Polyphenols are the most abundant antioxidative compounds in our diet that can be found in many types of fruit, vegetable, cereals, legumes, chocolate and in different beverages, such as coffee, tea and wine. The health effects of polyphenols depend on the amount consumed and on their bioavailability. Certain studies have subsequently confirmed health benefits of phytoestrogen intake, including a lowered risk of osteoporosis, heart disease and breast cancer. On the other hand, phytoestrogens are frequently considered as endocrine disruptors, indicating that they have the potential to cause adverse health effects as well. They are able to bind to estrogen receptors and, in turn, exert estrogenic or antiestrogenic effects. In spite of their frequent use, they have only just recently received considerable attention due to their complex chemical structure. Namely, phytoestrogens are ingested predominantly as glycosides, which immediately undergo hydrolysis, further metabolism and/or absorption. Therefore, bioavailability differs considerably between the various polyphenols, and the most abundant polyphenols in our diet are not necessarily those that have the best bioavailability profile. Often phytoestrogens metabolites possess greater biological activity than that of their precursor molecule. In the scope of this thesis Endocrine Disruptome software was employed to predict the binding affinities of selected polyphenols, as well as those of their metabolites to a number of nuclear receptors. The main focus was on isoflavonoids genistein and daidzein, to which we are predominantly exposed to through food consumption. Due to the structural similarity of isoflavones with estradiol they possess weak estrogenic or androgenic effects. Based on thorough examination of previously published in vitro and in vivo studies we established that mycoestrogens have the highest affinity for estrogen receptors, followed by coumestrans, flavonoids and chalcones, that have the lowest binding affinity for nuclear receptor. In addition, there has been receptor selectivity for genistein predicted for estrogen receptor β, which might explain the differences in exerting effects of phytoestrogens. We have also predicted the highest binding affinity for genistein and daidzein of all examined polyphenols for agonistic and antagonistic conformation of estrogen receptor. Predictions for binding affinities of selected polyphenols and metabolites to nuclear receptors made by Endocrine Disruptome were quite similar to those, previously obtained in in vitro studies. Nevertheless, our results were not completely in agreement with those obtained in in vivo studies. This is due to poor bioavailability of phytoestrogens, which is reflected in differences between in vivo and in vitro/in silico results. We can also confirm the existence of potential for endocrine toxicity, which is predominantly caused by estrogen and androgen receptors. Despite a remarkable contribution of in silico methods as a practical tool for the prediction of the endocrine disrupting potential, further development of software is still needed to be able to produce reliable and accurate results.