These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
Suggestions for second-pass anti-COVID-19 drugs based on the Artificial Intelligence measures of molecular similarity, shape and pharmacophore distribution.
preprintrevised on 15.04.2020, 14:56 and posted on 17.04.2020, 07:03 by Martyna Moskal, Wiktor Beker, Rafał Roszak, Ewa P. Gajewska, Agnieszka Wołos, Karol Molga, Sara Szymkuć, Grzegorz Grynkiewicz, Bartosz Grzybowski
Artificial Intelligence algorithms are used to identify “progeny” drugs that are similar to the “parents” already being tested against COVID-19. These algorithms assess similarity not only by the molecular make-up of the molecules, but also by the “context” in which specific functional groups are arrangedand/or by three-dimensional distribution of pharmacophores. The parent-progeny relationships span same-indication drugs (mostly antivirals) as well as those in which the “progenies” have different and perhaps less intuitive primary indications (e.g., immunosuppressant or anti-cancer progenies from antiviral parents). The “progenies” are either already approved drugs or medications in advanced clinical trials – should the currently tested “parent” medicines fail in clinical trials, these “progenies” could be, therefore, re-purposed against the COVID-19 on the timescales relevant to the current pandemic.