

Related papers

• Text-Guided Multi-Property Molecular Optimization with a Diffusion Language Model [77.50732023411811]
  We propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM) TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions. Our approach surpasses state-of-the-art methods in optimizing molecular structural similarity and enhancing chemical properties on the benchmark dataset.
  arXiv  Detail & Related papers  (2024-10-17T14:30:27Z)
• CryoFM: A Flow-based Foundation Model for Cryo-EM Densities [50.291974465864364]
  We present CryoFM, a foundation model designed as a generative model, learning the distribution of high-quality density maps. Built on flow matching, CryoFM is trained to accurately capture the prior distribution of biomolecular density maps.
  arXiv  Detail & Related papers  (2024-10-11T08:53:58Z)
• Data-Efficient Molecular Generation with Hierarchical Textual Inversion [48.816943690420224]
  We introduce Hierarchical textual Inversion for Molecular generation (HI-Mol), a novel data-efficient molecular generation method. HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution. Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution.
  arXiv  Detail & Related papers  (2024-05-05T08:35:23Z)
• Localising two sub-diffraction emitters in 3D using quantum correlation microscopy [7.994006808120411]
  Quantum correlation microscopy provides diffraction-unlimited three-dimensional localisation for two emitters within a single diffraction-limited spot. Diffraction unlimited localisation is achieved using both intensity and photon correlation from Hanbury Brown and Twiss measurements at as few as four measurement locations.
  arXiv  Detail & Related papers  (2023-10-04T05:07:42Z)
• High-resolution 'magic'-field spectroscopy on trapped polyatomic molecules [62.997667081978825]
  Rapid progress in cooling and trapping of molecules has enabled first experiments on high resolution spectroscopy of trapped diatomic molecules. Extending this work to polyatomic molecules provides unique opportunities due to more complex geometries and additional internal degrees of freedom.
  arXiv  Detail & Related papers  (2021-10-21T15:46:17Z)
• Chemical-Reaction-Aware Molecule Representation Learning [88.79052749877334]
  We propose using chemical reactions to assist learning molecule representation. Our approach is proven effective to 1) keep the embedding space well-organized and 2) improve the generalization ability of molecule embeddings. Experimental results demonstrate that our method achieves state-of-the-art performance in a variety of downstream tasks.
  arXiv  Detail & Related papers  (2021-09-21T00:08:43Z)
• Ultracold $^{88}\rm{Sr}_2$ molecules in the absolute ground state [0.0]
  We report efficient all-optical creation of an ultracold gas of alkaline-earth-metal dimers in their absolute ground state. Our results pave the way for the use of alkaline-earth-metal dimers for high-precision spectroscopy.
  arXiv  Detail & Related papers  (2021-08-12T23:33:17Z)
• Linear probing of molecules at micrometric distances from a surface with sub-Doppler frequency resolution [0.0]
  We exploit the linearity and high-resolution of our technique to gain novel spectroscopic information on the $mathrmSF_6$ greenhouse gas. The natural extension of our work to thin-cells will allow compact frequency references and improved measurements of the Casimir-Polder interaction with molecules.
  arXiv  Detail & Related papers  (2021-06-13T09:49:23Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Spatially-Variant CNN-based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation in Optical Microscopy [6.09170287691728]
  We present a method that improves the resolution of light microscopy images of thin, yet non-flat objects. We estimate the parameters of a spatially-variant Point-Spread function (PSF) model using a Convolutional Neural Network (CNN) Our method recovers PSF parameters from the image itself with up to a squared Pearson correlation coefficient of 0.99 in ideal conditions.
  arXiv  Detail & Related papers  (2020-10-08T14:20:16Z)
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach [2.562811344441631]
  Gradient-domain machine learning (GDML) is an accurate and efficient approach to learn a molecular potential and associated force field. We demonstrate its application to learn an effective coarse-grained (CG) model from all-atom simulation data. Using ensemble learning and stratified sampling, we propose a data-efficient and memory-saving alternative.
  arXiv  Detail & Related papers  (2020-05-04T21:20:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.