Description
Malaria is a silent and growing pandemic which poses a formidable challenge due to the emergence of drug-resistant parasites and the impact of climate change. It is caused by the parasite Plasmodium falciparum, and remains a significant global health concern, causing over 435,000 deaths annually across more than 100 countries. While natural products have been historically used in the development of antimalarial drugs, synthetic medicines have largely taken their place. However, the use of natural products, such as those found in Cassia abbreviata Oliv, in combating malaria remains largely captivating. On the other hand, in silico or the incooperation of Artificial Intelligence using computational methods provide affordable methods that can be used to timeously screen large datasets of compounds in search of potential antimalarial drugs. Therefore, in this work, antimalarial phytochemicals from C. abbreviata that bind to specific Plasmodium falciparum proteins targets were identified using machine learning models in conjunction with structure–based virtual screening approaches. To develop the machine learning Random Forest model, a dataset comprising known anti-Plasmodia inhibitors and their corresponding targets retrieved from the ChEMBL database was cleaned and used for training and validation of the model. Using the model, potential ligands for the Plasmodium falciparum targets were identified from a previously analysed dataset of thirty-one (31) phytochemicals from C. abbreviata. The results revealed that a Plasmodium falciparum Isolate K1 protein called Merozoite Surface Protein 2 (MSP2) is a potential target for six phytochemicals. To conform the binding of the compounds to the target structure-based virtual screening of the C. abbreviata dataset was performed by docking them to MSP2 to evaluate their binding affinity and interactions with the protein. The six phytochemicals from C. abbreviata exhibited favourable binding energies ranging from -9.35 kcal/mol to -14.7 kcal/mol. Of these, two compounds were flavonoids with hydroxyl groups (-OH) that scavenge free radicals induced by the malaria parasite and four were terpenoids with multiple isoprene units associated with their antimalarial activity. Therefore, by using a predictive Random Forest machine learning model and its integration with docking studies 6 phytochemicals from C. abbreviata with potential antimalarial activity and their target were identified. Thus, exploration of the binding of phytochemicals from C. abbreviata to a key malaria protein associated with the survival and growth of the Plasmodium falciparum parasite in the human body holds promise in the ongoing fight against malaria.
| Contact Geneva Health Forum | I would like to receive information about the GHF 2024 conference and other GHF activities / Je souhaite recevoir des informations sur la conférence GHF 2024 et d'autres activités du GHF. |
|---|
