Accurate structure prediction of biomolecular interactions with AlphaFold 3.

The introduction of AlphaFold 21 has spurred a revolution in modelling the structure of proteins and their interactions, enabling a huge range of applications in protein modelling and design2-6. Here we describe our AlphaFold 3 model with a substantially updated diffusion-based architecture that is capable of predicting the joint structure of complexes including proteins, nucleic acids, small molecules, ions and modified residues. The new AlphaFold model demonstrates substantially improved accuracy over many previous specialized tools: far greater accuracy for protein-ligand interactions compared with state-of-the-art docking tools, much higher accuracy for protein-nucleic acid interactions compared with nucleic-acid-specific predictors and substantially higher antibody-antigen prediction accuracy compared with AlphaFold-Multimer v.2.37,8. Together, these results show that high-accuracy modelling across biomolecular space is possible within a single unified deep-learning framework.

Highly accurate protein structure prediction with AlphaFold.

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1-4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence-the structure prediction component of the 'protein folding problem'8-has been an important open research problem for more than 50 years9. Despite recent progress10-14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm.

Highly accurate protein structure prediction for the human proteome.

Protein structures can provide invaluable information, both for reasoning about biological processes and for enabling interventions such as structure-based drug development or targeted mutagenesis. After decades of effort, 17% of the total residues in human protein sequences are covered by an experimentally determined structure1. Here we markedly expand the structural coverage of the proteome by applying the state-of-the-art machine learning method, AlphaFold2, at a scale that covers almost the entire human proteome (98.5% of human proteins). The resulting dataset covers 58% of residues with a confident prediction, of which a subset (36% of all residues) have very high confidence. We introduce several metrics developed by building on the AlphaFold model and use them to interpret the dataset, identifying strong multi-domain predictions as well as regions that are likely to be disordered. Finally, we provide some case studies to illustrate how high-quality predictions could be used to generate biological hypotheses. We are making our predictions freely available to the community and anticipate that routine large-scale and high-accuracy structure prediction will become an important tool that will allow new questions to be addressed from a structural perspective.

Deep learning is widely applicable to phenotyping embryonic development and disease.

Genome editing simplifies the generation of new animal models for congenital disorders. However, the detailed and unbiased phenotypic assessment of altered embryonic development remains a challenge. Here, we explore how deep learning (U-Net) can automate segmentation tasks in various imaging modalities, and we quantify phenotypes of altered renal, neural and craniofacial development in Xenopus embryos in comparison with normal variability. We demonstrate the utility of this approach in embryos with polycystic kidneys (pkd1 and pkd2) and craniofacial dysmorphia (six1). We highlight how in toto light-sheet microscopy facilitates accurate reconstruction of brain and craniofacial structures within X. tropicalis embryos upon dyrk1a and six1 loss of function or treatment with retinoic acid inhibitors. These tools increase the sensitivity and throughput of evaluating developmental malformations caused by chemical or genetic disruption. Furthermore, we provide a library of pre-trained networks and detailed instructions for applying deep learning to the reader's own datasets. We demonstrate the versatility, precision and scalability of deep neural network phenotyping on embryonic disease models. By combining light-sheet microscopy and deep learning, we provide a framework for higher-throughput characterization of embryonic model organisms. This article has an associated 'The people behind the papers' interview.

Author Correction: U-Net: deep learning for cell counting, detection, and morphometry.

In the version of this paper originally published, one of the affiliations for Dominic Mai was incorrect: "Center for Biological Systems Analysis (ZBSA), Albert-Ludwigs-University, Freiburg, Germany" should have been "Life Imaging Center, Center for Biological Systems Analysis, Albert-Ludwigs-University, Freiburg, Germany." This change required some renumbering of subsequent author affiliations. These corrections have been made in the PDF and HTML versions of the article, as well as in any cover sheets for associated Supplementary Information.

U-Net: deep learning for cell counting, detection, and morphometry.

U-Net is a generic deep-learning solution for frequently occurring quantification tasks such as cell detection and shape measurements in biomedical image data. We present an ImageJ plugin that enables non-machine-learning experts to analyze their data with U-Net on either a local computer or a remote server/cloud service. The plugin comes with pretrained models for single-cell segmentation and allows for U-Net to be adapted to new tasks on the basis of a few annotated samples.

Applying and improving AlphaFold at CASP14.

We describe the operation and improvement of AlphaFold, the system that was entered by the team AlphaFold2 to the "human" category in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The AlphaFold system entered in CASP14 is entirely different to the one entered in CASP13. It used a novel end-to-end deep neural network trained to produce protein structures from amino acid sequence, multiple sequence alignments, and homologous proteins. In the assessors' ranking by summed z scores (>2.0), AlphaFold scored 244.0 compared to 90.8 by the next best group. The predictions made by AlphaFold had a median domain GDT_TS of 92.4; this is the first time that this level of average accuracy has been achieved during CASP, especially on the more difficult Free Modeling targets, and represents a significant improvement in the state of the art in protein structure prediction. We reported how AlphaFold was run as a human team during CASP14 and improved such that it now achieves an equivalent level of performance without intervention, opening the door to highly accurate large-scale structure prediction.

Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study.

BACKGROUND: Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. OBJECTIVE: Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. METHODS: The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. RESULTS: We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model's generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. CONCLUSIONS: Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

An objective comparison of cell-tracking algorithms.

We present a combined report on the results of three editions of the Cell Tracking Challenge, an ongoing initiative aimed at promoting the development and objective evaluation of cell segmentation and tracking algorithms. With 21 participating algorithms and a data repository consisting of 13 data sets from various microscopy modalities, the challenge displays today's state-of-the-art methodology in the field. We analyzed the challenge results using performance measures for segmentation and tracking that rank all participating methods. We also analyzed the performance of all of the algorithms in terms of biological measures and practical usability. Although some methods scored high in all technical aspects, none obtained fully correct solutions. We found that methods that either take prior information into account using learning strategies or analyze cells in a global spatiotemporal video context performed better than other methods under the segmentation and tracking scenarios included in the challenge.

A 3D digital atlas of the Nicotiana tabacum root tip and its use to investigate changes in the root apical meristem induced by the Agrobacterium 6b oncogene.

Using the intrinsic Root Coordinate System (iRoCS) Toolbox, a digital atlas at cellular resolution has been constructed for Nicotiana tabacum roots. Mitotic cells and cells labeled for DNA replication with 5-ethynyl-2'-deoxyuridine (EdU) were mapped. The results demonstrate that iRoCS analysis can be applied to roots that are thicker than those of Arabidopsis thaliana without histological sectioning. A three-dimensional (3-D) analysis of the root tip showed that tobacco roots undergo several irregular periclinal and tangential divisions. Irrespective of cell type, rapid cell elongation starts at the same distance from the quiescent center, however, boundaries between cell proliferation and transition domains are cell-type specific. The data support the existence of a transition domain in tobacco roots. Cell endoreduplication starts in the transition domain and continues into the elongation zone. The tobacco root map was subsequently used to analyse root organization changes caused by the inducible expression of the Agrobacterium 6b oncogene. In tobacco roots that express the 6b gene, the root apical meristem was shorter and radial cell growth was reduced, but the mitotic and DNA replication indexes were not affected. The epidermis of 6b-expressing roots produced less files and underwent abnormal periclinal divisions. The periclinal division leading to mature endodermis and cortex3 cell files was delayed. These findings define additional targets for future studies on the mode of action of the Agrobacterium 6b oncogene.

The Rac1 regulator ELMO controls basal body migration and docking in multiciliated cells through interaction with Ezrin.

Cilia are microtubule-based organelles that are present on most cells and are required for normal tissue development and function. Defective cilia cause complex syndromes with multiple organ manifestations termed ciliopathies. A crucial step during ciliogenesis in multiciliated cells (MCCs) is the association of future basal bodies with the apical plasma membrane, followed by their correct spacing and planar orientation. Here, we report a novel role for ELMO-DOCK1, which is a bipartite guanine nucleotide exchange factor complex for the small GTPase Rac1, and for the membrane-cytoskeletal linker Ezrin, in regulating centriole/basal body migration, docking and spacing. Downregulation of each component results in ciliopathy-related phenotypes in zebrafish and disrupted ciliogenesis in Xenopus epidermal MCCs. Subcellular analysis revealed a striking impairment of basal body docking and spacing, which is likely to account for the observed phenotypes. These results are substantiated by showing a genetic interaction between elmo1 and ezrin b. Finally, we provide biochemical evidence that the ELMO-DOCK1-Rac1 complex influences Ezrin phosphorylation and thereby probably serves as an important molecular switch. Collectively, we demonstrate that the ELMO-Ezrin complex orchestrates ciliary basal body migration, docking and positioning in vivo.

The iRoCS Toolbox--3D analysis of the plant root apical meristem at cellular resolution.

To achieve a detailed understanding of processes in biological systems, cellular features must be quantified in the three-dimensional (3D) context of cells and organs. We described use of the intrinsic root coordinate system (iRoCS) as a reference model for the root apical meristem of plants. iRoCS enables direct and quantitative comparison between the root tips of plant populations at single-cell resolution. The iRoCS Toolbox automatically fits standardized coordinates to raw 3D image data. It detects nuclei or segments cells, automatically fits the coordinate system, and groups the nuclei/cells into the root's tissue layers. The division status of each nucleus may also be determined. The only manual step required is to mark the quiescent centre. All intermediate outputs may be refined if necessary. The ability to learn the visual appearance of nuclei by example allows the iRoCS Toolbox to be easily adapted to various phenotypes. The iRoCS Toolbox is provided as an open-source software package, licensed under the GNU General Public License, to make it accessible to a broad community. To demonstrate the power of the technique, we measured subtle changes in cell division patterns caused by modified auxin flux within the Arabidopsis thaliana root apical meristem.

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: the CADDementia challenge.

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Shroom3 is required downstream of FGF signalling to mediate proneuromast assembly in zebrafish.

During development, morphogenetic processes require a precise coordination of cell differentiation, cell shape changes and, often, cell migration. Yet, how pattern information is used to orchestrate these different processes is still unclear. During lateral line (LL) morphogenesis, a group of cells simultaneously migrate and assemble radially organized cell clusters, termed rosettes, that prefigure LL sensory organs. This process is controlled by Fibroblast growth factor (FGF) signalling, which induces cell fate changes, cell migration and cell shape changes. However, the exact molecular mechanisms induced by FGF activation that mediate these changes on a cellular level are not known. Here, we focus on the mechanisms by which FGFs control apical constriction and rosette assembly. We show that apical constriction in the LL primordium requires the activity of non-muscle myosin. We demonstrate further that shroom3, a well-known regulator of non-muscle myosin activity, is expressed in the LL primordium and that its expression requires FGF signalling. Using gain- and loss-of-function experiments, we demonstrate that Shroom3 is the main organizer of cell shape changes during rosette assembly, probably by coordinating Rho kinase recruitment and non-muscle myosin activation. In order to quantify morphogenesis in the LL primordium in an unbiased manner, we developed a unique trainable 'rosette detector'. We thus propose a model in which Shroom3 drives rosette assembly in the LL downstream of FGF in a Rho kinase- and non-muscle myosin-dependent manner. In conclusion, we uncovered the first mechanistic link between patterning and morphogenesis during LL sensory organ formation.

ViBE-Z: a framework for 3D virtual colocalization analysis in zebrafish larval brains.

Precise three-dimensional (3D) mapping of a large number of gene expression patterns, neuronal types and connections to an anatomical reference helps us to understand the vertebrate brain and its development. We developed the Virtual Brain Explorer (ViBE-Z), a software that automatically maps gene expression data with cellular resolution to a 3D standard larval zebrafish (Danio rerio) brain. ViBE-Z enhances the data quality through fusion and attenuation correction of multiple confocal microscope stacks per specimen and uses a fluorescent stain of cell nuclei for image registration. It automatically detects 14 predefined anatomical landmarks for aligning new data with the reference brain. ViBE-Z performs colocalization analysis in expression databases for anatomical domains or subdomains defined by any specific pattern; here we demonstrate its utility for mapping neurons of the dopaminergic system. The ViBE-Z database, atlas and software are provided via a web interface.

Correction of inter-scanner and within-subject variance in structural MRI based automated diagnosing.

Automated analysis of structural magnetic resonance images is a promising way to improve early detection of neurodegenerative brain diseases. Clinical applications of such methods involve multiple scanners with potentially different hardware and/or acquisition sequences and demographically heterogeneous groups. To improve classification performance, we propose to correct effects of subject-specific covariates (such as age, total intracranial volume, and sex) as well as effects of scanner by using a non-linear Gaussian process model. To test the efficacy of the correction, we performed classification of carriers of the genetic mutation leading to Huntington's disease (HD) versus healthy controls. Half of the HD carriers were free of typical HD symptoms and had an estimated 5 to 20years before onset of clinical symptoms, thus providing a model for preclinical diagnosis of a neurodegenerative disease. Structural magnetic resonance brain images were acquired at four sites with pairs of sites which had the identical scanner type, equipment, and acquisition parameters. For automatic classification, we used spatially normalized probabilistic maps of gray matter, then removed confounding effects by Gaussian process regression, and then performed classification with a support vector machine. Voxel-based morphometry of gray matter maps showed disease effects that were spatially wider spread than effects of scanner, but no significant interactions between scanner and disease were found. A model trained with data from a single scanner generalized well to data from a different scanner. When confounding diagnostics groups and scanner during training, e.g. by using controls from one scanner and gene carriers from another, classification accuracy dropped significantly in many cases. By regressing out confounds with Gaussian process regression, the performance levels were comparable to those obtained in scenarios without confound. We conclude that models trained on data acquired with a single scanner generalized well to data acquired with a different same-generation scanner even when the vendor differed. When confounding grouping and scanner during training is unavoidable to gather training data, regressing out inter-scanner and between-subject variability can reduce the loss in accuracy due to the confound.

Variational attenuation correction in two-view confocal microscopy.

BACKGROUND: Absorption and refraction induced signal attenuation can seriously hinder the extraction of quantitative information from confocal microscopic data. This signal attenuation can be estimated and corrected by algorithms that use physical image formation models. Especially in thick heterogeneous samples, current single view based models are unable to solve the underdetermined problem of estimating the attenuation-free intensities. RESULTS: We present a variational approach to estimate both, the real intensities and the spatially variant attenuation from two views of the same sample from opposite sides. Assuming noise-free measurements throughout the whole volume and pure absorption, this would in theory allow a perfect reconstruction without further assumptions. To cope with real world data, our approach respects photon noise, estimates apparent bleaching between the two recordings, and constrains the attenuation field to be smooth and sparse to avoid spurious attenuation estimates in regions lacking valid measurements. CONCLUSIONS: We quantify the reconstruction quality on simulated data and compare it to the state-of-the art two-view approach and commonly used one-factor-per-slice approaches like the exponential decay model. Additionally we show its real-world applicability on model organisms from zoology (zebrafish) and botany (Arabidopsis). The results from these experiments show that the proposed approach improves the quantification of confocal microscopic data of thick specimen.

Inversin relays Frizzled-8 signals to promote proximal pronephros development.

Mutations of inversin cause type II nephronophthisis, an infantile autosomal recessive disease characterized by cystic kidney disease and developmental defects. Inversin regulates Wnt signaling and is required for convergent extension movements during early embryogenesis. We now show that Inversin is essential for Xenopus pronephros formation, involving two distinct and opposing forms of cell movements. Knockdown of Inversin abrogated both proximal pronephros extension and distal tubule differentiation, phenotypes similar to that of Xenopus deficient in Frizzled-8. Exogenous Inversin rescued the pronephric defects caused by lack of Frizzled-8, indicating that Inversin acts downstream of Frizzled-8 in pronephros morphogenesis. Depletion of Inversin prevents the recruitment of Dishevelled in response to Frizzled-8 and impeded the accumulation of Dishevelled at the apical membrane of tubular epithelial cells in vivo. Thus, defective tubule morphogenesis seems to contribute to the renal pathology observed in patients with nephronophthisis type II.

Microridge-like structures anchor motile cilia.

Several tissues contain cells with multiple motile cilia that generate a fluid or particle flow to support development and organ functions; defective motility causes human disease. Developmental cues orient motile cilia, but how cilia are locked into their final position to maintain a directional flow is not understood. Here we find that the actin cytoskeleton is highly dynamic during early development of multiciliated cells (MCCs). While apical actin bundles become increasingly more static, subapical actin filaments are nucleated from the distal tip of ciliary rootlets. Anchorage of these subapical actin filaments requires the presence of microridge-like structures formed during MCC development, and the activity of Nonmuscle Myosin II. Optogenetic manipulation of Ezrin, a core component of the microridge actin-anchoring complex, or inhibition of Myosin Light Chain Kinase interfere with rootlet anchorage and orientation. These observations identify microridge-like structures as an essential component of basal body rootlet anchoring in MCCs.