Search

In this study, heterocyclic compounds containing a benzothiophene scaffold were designed and synthetized, and their inhibitory activity against cholinesterases (ChE) and the viability of SH-SY5Y cells have been evaluated. Benzothiophenes 4a–4i and benzothiophene-chalcone hybrids 5a–5i were tested against both acetylcholinesterase (AChE) and butyrylcholinesterase (BChE), revealing interesting structure–activity relationships. In general, benzothiophene–chalcone hybrids from series 5 proved to be better inhibitors of both enzymes, with compound 5f being the best AChE inhibitor (IC50 = 62.10 μM) and compound 5h being the best BChE inhibitor (IC50 = 24.35 μM), the last one having an IC50 similar to that of galantamine (IC50 = 28.08 μM), the reference compound. The in silico ADME profile of the compounds was also studied. Molecular docking calculations were carried out to analyze the best binding scores and to elucidate enzyme–inhibitors’ interactions.

Developing new drugs is a complex and formidable challenge, intensified by rapidly evolving global health needs. De novo drug design is a promising strategy to accelerate and refine this process. The recent introduction of Generative Artificial Intelligence (AI) algorithms has brought new attention to the field and catalyzed a paradigm shift, allowing rapid and semi-automatic design and optimization of drug-like molecules. This review explores the impact of de novo drug design, highlighting both traditional methodologies and the recently introduced generative algorithms, as well as the promising development of Active Learning (AL). It places special emphasis on their application in oncological drug development, where the need for novel therapeutic agents is urgent. The potential integration of these AI technologies with established computational and experimental methods heralds a new era in the rapid development of innovative drugs. Despite the promising developments and notable successes, these technologies are not without limitations, which require careful consideration and further advancement. This review, intended for professionals across related disciplines, provides a comprehensive introduction to AI-driven de novo drug design of small organic molecules. It aims to offer a clear understanding of the current state and future prospects of these innovative techniques in drug discovery.

Myelodysplastic neoplasms (MDS) are a heterogeneous group of hematological stem cell disorders characterized by dysplasia, cytopenias, and increased risk of acute leukemia. As prognosis differs widely between patients, and treatment options vary from observation to allogeneic stem cell transplantation, accurate and precise disease risk prognostication is critical for decision making. With this aim, we retrieved registry data from MDS patients from 90 Spanish institutions. A total of 7202 patients were included, which were divided into a training (80%) and a test (20%) set. A machine learning technique (random survival forests) was used to model overall survival (OS) and leukemia-free survival (LFS). The optimal model was based on 8 variables (age, gender, hemoglobin, leukocyte count, platelet count, neutrophil percentage, bone marrow blast, and cytogenetic risk group). This model achieved high accuracy in predicting OS (c-indexes; 0.759 and 0.776) and LFS (c-indexes; 0.812 and 0.845). Importantly, the model was superior to the revised International Prognostic Scoring System (IPSS-R) and the age-adjusted IPSS-R. This difference persisted in different age ranges and in all evaluated disease subgroups. Finally, we validated our results in an external cohort, confirming the superiority of the Artificial Intelligence Prognostic Scoring System for MDS (AIPSS-MDS) over the IPSS-R, and achieving a similar performance as the molecular IPSS. In conclusion, the AIPSS-MDS score is a new prognostic model based exclusively on traditional clinical, hematological, and cytogenetic variables. AIPSS-MDS has a high prognostic accuracy in predicting survival in MDS patients, outperforming other well-established risk-scoring systems.