An amino-domino model described by a cross-peptide-bond Ramachandran plot defines amino acid pairs as local structural units.

Protein structure, both at the global and local level, dictates function. Proteins fold from chains of amino acids, forming secondary structures, α-helices and ß-strands, that, at least for globular proteins, subsequently fold into a three-dimensional structure. Here, we show that a Ramachandran-type plot focusing on the two dihedral angles separated by the peptide bond, and entirely contained within an amino acid pair, defines a local structural unit. We further demonstrate the usefulness of this cross-peptide-bond Ramachandran plot by showing that it captures ß-turn conformations in coil regions, that traditional Ramachandran plot outliers fall into occupied regions of our plot, and that thermophilic proteins prefer specific amino acid pair conformations. Further, we demonstrate experimentally that the effect of a point mutation on backbone conformation and protein stability depends on the amino acid pair context, i.e., the identity of the adjacent amino acid, in a manner predictable by our method.

Unsupervised physics-informed deep learning-based reconstruction for time-resolved imaging by multiplexed ptychography.

We explore numerically an unsupervised, physics-informed, deep learning-based reconstruction technique for time-resolved imaging by multiplexed ptychography. In our method, the untrained deep learning model replaces the iterative algorithm's update step, yielding superior reconstructions of multiple dynamic object frames compared to conventional methodologies. More precisely, we demonstrate improvements in image quality and resolution, while reducing sensitivity to the number of recorded frames, the mutual orthogonality of different probe modes, overlap between neighboring probe beams and the cutoff frequency of the ptychographic microscope - properties that are generally of paramount importance for ptychographic reconstruction algorithms.

Meeting the unmet needs of clinicians from AI systems showcased for cardiology with deep-learning-based ECG analysis.

Despite their great promise, artificial intelligence (AI) systems have yet to become ubiquitous in the daily practice of medicine largely due to several crucial unmet needs of healthcare practitioners. These include lack of explanations in clinically meaningful terms, handling the presence of unknown medical conditions, and transparency regarding the system's limitations, both in terms of statistical performance as well as recognizing situations for which the system's predictions are irrelevant. We articulate these unmet clinical needs as machine-learning (ML) problems and systematically address them with cutting-edge ML techniques. We focus on electrocardiogram (ECG) analysis as an example domain in which AI has great potential and tackle two challenging tasks: the detection of a heterogeneous mix of known and unknown arrhythmias from ECG and the identification of underlying cardio-pathology from segments annotated as normal sinus rhythm recorded in patients with an intermittent arrhythmia. We validate our methods by simulating a screening for arrhythmias in a large-scale population while adhering to statistical significance requirements. Specifically, our system 1) visualizes the relative importance of each part of an ECG segment for the final model decision; 2) upholds specified statistical constraints on its out-of-sample performance and provides uncertainty estimation for its predictions; 3) handles inputs containing unknown rhythm types; and 4) handles data from unseen patients while also flagging cases in which the model's outputs are not usable for a specific patient. This work represents a significant step toward overcoming the limitations currently impeding the integration of AI into clinical practice in cardiology and medicine in general.

Interpretable Deep-Learning Unveils Structure-Property Relationships in Polybenzenoid Hydrocarbons.

In this work, interpretable deep learning was used to identify structure-property relationships governing the HOMO-LUMO gap and the relative stability of polybenzenoid hydrocarbons (PBHs) using a ring-based graph representation. This representation was combined with a subunit-based perception of PBHs, allowing chemical insights to be presented in terms of intuitive and simple structural motifs. The resulting insights agree with conventional organic chemistry knowledge and electronic structure-based analyses and also reveal new behaviors and identify influential structural motifs. In particular, we evaluated and compared the effects of linear, angular, and branching motifs on these two molecular properties and explored the role of dispersion in mitigating the torsional strain inherent in nonplanar PBHs. Hence, the observed regularities and the proposed analysis contribute to a deeper understanding of the behavior of PBHs and form the foundation for design strategies for new functional PBHs.

Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity?

STUDY QUESTION: What is the accuracy and agreement of embryologists when assessing the implantation probability of blastocysts using time-lapse imaging (TLI), and can it be improved with a data-driven algorithm? SUMMARY ANSWER: The overall interobserver agreement of a large panel of embryologists was moderate and prediction accuracy was modest, while the purpose-built artificial intelligence model generally resulted in higher performance metrics. WHAT IS KNOWN ALREADY: Previous studies have demonstrated significant interobserver variability amongst embryologists when assessing embryo quality. However, data concerning embryologists' ability to predict implantation probability using TLI is still lacking. Emerging technologies based on data-driven tools have shown great promise for improving embryo selection and predicting clinical outcomes. STUDY DESIGN, SIZE, DURATION: TLI video files of 136 embryos with known implantation data were retrospectively collected from two clinical sites between 2018 and 2019 for the performance assessment of 36 embryologists and comparison with a deep neural network (DNN). PARTICIPANTS/MATERIALS, SETTING, METHODS: We recruited 39 embryologists from 13 different countries. All participants were blinded to clinical outcomes. A total of 136 TLI videos of embryos that reached the blastocyst stage were used for this experiment. Each embryo's likelihood of successfully implanting was assessed by 36 embryologists, providing implantation probability grades (IPGs) from 1 to 5, where 1 indicates a very low likelihood of implantation and 5 indicates a very high likelihood. Subsequently, three embryologists with over 5 years of experience provided Gardner scores. All 136 blastocysts were categorized into three quality groups based on their Gardner scores. Embryologist predictions were then converted into predictions of implantation (IPG ≥ 3) and no implantation (IPG ≤ 2). Embryologists' performance and agreement were assessed using Fleiss kappa coefficient. A 10-fold cross-validation DNN was developed to provide IPGs for TLI video files. The model's performance was compared to that of the embryologists. MAIN RESULTS AND THE ROLE OF CHANCE: Logistic regression was employed for the following confounding variables: country of residence, academic level, embryo scoring system, log years of experience and experience using TLI. None were found to have a statistically significant impact on embryologist performance at α = 0.05. The average implantation prediction accuracy for the embryologists was 51.9% for all embryos (N = 136). The average accuracy of the embryologists when assessing top quality and poor quality embryos (according to the Gardner score categorizations) was 57.5% and 57.4%, respectively, and 44.6% for fair quality embryos. Overall interobserver agreement was moderate (κ = 0.56, N = 136). The best agreement was achieved in the poor + top quality group (κ = 0.65, N = 77), while the agreement in the fair quality group was lower (κ = 0.25, N = 59). The DNN showed an overall accuracy rate of 62.5%, with accuracies of 62.2%, 61% and 65.6% for the poor, fair and top quality groups, respectively. The AUC for the DNN was higher than that of the embryologists overall (0.70 DNN vs 0.61 embryologists) as well as in all of the Gardner groups (DNN vs embryologists-Poor: 0.69 vs 0.62; Fair: 0.67 vs 0.53; Top: 0.77 vs 0.54). LIMITATIONS, REASONS FOR CAUTION: Blastocyst assessment was performed using video files acquired from time-lapse incubators, where each video contained data from a single focal plane. Clinical data regarding the underlying cause of infertility and endometrial thickness before the transfer was not available, yet may explain implantation failure and lower accuracy of IPGs. Implantation was defined as the presence of a gestational sac, whereas the detection of fetal heartbeat is a more robust marker of embryo viability. The raw data were anonymized to the extent that it was not possible to quantify the number of unique patients and cycles included in the study, potentially masking the effect of bias from a limited patient pool. Furthermore, the lack of demographic data makes it difficult to draw conclusions on how representative the dataset was of the wider population. Finally, embryologists were required to assess the implantation potential, not embryo quality. Although this is not the traditional approach to embryo evaluation, morphology/morphokinetics as a means of assessing embryo quality is believed to be strongly correlated with viability and, for some methods, implantation potential. WIDER IMPLICATIONS OF THE FINDINGS: Embryo selection is a key element in IVF success and continues to be a challenge. Improving the predictive ability could assist in optimizing implantation success rates and other clinical outcomes and could minimize the financial and emotional burden on the patient. This study demonstrates moderate agreement rates between embryologists, likely due to the subjective nature of embryo assessment. In particular, we found that average embryologist accuracy and agreement were significantly lower for fair quality embryos when compared with that for top and poor quality embryos. Using data-driven algorithms as an assistive tool may help IVF professionals increase success rates and promote much needed standardization in the IVF clinic. Our results indicate a need for further research regarding technological advancement in this field. STUDY FUNDING/COMPETING INTEREST(S): Embryonics Ltd is an Israel-based company. Funding for the study was partially provided by the Israeli Innovation Authority, grant #74556. TRIAL REGISTRATION NUMBER: N/A.

A structure-function analysis of the yeast Elg1 protein reveals the importance of PCNA unloading in genome stability maintenance.

The sliding clamp, PCNA, plays a central role in DNA replication and repair. In the moving replication fork, PCNA is present at the leading strand and at each of the Okazaki fragments that are formed on the lagging strand. PCNA enhances the processivity of the replicative polymerases and provides a landing platform for other proteins and enzymes. The loading of the clamp onto DNA is performed by the Replication Factor C (RFC) complex, whereas its unloading can be carried out by an RFC-like complex containing Elg1. Mutations in ELG1 lead to DNA damage sensitivity and genome instability. To characterize the role of Elg1 in maintaining genomic integrity, we used homology modeling to generate a number of site-specific mutations in ELG1 that exhibit different PCNA unloading capabilities. We show that the sensitivity to DNA damaging agents and hyper-recombination of these alleles correlate with their ability to unload PCNA from the chromatin. Our results indicate that retention of modified and unmodified PCNA on the chromatin causes genomic instability. We also show, using purified proteins, that the Elg1 complex inhibits DNA synthesis by unloading SUMOylated PCNA from the DNA. Additionally, we find that mutations in ELG1 suppress the sensitivity of rad5Δ mutants to DNA damage by allowing trans-lesion synthesis to take place. Taken together, the data indicate that the Elg1-RLC complex plays an important role in the maintenance of genomic stability by unloading PCNA from the chromatin.

Computational multi-focus imaging combining sparse model with color dependent phase mask.

A method for extended depth of field imaging based on image acquisition through a thin binary phase plate followed by fast automatic computational post-processing is presented. By placing a wavelength dependent optical mask inside the pupil of a conventional camera lens, one acquires a unique response for each of the three main color channels, which adds valuable information that allows blind reconstruction of blurred images without the need of an iterative search process for estimating the blurring kernel. The presented simulation as well as capture of a real life scene show how acquiring a one-shot image focused at a single plane, enable generating a de-blurred scene over an extended range in space.

Water stabilizes an alternate turn conformation in horse heart myoglobin.

Comparison of myoglobin structures reveals that protein isolated from horse heart consistently adopts an alternate turn conformation in comparison to its homologues. Analysis of hundreds of high-resolution structures discounts crystallization conditions or the surrounding amino acid protein environment as explaining this difference, that is also not captured by the AlphaFold prediction. Rather, a water molecule is identified as stabilizing the conformation in the horse heart structure, which immediately reverts to the whale conformation in molecular dynamics simulations excluding that structural water.

Guided diffusion for inverse molecular design.

The holy grail of materials science is de novo molecular design, meaning engineering molecules with desired characteristics. The introduction of generative deep learning has greatly advanced efforts in this direction, yet molecular discovery remains challenging and often inefficient. Herein we introduce GaUDI, a guided diffusion model for inverse molecular design that combines an equivariant graph neural net for property prediction and a generative diffusion model. We demonstrate GaUDI's effectiveness in designing molecules for organic electronic applications by using single- and multiple-objective tasks applied to a generated dataset of 475,000 polycyclic aromatic systems. GaUDI shows improved conditional design, generating molecules with optimal properties and even going beyond the original distribution to suggest better molecules than those in the dataset. In addition to point-wise targets, GaUDI can also be guided toward open-ended targets (for example, a minimum or maximum) and in all cases achieves close to 100% validity of generated molecules.

Horizontal Flows and Manifold Stochastics in Geometric Deep Learning.

We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean. Both methods are inspired by stochastics on manifolds and geometric statistics, and provide examples of how stochastic methods - here horizontal frame bundle flows and non-linear bridge sampling schemes, can be used in geometric deep learning. We outline the theoretical foundation of the two methods, discuss their relation to Euclidean deep networks and existing methodology in geometric deep learning, and establish important properties of the proposed constructions.

Codon-specific Ramachandran plots show amino acid backbone conformation depends on identity of the translated codon.

Synonymous codons translate into chemically identical amino acids. Once considered inconsequential to the formation of the protein product, there is evidence to suggest that codon usage affects co-translational protein folding and the final structure of the expressed protein. Here we develop a method for computing and comparing codon-specific Ramachandran plots and demonstrate that the backbone dihedral angle distributions of some synonymous codons are distinguishable with statistical significance for some secondary structures. This shows that there exists a dependence between codon identity and backbone torsion of the translated amino acid. Although these findings cannot pinpoint the causal direction of this dependence, we discuss the vast biological implications should coding be shown to directly shape protein conformation and demonstrate the usefulness of this method as a tool for probing associations between codon usage and protein structure. Finally, we urge for the inclusion of exact genetic information into structural databases.

Machine learning approaches demonstrate that protein structures carry information about their genetic coding.

Synonymous codons translate into the same amino acid. Although the identity of synonymous codons is often considered inconsequential to the final protein structure, there is mounting evidence for an association between the two. Our study examined this association using regression and classification models, finding that codon sequences predict protein backbone dihedral angles with a lower error than amino acid sequences, and that models trained with true dihedral angles have better classification of synonymous codons given structural information than models trained with random dihedral angles. Using this classification approach, we investigated local codon-codon dependencies and tested whether synonymous codon identity can be predicted more accurately from codon context than amino acid context alone, and most specifically which codon context position carries the most predictive power.

Hamiltonian Operator for Spectral Shape Analysis.

Many shape analysis methods treat the geometry of an object as a metric space that can be captured by the Laplace-Beltrami operator. In this paper, we propose to adapt the classical Hamiltonian operator from quantum mechanics to the field of shape analysis. To this end, we study the addition of a potential function to the Laplacian as a generator for dual spaces in which shape processing is performed. We present general optimization approaches for solving variational problems involving the basis defined by the Hamiltonian using perturbation theory for its eigenvectors. The suggested operator is shown to produce better functional spaces to operate with, as demonstrated on different shape analysis tasks.

Access to PCNA by Srs2 and Elg1 Controls the Choice between Alternative Repair Pathways in Saccharomyces cerevisiae.

During DNA replication, stalling can occur when the replicative DNA polymerases encounter lesions or hard-to replicate regions. Under these circumstances, the processivity factor PCNA gets ubiquitylated at lysine 164, inducing the DNA damage tolerance (DDT) mechanisms that can bypass lesions encountered during DNA replication. PCNA can also be SUMOylated at the same residue or at lysine 127. Surprisingly, pol30-K164R mutants display a higher degree of sensitivity to DNA-damaging agents than pol30-KK127,164RR strains, unable to modify any of the lysines. Here, we show that in addition to translesion synthesis and strand-transfer DDT mechanisms, an alternative repair mechanism ("salvage recombination") that copies information from the sister chromatid is repressed by the recruitment of Srs2 to SUMOylated PCNA. Overexpression of Elg1, the PCNA unloader, or of the recombination protein Rad52 allows its activation. We dissect the genetic requirements for this pathway, as well as the interactions between Srs2 and Elg1.IMPORTANCE PCNA, the ring that encircles DNA maintaining the processivity of DNA polymerases, is modified by ubiquitin and SUMO. Whereas ubiquitin is required for bypassing lesions through the DNA damage tolerance (DDT) pathways, we show here that SUMOylation represses another pathway, salvage recombination. The Srs2 helicase is recruited to SUMOylated PCNA and prevents the salvage pathway from acting. The pathway can be induced by overexpressing the PCNA unloader Elg1, or the homologous recombination protein Rad52. Our results underscore the role of PCNA modifications in controlling the various bypass and DNA repair mechanisms.

DeepISP: Towards Learning an End-to-End Image Processing Pipeline.

We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) pipeline. Our model learns a mapping from the raw low-light mosaiced image to the final visually compelling image and encompasses low-level tasks such as demosaicing and denoising as well as higher-level tasks such as color correction and image adjustment. The training and evaluation of the pipeline were performed on a dedicated dataset containing pairs of low-light and well-lit images captured by a Samsung S7 smartphone camera in both raw and processed JPEG formats. The proposed solution achieves state-of-the-art performance in objective evaluation of PSNR on the subtask of joint denoising and demosaicing. For the full end-to-end pipeline, it achieves better visual quality compared to the manufacturer ISP, in both a subjective human assessment and when rated by a deep model trained for assessing image quality.

Class-Aware Fully-Convolutional Gaussian and Poisson Denoising.

We propose a fully-convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state-of-the-art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts performance, enhances textures and reduces artifacts.

Tight Regulation of Srs2 Helicase Activity Is Crucial for Proper Functioning of DNA Repair Mechanisms.

Proper DNA damage repair is one of the most vital and fundamental functions of every cell. Several different repair mechanisms exist to deal with various types of DNA damage, in various stages of the cell cycle and under different conditions. Homologous recombination is one of the most important repair mechanisms in all organisms. Srs2, a regulator of homologous recombination, is a DNA helicase involved in DNA repair, cell cycle progression and genome integrity. Srs2 can remove Rad51 from ssDNA, and is thought to inhibit unscheduled recombination. However, Srs2 has to be precisely regulated, as failure to do so is toxic and can lead to cell death. We noticed that a very slight elevation of the levels of Srs2 (by addition of a single extra copy of the SRS2 gene) leads to hyper-sensitivity of yeast cells to methyl methanesulfonate (MMS, a DNA damaging agent). This effect is seen in haploid, but not in diploid, cells. We analyzed the mechanism that controls haploid/diploid sensitivity and arrived to the conclusion that the sensitivity requires the activity of RAD59 and RDH54, whose expression in diploid cells is repressed. We carried out a mutational analysis of Srs2 to determine the regions of the protein required for the sensitization to genotoxins. Interestingly, Srs2 needs the HR machinery and its helicase activity for its toxicity, but does not need to dismantle Rad51. Our work underscores the tight regulation that is required on the levels of Srs2 activity, and the fact that Srs2 helicase activity plays a more central role in DNA repair than the ability of Srs2 to dismantle Rad51 filaments.

The Main Role of Srs2 in DNA Repair Depends on Its Helicase Activity, Rather than on Its Interactions with PCNA or Rad51.

Homologous recombination (HR) is a mechanism that repairs a variety of DNA lesions. Under certain circumstances, however, HR can generate intermediates that can interfere with other cellular processes such as DNA transcription or replication. Cells have therefore developed pathways that abolish undesirable HR intermediates. The Saccharomyces cerevisiae yeast Srs2 helicase has a major role in one of these pathways. Srs2 also works during DNA replication and interacts with the clamp PCNA. The relative importance of Srs2's helicase activity, Rad51 removal function, and PCNA interaction in genome stability remains unclear. We created a new SRS2 allele [srs2(1-850)] that lacks the whole C terminus, containing the interaction site for Rad51 and PCNA and interactions with many other proteins. Thus, the new allele encodes an Srs2 protein bearing only the activity of the DNA helicase. We find that the interactions of Srs2 with Rad51 and PCNA are dispensable for the main role of Srs2 in the repair of DNA damage in vegetative cells and for proper completion of meiosis. On the other hand, it has been shown that in cells impaired for the DNA damage tolerance (DDT) pathways, Srs2 generates toxic intermediates that lead to DNA damage sensitivity; we show that this negative Srs2 activity requires the C terminus of Srs2. Dissection of the genetic interactions of the srs2(1-850) allele suggest a role for Srs2's helicase activity in sister chromatid cohesion. Our results also indicate that Srs2's function becomes more central in diploid cells.IMPORTANCE Homologous recombination (HR) is a key mechanism that repairs damaged DNA. However, this process has to be tightly regulated; failure to regulate it can lead to genome instability. The Srs2 helicase is considered a regulator of HR; it was shown to be able to evict the recombinase Rad51 from DNA. Cells lacking Srs2 exhibit sensitivity to DNA-damaging agents, and in some cases, they display defects in DNA replication. The relative roles of the helicase and Rad51 removal activities of Srs2 in genome stability remain unclear. To address this question, we created a new Srs2 mutant which has only the DNA helicase domain. Our study shows that only the DNA helicase domain is needed to deal with DNA damage and assist in DNA replication during vegetative growth and in meiosis. Thus, our findings shift the view on the role of Srs2 in the maintenance of genome integrity.

Cross-Talk between Carbon Metabolism and the DNA Damage Response in S. cerevisiae.

Yeast cells with DNA damage avoid respiration, presumably because products of oxidative metabolism can be harmful to DNA. We show that DNA damage inhibits the activity of the Snf1 (AMP-activated) protein kinase (AMPK), which activates expression of genes required for respiration. Glucose and DNA damage upregulate SUMOylation of Snf1, catalyzed by the SUMO E3 ligase Mms21, which inhibits SNF1 activity. The DNA damage checkpoint kinases Mec1/ATR and Tel1/ATM, as well as the nutrient-sensing protein kinase A (PKA), regulate Mms21 activity toward Snf1. Mec1 and Tel1 are required for two SNF1-regulated processes-glucose sensing and ADH2 gene expression-even without exogenous genotoxic stress. Our results imply that inhibition of Snf1 by SUMOylation is a mechanism by which cells lower their respiration in response to DNA damage. This raises the possibility that activation of DNA damage checkpoint mechanisms could contribute to aerobic fermentation (Warburg effect), a hallmark of cancer cells.

A genetic screen for high copy number suppressors of the synthetic lethality between elg1Δ and srs2Δ in yeast.

Elg1 and Srs2 are two proteins involved in maintaining genome stability in yeast. After DNA damage, the homotrimeric clamp PCNA, which provides stability and processivity to DNA polymerases and serves as a docking platform for DNA repair enzymes, undergoes modification by the ubiquitin-like molecule SUMO. PCNA SUMOylation helps recruit Srs2 and Elg1 to the replication fork. In the absence of Elg1, both SUMOylated PCNA and Srs2 accumulate at the chromatin fraction, indicating that Elg1 is required for removing SUMOylated PCNA and Srs2 from DNA. Despite this interaction, which suggests that the two proteins work together, double mutants elg1Δ srs2Δ have severely impaired growth as haploids and exhibit synergistic sensitivity to DNA damage and a synergistic increase in gene conversion. In addition, diploid elg1Δ srs2Δ double mutants are dead, which implies that an essential function in the cell requires at least one of the two gene products for survival. To gain information about this essential function, we have carried out a high copy number suppressor screen to search for genes that, when overexpressed, suppress the synthetic lethality between elg1Δ and srs2Δ. We report the identification of 36 such genes, which are enriched for functions related to DNA- and chromatin-binding, chromatin packaging and modification, and mRNA export from the nucleus.