RESUMEN
Generative models are frequently used for de novo design in drug discovery projects to propose new molecules. However, the question of whether or not the generated molecules can be synthesized is not systematically taken into account during generation, even though being able to synthesize the generated molecules is a fundamental requirement for such methods to be useful in practice. Methods have been developed to estimate molecule "synthesizability", but, so far, there is no consensus on whether or not a molecule is synthesizable. In this paper we introduce the Retro-Score (RScore), which computes a synthetic accessibility score of molecules by performing a full retrosynthetic analysis through our data-driven synthetic planning software Spaya, and its dedicated API: Spaya-API (https://spaya.ai). We start by comparing several synthetic accessibility scores to a binary "chemist score" as estimated by chemists on a bench of generated molecules, as a first experimental validation that the RScore is a reliable synthetic accessibility score. We then describe a pipeline to generate molecules that validate a list of targets while still being easy to synthesize. We further this idea by performing experiments comparing molecular generator outputs across a range of constraints and conditions. We show that the RScore can be learned by a Neural Network, which leads to a new score: RSPred. We demonstrate that using the RScore or RSPred as a constraint during molecular generation enables our molecular generators to produce more synthesizable solutions, with higher diversity. The open-source Python code containing all the scores and the experiments can be found on ( https://github.com/iktos/generation-under-synthetic-constraint ).
RESUMEN
Neglected tropical diseases (NTDs) are a group of diseases that, besides prevailing in poverty conditions, contribute to the maintenance of social inequality, being a strong barrier to a country development. Schistosomiasis, a NTD, is a tropical and subtropical disease caused by the trematode Schistosoma mansoni (Africa, Middle East, Caribbean, Brazil, Venezuela, Suriname), japonicum (China, Indonesia, the Philippines), mekongi (several districts of Cambodia and the Lao People's Democratic Republic), intercalatum and guianensis (areas of tropical rainforests in Central Africa) and hematobium (Middle East Africa, Corsica, France) whose adult forms inhabit the mesenteric vessels of the host, while the intermediate forms are found in the aquatic gastropod snails of the genus Biomphalaria. Currently, praziquantel (PZQ) is the first line drug chosen for the treatment of schistosomiasis according to the World Health Organization (WHO) Model List of Essential Medicines, 2015. PZQ chemotherapy is considered to be the most important development for decades in the treatment of schistosomiasis. Beside the PZQ, oxamniquine (OXA) has been first described in 1969 and launched in Brazil by Pfizer under the name of Mansil® for oral administration. It has a lower cost when compared to PZQ, being active in the intestinal and hepatosplenic infections caused exclusively by S. mansoni, single species in Brazil. Both PZQ and OXA have limitations, as low efficacy in the treatment of acute schistosomiasis, low activity against S. mansoni in immature stages and resistance or tolerance, which is the reason why further research are still necessary for the development of a second generation of antischistosomal drugs. For the development of new PZQ analogs, three main strategies can be adopted: (a) synthesis and evaluation of PZQ analogues; (b) rational design of new pharmacophores; (c) discovery of new active compounds from screening programs on a large scale. Such (b) approach is difficult as the target of PZQ still unknown, the synthesis of new active analogues is possible from delineation of structure-activity relationships for PZQ. Thus, we proposed for a review article an accurate analysis of PZQ and OXA medicinal properties and uses, focusing on the pharmacochemical aspects of both drugs through 178 bibliographic references. The mechanisms of action will be discussed, with the latest information available in the literature (for the first time in the case of the oxamniquine). Cases of resistance are also discussed. As both drugs are available as a racemic mixture the biological impact of their stereochemistry to activity and side effects are reviewed. The results obtained for the combination of PZQ and artemisinin derivatives against immature worms are also introduced in the discussion. Using the information about more than 200 PZQ new derivatives synthetized during almost 35years since its discovery, a deep structure-activity relationship (SAR) is also proposed in this study.
