Automatic Ploidy Prediction and Quality Assessment of Human Blastocyst Using Time-Lapse Imaging.

Assessing fertilized human embryos is crucial for in vitro-fertilization (IVF), a task being revolutionized by artificial intelligence and deep learning. Existing models used for embryo quality assessment and chromosomal abnormality (ploidy) detection could be significantly improved by effectively utilizing time-lapse imaging to identify critical developmental time points for maximizing prediction accuracy. Addressing this, we developed and compared various embryo ploidy status prediction models across distinct embryo development stages. We present BELA (Blastocyst Evaluation Learning Algorithm), a state-of-the-art ploidy prediction model surpassing previous image- and video-based models, without necessitating subjective input from embryologists. BELA uses multitask learning to predict quality scores that are used downstream to predict ploidy status. By achieving an AUC of 0.76 for discriminating between euploidy and aneuploidy embryos on the Weill Cornell dataset, BELA matches the performance of models trained on embryologists' manual scores. While not a replacement for preimplantation genetic testing for aneuploidy (PGT-A), BELA exemplifies how such models can streamline the embryo evaluation process, reducing time and effort required by embryologists.

A non-invasive artificial intelligence approach for the prediction of human blastocyst ploidy: a retrospective model development and validation study.

BACKGROUND: One challenge in the field of in-vitro fertilisation is the selection of the most viable embryos for transfer. Morphological quality assessment and morphokinetic analysis both have the disadvantage of intra-observer and inter-observer variability. A third method, preimplantation genetic testing for aneuploidy (PGT-A), has limitations too, including its invasiveness and cost. We hypothesised that differences in aneuploid and euploid embryos that allow for model-based classification are reflected in morphology, morphokinetics, and associated clinical information. METHODS: In this retrospective study, we used machine-learning and deep-learning approaches to develop STORK-A, a non-invasive and automated method of embryo evaluation that uses artificial intelligence to predict embryo ploidy status. Our method used a dataset of 10 378 embryos that consisted of static images captured at 110 h after intracytoplasmic sperm injection, morphokinetic parameters, blastocyst morphological assessments, maternal age, and ploidy status. Independent and external datasets, Weill Cornell Medicine EmbryoScope+ (WCM-ES+; Weill Cornell Medicine Center of Reproductive Medicine, NY, USA) and IVI Valencia (IVI Valencia, Health Research Institute la Fe, Valencia, Spain) were used to test the generalisability of STORK-A and were compared measuring accuracy and area under the receiver operating characteristic curve (AUC). FINDINGS: Analysis and model development included the use of 10 378 embryos, all with PGT-A results, from 1385 patients (maternal age range 21-48 years; mean age 36·98 years [SD 4·62]). STORK-A predicted aneuploid versus euploid embryos with an accuracy of 69·3% (95% CI 66·9-71·5; AUC 0·761; positive predictive value [PPV] 76·1%; negative predictive value [NPV] 62·1%) when using images, maternal age, morphokinetics, and blastocyst score. A second classification task trained to predict complex aneuploidy versus euploidy and single aneuploidy produced an accuracy of 74·0% (95% CI 71·7-76·1; AUC 0·760; PPV 54·9%; NPV 87·6%) using an image, maternal age, morphokinetic parameters, and blastocyst grade. A third classification task trained to predict complex aneuploidy versus euploidy had an accuracy of 77·6% (95% CI 75·0-80·0; AUC 0·847; PPV 76·7%; NPV 78·0%). STORK-A reported accuracies of 63·4% (AUC 0·702) on the WCM-ES+ dataset and 65·7% (AUC 0·715) on the IVI Valencia dataset, when using an image, maternal age, and morphokinetic parameters, similar to the STORK-A test dataset accuracy of 67·8% (AUC 0·737), showing generalisability. INTERPRETATION: As a proof of concept, STORK-A shows an ability to predict embryo ploidy in a non-invasive manner and shows future potential as a standardised supplementation to traditional methods of embryo selection and prioritisation for implantation or recommendation for PGT-A. FUNDING: US National Institutes of Health.

Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review.

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.

Machine learning models for identifying predictors of clinical outcomes with first-line immune checkpoint inhibitor therapy in advanced non-small cell lung cancer.

Immune checkpoint inhibitors (ICIs) are standard-of-care as first-line (1L) therapy for advanced non-small cell lung cancer (aNSCLC) without actionable oncogenic driver mutations. While clinical trials demonstrated benefits of ICIs over chemotherapy, variation in outcomes across patients has been observed and trial populations may not be representative of clinical practice. Predictive models can help understand heterogeneity of treatment effects, identify predictors of meaningful clinical outcomes, and may inform treatment decisions. We applied machine learning (ML)-based survival models to a real-world cohort of patients with aNSCLC who received 1L ICI therapy extracted from a US-based electronic health record database. Model performance was evaluated using metrics including concordance index (c-index), and we used explainability techniques to identify significant predictors of overall survival (OS) and progression-free survival (PFS). The ML model achieved c-indices of 0.672 and 0.612 for OS and PFS, respectively, and Kaplan-Meier survival curves showed significant differences between low- and high-risk groups for OS and PFS (both log-rank test p < 0.0001). Identified predictors were mostly consistent with the published literature and/or clinical expectations and largely overlapped for OS and PFS; Eastern Cooperative Oncology Group performance status, programmed cell death-ligand 1 expression levels, and serum albumin were among the top 5 predictors for both outcomes. Prospective and independent data set evaluation is required to confirm these results.

Weakly-supervised tumor purity prediction from frozen H&E stained slides.

BACKGROUND: Estimating tumor purity is especially important in the age of precision medicine. Purity estimates have been shown to be critical for correction of tumor sequencing results, and higher purity samples allow for more accurate interpretations from next-generation sequencing results. Molecular-based purity estimates using computational approaches require sequencing of tumors, which is both time-consuming and expensive. METHODS: Here we propose an approach, weakly-supervised purity (wsPurity), which can accurately quantify tumor purity within a digitally captured hematoxylin and eosin (H&E) stained histological slide, using several types of cancer from The Cancer Genome Atlas (TCGA) as a proof-of-concept. FINDINGS: Our model predicts cancer type with high accuracy on unseen cancer slides from TCGA and shows promising generalizability to unseen data from an external cohort (F1-score of 0.83 for prostate adenocarcinoma). In addition we compare performance of our model on tumor purity prediction with a comparable fully-supervised approach on our TCGA held-out cohort and show our model has improved performance, as well as generalizability to unseen frozen slides (0.1543 MAE on an independent test cohort). In addition to tumor purity prediction, our approach identified high resolution tumor regions within a slide, and can also be used to stratify tumors into high and low tumor purity, using different cancer-dependent thresholds. INTERPRETATION: Overall, we demonstrate our deep learning model's different capabilities to analyze tumor H&E sections. We show our model is generalizable to unseen H&E stained slides from data from TCGA as well as data processed at Weill Cornell Medicine. FUNDING: Starr Cancer Consortium Grant (SCC I15-0027) to Iman Hajirasouliha.

Computational pathology for musculoskeletal conditions using machine learning: advances, trends, and challenges.

Histopathology is widely used to analyze clinical biopsy specimens and tissues from pre-clinical models of a variety of musculoskeletal conditions. Histological assessment relies on scoring systems that require expertise, time, and resources, which can lead to an analysis bottleneck. Recent advancements in digital imaging and image processing provide an opportunity to automate histological analyses by implementing advanced statistical models such as machine learning and deep learning, which would greatly benefit the musculoskeletal field. This review provides a high-level overview of machine learning applications, a general pipeline of tissue collection to model selection, and highlights the development of image analysis methods, including some machine learning applications, to solve musculoskeletal problems. We discuss the optimization steps for tissue processing, sectioning, staining, and imaging that are critical for the successful generalizability of an automated image analysis model. We also commenting on the considerations that should be taken into account during model selection and the considerable advances in the field of computer vision outside of histopathology, which can be leveraged for image analysis. Finally, we provide a historic perspective of the previously used histopathological image analysis applications for musculoskeletal diseases, and we contrast it with the advantages of implementing state-of-the-art computational pathology approaches. While some deep learning approaches have been used, there is a significant opportunity to expand the use of such approaches to solve musculoskeletal problems.

AD-linked R47H-TREM2 mutation induces disease-enhancing microglial states via AKT hyperactivation.

The hemizygous R47H variant of triggering receptor expressed on myeloid cells 2 (TREM2), a microglia-specific gene in the brain, increases risk for late-onset Alzheimer's disease (AD). Using transcriptomic analysis of single nuclei from brain tissues of patients with AD carrying the R47H mutation or the common variant (CV)­TREM2, we found that R47H-associated microglial subpopulations had enhanced inflammatory signatures reminiscent of previously identified disease-associated microglia (DAM) and hyperactivation of AKT, one of the signaling pathways downstream of TREM2. We established a tauopathy mouse model with heterozygous knock-in of the human TREM2 with the R47H mutation or CV and found that R47H induced and exacerbated TAU-mediated spatial memory deficits in female mice. Single-cell transcriptomic analysis of microglia from these mice also revealed transcriptomic changes induced by R47H that had substantial overlaps with R47H microglia in human AD brains, including robust increases in proinflammatory cytokines, activation of AKT signaling, and elevation of a subset of DAM signatures. Pharmacological AKT inhibition with MK-2206 largely reversed the enhanced inflammatory signatures in primary R47H microglia treated with TAU fibrils. In R47H heterozygous tauopathy mice, MK-2206 treatment abolished a tauopathy-dependent microglial subcluster and rescued tauopathy-induced synapse loss. By uncovering disease-enhancing mechanisms of the R47H mutation conserved in human and mouse, our study supports inhibitors of AKT signaling as a microglial modulating strategy to treat AD.

Comprehensive subtyping of Parkinson's disease patients with similarity fusion: a case study with BioFIND data.

Parkinson's disease (PD) is a complex neurodegenerative disorder with diverse clinical manifestations. To better understand this disease, research has been done to categorize, or subtype, patients, using an array of criteria derived from clinical assessments and biospecimen analyses. In this study, using data from the BioFIND cohort, we aimed at identifying subtypes of moderate-to-advanced PD via comprehensively considering motor and non-motor manifestations. A total of 103 patients were included for analysis. Through the use of a patient-wise similarity matrix fusion technique and hierarchical agglomerative clustering analysis, three unique subtypes emerged from the clustering results. Subtype I, comprised of 60 patients (~58.3%), was characterized by mild symptoms, both motor and non-motor. Subtype II, comprised of 20 (~19.4%) patients, was characterized by an intermediate severity, with a high tremor score and mild non-motor symptoms. Subtype III, comprised of 23 (~22.3%) patients, was characterized by more severe motor and non-motor symptoms. These subtypes show statistically significant differences when looking at motor (on and off medication) clinical features and non-motor clinical features, while there was no clear difference in demographics, biomarker levels, and genetic risk scores.

A Deep Learning Approach to Diagnostic Classification of Prostate Cancer Using Pathology-Radiology Fusion.

BACKGROUND: A definitive diagnosis of prostate cancer requires a biopsy to obtain tissue for pathologic analysis, but this is an invasive procedure and is associated with complications. PURPOSE: To develop an artificial intelligence (AI)-based model (named AI-biopsy) for the early diagnosis of prostate cancer using magnetic resonance (MR) images labeled with histopathology information. STUDY TYPE: Retrospective. POPULATION: Magnetic resonance imaging (MRI) data sets from 400 patients with suspected prostate cancer and with histological data (228 acquired in-house and 172 from external publicly available databases). FIELD STRENGTH/SEQUENCE: 1.5 to 3.0 Tesla, T2-weighted image pulse sequences. ASSESSMENT: MR images reviewed and selected by two radiologists (with 6 and 17 years of experience). The patient images were labeled with prostate biopsy including Gleason Score (6 to 10) or Grade Group (1 to 5) and reviewed by one pathologist (with 15 years of experience). Deep learning models were developed to distinguish 1) benign from cancerous tumor and 2) high-risk tumor from low-risk tumor. STATISTICAL TESTS: To evaluate our models, we calculated negative predictive value, positive predictive value, specificity, sensitivity, and accuracy. We also calculated areas under the receiver operating characteristic (ROC) curves (AUCs) and Cohen's kappa. RESULTS: Our computational method (https://github.com/ih-lab/AI-biopsy) achieved AUCs of 0.89 (95% confidence interval [CI]: [0.86-0.92]) and 0.78 (95% CI: [0.74-0.82]) to classify cancer vs. benign and high- vs. low-risk of prostate disease, respectively. DATA CONCLUSION: AI-biopsy provided a data-driven and reproducible way to assess cancer risk from MR images and a personalized strategy to potentially reduce the number of unnecessary biopsies. AI-biopsy highlighted the regions of MR images that contained the predictive features the algorithm used for diagnosis using the class activation map method. It is a fully automatic method with a drag-and-drop web interface (https://ai-biopsy.eipm-research.org) that allows radiologists to review AI-assessed MR images in real time. LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY STAGE: 2.

Fibrillar pharmacology of functionalized nanocellulose.

Cellulose nanocrystals (CNC) are linear organic nanomaterials derived from an abundant naturally occurring biopolymer resource. Strategic modification of the primary and secondary hydroxyl groups on the CNC introduces amine and iodine group substitution, respectively. The amine groups (0.285 mmol of amine per gram of functionalized CNC (fCNC)) are further reacted with radiometal loaded-chelates or fluorescent dyes as tracers to evaluate the pharmacokinetic profile of the fCNC in vivo. In this way, these nanoscale macromolecules can be covalently functionalized and yield water-soluble and biocompatible fibrillar nanoplatforms for gene, drug and radionuclide delivery in vivo. Transmission electron microscopy of fCNC reveals a length of 162.4 ± 16.3 nm, diameter of 11.2 ± 1.52 nm and aspect ratio of 16.4 ± 1.94 per particle (mean ± SEM) and is confirmed using atomic force microscopy. Size exclusion chromatography of macromolecular fCNC describes a fibrillar molecular behavior as evidenced by retention times typical of late eluting small molecules and functionalized carbon nanotubes. In vivo, greater than 50% of intravenously injected radiolabeled fCNC is excreted in the urine within 1 h post administration and is consistent with the pharmacological profile observed for other rigid, high aspect ratio macromolecules. Tissue distribution of fCNC shows accumulation in kidneys, liver, and spleen (14.6 ± 6.0; 6.1 ± 2.6; and 7.7 ± 1.4% of the injected activity per gram of tissue, respectively) at 72 h post-administration. Confocal fluorescence microscopy reveals cell-specific accumulation in these target tissue sinks. In summary, our findings suggest that functionalized nanocellulose can be used as a potential drug delivery platform for the kidneys.

Multi-task deep learning-based survival analysis on the prognosis of late AMD using the longitudinal data in AREDS.

Age-related macular degeneration (AMD) is the leading cause of vision loss. Some patients experience vision loss over a delayed timeframe, others at a rapid pace. Physicians analyze time-of-visit fundus photographs to predict patient risk of developing late-AMD, the most severe form of AMD. Our study hypothesizes that 1) incorporating historical data improves predictive strength of developing late-AMD and 2) state-of-the-art deep-learning techniques extract more predictive image features than clinicians do. We incorporate longitudinal data from the Age-Related Eye Disease Studies and deep-learning extracted image features in survival settings to predict development of late- AMD. To extract image features, we used multi-task learning frameworks to train convolutional neural networks. Our findings show 1) incorporating longitudinal data improves prediction of late-AMD for clinical standard features, but only the current visit is informative when using complex features and 2) "deep-features" are more informative than clinician derived features. We make codes publicly available at https://github.com/bionlplab/AMD_prognosis_amia2021.

Gold/alpha-lactalbumin nanoprobes for the imaging and treatment of breast cancer.

Theranostic agents should ideally be renally cleared and biodegradable. Here, we report the synthesis, characterization and theranostic applications of fluorescent ultrasmall gold quantum clusters that are stabilized by the milk metalloprotein alpha-lactalbumin. We synthesized three types of these nanoprobes that together display fluorescence across the visible and near-infrared spectra when excited at a single wavelength through optical colour coding. In live tumour-bearing mice, the near-infrared nanoprobe generates contrast for fluorescence, X-ray computed tomography and magnetic resonance imaging, and exhibits long circulation times, low accumulation in the reticuloendothelial system, sustained tumour retention, insignificant toxicity and renal clearance. An intravenously administrated near-infrared nanoprobe with a large Stokes shift facilitated the detection and image-guided resection of breast tumours in vivo using a smartphone with modified optics. Moreover, the partially unfolded structure of alpha-lactalbumin in the nanoprobe helps with the formation of an anti-cancer lipoprotein complex with oleic acid that triggers the inhibition of the MAPK and PI3K-AKT pathways, immunogenic cell death and the recruitment of infiltrating macrophages. The biodegradability and safety profile of the nanoprobes make them suitable for the systemic detection and localized treatment of cancer.

γ-Secretase Partitioning into Lipid Bilayers Remodels Membrane Microdomains after Direct Insertion.

γ-Secretase is a multisubunit complex that catalyzes intramembranous cleavage of transmembrane proteins. The lipid environment forms membrane microdomains that serve as spatio-temporal platforms for proteins to function properly. Despite substantial advances in the regulation of γ-secretase, the effect of the local membrane lipid microenvironment on the regulation of γ-secretase is poorly understood. Here, we characterized and quantified the partitioning of γ-secretase and its substrates, the amyloid precursor protein (APP) and Notch, into lipid bilayers using solid-supported model membranes. Notch substrate is preferentially localized in the liquid-disordered (Ld) lipid domains, whereas APP and γ-secretase partition as single or higher complex in both phases but highly favor the ordered phase, especially after recruiting lipids from the ordered phase, indicating that the activity and specificity of γ-secretase against these two substrates are modulated by membrane lateral organization. Moreover, time-elapse measurements reveal that γ-secretase can recruit specific membrane components from the cholesterol-rich Lo phase and thus creates a favorable lipid environment for substrate recognition and therefore activity. This work offers insight into how γ-secretase and lipid modulate each other and control its activity and specificity.

Acute and chronic demyelinated CNS lesions exhibit opposite elastic properties.

Increased deposition of extracellular matrix (ECM) is a known inhibitor of axonal regrowth and remyelination. Recent in vitro studies have demonstrated that oligodendrocyte differentiation is impacted by the physical properties of the ECM. However, characterization of the mechanical properties of the healthy and injured CNS myelin is challenging, and has largely relied on non-invasive, low-resolution methods. To address this, we have employed atomic force microscopy to perform micro-indentation measurements of demyelinated tissue at cellular scale. Analysis of mouse and human demyelinated brains indicate that acute demyelination results in decreased tissue stiffness that recovers with remyelination; while chronic demyelination is characterized by increased tissue stiffness, which correlates with augmented ECM deposition. Thus, changes in the mechanical properties of the acutely (softer) or chronically (stiffer) demyelinated brain might contribute to differences in their regenerative capacity. Our findings are relevant to the optimization of cell-based therapies aimed at promoting CNS regeneration and remyelination.

The Drosophila Ninein homologue Bsg25D cooperates with Ensconsin in myonuclear positioning.

Skeletal muscle consists of multinucleated cells in which the myonuclei are evenly spaced throughout the cell. In Drosophila, this pattern is established in embryonic myotubes, where myonuclei move via microtubules (MTs) and the MT-associated protein Ensconsin (Ens)/MAP7, to achieve their distribution. Ens regulates multiple aspects of MT biology, but little is known about how Ens itself is regulated. We find that Ens physically interacts and colocalizes with Bsg25D, the Drosophila homologue of the centrosomal protein Ninein. Bsg25D loss enhances myonuclear positioning defects in embryos sensitized by partial Ens loss. Bsg25D overexpression causes severe positioning defects in immature myotubes and fully differentiated myofibers, where it forms ectopic MT organizing centers, disrupts perinuclear MT arrays, reduces muscle stiffness, and decreases larval crawling velocity. These studies define a novel relationship between Ens and Bsg25D. At endogenous levels, Bsg25D positively regulates Ens activity during myonuclear positioning, but excess Bsg25D disrupts Ens localization and MT organization, with disastrous consequences for myonuclear positioning and muscle function.

Identification of distinct nanoparticles and subsets of extracellular vesicles by asymmetric flow field-flow fractionation.

The heterogeneity of exosomal populations has hindered our understanding of their biogenesis, molecular composition, biodistribution and functions. By employing asymmetric flow field-flow fractionation (AF4), we identified two exosome subpopulations (large exosome vesicles, Exo-L, 90-120 nm; small exosome vesicles, Exo-S, 60-80 nm) and discovered an abundant population of non-membranous nanoparticles termed 'exomeres' (~35 nm). Exomere proteomic profiling revealed an enrichment in metabolic enzymes and hypoxia, microtubule and coagulation proteins as well as specific pathways, such as glycolysis and mTOR signalling. Exo-S and Exo-L contained proteins involved in endosomal function and secretion pathways, and mitotic spindle and IL-2/STAT5 signalling pathways, respectively. Exo-S, Exo-L and exomeres each had unique N-glycosylation, protein, lipid, DNA and RNA profiles and biophysical properties. These three nanoparticle subsets demonstrated diverse organ biodistribution patterns, suggesting distinct biological functions. This study demonstrates that AF4 can serve as an improved analytical tool for isolating extracellular vesicles and addressing the complexities of heterogeneous nanoparticle subpopulations.

Validation of Anti-Mouse PDL-1 Goat Polyclonal Antibody Staining with Mouse PDL-1 In Situ Hybridization on Adjacent Sections of Cell Pellets and Mouse Tumors.

Finding a valid antibody to detect mouse programmed death ligand 1 (PDL-1) by immunohistochemistry or immunofluorescence staining has been notoriously difficult. Successful validation of an antibody requires the use of multiple detection methods with the ability to compare appropriate positive and negative controls. Here, we describe in detail the protocols used to validate a mouse-specific PDL-1 antibody used in immunohistochemistry staining with an mRNA in situ hybridization on adjacent sections of mouse B16 tumor. This validation is supported by immunohistochemistry staining of PDL-1 on B16 cell pellets either treated or not treated with IFN-gamma.

Automated Double In Situ Detection of Mouse Lgr5 mRNA and Lysozyme Protein in Examining the Neighboring Cell Types of the Mouse Intestinal Crypt.

Automated detection of mRNAs and proteins in the same tissue sections is not a routine procedure. Successful experiment depends on the preparation of the tissue, the detection procedure, as well as the quality of the probes and antibodies. The multiplexed detections require experimental conditions, preserving the state of the molecular targets of interest and providing expression pattern of each target the same as in a single detection. Here we describe in detail the automated protocols used to detect mouse Lgr5 mRNA by in situ hybridization and immunofluorescence detection of lysozyme in the same mouse intestinal sections. Both the in situ hybridization and the protein detection were performed with an automated staining processor and provided strong and reproducible results.