The treatment of complex diseases often involves the use of multiple drugs, a practice known as polypharmacy. However, this approach comes with the risk of drug-drug interactions (DDIs), which can lead to unanticipated adverse effects and even toxicity. Therefore, ensuring the safety of polypharmacy requires identifying DDIs and exploring their underlying mechanisms. Traditional wet lab methods for detecting DDIs are expensive and time-consuming, while computational methods have been developed to predict DDIs. Many of these methods have limitations, and they often struggle to predict potential DDIs between known drugs in the DDI network and drugs from outside that network without any connections to other drugs. Moreover, they may lack the capability to delve into the underlying mechanisms of DDIs and provide meaningful interpretations. In response to these challenges, we introduce a novel machine learning-based method called NGMG, which leverages a knowledge graph to identify feature representations for each drug based on its chemical and topological properties in the DDI network. Then, it combines these features for each drug pair and feeds them into a predictor to obtain a final DDI prediction score. Our experimental results demonstrate the effectiveness of NGMG in two crucial DDI prediction scenarios: identifying potential DDIs among known drugs within the DDI network and predicting interactions between drugs within the DDI network and some drugs from outside the network without any connections to other drugs.

Lung cancer, which is the leading cause of cancer-related death worldwide and is characterized by genetic changes and heterogeneity, presents a significant treatment challenge. Existing approaches utilizing Machine Learning (ML) techniques for identifying driver modules lack specificity, particularly for lung cancer. This study addresses this limitation by proposing a novel method that combines gene-gene interaction network construction with ML-based clustering to identify lung cancer-specific driver modules. The methodology involves mapping biological processes to genes and constructing a weighted gene-gene interaction network to identify correlations within gene clusters. A clustering algorithm is then applied to identify potential cancer-driver modules, focusing on biologically relevant modules that contribute to lung cancer development. The results highlight the effectiveness and robustness of the clustering approach, identifying 110 unique clusters ranging in size from 4 to 10. These clusters surpass evaluation requirements and demonstrate significant relevance to critical cancer-related pathways. The identified driver modules hold promise for influencing future approaches to lung cancer diagnosis, prognosis, and treatment. This research expands our understanding of lung cancer and sets the stage for further investigations and potential clinical advancements.

Breast cancer has become a severe public health concern and one of the leading causes of cancer-related death in women worldwide. Several genes and mutations in these genes linked to breast cancer have been identified using sophisticated techniques, despite the fact that the exact cause of breast cancer is still unknown. A commonly used feature for identifying driver mutations is the recurrence of a mutation in patients. Nevertheless, some mutations are more likely to occur than others for various reasons. Sequencing analysis has shown that cancer-driving genes operate across complex networks, often with mutations appearing in a modular pattern. In this work, as a retrospective study, we used TCGA data, which is gathered from breast cancer patients. We introduced a new machine-learning approach to examine gene functionality in networks derived from mutation associations, gene-gene interactions, and graph clustering for breast cancer analysis. These networks have uncovered crucial biological components in critical pathways, particularly those that exhibit low-frequency mutations. The statistical strength of the clinical study is significantly boosted by evaluating the network as a whole instead of just single gene effects. Our method successfully identified essential driver genes with diverse mutation frequencies. We then explored the functions of these potential driver genes and their related pathways. By uncovering low-frequency genes, we shed light on understudied pathways associated with breast cancer. Additionally, we present a novel Monte Carlo-based algorithm to identify driver modules in breast cancer. Our findings highlight the significance and role of these modules in critical signaling pathways in breast cancer, providing a comprehensive understanding of breast cancer development. Materials and implementations are available at: [https://github.com/MahnazHabibi/BreastCancer].

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) requires the fast discovery of effective treatments to fight this worldwide concern. Several genes associated with the SARS-CoV-2, which are essential for its functionality, pathogenesis, and survival, have been identified. These genes, which play crucial roles in SARS-CoV-2 infection, are considered potential therapeutic targets. Developing drugs against these essential genes to inhibit their regular functions could be a good approach for COVID-19 treatment. Artificial intelligence and machine learning methods provide powerful infrastructures for interpreting and understanding the available data and can assist in finding fast explanations and cures. We propose a method to highlight the essential genes that play crucial roles in SARS-CoV-2 pathogenesis. For this purpose, we define eleven informative topological and biological features for the biological and PPI networks constructed on gene sets that correspond to COVID-19. Then, we use three different unsupervised learning algorithms with different approaches to rank the important genes with respect to our defined informative features. Finally, we present a set of 18 important genes related to COVID-19. Materials and implementations are available at: https://github.com/MahnazHabibi/Gene_analysis.

It is complicated to identify cancer-causing mutations. The recurrence of a mutation in patients remains one of the most reliable features of mutation driver status. However, some mutations are more likely to happen than others for various reasons. Different sequencing analysis has revealed that cancer driver genes operate across complex pathways and networks, with mutations often arising in a mutually exclusive pattern. Genes with low-frequency mutations are understudied as cancer-related genes, especially in the context of networks. Here we propose a machine learning method to study the functionality of mutually exclusive genes in the networks derived from mutation associations, gene-gene interactions, and graph clustering. These networks have indicated critical biological components in the essential pathways, especially those mutated at low frequency. Studying the network and not just the impact of a single gene significantly increases the statistical power of clinical analysis. The proposed method identified important driver genes with different frequencies. We studied the function and the associated pathways in which the candidate driver genes participate. By introducing lower-frequency genes, we recognized less studied cancer-related pathways. We also proposed a novel clustering method to specify driver modules. We evaluated each driver module with different criteria, including the terms of biological processes and the number of simultaneous mutations in each cancer. Materials and implementations are available at: https://github.com/MahnazHabibi/MutationAnalysis.