Prediction of antischistosomal small molecules using machine learning in the era of big data

GNN-DDAS: Drug discovery for identifying anti-schistosome small molecules based on graph neural network

Schistosomiasis is a tropical disease that poses a significant risk to hundreds of millions of people, yet often goes unnoticed. While praziquantel, a widely used anti-schistosome drug, has a low cost and a high cure rate, it has several drawbacks. These include ineffectiveness against schistosome larvae, reduced efficacy in young children, and emerging drug resistance. Discovering new and active anti-schistosome small molecules is therefore critical, but this process presents the challenge of low accuracy in computer-aided methods. To address this issue, we proposed GNN-DDAS, a novel deep learning framework based on graph neural networks (GNN), designed for drug discovery to identify active anti-schistosome (DDAS) small molecules. Initially, a multi-layer perceptron was used to derive sequence features from various representations of small molecule SMILES. Next, GNN was employed to extract structural features from molecular graphs. Finally, the extracted sequence and structural features were then concatenated and fed into a fully connected network to predict active anti-schistosome small molecules. Experimental results showed that GNN-DDAS exhibited superior performance compared to the benchmark methods on both benchmark and real-world application datasets. Additionally, the use of GNNExplainer model allowed us to analyze the key substructure features of small molecules, providing insight into the effectiveness of GNN-DDAS. Overall, GNN-DDAS provided a promising solution for discovering new and active anti-schistosome small molecules.

Targeting SmCB1: Perspectives and Insights to Design Antischistosomal Drugs

Neglected tropical diseases (NTDs) are prevalent in tropical and subtropical countries, and schistosomiasis is among the most relevant diseases worldwide. In addition, one of the two biggest problems in developing drugs against this disease is related to drug resistance, which promotes the demand to develop new drug candidates for this purpose. Thus, one of the drug targets most explored, Schistosoma mansoni Cathepsin B1 (SmCB1 or Sm31), provides new opportunities in drug development due to its essential functions for the parasite's survival. In this way, here, the latest developments in drug design studies targeting SmCB1 were approached, focusing on the most promising analogs of nitrile, vinyl sulphones, and peptidomimetics. Thus, it was shown that despite being a disease known since ancient times, it remains prevalent throughout the world, with high mortality rates. The therapeutic arsenal of antischistosomal drugs (ASD) consists only of praziquantel, which is widely used for this purpose and has several advantages, such as efficacy and safety. However, it has limitations, such as the impossibility of acting on the immature worm and exploring new targets to overcome these limitations. SmCB1 shows its potential as a cysteine protease with a catalytic triad consisting of Cys100, His270, and Asn290. Thus, design studies of new inhibitors focus on their catalytic mechanism for designing new analogs. In fact, nitrile and sulfonamide analogs show the most significant potential in drug development, showing that these chemical groups can be better exploited in drug discovery against schistosomiasis. We hope this manuscript guides the authors in searching for promising new antischistosomal drugs.

Development of a proteochemometric-based support vector machine model for predicting bioactive molecules of tubulin receptors

Microtubules are receiving enormous interest in drug discovery due to the important roles they play in cellular functions. Targeting tubulin polymerization presents an excellent opportunity for the development of anti-tubulin drugs. Drug resistance and high toxicity of currently used tubulin-binding agents have necessitated the pursuit of novel drug candidates with increased therapeutic potency. The design of novel drug candidates can be achieved using efficient computational techniques to support existing efforts. Proteochemometric (PCM) modeling is a computational technique that can be employed to elucidate the bioactivity relations between related targets and multiple ligands. We have developed a PCM-based Support Vector Machine (SVM) approach for predicting the bioactivity between tubulin receptors and small, drug-like molecules. The bioactivity datasets used for training the SVM algorithm were obtained from the Binding DB database. The SVM-based PCM model yielded a good overall predictive performance with an area under the curve (AUC) of 87%, Matthews correlation coefficient (MCC) of 72%, overall accuracy of 93%, and a classification error of 7%. The algorithm allows the prediction of the likelihood of new interactions based on confidence scores between the query datasets, comprising ligands in SMILES format and protein sequences of tubulin targets. The algorithm has been implemented as a web server known as TubPred, accessible via http://35.167.90.225:5000/ .