Cryo-Electron Microscopy (CryoEM) Single Particle Analysis (SPA) is pivotal for elucidating protein structures and their conformational dynamics. Several critical steps are required to obtain accurate maps. First, the ab initio relative orientations and shifts between images must be determined. Second, the common issue of specimens presenting a preferred orientation should be adequately addressed. Third, all of the above must account for particle flexibility and sample heterogeneity. Additionally, these steps are interrelated, making the search for all these parameters a real challenge when considering convergence robustness. In this context, we present ReconSIREN, a novel deep learning framework that addresses the key steps outlined before in an ab initio manner while greatly minimizing one of the most important practical burdens in SPA, namely the errors introduced in the CryoEM maps by the existence of preferred orientations; the latter is achieved by a change of the optimization approach that avoids the so-called “attraction problem”, and by the introduction of a new type of geometrical priors. It does so fully ab initio, using deep learning training/inference steps without resorting to more traditional optimization approaches, and generating highly accurate initial reconstructions. We present maps as both homogeneous (consensus) maps and a full conformational landscape for analyzing flexibility and heterogeneity. Thanks to its Mixture-of-Experts (MoE) architecture, ReconSIREN distributes the estimation workload across independent experts, improving optimization efficiency and simplifying the process.
Single-particle cryo-electron microscopy (cryo-EM) relies on mature computational tools, but experts must still inspect intermediate results, choose among alternative processing routes, and decide when earlier choices should be revised. Here we present CryoPilot, a system of two language-model agents that carries cryo-...
Pranav Punuru, T. Klose, D. Kihara· bioRxiv· 0 citations
Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab initio accuracy. They decompose total configuration energies into simple effective interactions whose parameters are traditionally assigned based on atom or bond types, enabli...
Berkay Gunes, Leif Seute, Jigyasa Nigam et al.· 0 citations
The EMber family of vision transformers are introduced, pre-trained on>50 million experimental particle images from 214 EMPIAR datasets together with simulated projections from 268,000 molecular assemblies, and it is demonstrated how to learn representations that capture biological information for use across multiple c...
N. Chalapathi, Theodore Sternlieb, Ethan Han et al.· 0 citations
Atomistic simulations often struggle to capture the full conformational landscape of biomolecular complexes on experimentally relevant timescales, leaving gaps in our understanding of functionally relevant thermodynamics and kinetics. Cryo-electron microscopy (cryo-EM) provides high-resolution structural snapshots span...
Anupam Anand Ojha, Praveen Ranganath Prabhakar, I. Andricioaei et al.· bioRxiv· 0 citations
Enhanced-sampling methods enable molecular simulations to access configurational regions that are difficult to explore with conventional dynamics, but their efficiency often deteriorates as the number of collective variables (CVs) increases. Here, we introduce an enhanced-sampling framework that couples Stein variation...
Abstract Radiation damage is the fundamental limitation to the useful exposure in single-particle electron cryomicroscopy (cryoEM), so the goal of the field is to record near-perfect images, to extract as much information as possible from them, and then use this information to determine the three-dimensional structure...
A. Patwardhan, P. Rosenthal, C. J. Russo et al.· Quarterly Reviews of Biophys...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.