The establishment of a complex multi-scale model of biological tissue is of great significance for the study of related diseases, and the integration of relevant quantitative data is the premise to achieve this goal. Whereas, the systematic collation of data sets related to placental tissue is relatively lacking. In this study, 18 published transcriptomes (a total of 425 samples) datasets of human pregnancy-related tissues (including chorionic villus and decidua, term placenta, endometrium, in vitro cell lines, etc.) from public databases were collected and analyzed. We compared the most widely used dimensionality reduction (DR) methods to generate a 2D-map for visualization of these data. We also compared the effects of different parameter settings and commonly used manifold learning methods on the results. The result indicates that the nonlinear method can better preserve the small differences between different subtypes of placental tissue than the linear method. It led the foundation for the study on accurate computational modeling of placental tissue development in the future. The datasets and analysis provide a useful source for the researchers in the field of the maternal-fetal interface and the establishment of pregnancy.