Artificial intelligence system for outcome evaluations of human in vitro fertilization-derived embryos.

BACKGROUND: In vitro fertilization (IVF) has emerged as a transformative solution for infertility. However, achieving favorable live-birth outcomes remains challenging. Current clinical IVF practices in IVF involve the collection of heterogeneous embryo data through diverse methods, including static images and temporal videos. However, traditional embryo selection methods, primarily reliant on visual inspection of morphology, exhibit variability and are contingent on the experience of practitioners. Therefore, an automated system that can evaluate heterogeneous embryo data to predict the final outcomes of live births is highly desirable. METHODS: We employed artificial intelligence (AI) for embryo morphological grading, blastocyst embryo selection, aneuploidy prediction, and final live-birth outcome prediction. We developed and validated the AI models using multitask learning for embryo morphological assessment, including pronucleus type on day 1 and the number of blastomeres, asymmetry, and fragmentation of blastomeres on day 3, using 19,201 embryo photographs from 8271 patients. A neural network was trained on embryo and clinical metadata to identify good-quality embryos for implantation on days or day 5, and predict live-birth outcomes. Additionally, a 3D convolutional neural network was trained on 418 time-lapse videos of preimplantation genetic testing (PGT)-based ploidy outcomes for aneuploidy prediction and consequent live-birth outcomes. RESULTS: These two approaches enabled us to automatically assess the implantation potential. By combining embryo and maternal metrics in an ensemble AI model, we evaluated live-birth outcomes in a prospective cohort that achieved higher accuracy than experienced embryologists (46.1% vs. 30.7% on day 3, 55.0% vs. 40.7% on day 5). Our results demonstrate the potential for AI-based selection of embryos based on characteristics beyond the observational abilities of human clinicians (area under the curve: 0.769, 95% confidence interval: 0.709-0.820). These findings could potentially provide a noninvasive, high-throughput, and low-cost screening tool to facilitate embryo selection and achieve better outcomes. CONCLUSIONS: Our study underscores the AI model's ability to provide interpretable evidence for clinicians in assisted reproduction, highlighting its potential as a noninvasive, efficient, and cost-effective tool for improved embryo selection and enhanced IVF outcomes. The convergence of cutting-edge technology and reproductive medicine has opened new avenues for addressing infertility challenges and optimizing IVF success rates.

Deep-learning-enabled protein-protein interaction analysis for prediction of SARS-CoV-2 infectivity and variant evolution.

Host-pathogen interactions and pathogen evolution are underpinned by protein-protein interactions between viral and host proteins. An understanding of how viral variants affect protein-protein binding is important for predicting viral-host interactions, such as the emergence of new pathogenic SARS-CoV-2 variants. Here we propose an artificial intelligence-based framework called UniBind, in which proteins are represented as a graph at the residue and atom levels. UniBind integrates protein three-dimensional structure and binding affinity and is capable of multi-task learning for heterogeneous biological data integration. In systematic tests on benchmark datasets and further experimental validation, UniBind effectively and scalably predicted the effects of SARS-CoV-2 spike protein variants on their binding affinities to the human ACE2 receptor, as well as to SARS-CoV-2 neutralizing monoclonal antibodies. Furthermore, in a cross-species analysis, UniBind could be applied to predict host susceptibility to SARS-CoV-2 variants and to predict future viral variant evolutionary trends. This in silico approach has the potential to serve as an early warning system for problematic emerging SARS-CoV-2 variants, as well as to facilitate research on protein-protein interactions in general.

Homologous or heterogenous vaccination boosters enhance neutralizing activities against SARS-CoV-2 Omicron BA.1 variant.

The SARS-CoV-2 Omicron BA.1 variant of concern contains more than 30 mutations in the spike protein, with half of these mutations localized in the receptor-binding domain (RBD). Emerging evidence suggests that these large number of mutations impact the neutralizing efficacy of vaccines and monoclonal antibodies. We investigated the relative contributions of spike protein and RBD mutations in Omicron BA.1 variants on infectivity, cell-cell fusion, and their sensitivity to neutralization by monoclonal antibodies or vaccinated sera from individuals who received homologous (CoronaVac, SinoPharm) or heterologous (CoronaVac-BNT162b2, BioNTech) and nonhuman primates that received a recombinant RBD protein vaccine. Our data overall reveal that the mutations in the spike protein reduced infectivity and cell-cell fusion compared to the D614G variant. The impaired infectivity and cell-cell fusion were dependent on non-RBD mutations. We also find reduced sensitivity to neutralization by monoclonal antibodies and vaccinated sera. However, our results also show that nonhuman primates receiving a recombinant RBD protein vaccine show substantial neutralization activity. Our study sheds light on the molecular differences in neutralizing antibody escape by the Omicron BA.1 variant, and highlights the promise of recombinant RBD vaccines in neutralizing the threat posed by the Omicron BA.1 variant.

Pathological observation of brain arteries and spontaneous aneurysms in hypertensive rats.

OBJECTIVE: To investigate the role of hypertension in the pathogenesis of cerebral aneurysms in rats. METHODS: Twenty spontaneous hypertensive rats (SHR) and 10 Wistar-Kyoto rats (WKY) were included in this observational study. Animals were fed with normal diet and drinking water. No experimental modifications were undertaken in either group. They were sacrificed at one year of age, the bifurcations of the circle of Willis were dissected and longitudinal serial sections were prepared for light microscopic and transmission electron microscopic study. RESULTS: In the SHR group, 2 of the 20 rats formed an aneurysm respectively at the bifurcations of the basilar artery. As revealed by electron microscopy, injury at the bifurcation of the artery first occurred on the steeper side of the intimal pad. Furthermore, loss of endothelial cells, small depressions on the intima, disruptive internal elastic lamina and lymphocytes or red blood cells infiltration were noted at the steeper side of the intimal pad. No significant changes were observed in WKY group. CONCLUSIONS: Cerebral aneurysms can form spontaneously in SHR without ligation of the common carotid artery and without a diet containing beta-aminoproprionitrile. Long-standing systemic arterial hypertension is one of the etiological factors that contributes to aneurysm formation in SHR rats.