Date Published: February 8, 2018
Publisher: Public Library of Science
Author(s): Yunierkis Perez-Castillo, Aminael Sánchez-Rodríguez, Eduardo Tejera, Maykel Cruz-Monteagudo, Fernanda Borges, M. Natália D. S. Cordeiro, Huong Le-Thi-Thu, Hai Pham-The, Giovanni Maga.
Gastric cancer is the third leading cause of cancer-related mortality worldwide and despite advances in prevention, diagnosis and therapy, it is still regarded as a global health concern. The efficacy of the therapies for gastric cancer is limited by a poor response to currently available therapeutic regimens. One of the reasons that may explain these poor clinical outcomes is the highly heterogeneous nature of this disease. In this sense, it is essential to discover new molecular agents capable of targeting various gastric cancer subtypes simultaneously. Here, we present a multi-objective approach for the ligand-based virtual screening discovery of chemical compounds simultaneously active against the gastric cancer cell lines AGS, NCI-N87 and SNU-1. The proposed approach relays in a novel methodology based on the development of ensemble models for the bioactivity prediction against each individual gastric cancer cell line. The methodology includes the aggregation of one ensemble per cell line using a desirability-based algorithm into virtual screening protocols. Our research leads to the proposal of a multi-targeted virtual screening protocol able to achieve high enrichment of known chemicals with anti-gastric cancer activity. Specifically, our results indicate that, using the proposed protocol, it is possible to retrieve almost 20 more times multi-targeted compounds in the first 1% of the ranked list than what is expected from a uniform distribution of the active ones in the virtual screening database. More importantly, the proposed protocol attains an outstanding initial enrichment of known multi-targeted anti-gastric cancer agents.
Gastric cancer (GC) is the third leading cause of cancer-related mortality worldwide. Despite advances in prevention, diagnosis and therapy, GC is still regarded as a global health concern. The high mortality of GC is mainly due to late diagnosis and poor response to the currently available therapeutic regimens . Overall, clinical response to chemotherapy ranges from 20 to 40%. Fluoropyrimidine- and platinum-based chemotherapeutic treatments are recommended in the neoadjuvant or adjuvant setting as the first-line treatment in patients with advanced and unresectable GC. The search for alternatives to conventional chemotherapeutic regimens is an active field of work in drug-design related to GC. In this sense, a number of recent papers reports advances in the discovery of drug targets e.g. key components of specific oncogenic pathways that could be targeted by novel therapies. However, based on the results of phase III clinical trials, targeted therapies have shown to offer only a limited survival advantage of a few months (1.5–2.2 months) .
Here, we have presented the application of a workflow relying on our recently reported methodology based on ensemble modeling and desirability  for exploring VS models to identify broad-spectrum anti-GC chemicals. Bioactivity data for the GC cell lines AGS, NCI-N87 and SNU-1 were collected from the ChEMBL database and subjected to a thorough curation process. Ensemble modeling led to accurate and generalizable QSAR models. These ensemble models were then used for exploring possible multi-objective VS protocols. The best VS protocol was able to achieve high values of enrichment in VS simulations, proving that our approach could be an effective tool for the rational discovery of broad-spectrum anti-GC chemicals. The results obtained in the VS of the DrugBank database also supported this conclusion. This VS protocol will be applied to the VS identification of potential broad-spectrum anti-GC chemicals from databases of commercially available chemical compounds. These predictions will be evaluated in the wet-lab in further research stages.