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.

The GM-CSF, IL-3 and IL-5 family of cytokines, also known as the βc family due to their receptors sharing the signalling subunit βc, regulates multiple biological processes such as native and adaptive immunity, inflammation, normal and malignant hemopoieis, and autoimmunity. Australian scientists played a major role in the discovery and biological characterisation of the βc cytokines and their recent work is revealing unique features of cytokine receptor assembly and signalling. Furthermore, specific antibodies have been generated to modulate their function. Characterisation of the structural and dynamic requirements for the activation of the βc receptor family and the molecular definition of downstream signalling pathways are providing new insights into cytokine receptor signalling as well as new therapeutic opportunities.

Therapeutic options are limited for elderly patients with acute myeloid leukemia (AML). A phase Ib/II study was undertaken to evaluate the maximum-tolerated dose (MTD) and preliminary efficacy of the pan-histone deacetylase inhibitor panobinostat (LBH589) in combination with azacitidine in patients with AML or high-risk myelodysplastic syndrome (MDS) naïve to intensive chemotherapy. Thirty-nine patients (AML=29, MDS=10) received azacitidine 75 mg/m2 subcutaneously (days 1–5) and oral panobinostat (starting on day 5, thrice weekly for seven doses) in 28-day cycles until toxicity or disease progression. Dose-limiting toxicities during the phase Ib stage were observed in 0/4 patients receiving 10 mg panobinostat, in 1/7 patients (fatigue) receiving 20 mg, in 1/6 patients (fatigue) receiving 30 mg and in 4/5 patients (fatigue, syncope, hyponatremia and somnolence) receiving 40 mg. In phase II, an additional 17 patients received panobinostat at a MTD of 30 mg. The overall response rate (ORR=CR+CRi+PR) in patients with AML was 31% (9/29) and that in patients with MDS was 50% (5/10). After a median follow-up of 13 months, the median overall survival was 8 and 16 months in patients with AML and MDS, respectively. Increased histone H3 and H4 acetylation was a useful early biomarker of clinical response. Combining panobinostat with azacitidine was tolerable and clinically active in high-risk MDS/AML patients, warranting further exploration.

Granulocyte-macrophage colony-stimulating factor (GM-CSF) is a pluripotent cytokine produced by many cells in the body, which regulates normal and malignant hemopoiesis as well as innate and adaptive immunity. GM-CSF assembles and activates its heterodimeric receptor complex on the surface of myeloid cells, initiating multiple signaling pathways that control key functions such as cell survival, cell proliferation, and functional activation. Understanding the molecular composition of these pathways, the interaction of the various components as well as the kinetics and dose-dependent mechanics of receptor activation provides valuable insights into the function of GM-CSF as well as the related cytokines, interleukin-3 and interleukin-5. This knowledge provides opportunities for the development of new therapies to block the action of these cytokines in hematological malignancy and chronic inflammation.

SummaryCytokines are secreted soluble peptides that precisely regulate multiple cellular functions. Amongst these the GM-CSF/IL-3/IL-5 family of cytokines controls whether hematopoietic cells will survive or apoptose, proliferate, differentiate, migrate, or perform effector functions such as phagocytosis or reactive oxygen species release. Their potent and pleiotropic activities are mediated through binding to high affinity membrane receptors at surprisingly low numbers per cell. Receptor binding triggers a cascade of intracellular signaling events, including reversible phosphorylation of receptor subunits and associated signaling molecules, leading to multiple biological responses, with the prevention of apoptosis or ''cell survival'' being a key cellular function that underpins all others. Many chronic inflammatory diseases and a number of haematological malignancies are driven by deregulated GM-CSF, IL-3, or IL-5 cytokine receptor signaling, highlighting their importance in disease. A major step in understanding how these cytokine receptors function is to elucidate their three dimensional structure and to relate this to the many signaling pathways emanating from their receptors. We have recently solved the structure of the human GM-CSF receptor complexed to GM-CSF which revealed distinct forms of receptor assembly: a hexamer that comprises two molecules each of GM-CSF, GM-CSF receptor alpha chain and GM-CSF receptor beta chain; and an unexpected dodecamer in which two hexameric complexes associate through a novel site 4. This latter form is necessary to bring JAK2 molecules sufficiently close together to enable full receptor activation. In this review we focus on the most recent insights in cytokine receptor signaling, and in receptor assembly. The stage is now set to link distinct forms of cytokine receptor assembled structures to specific forms of cytokine receptor signaling and function. Armed with this knowledge it may be possible to map distinct cytokine receptor signaling pathways from the cell surface to the cell nucleus which may themselves become new therapeutic targets. IUBMBIUBMB Life, 62 (7): [509][510][511][512][513][514][515][516][517][518] 2010

No abstract

Prognostic gene expression signatures have been proposed as clinical tools to clarify therapeutic options in acute myeloid leukemia (AML). However, these signatures rely on measuring large numbers of genes and often perform poorly when applied to independent cohorts or those with older patients. Long intergenic non-coding RNAs (lincRNAs) are emerging as important regulators of cell identity and oncogenesis, but knowledge of their utility as prognostic markers in AML is limited. Here we analyze transcriptomic data from multiple cohorts of clinically annotated AML patients and report that (i) microarrays designed for coding gene expression can be repurposed to yield robust lincRNA expression data, (ii) some lincRNA genes are located in close proximity to hematopoietic coding genes and show strong expression correlations in AML, (iii) lincRNA gene expression patterns distinguish cytogenetic and molecular subtypes of AML, (iv) lincRNA signatures composed of three or four genes are independent predictors of clinical outcome and further dichotomize survival in European Leukemia Net (ELN) risk groups and (v) an analytical tool based on logistic regression analysis of quantitative PCR measurement of four lincRNA genes (LINC4) can be used to determine risk in AML.

Transcriptional activation of egr-1 by granulocyte-macrophage colony-stimulating factor but not interleukin 3 requires phosphorylation of cAMP response element-binding protein (CREB) on serine 133.