Recommending Drug Combinations Using Reinforcement Learning targeting Genes/proteins associated with Heterozygous Familial Hypercholesterolemia: A comprehensive Systematic Review and Net-work Meta-analysis

Kiaei, Ali Akbar; Boush, Mahnaz; Abadijou, Sadegh; Momeni, Saeb; Safaei, Danial; Bahadori, Reza; Salari, Nader; Mohammadi, Masoud

doi:10.21203/rs.3.rs-2379891/v1

Cited by 7 publications

(8 citation statements)

References 38 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, They conduct a network meta-analysis to evaluate the efficacy in relation to effectiveness. [280][281][282][283][284][285][286][287][288][289] Figure 1: The impact of suggested drug combinations on the management of Lung adenocarcinoma cases…”

Section: -110mentioning

confidence: 99%

A graphSAGE discovers synergistic combinations of Gefitinib, paclitaxel, and Icotinib for Lung adenocarcinoma management by targeting human genes and proteins: the RAIN protocol

Sadeghi,

Kiaei,

Boush

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Adenocarcinoma of the lung is the most common type of lung cancer, and it is characterized by distinct cellular and molecular features. It occurs when abnormal lung cells multiply out of control and form a tumor in the outer region of the lungs. Adenocarcinoma of the lung is a serious and life-threatening condition that requires effective and timely management to improve the survival and quality of life of the patients. One of the challenges in this cancer treatment is finding the optimal combination of drugs that can target the genes or proteins that are involved in the disease process. Method: In this article, we propose a novel method to recommend combinations of trending drugs to target its associated proteins/genes, using a Graph Neural Network (GNN) under the RAIN protocol. The RAIN protocol is a three-step framework that consists of: 1) Applying graph neural networks to recommend drug combinations by passing messages between trending drugs for managing disease and genes that act as potential targets for disease; 2) Retrieving relevant articles with clinical trials that include those proposed drugs in previous step using Natural Language Processing (NLP); 3) Analyzing the network meta-analysis to measure the comparative efficacy of the drug combinations. Result: We applied our method to a dataset of nodes and edges that represent the network, where each node is a drug or a gene, and each edge is a p-value between them. We found that the graph neural network recommends combining Gefitinib, Paclitaxel, and Icotinib as the most effective drug combination to target this cancer associated proteins/genes. We reviewed the clinical trials and expert opinions on these medications and found that they support our claim. The network meta-analysis also confirmed the effectiveness of these drugs on associated genes. Conclusion: Our method is a novel and promising approach to recommend trending drugs combination to target cancer associated proteins/genes, using graph neural networks under the RAIN protocol. It can help clinicians and researchers to find the best treatment options for patients, and also provide insights into the underlying mechanisms of the disease.

show abstract

Section: -110mentioning

confidence: 99%

A graphSAGE discovers synergistic combinations of Gefitinib, paclitaxel, and Icotinib for Lung adenocarcinoma management by targeting human genes and proteins: the RAIN protocol

Sadeghi,

Kiaei,

Boush

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This methodology represents a notable advancement in computational drug discovery and personalized medicine. (113,114,115,116), (57,113,114,115,116,117 ,119,123), (89,124,125,126,127,128) 3.2. Stage II : NLP-driven Article Retrieval In this systematic review and meta-analysis, investigators conducted a comprehensive search for relevant studies using specified keywords across various databases up to July 20, 2022.…”

Section: * C20h23n7o7mentioning

confidence: 99%

AI-Enhanced RAIN Protocol: A Systematic Approach to Optimize Drug Combinations for Rectal Neoplasm Treatment

Dashti,

Kiaei,

Boush

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundRectal cancers, or rectal neoplasms, are tumors that develop from the lining of the rectum, the concluding part of the large intestine ending at the anus. These tumors often start as benign polyps and may evolve into malignancies over several years. The causes of rectal cancer are diverse, with genetic mutations being a key factor. These mutations lead to uncontrolled cell growth, resulting in tumors that can spread and damage healthy tissue. Age, genetic predisposition, diet, and hereditary conditions are among the risk factors. Treating rectal cancer is critical to prevent severe health issues and death. Untreated, it can cause intestinal blockage, metastasis, and deteriorate the patient’s quality of life. Effective treatment hinges on finding the right drug combinations to improve therapeutic outcomes. Given the intricacies of cancer biology, treatments often combine surgery, chemotherapy, and radiation, with drugs chosen to target different tumor growth mechanisms, aiming to reduce the tumor and limit side effects. The continuous advancement in cancer treatments highlights the need for ongoing research to discover new drug combinations, offering patients improved recovery prospects and a better quality of life. This background encapsulates a detailed yet succinct understanding of rectal neoplasms, their origins, the urgency of treatment, and the quest for effective drug therapies, paving the way for discussions on treatment advancements and patient care impacts.MethodThis study employed the RAIN protocol, comprising three steps: firstly, utilizing the GraphSAGE model to propose drug combinations for rectal neoplasm treatment Each node in the graph model is a drug or a human gene/protein that acts as potential target for the disease, and the edges are P-values between them; secondly, conducting a systematic review across various databases including Web of Science, Google Scholar, Scopus, Science Direct, PubMed, and Embase, with NLP investigation; and thirdly, employing a meta-analysis network to assess the efficacy of drugs and genes in relation to each other. All implementations was conducted using Python software.ResultThe study evaluated the efficacy of Oxaliplatin, Leucovorin, and Capecitabine in treating Rectal Neoplasms, confirming their effectiveness through a review of 30 studies. The p-values for individual drugs were 0.019, 0.019, and 0.016 respectively, while the combined use of all three yielded a p-value of 0.016.ConclusionGiven the significance of rectal neoplasms, policymakers are urged to prioritize the healthcare needs of affected individuals. Utilizing artificial intelligence within the RAIN protocol can offer valuable insights for tailoring effective drug combinations to better address the treatment and management of rectal neoplasms patients.Abstract FigureHighlightsRectal cancers, evolving from benign polyps to malignancies, underscore the critical need for timely and effective treatment to prevent severe health complications.Genetic mutations, a pivotal factor in rectal cancer, trigger uncontrolled cell growth and necessitate targeted drug therapies to combat tumor spread.The RAIN protocol, leveraging the GraphSAGE model and systematic reviews, offers a novel approach to identify potent drug combinations for rectal neoplasm treatment.The study’s findings advocate for policy intervention to ensure that healthcare systems adequately support individuals battling rectal neoplasms, with AI-driven protocols enhancing patient care.

show abstract

“…The research protocol for this article is based on RAIN (Salari et al, 2023b). Numerous research studies have employed the RAIN protocol as a framework for their research (Boush et al, 2023;Jafari et al, 2022a;Kiaei et al, 2022Kiaei et al, , 2023Salari et al, 2021Salari et al, , 2022bSalari et al, , 2022bSalari et al, , 2023a.…”

Section: Quality Evaluationmentioning

confidence: 99%

Systematic review and network meta-analysis of drug combinations suggested by machine learning on genes and proteins, with the aim of improving the effectiveness of Ipilimumab in treating Melanoma

Safaei

Kiaei

Boush

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background(Importance)One of the most dangerous kinds of skin cancer, Melanoma, develops in the cells (melanocytes) that make melanin, the pigment responsible for giving your skin its color. As well as developing everywhere on the body, including the eyes, Melanoma can sporadic occur internally, such as in the nose or throat. It is unknown what causes all melanomas, although exposure to ultraviolet (UV) radiation from the sun, tanning salons, and lamps increases the risk of getting them. As a result, radiation exposure increases the chance of obtaining Melanoma. Limiting your exposure to UV radiation can help reduce your risk of Melanoma.(Objective)Due to the unknown nature of this disease and its severe impact on human genes, the use of safe and effective drug combinations for treatment is very important. Proposed drug combinations should be administered with the greatest positive effect on the genes involved. Therefore, it is important to suggest an effective drug combination that can significantly affect the genes involved.Method(Data sources)This systematic review and network meta-analysis searched various databases, including Science Direct, Embase, Scopus, PubMed, Web of Science (ISI), and Google Scholar, without a lower time limit and up until July 2022, for articles focused on drug combinations for managing Melanoma. The study utilized a network meta-analysis to explore the effectiveness of the proposed medication combination on genes and proteins that may act as potential targets for improving Melanoma treatment.ResultsThe results of this study show that the p-value between the proposed drug combination and Melanoma was 1.12E-08. This is while the p-value of Melanoma and only one drug has a maximum value of 0.0149. Therefore, the proposed drug combination’s effectiveness for treating Melanoma has increased 74 times. A systematic review has investigated the validity of the proposed drug combinations, human genes network meta-analysis, and prescription drug information.ConclusionThe findings from this systematic review and meta-analysis suggest that the proposed drug combination reduces the p-value between Melanoma and genes that could potentially be targeted to slow the progression of the disease, ultimately improving its management. Therefore, selecting the appropriate drug combination is critical for enhancing community health and reducing per capita treatment expenses.HighlightsMelanoma is one of the most aggressive kinds of skin cancer, and it begins in the cells (melanocytes) responsible for producing melanin.Therapy must make use of pharmacological combinations that are both safe and effective.Any proposed medication combinations must be delivered in a way that will have the maximum possible beneficial impact on the genes at play.In this research, an effective pharmacological combination for the treatment of melanoma illness is investigated.The results suggest that the suggested treatment combination is beneficial in the treatment of Melanoma, as it reduces the p-value between the disease and the genes identified as potential targets for therapy. This indicates that the proposed treatment approach has the potential to improve the management of Melanoma.

show abstract

Recommending Drug Combinations Using Reinforcement Learning targeting Genes/proteins associated with Heterozygous Familial Hypercholesterolemia: A comprehensive Systematic Review and Net-work Meta-analysis

Cited by 7 publications

References 38 publications

A graphSAGE discovers synergistic combinations of Gefitinib, paclitaxel, and Icotinib for Lung adenocarcinoma management by targeting human genes and proteins: the RAIN protocol

A graphSAGE discovers synergistic combinations of Gefitinib, paclitaxel, and Icotinib for Lung adenocarcinoma management by targeting human genes and proteins: the RAIN protocol

AI-Enhanced RAIN Protocol: A Systematic Approach to Optimize Drug Combinations for Rectal Neoplasm Treatment

Systematic review and network meta-analysis of drug combinations suggested by machine learning on genes and proteins, with the aim of improving the effectiveness of Ipilimumab in treating Melanoma

Contact Info

Product

Resources

About