Chromatin immunoprecipitation (ChIP) defines the genomic distribution of proteins and their modifications but is limited by the cell numbers required (ideally >10(7)). Here we describe a protocol that uses carrier chromatin and PCR, 'carrier' ChIP (CChIP), to permit analysis of as few as 100 cells. We assayed histone modifications at key regulator genes (such as Nanog, Pou5f1 (also known as Oct4) and Cdx2) by CChIP in mouse embryonic stem (ES) cells and in inner cell mass (ICM) and trophectoderm of cultured blastocysts. Activating and silencing modifications (H4 acetylation and H3K9 methylation) mark active and silent promoters as predicted, and we find close correlation between values derived from CChIP (1,000 ES cells) and conventional ChIP (5 x 10(7) ES cells). Studies on genes silenced in both ICM and ES cells (Cdx2, Cfc1, Hhex and Nkx2-2, also known as Nkx) show that the intensity of silencing marks is relatively diminished in ES cells, indicating a possible relaxation of some components of silencing on adaptation to culture.

Dosage compensation in mammals involves silencing of one X chromosome in XX females and requires expression, in cis, of Xist RNA. The X to be inactivated is randomly chosen in cells of the inner cell mass (ICM) at the blastocyst stage of development. Embryonic stem (ES) cells derived from the ICM of female mice have two active X chromosomes, one of which is inactivated as the cells differentiate in culture, providing a powerful model system to study the dynamics of X inactivation. Using microarrays to assay expression of X-linked genes in undifferentiated female and male mouse ES cells, we detect global up-regulation of expression (1.4- to 1.6-fold) from the active X chromosomes, relative to autosomes. We show a similar up-regulation in ICM from male blastocysts grown in culture. In male ES cells, up-regulation reaches 2-fold after 2–3 weeks of differentiation, thereby balancing expression between the single X and the diploid autosomes. We show that silencing of X-linked genes in female ES cells occurs on a gene-by-gene basis throughout differentiation, with some genes inactivating early, others late, and some escaping altogether. Surprisingly, by allele-specific analysis in hybrid ES cells, we also identified a subgroup of genes that are silenced in undifferentiated cells. We propose that X-linked genes are silenced in female ES cells by spreading of Xist RNA through the X chromosome territory as the cells differentiate, with silencing times for individual genes dependent on their proximity to the Xist locus.

STUDY QUESTION Can an artificial intelligence (AI)-based model predict human embryo viability using images captured by optical light microscopy? SUMMARY ANSWER We have combined computer vision image processing methods and deep learning techniques to create the non-invasive Life Whisperer AI model for robust prediction of embryo viability, as measured by clinical pregnancy outcome, using single static images of Day 5 blastocysts obtained from standard optical light microscope systems. WHAT IS KNOWN ALREADY Embryo selection following IVF is a critical factor in determining the success of ensuing pregnancy. Traditional morphokinetic grading by trained embryologists can be subjective and variable, and other complementary techniques, such as time-lapse imaging, require costly equipment and have not reliably demonstrated predictive ability for the endpoint of clinical pregnancy. AI methods are being investigated as a promising means for improving embryo selection and predicting implantation and pregnancy outcomes. STUDY DESIGN, SIZE, DURATION These studies involved analysis of retrospectively collected data including standard optical light microscope images and clinical outcomes of 8886 embryos from 11 different IVF clinics, across three different countries, between 2011 and 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS The AI-based model was trained using static two-dimensional optical light microscope images with known clinical pregnancy outcome as measured by fetal heartbeat to provide a confidence score for prediction of pregnancy. Predictive accuracy was determined by evaluating sensitivity, specificity and overall weighted accuracy, and was visualized using histograms of the distributions of predictions. Comparison to embryologists’ predictive accuracy was performed using a binary classification approach and a 5-band ranking comparison. MAIN RESULTS AND THE ROLE OF CHANCE The Life Whisperer AI model showed a sensitivity of 70.1% for viable embryos while maintaining a specificity of 60.5% for non-viable embryos across three independent blind test sets from different clinics. The weighted overall accuracy in each blind test set was >63%, with a combined accuracy of 64.3% across both viable and non-viable embryos, demonstrating model robustness and generalizability beyond the result expected from chance. Distributions of predictions showed clear separation of correctly and incorrectly classified embryos. Binary comparison of viable/non-viable embryo classification demonstrated an improvement of 24.7% over embryologists’ accuracy (P = 0.047, n = 2, Student’s t test), and 5-band ranking comparison demonstrated an improvement of 42.0% over embryologists (P = 0.028, n = 2, Student’s t test). LIMITATIONS, REASONS FOR CAUTION The AI model developed here is limited to analysis of Day 5 embryos; therefore, further evaluation or modification of the model is needed to incorporate information from different time points. The endpoint described is clinical pregnancy as measured by fetal heartbeat, and this does not indicate the probability of live birth. The current investigation was performed with retrospectively collected data, and hence it will be of importance to collect data prospectively to assess real-world use of the AI model. WIDER IMPLICATIONS OF THE FINDINGS These studies demonstrated an improved predictive ability for evaluation of embryo viability when compared with embryologists’ traditional morphokinetic grading methods. The superior accuracy of the Life Whisperer AI model could lead to improved pregnancy success rates in IVF when used in a clinical setting. It could also potentially assist in standardization of embryo selection methods across multiple clinical environments, while eliminating the need for complex time-lapse imaging equipment. Finally, the cloud-based software application used to apply the Life Whisperer AI model in clinical practice makes it broadly applicable and globally scalable to IVF clinics worldwide. STUDY FUNDING/COMPETING INTEREST(S) Life Whisperer Diagnostics, Pty Ltd is a wholly owned subsidiary of the parent company, Presagen Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation and Startup Fund (RCSF). ‘In kind’ support and embryology expertise to guide algorithm development were provided by Ovation Fertility. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. Presagen has filed a provisional patent for the technology described in this manuscript (52985P pending). A.P.M. owns stock in Life Whisperer, and S.M.D., A.J., T.N. and A.P.M. are employees of Life Whisperer.

Computer-automated time-lapse analysis has been shown to improve embryo selection by providing quantitative and objective information to supplement traditional morphology. In this multi-centre study, the relationship between such computer-derived outputs (High, Medium, Low scores), embryo implantation and clinical pregnancy were examined. Data were collected from six clinics, including 205 patients whose embryos were imaged by the Eeva™System. The Eeva scores were blinded and not considered during embryo selection. Embryos with High and Medium scores had significantly higher implantation rates than those with Low scores (37% and 35% versus 15%; P < 0.0001; P = 0.0004). Similar trends in implantation rates were observed in different IVF centres each using their own protocols. Further analysis revealed that patients with at least one High embryo transferred had significantly higher clinical pregnancy rates than those with only Low embryos transferred (51% versus 34%; P = 0.02), although patients’ clinical characteristics across groups were comparable. These data, together with previous research and clinical studies, confirm that computer-automated Eeva scores provide valuable information, which may improve the clinical outcome of IVF procedures and ultimately facilitate the trend of single embryo selection.