Predicting Endometrial Receptivity with Targeted Second Generation Sequencing
Name
Alvin Meltsov
Abstract
In assisted reproductive medicine, optimal estimation of the time window for embryo implantation (WOI) is considered paramount for increased chance of pregnancy. This estimate is given based on the characteristics of the uterus inner layer, endometrium, and occurs around days 19–21 of the menstrual cycle. During then, the endometrium is considered as “receptive”. In one out of three patients, this general estimation is not accurate enough. A personalized approach for determining WOI has shown to be an effective solution in cases of infertility and recurrent implantation failures. While there are some of genomic diagnostic tools developed for evaluating the receptivity through transcriptomic profiling of the endometrium, none of them are currently based on accurate and targeted second generation sequencing.
In this study, a semi-supervised non-iterative approach for predicting the endometrial receptivity was developed. The transcriptomic signature of 68 biomarker candidate genes was captured with targeted allele counting sequencing (TAC-seq) protocol. To develop a suitable computational model, a reference set of 68 sequenced endometrial tissue samples of pre-receptive, receptive and post-receptive origin were used. Based on these samples, the dynamics and grouping of the endometrial transcriptomic timeline was modeled. Finally, a user-friendly web application was developed for interfacing with the model. This application is now used for clinical receptivity diagnostic assay.
In this study, a semi-supervised non-iterative approach for predicting the endometrial receptivity was developed. The transcriptomic signature of 68 biomarker candidate genes was captured with targeted allele counting sequencing (TAC-seq) protocol. To develop a suitable computational model, a reference set of 68 sequenced endometrial tissue samples of pre-receptive, receptive and post-receptive origin were used. Based on these samples, the dynamics and grouping of the endometrial transcriptomic timeline was modeled. Finally, a user-friendly web application was developed for interfacing with the model. This application is now used for clinical receptivity diagnostic assay.
Graduation Thesis language
English
Graduation Thesis type
Master - Computer Science
Supervisor(s)
Priit Palta, Kaarel Krjutškov
Defence year
2021