Depression is considered one of the most important diseases worldwide in terms of mental disorders, because since in recent years there has been a high growth in its digit of affectation. (OMS, 2018) For this reason, antidepressant drugs are created in order to mitigate the effects caused by this disorder; however, its effectiveness in all its aspects is not enough, thus generating little efficiency and a large number of side effects. This is where the creation of new drugs, in this case antidepressants of the SSRIs class (Selective serotonin reuptake inhibitors), which search to generate fewer side effects and as the name says, have greater selectivity for the reuptake of Serotonin In spite of this, the creation of new drugs requires a great amount of expenses and time; thus requiring analogously, not only the creation of new drugs, but also the invention of new methodologies for this process. For this research, the QSAR methodology was used, which has the ultimate goal of theoretically designing possible future new drugs, from the union of sets of computational techniques; with the aim of finding an analog of the SSRIs class which potentially presents a greater affinity for the active site of SERT, a serotonin reuptake protein. (Lozano & Scior, 2012) From here, the whole process that required the methodology was followed; which includes a process of virtual screening and one of machine learning; considering different molecular modeling techniques, biological activity data, physicochemical properties, statistics and bioinformatics; incorporated into each other for the theoretical creation of the new drug of the SSRIs class with potential greater affinity for its interaction site.