https://3demmethods.i2pc.es/index.php?action=history&feed=atom&title=2022Wu_Manifold 2026-05-24T21:07:05Z Revision history for this page on the wiki MediaWiki 1.44.2 https://3demmethods.i2pc.es/index.php?title=2022Wu_Manifold&diff=4329&oldid=prev 2023-06-14T08:44:33Z

<p>Created page with &quot;== Citation == Wu, Zhaolong / Chen, Enbo / Zhang, Shuwen / Ma, Yinping / Mao, Youdong Visualizing conformational space of functional biomolecular complexes by deep manifold...&quot;</p> <p><b>New page</b></p><div>== Citation ==<br /> <br /> Wu, Zhaolong / Chen, Enbo / Zhang, Shuwen / Ma, Yinping / Mao, Youdong <br /> Visualizing conformational space of functional biomolecular complexes by deep manifold learning <br /> 2022. Intl. J. of Molecular Sciences, Vol. 23, No. 16, p. 8872 <br /> <br /> == Abstract ==<br /> <br /> The cellular functions are executed by biological macromolecular complexes in nonequilibrium<br /> dynamic processes, which exhibit a vast diversity of conformational states. Solving the<br /> conformational continuum of important biomolecular complexes at the atomic level is essential to<br /> understanding their functional mechanisms and guiding structure-based drug discovery. Here, we<br /> introduce a deep manifold learning framework, named AlphaCryo4D, which enables atomic-level<br /> cryogenic electron microscopy (cryo-EM) reconstructions that approximately visualize the conformational<br /> space of biomolecular complexes of interest. AlphaCryo4D integrates 3D deep residual<br /> learning with manifold embedding of pseudo-energy landscapes, which simultaneously improves 3D<br /> classification accuracy and reconstruction resolution via an energy-based particle-voting algorithm. In<br /> blind assessments using simulated heterogeneous datasets, AlphaCryo4D achieved 3D classification<br /> accuracy three times those of alternative methods and reconstructed continuous conformational<br /> changes of a 130-kDa protein at sub-3 Å resolution. By applying this approach to analyze several<br /> experimental datasets of the proteasome, ribosome and spliceosome, we demonstrate its potential<br /> generality in exploring hidden conformational space or transient states of macromolecular complexes<br /> that remain hitherto invisible. Integration of this approach with time-resolved cryo-EM further allows<br /> visualization of conformational continuum in a nonequilibrium regime at the atomic level, thus<br /> potentially enabling therapeutic discovery against highly dynamic biomolecular targets.<br /> <br /> == Keywords ==<br /> <br /> == Links ==<br /> <br /> https://www.mdpi.com/1422-0067/23/16/8872<br /> <br /> == Related software ==<br /> <br /> == Related methods ==<br /> <br /> == Comments ==</div>

WikiSysop