Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning
The cellular functions are executed by biological macromolecular complexes in nonequilibrium dynamic processes, which exhibit a vast diversity of conformational states. Solving the conformational continuum of important biomolecular complexes at the atomic level is essential to understanding their fu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/16/8872 |
| _version_ | 1797409887268896768 |
|---|---|
| author | Zhaolong Wu Enbo Chen Shuwen Zhang Yinping Ma Youdong Mao |
| author_facet | Zhaolong Wu Enbo Chen Shuwen Zhang Yinping Ma Youdong Mao |
| author_sort | Zhaolong Wu |
| collection | DOAJ |
| description | The cellular functions are executed by biological macromolecular complexes in nonequilibrium dynamic processes, which exhibit a vast diversity of conformational states. Solving the conformational continuum of important biomolecular complexes at the atomic level is essential to understanding their functional mechanisms and guiding structure-based drug discovery. Here, we introduce a deep manifold learning framework, named AlphaCryo4D, which enables atomic-level cryogenic electron microscopy (cryo-EM) reconstructions that approximately visualize the conformational space of biomolecular complexes of interest. AlphaCryo4D integrates 3D deep residual learning with manifold embedding of pseudo-energy landscapes, which simultaneously improves 3D classification accuracy and reconstruction resolution via an energy-based particle-voting algorithm. In blind assessments using simulated heterogeneous datasets, AlphaCryo4D achieved 3D classification accuracy three times those of alternative methods and reconstructed continuous conformational changes of a 130-kDa protein at sub-3 Å resolution. By applying this approach to analyze several experimental datasets of the proteasome, ribosome and spliceosome, we demonstrate its potential generality in exploring hidden conformational space or transient states of macromolecular complexes that remain hitherto invisible. Integration of this approach with time-resolved cryo-EM further allows visualization of conformational continuum in a nonequilibrium regime at the atomic level, thus potentially enabling therapeutic discovery against highly dynamic biomolecular targets. |
| first_indexed | 2024-03-09T04:20:59Z |
| format | Article |
| id | doaj.art-7e38f6a68db54b4cbf54f043a7d8bed1 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T04:20:59Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-7e38f6a68db54b4cbf54f043a7d8bed12023-12-03T13:46:50ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-08-012316887210.3390/ijms23168872Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold LearningZhaolong Wu0Enbo Chen1Shuwen Zhang2Yinping Ma3Youdong Mao4State Key Laboratory for Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing 100871, ChinaState Key Laboratory for Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing 100871, ChinaState Key Laboratory for Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing 100871, ChinaComputing Center, Peking University, Beijing 100871, ChinaState Key Laboratory for Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing 100871, ChinaThe cellular functions are executed by biological macromolecular complexes in nonequilibrium dynamic processes, which exhibit a vast diversity of conformational states. Solving the conformational continuum of important biomolecular complexes at the atomic level is essential to understanding their functional mechanisms and guiding structure-based drug discovery. Here, we introduce a deep manifold learning framework, named AlphaCryo4D, which enables atomic-level cryogenic electron microscopy (cryo-EM) reconstructions that approximately visualize the conformational space of biomolecular complexes of interest. AlphaCryo4D integrates 3D deep residual learning with manifold embedding of pseudo-energy landscapes, which simultaneously improves 3D classification accuracy and reconstruction resolution via an energy-based particle-voting algorithm. In blind assessments using simulated heterogeneous datasets, AlphaCryo4D achieved 3D classification accuracy three times those of alternative methods and reconstructed continuous conformational changes of a 130-kDa protein at sub-3 Å resolution. By applying this approach to analyze several experimental datasets of the proteasome, ribosome and spliceosome, we demonstrate its potential generality in exploring hidden conformational space or transient states of macromolecular complexes that remain hitherto invisible. Integration of this approach with time-resolved cryo-EM further allows visualization of conformational continuum in a nonequilibrium regime at the atomic level, thus potentially enabling therapeutic discovery against highly dynamic biomolecular targets.https://www.mdpi.com/1422-0067/23/16/8872AlphaCryo4Dcryogenic electron microscopybiomolecular complexstructural dynamicsconformational spaceenergy landscape |
| spellingShingle | Zhaolong Wu Enbo Chen Shuwen Zhang Yinping Ma Youdong Mao Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning International Journal of Molecular Sciences AlphaCryo4D cryogenic electron microscopy biomolecular complex structural dynamics conformational space energy landscape |
| title | Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning |
| title_full | Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning |
| title_fullStr | Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning |
| title_full_unstemmed | Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning |
| title_short | Visualizing Conformational Space of Functional Biomolecular Complexes by Deep Manifold Learning |
| title_sort | visualizing conformational space of functional biomolecular complexes by deep manifold learning |
| topic | AlphaCryo4D cryogenic electron microscopy biomolecular complex structural dynamics conformational space energy landscape |
| url | https://www.mdpi.com/1422-0067/23/16/8872 |
| work_keys_str_mv | AT zhaolongwu visualizingconformationalspaceoffunctionalbiomolecularcomplexesbydeepmanifoldlearning AT enbochen visualizingconformationalspaceoffunctionalbiomolecularcomplexesbydeepmanifoldlearning AT shuwenzhang visualizingconformationalspaceoffunctionalbiomolecularcomplexesbydeepmanifoldlearning AT yinpingma visualizingconformationalspaceoffunctionalbiomolecularcomplexesbydeepmanifoldlearning AT youdongmao visualizingconformationalspaceoffunctionalbiomolecularcomplexesbydeepmanifoldlearning |