Prediction of Drug-Drug Interactions by Using Profile Fingerprint Vectors and Protein Similarities

Deep Modeling of Gain-of-Function Mutations on Androgen Receptor

The efficiency of Androgen Receptor (AR) pathway inhibitors for prostate cancer (PCa) is on decline due to resistance mechanisms including the occurrence of gain-of-function mutations on human androgen receptor (AR). Hence, understanding and predicting such mutations is crucial for developing effective PCa treatment strategies. Leveraging accu- mulated data on clinically relevant AR mutants with recent advances in deep modeling techniques, this study aims to unveil and quantify critical AR mutation-drug relation- ships. By incorporating molecular descriptors for drugs and mutated genes sequences, this work represented these features as single vectors and demonstrates their effective- ness in modeling AR mutant responses to conventional antiandrogens. The developed approach achieves above 80% accuracy in predicting the gain-of-function behavior of AR mutants and therefore can potentially uncover unknown agonist/antagonist relationships among mutant-drug pairs.

Geometric Molecular Graph Representation Learning Model for Drug-Drug Interactions Prediction

Drug-drug interaction (DDI) can trigger many adverse effects in patients and has emerged as a threat to medicine and public health. Therefore, it is important to predict potential drug interactions since it can provide combination strategies of drugs for systematic and effective treatment. Existing deep learning-based methods often rely on DDI functional networks, or use them as an important part of the model information source. However, it is difficult to discover the interactions of a new drug. To address the above limitations, we propose a geometric molecular graph representation learning model (Mol-DDI) for DDI prediction based on the basic assumption that structure determines function. Mol-DDI only considers the covalent and non-covalent bond information of molecules, then it uses the pre-training idea of large-scale models to learn drug molecular representations and predict drug interactions during the fine-tuning process. Experimental results show that the Mol-DDI model outperforms others on the three datasets and performs better in predicting new drug interaction experiments.

KGRLFF: Detecting Drug-Drug Interactions Based on Knowledge Graph Representation Learning and Feature Fusion

Accurate prediction of drug-drug interactions (DDIs) plays an important role in improving the efficiency of drug development and ensuring the safety of combination therapy. Most existing models rely on a single source of information to predict DDIs, and few models can perform tasks on biomedical knowledge graphs. This paper proposes a new hybrid method, namely Knowledge Graph Representation Learning and Feature Fusion (KGRLFF), to fully exploit the information from the biomedical knowledge graph and molecular structure of drugs to better predict DDIs. KGRLFF first uses a Bidirectional Random Walk sampling method based on the PageRank algorithm (BRWP) to obtain higher-order neighborhood information of drugs in the knowledge graph, including neighboring nodes, semantic relations, and higher-order information associated with triple facts. Then, an embedded representation learning model named Knowledge Graph-based Cyclic Recursive Aggregation (KGCRA) is used to learn the embedded representations of drugs by recursively propagating and aggregating messages with drugs as both the source and destination. In addition, the model learns the molecular structures of the drugs to obtain the structured features. Finally, a Feature Representation Fusion Strategy (FRFS) was developed to integrate embedded representations and structured feature representations. Experimental results showed that KGRLFF is feasible for predicting potential DDIs.

DDI-GCN: Drug-drug interaction prediction via explainable graph convolutional networks

Drug-drug interactions (DDI) may lead to unexpected side effects, which is a growing concern in both academia and industry. Many DDIs have been reported, but the underlying mechanisms are not well understood. Predicting and understanding DDIs can help researchers to improve drug safety and protect patient health. Here, we introduce DDI-GCN, a method that utilizes graph convolutional networks (GCN) to predict DDIs based on chemical structures. We demonstrate that this method achieves state-of-the-art prediction performance on the independent hold-out set. It can also provide visualization of structural features associated with DDIs, which can help us to study the underlying mechanisms. To make it easy and accessible to use, we developed a web server for DDI-GCN, which is freely available at http://wengzq-lab.cn/ddi/.

Artificial Intelligence and Data Mining for the Pharmacovigilance of Drug-Drug Interactions

Despite increasing mechanistic understanding, undetected and underrecognized drug-drug interactions (DDIs) persist. This elusiveness relates to an interwoven complexity of increasing polypharmacy, multiplex mechanistic pathways, and human biological individuality. This persistent elusiveness motivates development of artificial intelligence (AI)-based approaches to enhancing DDI detection and prediction capabilities. The literature is vast and roughly divided into "prediction" and "detection." The former relatively emphasizes biological and chemical knowledge bases, drug development, new drugs, and beneficial interactions, whereas the latter utilizes more traditional sources such as spontaneous reports, claims data, and electronic health records to detect novel adverse DDIs with authorized drugs. However, it is not a bright line, either nominally or in practice, and both are in scope for pharmacovigilance supporting signal detection but also signal refinement and evaluation, by providing data-based mechanistic arguments for/against DDI signals. The wide array of intricate and elegant methods has expanded the pharmacovigilance tool kit. How much they add to real prospective pharmacovigilance, reduce the public health impact of DDIs, and at what cost in terms of false alarms amplified by automation bias and its sequelae are open questions. (Clin Ther. 2023;45:XXX-XXX) © 2023 Elsevier HS Journals, Inc.

Cluster-based text mining for extracting drug candidates for the prevention of COVID-19 from the biomedical literature

Objective

The coronavirus disease 2019 (COVID-19) health crisis that began at the end of 2019 made researchers around the world quickly race to find effective solutions. Related literature exploded and it was inevitable that an automated approach was needed to find useful information, namely text mining, to overcome COVID-19, especially in terms of drug candidate discovery. While text mining methods for finding drug candidates mostly try to extract bioentity associations from PubMed, very few of them mine with a clustering approach. The purpose of this study was to demonstrate the effectiveness of our approach to identify drugs for the prevention of COVID-19 through literature review, cluster analysis, drug docking calculations, and clinical trial data.

Methods

This research was conducted in four main stages. First, the text mining stage was carried out by involving Bidirectional Encoder Representations from Transformers for Biomedical to obtain vector representation of each word in the sentence from texts. The next stage generated the disease-drug associations, which were obtained from the correlation between disease and drug. Next, the clustering stage grouped the rules through the similarity of diseases by utilizing Term Frequency-Inverse Document Frequency as its feature. Finally, the drug candidate extraction stage was processed through leveraging PubChem and DrugBank databases. We further used the drug docking package AUTODOCK VINA in PyRx software to verify the results.

Results

Comparative analyses showed that the percentage of findings using mining with clustering outperformed mining without clustering in all experimental settings. In addition, we suggest that the top three drugs/phytochemicals by drug docking analysis may be effective in preventing COVID-19.

Conclusions

The proposed method for text mining utilizing the clustering method is quite promising in the discovery of drug candidates for the prevention of COVID-19 through the biomedical literature.

CPInformer for Efficient and Robust Compound-Protein Interaction Prediction

Recently, deep learning has become the mainstream methodology for Compound-Protein Interaction (CPI) prediction. However, the existing compound-protein feature extraction methods have some issues that limit their performance. First, graph networks are widely used for structural compound feature extraction, but the chemical properties of a compound depend on functional groups rather than graphic structure. Besides, the existing methods lack capabilities in extracting rich and discriminative protein features. Last, the compound-protein features are usually simply combined for CPI prediction, without considering information redundancy and effective feature mining. To address the above issues, we propose a novel CPInformer method. Specifically, we extract heterogeneous compound features, including structural graph features and functional class fingerprints, to reduce prediction errors caused by similar structural compounds. Then, we combine local and global features using dense connections to obtain multi-scale protein features. Last, we apply ProbSparse self-attention to protein features, under the guidance of compound features, to eliminate information redundancy, and to improve the accuracy of CPInformer. More importantly, the proposed method identifies the activated local regions that link a CPI, providing a good visualisation for the CPI state. The results obtained on five benchmarks demonstrate the merits and superiority of CPInformer over the state-of-the-art approaches.

A Rule-Based Inference Framework to Explore and Explain the Biological Related Mechanisms of Potential Drug-Drug Interactions

As more drugs are developed and the incidence of polypharmacy increases, it is becoming critically important to anticipate potential DDIs before they occur in the clinic, along with those for which effects might go unobserved. However, traditional methods for DDI identification are unable to coalesce interaction mechanisms out of vast lists of potential or known DDIs, much less study them accurately. Computational methods have great promise but have realized only limited clinical utility. This work develops a rule-based inference framework to predict DDI mechanisms and support determination of their clinical relevance. Given a drug pair, our framework interrogates and describes DDI mechanisms based on a knowledge graph that integrates extensive available biomedical resources through semantic web technologies and backward chaining inference, effectively identifying facts within the graph that prove and explain the mechanisms of the drugs' interaction. The framework was evaluated through a case study combining a chemotherapy agent, irinotecan, and a widely used antibiotic, levofloxacin. The mutual interactions identified indicate that our framework can effectively explore and explain the mechanisms of potential DDIs. This approach has the potential to improve drug discovery and design and to support rapid and cost-effective identification of DDIs along with their putative mechanisms, a key step in determining clinical relevance and supporting clinical decision-making.

Estimating the Optimal Dexketoprofen Pharmaceutical Formulation with Machine Learning Methods and Statistical Approaches

Objectives

Orally disintegrating tablets (ODTs) can be utilized without any drinking water; this feature makes ODTs easy to use and suitable for specific groups of patients. Oral administration of drugs is the most commonly used route, and tablets constitute the most preferable pharmaceutical dosage form. However, the preparation of ODTs is costly and requires long trials, which creates obstacles for dosage trials. The aim of this study was to identify the most appropriate formulation using machine learning (ML) models of ODT dexketoprofen formulations, with the goal of providing a cost-effective and time-reducing solution.

Methods

This research utilized nonlinear regression models, including the k-nearest neighborhood (k-NN), support vector regression (SVR), classification and regression tree (CART), bootstrap aggregating (bagging), random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) methods, as well as the t-test, to predict the quantity of various components in the dexketoprofen formulation within fixed criteria.

Results

All the models were developed with Python libraries. The performance of the ML models was evaluated with R² values and the root mean square error. Hardness values of 0.99 and 2.88, friability values of 0.92 and 0.02, and disintegration time values of 0.97 and 10.09 using the GBM algorithm gave the best results.

Conclusions

In this study, we developed a computational approach to estimate the optimal pharmaceutical formulation of dexketoprofen. The results were evaluated by an expert, and it was found that they complied with Food and Drug Administration criteria.