SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08138 · ECCV · 2022

CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images

Nina Miolane, Julien Martel, Gordon Wetzstein, Axel Levy, Frédéric Poitevin, Youssef Nashed, Ariana Peck, Daniel Ratner, Mike Dunne

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 13 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
compSPI/cryoAI canonical 12 of 13
FunctionStatusWhere it lives
euler_angles2matrix Ran compSPI/cryoAI/src/geom_utils.py
code served (permissive licence) · get_code("ffbf3a813bdbc33e")
fourier_to_primal_2D Ran compSPI/cryoAI/src/ctf_utils.py
code served (permissive licence) · get_code("0fe6c61e1eda758a")
get_power Ran compSPI/cryoAI/src/dataio.py
code served (permissive licence) · get_code("dcd0b9b5b77266e0")
get_ref_matrix Ran compSPI/cryoAI/src/geom_utils.py
code served (permissive licence) · get_code("88117ba9f8e95257")
get_rotation_accuracy Ran compSPI/cryoAI/src/geom_utils.py
code served (permissive licence) · get_code("b14237dcb152fb9a")
imag Ran compSPI/cryoAI/src/loss_utils.py
code served (permissive licence) · get_code("4b1849f54b1662c2")
layer_factory Ran compSPI/cryoAI/src/ml_modules.py
code served (permissive licence) · get_code("44016b212e533147")
pairwise_cos_sim Ran compSPI/cryoAI/src/loss_utils.py
code served (permissive licence) · get_code("9a435ee22ee796f8")
primal_to_fourier_2D Ran compSPI/cryoAI/src/ctf_utils.py
code served (permissive licence) · get_code("af24a395eb0623d7")
primal_to_fourier_3D Ran compSPI/cryoAI/src/ctf_utils.py
code served (permissive licence) · get_code("39ca2f4770ffd96b")
real Ran compSPI/cryoAI/src/loss_utils.py
code served (permissive licence) · get_code("d39b04695bee5dd0")
which_half_space Ran compSPI/cryoAI/src/ml_modules.py
code served (permissive licence) · get_code("a0706e978251531b")
build_model_fouriernet Not yet run compSPI/cryoAI/src/ml_modules.py
code served (permissive licence) · get_code("aa16d674e221a373")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Cryo-electron microscopy (cryo-EM) has become a tool of fundamental importance in structural biology, helping us understand the basic building blocks of life. The algorithmic challenge of cryo-EM is to jointly estimate the unknown 3D poses and the 3D electron scattering potential of a biomolecule from millions of extremely noisy 2D images. Existing reconstruction algorithms, however, cannot easily keep pace with the rapidly growing size of cryo-EM datasets due to their high computational and memory cost. We introduce cryoAI, an ab initio reconstruction algorithm for homogeneous conformations that uses direct gradient-based optimization of particle poses and the electron scattering potential from single-particle cryo-EM data. CryoAI combines a learned encoder that predicts the poses of each particle image with a physicsbased decoder to aggregate each particle image into an implicit representation of the scattering potential volume. This volume is stored in the Fourier domain for computational efficiency and leverages a modern coordinate network architecture for memory efficiency. Combined with a symmetric loss function, this framework achieves results of a quality on par with state-of-the-art cryo-EM solvers for both simulated and experimental data, one order of magnitude faster for large datasets and with significantly lower memory requirements than existing methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.08138")
get_code_for_paper("2203.08138")
have("2203.08138")

Connect an agent — have() is free.