Ghostbuster: A phase retrieval diffraction tomography algorithm for cryo-EM.

Ewald sphere curvature correction, which extends beyond the projection approximation, stretches the shallow depth of field in cryo-EM reconstructions of thick particles. Here we show that even for previously assumed thin particles, reconstruction artifacts which we refer to as ghosts can appear. By retrieving the lost phases of the electron exitwaves and accounting for the first Born approximation scattering within the particle, we show that these ghosts can be effectively eliminated. Our simulations demonstrate how such ghostbusting can improve reconstructions as compared to existing state-of-the-art software. Like ptychographic cryo-EM, our Ghostbuster algorithm uses phase retrieval to improve reconstructions, but unlike the former, we do not need to modify the existing data acquisition pipelines.

Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries.

Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. Here we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs) that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.7-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library's predicted success to actual measurements, we demonstrate our method's ability to explore tradeoffs between library success and diversity. Results of our work highlight the significant impact machine learning models can have on scFv development. We expect our method to be broadly applicable and provide value to other protein engineering tasks.

Fully automated multi-grid cryoEM screening using Smart Leginon.

Single-particle cryo-electron microscopy (cryoEM) is a swiftly growing method for understanding protein structure. With increasing demand for high-throughput, high-resolution cryoEM services comes greater demand for rapid and automated cryoEM grid and sample screening. During screening, optimal grids and sample conditions are identified for subsequent high-resolution data collection. Screening is a major bottleneck for new cryoEM projects because grids must be optimized for several factors, including grid type, grid hole size, sample concentration, buffer conditions, ice thickness and particle behavior. Even for mature projects, multiple grids are commonly screened to select a subset for high-resolution data collection. Here, machine learning and novel purpose-built image-processing and microscope-handling algorithms are incorporated into the automated data-collection software Leginon, to provide an open-source solution for fully automated high-throughput grid screening. This new version, broadly called Smart Leginon, emulates the actions of an operator in identifying areas on the grid to explore as potentially useful for data collection. Smart Leginon Autoscreen sequentially loads and examines grids from an automated specimen-exchange system to provide completely unattended grid screening across a set of grids. Comparisons between a multi-grid autoscreen session and conventional manual screening by 5 expert microscope operators are presented. On average, Autoscreen reduces operator time from ∼6 h to <10 min and provides a percentage of suitable images for evaluation comparable to the best operator. The ability of Smart Leginon to target holes that are particularly difficult to identify is analyzed. Finally, the utility of Smart Leginon is illustrated with three real-world multi-grid user screening/collection sessions, demonstrating the efficiency and flexibility of the software package. The fully automated functionality of Smart Leginon significantly reduces the burden on operator screening time, improves the throughput of screening and recovers idle microscope time, thereby improving availability of cryoEM services.

Learning to automate cryo-electron microscopy data collection with Ptolemy.

Over the past decade, cryo-electron microscopy (cryoEM) has emerged as an important method for determining near-native, near-atomic resolution 3D structures of biological macromolecules. To meet the increasing demand for cryoEM, automated methods that improve throughput and efficiency of microscope operation are needed. Currently, the targeting algorithms provided by most data-collection software require time-consuming manual tuning of parameters for each grid, and, in some cases, operators must select targets completely manually. However, the development of fully automated targeting algorithms is non-trivial, because images often have low signal-to-noise ratios and optimal targeting strategies depend on a range of experimental parameters and macromolecule behaviors that vary between projects and collection sessions. To address this, Ptolemy provides a pipeline to automate low- and medium-magnification targeting using a suite of purpose-built computer vision and machine-learning algorithms, including mixture models, convolutional neural networks and U-Nets. Learned models in this pipeline are trained on a large set of images from real-world cryoEM data-collection sessions, labeled with locations selected by human operators. These models accurately detect and classify regions of interest in low- and medium-magnification images, and generalize to unseen sessions, as well as to images collected on different microscopes at another facility. This open-source, modular pipeline can be integrated with existing microscope control software to enable automation of cryoEM data collection and can serve as a foundation for future cryoEM automation software.

Smart data collection for CryoEM.

This report provides an overview of the discussions, presentations, and consensus thinking from the Workshop on Smart Data Collection for CryoEM held at the New York Structural Biology Center on April 6-7, 2022. The goal of the workshop was to address next generation data collection strategies that integrate machine learning and real-time processing into the workflow to reduce or eliminate the need for operator intervention.

Synthetic molecular evolution of antimicrobial peptides.

As we learn more about how peptide structure and activity are related, we anticipate that antimicrobial peptides will be engineered to have strong potency and distinct functions and that synthetic peptides will have new biomedical applications, such as treatments for emerging infectious diseases. As a result of the enormous number of possible amino acid sequences and the low-throughput nature of antimicrobial peptide assays, computational tools for peptide design and optimization are needed for direct experimentation toward obtaining functional sequences. Recent developments in computational tools have improved peptide design, saving labor, reagents, costs, and time. At the same time, improvements in peptide synthesis and experimental platforms continue to reduce the cost and increase the throughput of peptide-drug screening. In this review, we discuss the current methods of peptide design and engineering, including in silico methods and peptide synthesis and screening, and highlight areas of potential improvement.

An engineered protein-phosphorylation toggle network with implications for endogenous network discovery.

Synthetic biological networks comprising fast, reversible reactions could enable engineering of new cellular behaviors that are not possible with slower regulation. Here, we created a bistable toggle switch in Saccharomyces cerevisiae using a cross-repression topology comprising 11 protein-protein phosphorylation elements. The toggle is ultrasensitive, can be induced to switch states in seconds, and exhibits long-term bistability. Motivated by our toggle's architecture and size, we developed a computational framework to search endogenous protein pathways for other large and similar bistable networks. Our framework helped us to identify and experimentally verify five formerly unreported endogenous networks that exhibit bistability. Building synthetic protein-protein networks will enable bioengineers to design fast sensing and processing systems, allow sophisticated regulation of cellular processes, and aid discovery of endogenous networks with particular functions.

Learning the protein language: Evolution, structure, and function.

Language models have recently emerged as a powerful machine-learning approach for distilling information from massive protein sequence databases. From readily available sequence data alone, these models discover evolutionary, structural, and functional organization across protein space. Using language models, we can encode amino-acid sequences into distributed vector representations that capture their structural and functional properties, as well as evaluate the evolutionary fitness of sequence variants. We discuss recent advances in protein language modeling and their applications to downstream protein property prediction problems. We then consider how these models can be enriched with prior biological knowledge and introduce an approach for encoding protein structural knowledge into the learned representations. The knowledge distilled by these models allows us to improve downstream function prediction through transfer learning. Deep protein language models are revolutionizing protein biology. They suggest new ways to approach protein and therapeutic design. However, further developments are needed to encode strong biological priors into protein language models and to increase their accessibility to the broader community.

CryoDRGN: reconstruction of heterogeneous cryo-EM structures using neural networks.

Cryo-electron microscopy (cryo-EM) single-particle analysis has proven powerful in determining the structures of rigid macromolecules. However, many imaged protein complexes exhibit conformational and compositional heterogeneity that poses a major challenge to existing three-dimensional reconstruction methods. Here, we present cryoDRGN, an algorithm that leverages the representation power of deep neural networks to directly reconstruct continuous distributions of 3D density maps and map per-particle heterogeneity of single-particle cryo-EM datasets. Using cryoDRGN, we uncovered residual heterogeneity in high-resolution datasets of the 80S ribosome and the RAG complex, revealed a new structural state of the assembling 50S ribosome, and visualized large-scale continuous motions of a spliceosome complex. CryoDRGN contains interactive tools to visualize a dataset's distribution of per-particle variability, generate density maps for exploratory analysis, extract particle subsets for use with other tools and generate trajectories to visualize molecular motions. CryoDRGN is open-source software freely available at http://cryodrgn.csail.mit.edu .

Topaz-Denoise: general deep denoising models for cryoEM and cryoET.

Cryo-electron microscopy (cryoEM) is becoming the preferred method for resolving protein structures. Low signal-to-noise ratio (SNR) in cryoEM images reduces the confidence and throughput of structure determination during several steps of data processing, resulting in impediments such as missing particle orientations. Denoising cryoEM images can not only improve downstream analysis but also accelerate the time-consuming data collection process by allowing lower electron dose micrographs to be used for analysis. Here, we present Topaz-Denoise, a deep learning method for reliably and rapidly increasing the SNR of cryoEM images and cryoET tomograms. By training on a dataset composed of thousands of micrographs collected across a wide range of imaging conditions, we are able to learn models capturing the complexity of the cryoEM image formation process. The general model we present is able to denoise new datasets without additional training. Denoising with this model improves micrograph interpretability and allows us to solve 3D single particle structures of clustered protocadherin, an elongated particle with previously elusive views. We then show that low dose collection, enabled by Topaz-Denoise, improves downstream analysis in addition to reducing data collection time. We also present a general 3D denoising model for cryoET. Topaz-Denoise and pre-trained general models are now included in Topaz. We expect that Topaz-Denoise will be of broad utility to the cryoEM community for improving micrograph and tomogram interpretability and accelerating analysis.

Positive-unlabeled convolutional neural networks for particle picking in cryo-electron micrographs.

Cryo-electron microscopy is a popular method for the determination of protein structures; however, identifying a sufficient number of particles for analysis can take months of manual effort. Current computational approaches find many false positives and require ad hoc postprocessing, especially for unusually shaped particles. To address these shortcomings, we develop Topaz, an efficient and accurate particle-picking pipeline using neural networks trained with a general-purpose positive-unlabeled learning method. This framework enables particle detection models to be trained with few sparsely labeled particles and no labeled negatives. Topaz retrieves many more real particles than conventional picking methods while maintaining low false-positive rates, is capable of picking challenging unusually shaped proteins (for example, small, non-globular and asymmetric particles), produces more representative particle sets and does not require post hoc curation. We demonstrate the performance of Topaz on two difficult datasets and three conventional datasets. Topaz is modular, standalone, free and open source ( http://topaz.csail.mit.edu ).

Visualization of clustered protocadherin neuronal self-recognition complexes.

Neurite self-recognition and avoidance are fundamental properties of all nervous systems1. These processes facilitate dendritic arborization2,3, prevent formation of autapses4 and allow free interaction among non-self neurons1,2,4,5. Avoidance among self neurites is mediated by stochastic cell-surface expression of combinations of about 60 isoforms of α-, ß- and γ-clustered protocadherin that provide mammalian neurons with single-cell identities1,2,4-13. Avoidance is observed between neurons that express identical protocadherin repertoires2,5, and single-isoform differences are sufficient to prevent self-recognition10. Protocadherins form isoform-promiscuous cis dimers and isoform-specific homophilic trans dimers10,14-20. Although these interactions have previously been characterized in isolation15,17-20, structures of full-length protocadherin ectodomains have not been determined, and how these two interfaces engage in self-recognition between neuronal surfaces remains unknown. Here we determine the molecular arrangement of full-length clustered protocadherin ectodomains in single-isoform self-recognition complexes, using X-ray crystallography and cryo-electron tomography. We determine the crystal structure of the clustered protocadherin γB4 ectodomain, which reveals a zipper-like lattice that is formed by alternating cis and trans interactions. Using cryo-electron tomography, we show that clustered protocadherin γB6 ectodomains tethered to liposomes spontaneously assemble into linear arrays at membrane contact sites, in a configuration that is consistent with the assembly observed in the crystal structure. These linear assemblies pack against each other as parallel arrays to form larger two-dimensional structures between membranes. Our results suggest that the formation of ordered linear assemblies by clustered protocadherins represents the initial self-recognition step in neuronal avoidance, and thus provide support for the isoform-mismatch chain-termination model of protocadherin-mediated self-recognition, which depends on these linear chains11.

Divergence in DNA Specificity among Paralogous Transcription Factors Contributes to Their Differential In Vivo Binding.

Paralogous transcription factors (TFs) are oftentimes reported to have identical DNA-binding motifs, despite the fact that they perform distinct regulatory functions. Differential genomic targeting by paralogous TFs is generally assumed to be due to interactions with protein co-factors or the chromatin environment. Using a computational-experimental framework called iMADS (integrative modeling and analysis of differential specificity), we show that, contrary to previous assumptions, paralogous TFs bind differently to genomic target sites even in vitro. We used iMADS to quantify, model, and analyze specificity differences between 11 TFs from 4 protein families. We found that paralogous TFs have diverged mainly at medium- and low-affinity sites, which are poorly captured by current motif models. We identify sequence and shape features differentially preferred by paralogous TFs, and we show that the intrinsic differences in specificity among paralogous TFs contribute to their differential in vivo binding. Thus, our study represents a step forward in deciphering the molecular mechanisms of differential specificity in TF families.

Human-chimpanzee differences in a FZD8 enhancer alter cell-cycle dynamics in the developing neocortex.

The human neocortex differs from that of other great apes in several notable regards, including altered cell cycle, prolonged corticogenesis, and increased size [1-5]. Although these evolutionary changes most likely contributed to the origin of distinctively human cognitive faculties, their genetic basis remains almost entirely unknown. Highly conserved non-coding regions showing rapid sequence changes along the human lineage are candidate loci for the development and evolution of uniquely human traits. Several studies have identified human-accelerated enhancers [6-14], but none have linked an expression difference to a specific organismal trait. Here we report the discovery of a human-accelerated regulatory enhancer (HARE5) of FZD8, a receptor of the Wnt pathway implicated in brain development and size [15, 16]. Using transgenic mice, we demonstrate dramatic differences in human and chimpanzee HARE5 activity, with human HARE5 driving early and robust expression at the onset of corticogenesis. Similar to HARE5 activity, FZD8 is expressed in neural progenitors of the developing neocortex [17-19]. Chromosome conformation capture assays reveal that HARE5 physically and specifically contacts the core Fzd8 promoter in the mouse embryonic neocortex. To assess the phenotypic consequences of HARE5 activity, we generated transgenic mice in which Fzd8 expression is under control of orthologous enhancers (Pt-HARE5::Fzd8 and Hs-HARE5::Fzd8). In comparison to Pt-HARE5::Fzd8, Hs-HARE5::Fzd8 mice showed marked acceleration of neural progenitor cell cycle and increased brain size. Changes in HARE5 function unique to humans thus alter the cell-cycle dynamics of a critical population of stem cells during corticogenesis and may underlie some distinctive anatomical features of the human brain.