Computer software (SiD) assisted real-time single sperm selection associated with fertilization and blastocyst formation.

RESEARCH QUESTION: Is it possible to explore an association between individual sperm kinematics evaluated in real time and spermatozoa selected by an embryologist for intracytoplasmic sperm injection (ICSI), with subsequent normal fertilization and blastocyst formation using a novel artificial vision-based software (SiD V1.0; IVF 2.0, UK)? DESIGN: ICSI procedures were randomly video recorded and subjected to analysis using SiD V1.0, proprietary software developed by our group. In total, 383 individual spermatozoa were retrospectively analysed from a dataset of 78 ICSI-assisted reproductive technology cycles. SiD software computes the progressive motility parameters, straight-line velocity (VSL) and linearity of the curvilinear path (LIN), of each sperm trajectory, along with a quantitative value, head movement pattern (HMP), which is an indicator of the characteristics of the sperm head movement patterns. The mean VSL, LIN and HMP measurements for each set of spermatozoa were compared based on different outcome measures. RESULTS: Statistically significant differences were found in VSL, LIN and HMP among those spermatozoa selected for injection (P < 0.001). Additionally, LIN and HMP were found to be significantly different between successful and unsuccessful fertilization (P = 0.038 and P = 0.029, respectively). Additionally, significantly higher SiD scores were found for those spermatozoa that achieved both successful fertilization (P = 0.004) and blastocyst formation (P = 0.013). CONCLUSION: The possibility of carrying out real-time analyses of individual spermatozoa using an automatic tool such as SiD creates the opportunity to assist the embryologist in selecting the better spermatozoon for injection in an ICSI procedure.

Predicted regulatory SNPs reveal potential drug targets and novel companion diagnostics in psoriasis.

Psoriasis is an autoimmune disease associated with interleukins, their receptors, key transcription factors and more recently, antimicrobial peptides (AMPs). Cathelicidin LL-37 is an AMP proposed to play a fundamental role in psoriasis etiology. With our proprietary software SNPClinic v.1.0, we analyzed 203 common SNPs (MAF frequency â€‹> â€‹1%) in proximal promoters of 22 genes associated with psoriasis. These include nine genes which protein products are classic drug targets for psoriasis (TNF, IL17A, IL17B, IL17C, IL17F, IL17RA, IL12A, IL12B and IL23A). SNPClinic predictions were run with DNAseI-HUP chromatin accessibility data in eight psoriasis/epithelia-relevant cell lines from ENCODE including keratinocytes (NHEK), TH1 and TH17 lymphocytes. Results were ranked quantitatively by transcriptional relevance according to our novel Functional Impact Factor (FIF) parameter. We found six rSNPs in five genes (CAMP/cathelicidin, S100A7/psoriasin, IL17C, IL17RA and TNF) and each was confirmed as true rSNP in at least one public eQTL database including GTEx portal and ENCODE (Phase 3). Predicted regulatory SNPs in cathelicidin, IL17C and IL17RA genes may explain hyperproliferation of keratinocytes. Predicted rSNPs in psoriasin, IL17C and cathelicidin may contribute to activation and polarization of lymphocytes. Predicted rSNPs in TNF gene are concordant with the epithelium-mesenchymal transition. In spite that these results must be validated in vitro and in vivo with a functional genomics approach, we propose FOXP2, RUNX2, NR2F1, ELF1 and HESX1 transcription factors (those with the highest FIF on each gene) as novel drug targets for psoriasis. Furthermore, four out of six rSNPs uncovered by SNPClinic v.1.0 software, could also be validated in the clinic as companion diagnostics/pharmacogenetics assays for psoriasis prescribed drugs that block TNF-α (e.g. Etanercept), IL-17 (e.g. Secukinumab) and IL-17 receptor (Brodalumab).

Evaluating predictive models in reproductive medicine.

Predictive modeling has become a distinct subdiscipline of reproductive medicine, and researchers and clinicians are just learning the skills and expertise to evaluate artificial intelligence (AI) studies. Diagnostic tests and model predictions are subject to evaluation. Their use offers potential for both harm and benefit in terms of diagnosis, treatment, and prognosis. The performance of AI models and their potential clinical utility hinge on the quality and size of the databases used, the types and distribution of data, and the particular AI method applied. Additionally, when images are involved, the method of capturing, preprocessing, and treatment and accurate labeling of images becomes an important component of AI modeling. Inconsistent image treatment or inaccurate labeling of images can lead to an inconsistent database, resulting in poor AI accuracy. We discuss the critical appraisal of AI models in reproductive medicine and convey the importance of transparency and standardization in reporting AI models so that the risk of bias and the potential clinical utility of AI can be assessed.

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

Artificial intelligence (AI) systems have been proposed for reproductive medicine since 1997. Although AI is the main driver of emergent technologies in reproduction, such as robotics, Big Data, and internet of things, it will continue to be the engine for technological innovation for the foreseeable future. What does the future of AI research look like?

Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation.

RESEARCH QUESTION: Can a deep machine learning artificial intelligence algorithm predict ploidy and implantation in a known data set of static blastocyst images, and how does its performance compare against chance and experienced embryologists? DESIGN: A database of blastocyst images with known outcome was applied with an algorithm dubbed ERICA (Embryo Ranking Intelligent Classification Algorithm). It was evaluated against its ability to predict euploidy, compare ploidy prediction against randomly assigned prognosis labels and against senior embryologists, and if it could rank an euploid embryo highly. RESULTS: A total of 1231 embryo images were classed as good prognosis if euploid and implanted or poor prognosis if aneuploid and failed to implant. An accuracy of 0.70 was obtained with ERICA, with positive predictive value of 0.79 for predicting euploidy. ERICA had greater normalized discontinued cumulative gain (ranking metric) than random selection (P = 0.0007), and both embryologists (P = 0.0014 and 0.0242, respectively). ERICA ranked an euploid blastocyst first in 78.9% and at least one euploid embryo within the top two blastocysts in 94.7% of cases, better than random classification and the two senior embryologists. Average embryo ranking time for four blastocysts was under 25 s. CONCLUSION: Artificial intelligence lends itself well to image pattern recognition. We have trained ERICA to rank embryos based on ploidy and implantation potential using single static embryo image. This tool represents a potentially significant advantage to assist embryologists to choose the best embryo, saving time spent annotating and does not require time lapse or invasive biopsy. Future work should be directed to evaluate reproducibility in different data sets.

Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning.

Assessing the viability of a blastosyst is still empirical and non-reproducible nowadays. We developed an algorithm based on artificial vision and machine learning (and other classifiers) that predicts pregnancy using the beta human chorionic gonadotropin (b-hCG) test from both the morphology of an embryo and the age of the patients. We employed two high-quality databases with known pregnancy outcomes (n = 221). We created a system consisting of different classifiers that is feed with novel morphometric features extracted from the digital micrographs, along with other non-morphometric data to predict pregnancy. It was evaluated using five different classifiers: probabilistic bayesian, Support Vector Machines (SVM), deep neural network, decision tree, and Random Forest (RF), using a k-fold cross validation to assess the model's generalization capabilities. In the database A, the SVM classifier achieved an F1 score of 0.74, and AUC of 0.77. In the database B the RF classifier obtained a F1 score of 0.71, and AUC of 0.75. Our results suggest that the system is able to predict a positive pregnancy test from a single digital image, offering a novel approach with the advantages of using a small database, being highly adaptable to different laboratory settings, and easy integration into clinical practice.

Is sex an influential factor in type-1 diabetes neurofunctional development? A preliminary study.

The aim of the study was to evaluate the neurofunctional effect of gender in Type-1 Diabetes Mellitus (T1DM) patients during a Visual Spatial Working Memory (VSWM) task. The study included 28 participants with ages ranging from 17-28 years. Fourteen well-controlled T1DM patients (7 female) and 14 controls matched by age, sex, and education level were scanned performing a block-design VSWM paradigm. Behavioral descriptive analyses and mean comparisons were done, and between-group and condition functional activation patterns were also compared. Whole-brain cumulative BOLD signal (CumBS), voxel-wise BOLD level frequency, Euclidean distance, and divergence indices were also calculated. There were no significant differences between or within-group sex differences for correct responses and reaction times. Functional activation analyses showed that females had activation in more brain regions, and with larger clusters of cortical activations than males. Furthermore, BOLD activation was higher in males. Despite the preliminary nature of the present study given the relatively small sample size, current results acknowledge for the first time that sex might contribute to differences in functional activation in T1DM patients. Findings suggest that sex differences should be considered when studying T1DM-disease development.

An Ontology Systems Approach on Human Brain Expression and Metaproteomics.

Research in the last decade has shown growing evidence of the gut microbiota influence on brain physiology. While many mechanisms of this influence have been proposed in animal models, most studies in humans are the result of a pathology-dysbiosis association and very few have related the presence of certain taxa with brain substructures or molecular pathways. In this paper, we associated the functional ontologies in the differential expression of brain substructures from the Allen Brain Atlas database, with those of the metaproteome from the Human Microbiome Project. Our results showed several coherent clustered ontologies where many taxa could influence brain expression and physiology. A detailed analysis of psychobiotics showed specific slim ontologies functionally associated with substructures in the basal ganglia and cerebellar cortex. Some of the most relevant slim ontology groups are related to Ion transport, Membrane potential, Synapse, DNA and RNA metabolism, and Antigen processing, while the most relevant neuropathology found was Parkinson disease. In some of these cases, new hypothetical gut microbiota-brain interaction pathways are proposed.

Predicting functional regulatory SNPs in the human antimicrobial peptide genes DEFB1 and CAMP in tuberculosis and HIV/AIDS.

Single nucleotide polymorphisms (SNPs) in transcription factor binding sites (TFBSs) within gene promoter region or enhancers can modify the transcription rate of genes related to complex diseases. These SNPs can be called regulatory SNPs (rSNPs). Data compiled from recent projects, such as the 1000 Genomes Project and ENCODE, has revealed essential information used to perform in silico prediction of the molecular and biological repercussions of SNPs within TFBS. However, most of these studies are very limited, as they only analyze SNPs in coding regions or when applied to promoters, and do not integrate essential biological data like TFBSs, expression profiles, pathway analysis, homotypic redundancy (number of TFBSs for the same TF in a region), chromatin accessibility and others, which could lead to a more accurate prediction. Our aim was to integrate different data in a biologically coherent method to analyze the proximal promoter regions of two antimicrobial peptide genes, DEFB1 and CAMP, that are associated with tuberculosis (TB) and HIV/AIDS. We predicted SNPs within the promoter regions that are more likely to interact with transcription factors (TFs). We also assessed the impact of homotypic redundancy using a novel approach called the homotypic redundancy weight factor (HWF). Our results identified 10 SNPs, which putatively modify the binding affinity of 24 TFs previously identified as related to TB and HIV/AIDS expression profiles (e.g. KLF5, CEBPA and NFKB1 for TB; FOXP2, BRCA1, CEBPB, CREB1, EBF1 and ZNF354C for HIV/AIDS; and RUNX2, HIF1A, JUN/AP-1, NR4A2, EGR1 for both diseases). Validating with the OregAnno database and cell-specific functional/non functional SNPs from additional 13 genes, our algorithm performed 53% sensitivity and 84.6% specificity to detect functional rSNPs using the DNAseI-HUP database. We are proposing our algorithm as a novel in silico method to detect true functional rSNPs in antimicrobial peptide genes. With further improvement, this novel method could be applied to other promoters in order to design probes and to discover new drug targets for complex diseases.