DiffFit: Differentiable Fitting of Molecule Structures to a Cryo-EM Map - Laboratoire Interdisciplinaire des Sciences du Numérique
Conference Poster Year : 2024

DiffFit: Differentiable Fitting of Molecule Structures to a Cryo-EM Map

Abstract

We introduce DiffFit, a differentiable algorithm for fitting protein atomistic structures into experimental Cryo-Electron Microscopy (cryo-EM) volume maps. This process is crucial in structural biology for reconstructing large meso-scale models of complex protein assemblies and complete cellular structures. Unlike current methods requiring manual fitting followed by automated fine-tuning, DiffFit enables automatic fitting with visual inspection and interactive revision. Our approach employs differentiable 3D rigid transformations and a novel loss function based on multi-resolution volume arrays and negative space exploitation. Evaluations on three use cases using realistic datasets demonstrate that DiffFit significantly outperforms previous methods. DiffFit is available as an open-source plugin (github .

Fichier principal
Vignette du fichier
Luo_2024_DDF.pdf (8.59 Mo) Télécharger le fichier
Vignette du fichier
Luo_2024_DDF.jpg (6.87 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Format Figure, Image

Dates and versions

hal-04684705 , version 1 (03-09-2024)

Licence

Copyright

Identifiers

  • HAL Id : hal-04684705 , version 1

Cite

Deng Luo, Zainab Alsuwaykit, Dawar Khan, Ondřej Strnad, Tobias Isenberg, et al.. DiffFit: Differentiable Fitting of Molecule Structures to a Cryo-EM Map. ICML 2024 - Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators, Jul 2024, Vienna, Austria. article no. 32, 6 p. ⟨hal-04684705⟩
44 View
6 Download

Share

More