Laurène Donati
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Laurène Donati has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Michael Unser
Biomedical Imaging Group, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
6 shared publications - Daniel Sage
Biomedical Imaging Group and Center for Imaging, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland.
2 shared publications - Harshit Gupta
EDEE, Ecole Polytechnique Federale de Lausanne Faculte des Sciences et Techniques de l'Ingenieur, 111838 Lausanne, Vaud Switzerland 1015
2 shared publications Masih Nilchian
Biomedical Imaging Group, École polytechnique fédérale de Lausanne (EPFL), Station 17, CH-1015 Lausanne, Switzerland
2 shared publications- Michael Thompson McCann
Theoretical Division, Los Alamos National Laboratory, Los Alamos, NM, USA
2 shared publications - Arne Seitz
Faculty of Life Sciences, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
1 shared publication
Latest Publications
- Open Access
- 13 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 759-774
CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial Learning
We present CryoGAN, a new paradigm for single-particle cryo-electron microscopy (cryo-EM) reconstruction based on unsupervised deep adversarial learning. In single-particle cryo-EM, the structure of a biomolecule needs to be reconstructed from a large set of noisy tomographic projections with unknown orientations. Current reconstruction techniques are based on a marginalized maximum-likelihood formulation that requires calculations over the set of all possible poses for each projection image, a computationally demanding procedure. Our approach is to seek a 3D structure that has simulated projections that match the real data in a distributional sense, thereby sidestepping pose estimation or marginalization. We prove that, in an idealized mathematical model of cryo-EM, this approach results in recovery of the correct structure. Motivated by distribution matching, we propose CryoGAN, a specialized GAN that consists of a 3D structure, a cryo-EM physics simulator, and a discriminator neural network. During reconstruction, the 3D structure is optimized so that its projections obtained through the simulator resemble real data (to the discriminator). Simultaneously, the discriminator is trained to distinguish real projections from simulated projections. CryoGAN takes as input only real projection images and the distribution of the cryo-EM imaging parameters. It involves neither prior training nor an initial estimation of the 3D structure. CryoGAN currently achieves a 10.8 Å resolution on a realistic synthetic dataset. Preliminary results on experimental β-galactosidase and 80S ribosome data demonstrate the ability of CryoGAN to exploit data statistics under standard experimental imaging conditions. We believe that this paradigm opens the door to a family of novel likelihood-free algorithms for cryo-EM reconstruction.
- 13 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 7 (25730436) , 759-774
Open AccessCryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial Learning
We present CryoGAN, a new paradigm for single-particle cryo-electron microscopy (cryo-EM) reconstruction based on unsupervised deep adversarial learning. In single-particle cryo-EM, the structure of a biomolecule needs to be reconstructed from a large set of noisy tomographic projections with unknown orientations. Current reconstruction techniques are based on a marginalized maximum-likelihood formulation that requires calculations over the set of all possible poses for each projection image, a computationally demanding procedure. Our approach is to seek a 3D structure that has simulated projections that match the real data in a distributional sense, thereby sidestepping pose estimation or marginalization. We prove that, in an idealized mathematical model of cryo-EM, this approach results in recovery of the correct structure. Motivated by distribution matching, we propose CryoGAN, a specialized GAN that consists of a 3D structure, a cryo-EM physics simulator, and a discriminator neural network. During reconstruction, the 3D structure is optimized so that its projections obtained through the simulator resemble real data (to the discriminator). Simultaneously, the discriminator is trained to distinguish real projections from simulated projections. CryoGAN takes as input only real projection images and the distribution of the cryo-EM imaging parameters. It involves neither prior training nor an initial estimation of the 3D structure. CryoGAN currently achieves a 10.8 Å resolution on a realistic synthetic dataset. Preliminary results on experimental β-galactosidase and 80S ribosome data demonstrate the ability of CryoGAN to exploit data statistics under standard experimental imaging conditions. We believe that this paradigm opens the door to a family of novel likelihood-free algorithms for cryo-EM reconstruction.
- Open Access
CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM via Deep Adversarial Learning
We present CryoGAN, a new paradigm for single-particle cryo-EM reconstruction based on unsupervised deep adversarial learning. The major challenge in single-particle cryo-EM is that the imaged particles have unknown poses. Current reconstruction techniques are based on a marginalized maximum-likelihood formulation that requires calculations over the set of all possible poses for each projection image, a computationally demanding procedure. CryoGAN sidesteps this problem by using a generative adversarial network (GAN) to learn the 3D structure that has simulated projections that most closely match the real data in a distributional sense. The architecture of CryoGAN resembles that of standard GAN, with the twist that the generator network is replaced by a model of the cryo-EM image acquisition process. CryoGAN is an unsupervised algorithm that only demands projection images and an estimate of the contrast transfer function parameters. No initial volume estimate or prior training is needed. Moreover, CryoGAN requires minimal user interaction and can provide reconstructions in a matter of hours on a high-end GPU. In addition, we provide sound mathematical guarantees on the recovery of the correct structure. CryoGAN currently achieves a 8.6 Å resolution on a realistic synthetic dataset. Preliminary results on real β -galactosidase data demonstrate CryoGAN’s ability to exploit data statistics under standard experimental imaging conditions. We believe that this paradigm opens the door to a family of novel likelihood-free algorithms for cryo-EM reconstruction.
Open AccessCryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM via Deep Adversarial Learning
We present CryoGAN, a new paradigm for single-particle cryo-EM reconstruction based on unsupervised deep adversarial learning. The major challenge in single-particle cryo-EM is that the imaged particles have unknown poses. Current reconstruction techniques are based on a marginalized maximum-likelihood formulation that requires calculations over the set of all possible poses for each projection image, a computationally demanding procedure. CryoGAN sidesteps this problem by using a generative adversarial network (GAN) to learn the 3D structure that has simulated projections that most closely match the real data in a distributional sense. The architecture of CryoGAN resembles that of standard GAN, with the twist that the generator network is replaced by a model of the cryo-EM image acquisition process. CryoGAN is an unsupervised algorithm that only demands projection images and an estimate of the contrast transfer function parameters. No initial volume estimate or prior training is needed. Moreover, CryoGAN requires minimal user interaction and can provide reconstructions in a matter of hours on a high-end GPU. In addition, we provide sound mathematical guarantees on the recovery of the correct structure. CryoGAN currently achieves a 8.6 Å resolution on a realistic synthetic dataset. Preliminary results on real β -galactosidase data demonstrate CryoGAN’s ability to exploit data statistics under standard experimental imaging conditions. We believe that this paradigm opens the door to a family of novel likelihood-free algorithms for cryo-EM reconstruction.
- Open Access
DeepImageJ: A user-friendly environment to run deep learning models in ImageJ
DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learn ing (DL) models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to the largest bioimage repository of pre-trained DL models (BioImage Model Zoo). Hence, non-experts can easily perform common image processing tasks in life-science research with DL-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. DeepImageJ is compatible with existing state-of-the-art solutions and it is equipped with utility tools for developers to include new models. Very recently, several train ing frameworks have adopted the deepImageJ format to deploy their work in one of the most used software in the field (ImageJ). Beyond its direct use, we expect deepImageJ to contribute to the broader dissemination and reuse of DL models in life-sciences applications and bioimage informatics.
Open AccessDeepImageJ: A user-friendly environment to run deep learning models in ImageJ
DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learn ing (DL) models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to the largest bioimage repository of pre-trained DL models (BioImage Model Zoo). Hence, non-experts can easily perform common image processing tasks in life-science research with DL-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. DeepImageJ is compatible with existing state-of-the-art solutions and it is equipped with utility tools for developers to include new models. Very recently, several train ing frameworks have adopted the deepImageJ format to deploy their work in one of the most used software in the field (ImageJ). Beyond its direct use, we expect deepImageJ to contribute to the broader dissemination and reuse of DL models in life-sciences applications and bioimage informatics.
- Open Access
- 1 December 2018
- Published by Elsevier in Journal of Structural Biology
- Vol. 204 (3) , 543-554
Fast multiscale reconstruction for Cryo-EM
- 1 December 2018
- Published by Elsevier in Journal of Structural Biology
- Vol. 204 (3) , 543-554
Open AccessFast multiscale reconstruction for Cryo-EM
- Open Access
- 1 August 2017
- Published by Elsevier in Ultramicroscopy
- Vol. 179, 47-56
Compressed sensing for STEM tomography
- 1 August 2017
- Published by Elsevier in Ultramicroscopy
- Vol. 179, 47-56
Open AccessCompressed sensing for STEM tomography
- Top Cited PapersOpen Access
DeconvolutionLab2: An open-source software for deconvolution microscopy
Top Cited PapersOpen AccessDeconvolutionLab2: An open-source software for deconvolution microscopy