Drug repurposing for hyperlipidemia associated disorders: An integrative network biology and machine learning approach

Rai, Sneha; Bhatia, Venugopal; Bhatnagar, Sonika

doi:10.1016/j.compbiolchem.2021.107505

Cited by 7 publications

(4 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[112][113][114] These AI-based approaches help understand many human diseases, such as COVID-19, SARS-CoV-2, monkeypox virus, Alzheimer's disease, malignancy, hyperlipidemia, muscle atrophy, and rare diseases, and further explore the target-specific repurposed drug for curing disease. [115][116][117][118][119][120][121][122][123][124][125] ML and DL, as both AI algorithms, are widely used for discovering the repurposed drugs for cancers, such as colorectal cancer, oral cancer, breast cancer, non-small-cell lung cancer, viral cancers, esophageal adenocarcinoma, chordoma, and acute myeloid leukemia. [126][127][128][129][130][131][132][133][134][135][136] These AI-based approaches could perform systematic processes by finding new diseaserelevant targets, extending the drug-target profile to include potential off-targets for new indications, and discovering associations between function-phenotype.…”

Section: Repurposing In Cancermentioning

confidence: 99%

“…Additionally, machine learning algorithm is a subtype of AI that automates decision‐making and makes predictions based on massive observed data from existing drugs and diseases, characterizes the molecules and conformational changes of drugs, identifies drug‐target interactions, and predicts drug‐response status by using multi‐omics datasets 112–114 . These AI‐based approaches help understand many human diseases, such as COVID‐19, SARS‐CoV‐2, monkeypox virus, Alzheimer's disease, malignancy, hyperlipidemia, muscle atrophy, and rare diseases, and further explore the target‐specific repurposed drug for curing disease 115–125 . ML and DL, as both AI algorithms, are widely used for discovering the repurposed drugs for cancers, such as colorectal cancer, oral cancer, breast cancer, non‐small‐cell lung cancer, viral cancers, esophageal adenocarcinoma, chordoma, and acute myeloid leukemia 126–136 .…”

Section: Ai‐based Approach For Drug Repurposing In Cancermentioning

confidence: 99%

See 1 more Smart Citation

PDE5 inhibitors against cancer via mediating immune cells in tumor microenvironment: AI‐based approach for future drug repurposing exploration

Zhang,

Huang,

Feng

et al. 2024

Interdisciplinary Medicine

View full text Add to dashboard Cite

Phosphodiesterase‐5 (PDE5) inhibitors are used clinically for the treatment of erectile dysfunction, pulmonary arterial hypertension, and other urological diseases. Emerging evidences have suggested the therapeutic capacity of PDE5 inhibitors as the repurposed drugs in oncology. However, the essential immune function of PDE5 inhibitors against cancer in tumor microenvironment (TME) remains unclear. This review aimed to summarize the recent advances regarding the repurposing of PDE5 inhibitors as anti‐cancer agents for cancer management to enhance the anti‐tumor immune response by mediating various immune cells, which included the myeloid‐derived suppressor cells, macrophages, T cells, fibroblasts, and natural killer cells in TME. Moreover, artificial intelligence (AI), as a new approach, is composed of traditional machine learning and deep learning methods and could be potentially used to identify the targets of immune cells in TME and predict the efficacy for repurposed drug toward malignancies. In summary, these endeavors provide novel insights into the comprehensive strategies for PDE5 inhibitors mediating immune cells against cancer and AI‐based approach for future drug repurposing exploration.

show abstract

Section: Repurposing In Cancermentioning

confidence: 99%

Section: Ai‐based Approach For Drug Repurposing In Cancermentioning

confidence: 99%

PDE5 inhibitors against cancer via mediating immune cells in tumor microenvironment: AI‐based approach for future drug repurposing exploration

Zhang,

Huang,

Feng

et al. 2024

Interdisciplinary Medicine

View full text Add to dashboard Cite

show abstract

“…Interestingly, all of them were upregulated in the DLP group (Figure 8E, Table S19). Four human proteins including transthyretin (TTR), heat shock protein HSP 90-alpha (HS90A), small ribosomal subunit protein (RACK1), and peroxiredoxin-4 (PRDX4) have been reported to be related to obesity, diabetes, and hyperlipidemia based on serum or tissue samples [69][70][71][72] . However, it has not been reported that the dysregulation of these human proteins in human feces is also associated with dyslipidemia.…”

Section: Metaexpertpro Analysis Revealed the Functions Associated Wit...mentioning

confidence: 99%

metaExpertPro: a computational workflow for metaproteomics spectral library construction and data-independent acquisition mass spectrometry data analysis

Sun,

Xing,

Liang

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundAnalysis of mass spectrometry-based metaproteomic data, in particular large-scale data-independent acquisition MS (DIA-MS) data, remains a computational challenge. Here, we aim to develop a software tool for efficiently constructing spectral libraries and analyzing extensive datasets of DIA-based metaproteomics.ResultsWe present a computational pipeline called metaExpertPro for metaproteomics data analysis. This pipeline encompasses spectral library generation using data-dependent acquisition MS (DDA-MS), protein identification and quantification using DIA-MS, functional and taxonomic annotation, as well as quantitative matrix generation for both microbiota and hosts. To enhance accessibility and ease of use, all modules and dependencies are encapsulated within a Docker container.By integrating FragPipe and DIA-NN, metaExpertPro offers compatibility with both Orbitrap-based and PASEF-based DDA and DIA data. To evaluate the depth and accuracy of identification and quantification, we conducted extensive assessments using human fecal samples and benchmark tests. Performance tests conducted on human fecal samples demonstrated that metaExpertPro quantified an average of 45,000 peptides in a 60-minute diaPASEF injection. Notably, metaExpertPro outperformed three existing software tools by characterizing a higher number of peptides and proteins. Importantly, metaExpertPro maintained a low factual False Discovery Rate (FDR) of less than 5% for protein groups across four benchmark tests. Applying a filter of five peptides per genus, metaExpertPro achieved relatively high accuracy (F-score = 0.67–0.90) in genus diversity and demonstrated a high correlation (rSpearman= 0.73–0.82) between the measured and true genus relative abundance in benchmark tests.Additionally, the quantitative results at the protein, taxonomy, and function levels exhibited high reproducibility and consistency across the commonly adopted public human gut microbial protein databases IGC and UHGP. In a metaproteomic analysis of dyslipidemia patients, metaExpertPro revealed characteristic alterations in microbial functions and potential interactions between the microbiota and the host.ConclusionsmetaExpertPro presents a robust one-stop computational solution for constructing metaproteomics spectral libraries, analyzing DIA-MS data, and annotating taxonomic as well as functional data.

show abstract

“…In recent times, by combining network biology and machine learning approaches, valuable insights have been gained regarding potential drugs that could be novel viable options for treating dyslipidemia [ 16 ]. Additionally, this innovative approach has also been adopted for the identification of new predictors of cardiovascular risk in patients with T2DM [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Uncovering Predictors of Lipid Goal Attainment in Type 2 Diabetes Outpatients Using Logic Learning Machine: Insights from the AMD Annals and AMD Artificial Intelligence Study Group

Masi

Zilich²,

Candido

et al. 2023

JCM

View full text Add to dashboard Cite

Identifying and treating lipid abnormalities is crucial for preventing cardiovascular disease in diabetic patients, yet only two-thirds of patients reach recommended cholesterol levels. Elucidating the factors associated with lipid goal attainment represents an unmet clinical need. To address this knowledge gap, we conducted a real-world analysis of the lipid profiles of 11.252 patients from the Annals of the Italian Association of Medical Diabetologists (AMD) database from 2005 to 2019. We used a Logic Learning Machine (LLM) to extract and classify the most relevant variables predicting the achievement of a low-density lipoprotein cholesterol (LDL-C) value lower than 100 mg/dL (2.60 mmol/L) within two years of the start of lipid-lowering therapy. Our analysis showed that 61.4% of the patients achieved the treatment goal. The LLM model demonstrated good predictive performance, with a precision of 0.78, accuracy of 0.69, recall of 0.70, F1 Score of 0.74, and ROC-AUC of 0.79. The most significant predictors of achieving the treatment goal were LDL-C values at the start of lipid-lowering therapy and their reduction after six months. Other predictors of a greater likelihood of reaching the target included high-density lipoprotein cholesterol, albuminuria, and body mass index at baseline, as well as younger age, male sex, more follow-up visits, no therapy discontinuation, higher Q-score, lower blood glucose and HbA1c levels, and the use of anti-hypertensive medication. At baseline, for each LDL-C range analysed, the LLM model also provided the minimum reduction that needs to be achieved by the next six-month visit to increase the likelihood of reaching the therapeutic goal within two years. These findings could serve as a useful tool to inform therapeutic decisions and to encourage further in-depth analysis and testing.

show abstract

Drug repurposing for hyperlipidemia associated disorders: An integrative network biology and machine learning approach

Cited by 7 publications

References 87 publications

PDE5 inhibitors against cancer via mediating immune cells in tumor microenvironment: AI‐based approach for future drug repurposing exploration

PDE5 inhibitors against cancer via mediating immune cells in tumor microenvironment: AI‐based approach for future drug repurposing exploration

metaExpertPro: a computational workflow for metaproteomics spectral library construction and data-independent acquisition mass spectrometry data analysis

Uncovering Predictors of Lipid Goal Attainment in Type 2 Diabetes Outpatients Using Logic Learning Machine: Insights from the AMD Annals and AMD Artificial Intelligence Study Group

Contact Info

Product

Resources

About