Convergence of cryo-electron microscopy and artificial intelligence in integrative structural biology: A critical review of advances, synergies, and implications for molecular biophysics and drug discovery
Abstract
Structural biology has entered a period of rapid methodological change defined by the convergence of cryo-electron microscopy (cryo-EM) and artificial intelligence (AI)-driven structure prediction. Prior reviews have generally addressed cryo-EM instrumentation or AI structure prediction individually, or their combination primarily from a structural biology or drug discovery perspective; a microscopy-centred synthesis tracing this convergence from detector physics and image-processing workflows through validation standards to in situ cryo-electron tomography (cryo-ET), while situating AI tools specifically as inputs to and complements of the cryo-EM workflow, has been comparatively underexplored. This review provides such a synthesis, organised around: (i) the instrumentation, image-processing, and validation advances underlying cryo-EM's resolution gains, including detector physics, contrast transfer function (CTF) estimation, Bayesian and deep-learning-based particle picking and reconstruction, and map-to-model validation and deposition; (ii) cryo-electron tomography and subtomogram averaging (STA) for in situ structural biology, including deep generative approaches to heterogeneity analysis; and (iii) the AlphaFold2, AlphaFold3, and RoseTTAFold All-Atom systems, considered specifically in relation to how they interface with and depend upon cryo-EM data for model building, refinement, and validation. Building on this microscopy-centred account, we propose a three-tier…
Read the paper
Related studies
- Learning from First-Generation Qualitative Approaches in the IS Discipline: An Evolutionary View and Some Implications for Authors and Evaluators (PART 1/2)
- Commentary on the clinical and preclinical dosage limits of interstitially administered magnetic fluids for therapeutic hyperthermia based on current practice and efficacy models
- Prosthesis: New Technological Opportunities and Innovative Biomedical Devices
- The history and future of neural modeling for cochlear implants
- Ryanodine receptors: waking up from refractoriness
- Novel Transgenic Rabbit Model Sheds Light on the Puzzling Role of Matrix Metalloproteinase-12 in Atherosclerosis
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.