Dataset Information

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

ABSTRACT: The goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines. However, there are no comprehensive guidelines on how to properly train and validate such machine learning models for drug sensitivity prediction. In this paper, we introduce a set of guidelines for different aspects of training gene expression-based predictors using cell line datasets. These guidelines provide extensive analysis of the generalization of drug sensitivity predictors and challenge many current practices in the community including the choice of training dataset and measure of drug sensitivity. The application of these guidelines in future studies will enable the development of more robust preclinical biomarkers.

SUBMITTER: Sharifi-Noghabi H

PROVIDER: S-EPMC8575017 | biostudies-literature | 2021 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

Sharifi-Noghabi Hossein H Jahangiri-Tazehkand Soheil S Smirnov Petr P Hon Casey C Mammoliti Anthony A Nair Sisira Kadambat SK Mer Arvind Singh AS Ester Martin M Haibe-Kains Benjamin B

Briefings in bioinformatics 20211101 6

The goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines. However, there are no comprehensive guidelines on how to prope ...[more]

PMID: 34382071

Similar Datasets

Project description:BackgroundRapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters.MethodsA retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings.ResultsParameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84-0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61-0.73), and an accuracy of 0.83 (95% CI 0.81-0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97-0.99), an AUPRC of 0.88 (95% CI 0.83-0.93), and an accuracy of 0.97 (95% CI 0.96-0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME.ConclusionsThe RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.

Project description:BackgroundSchizophrenia (SC) is one of the most common psychiatric diseases. Its potential pathogenic genes and effective treatment methods are still unclear. Cell senescence has been confirmed in mental diseases. A link exists between cellular senescence and immunity, and immune-related problems affect suicide rates in individuals suffering from schizophrenia. Therefore, the aims of this study were to identify candidate genes based on cell senescence that can affect the diagnosis and treatment of schizophrenia.MethodsTwo data sets of schizophrenia were provided by the Gene Expression Omnibus (GEO) database, one was taken as training and the other as a validation group. The genes related to cell senescence were obtained from the CellAge database. DEGs were identified using the Limma package and weighted gene co-expression network analysis (WGCNA). The function enrichment analysis was conducted, followed by machine learning-based identification for least absolute shrinking and selection operators (LASSO) regression. Random Forest were used to identify candidate immune-related central genes and establish artificial neural networks for verification of the candidate genes. The receiver operating characteristic curve (ROC curve) was used for the diagnosis of schizophrenia. Immune cell infiltrates were constructed to study immune cell dysregulation in schizophrenia, and relevant drugs with candidate genes were collected from the DrugBank database.ResultsThirteen co-expression modules were screened for schizophrenia, of which 124 were the most relevant genes.There were 23 intersected genes of schizophrenia (including DEGs and the cellular senescence-related genes), and through machine learning six candidate genes were finally screened out. The diagnostic value was evaluated using the ROC curve data. Based on these results it was confirmed that these candidate genes have high diagnostic value.Two drugs related to candidate genes, Fostamatinib and Ritodine, were collected from the DrugBanks database.ConclusionSix potential candidate genes (SFN, KDM5B, MYLK, IRF3, IRF7, and ID1) had been identified, all of which had diagnostic significance. Fostamatinib might be a drug choice for patients with schizophrenia to develop immune thrombocytopenic purpura (ITP) after treatment, providing effective evidence for the pathogenesis and drug treatment of schizophrenia.

Dataset Information

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

Publications

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets