Prediction of Breast Cancer Estrogen Receptor Status using Machine Learning
Ontology highlight
ABSTRACT:
ORGANISM(S): Homo sapiens
PROVIDER: GSE29210 | GEO | 2013/01/01
SECONDARY ACCESSION(S): PRJNA140059
REPOSITORIES: GEO
Similar Datasets
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
| S-ECPF-GEOD-29210 | biostudies-other
Project description:Background: Biopsy-based diagnosis is essential for maintaining renal allograft longevity by ensuring prompt treatment for graft complications. Although histologic assessment remains the gold standard, it carries significant limitations such as subjective interpretation, suboptimal reproducibility, and imprecise quantitation of disease burden. It is hoped that molecular diagnostics could enhance the efficiency, accuracy, and reproducibility of traditional histologic methods. Methods: Quantitative label-free mass spectrometry analysis was performed on a set of formalin-fixed, paraffin-embedded (FFPE) biopsies from renal transplant patients, comprising five biopsies with the diagnosis of T-cell-mediated rejection (TCMR), five biopsies for polyomavirus BK nephropathy (BKPyVN), and normal kidney control tissue (STA). Using the differential protein expression result as a classifier, three different machine learning algorithms were tested to build a molecular diagnostic model for TCMR. Results: The label-free proteomics method yielded 800-1350 proteins that could be quantified with high confidence per sample by single-shot measurements. Among these candidate proteins, 329 and 467 proteins were defined as differentially expressed proteins (DEPs) for TCMR in comparison with STA and BKPyVN, respectively. Comparing the FFPE quantitative proteomics data set obtained in this study using label-free method with a data set we previously reported using isobaric labeling technology, a classifier pool comprised of features from DEPs commonly quantified in both data sets, was generated for TCMR prediction. Leave-one-out cross-validation result demonstrated that the random forest (RF)-based model achieved the best predictive power. In a follow-up blind test using an independent sample set, the RF-based model yields 80% accuracy for TCMR and 100% for STA. When applying the established RF-based model to two public transcriptome datasets, 78.1%-82.9% sensitivity and 58.7%-64.4% specificity was achieved respectively. Conclusions: This proof-of-principle study demonstrates the clinical feasibility of proteomics profiling for FFPE biopsies using an accurate, efficient, and cost-effective platform integrated of quantitative label-free mass spectrometry analysis with a machine learning-derived diagnostic model. It costs less than 10 dollars per test.
2023-02-01 | PXD038601 | Pride
Project description:Analysis of gene expression in pathologically confirmed glioblastoma (GBM) samples. These data were used to test a classifier that was generated to distinguish GBM tumor samples with loss of neurofibromin 1 (NF1) function
2017-02-01 | GSE85033 | GEO
Project description:Descending thoracic aortic aneurysms and dissections can go undetected until severe and catastrophic, and few clinical indices exist to screen for aneurysms or predict their risk of dissection or rupture. This study generated a plasma proteomic dataset from 150 patients with descending thoracic aortic disease and 52 controls to identify proteomic signatures capable of differentiating descending thoracic aortic disease from non-disease controls, as well as between cases with aneurysm versus descending ‘type B’ dissection. Of the 1,468 peptides and 195 proteins quantified across all samples, 853 peptides and 99 proteins were quantitatively different between disease and control patients (BH adjusted p-value < 0.01 from t-tests). Supervised machine learning (ML) methods were used to classify disease from control and aneurysm from descending dissection cases. The highest precision-recall area under the curve (PR AUC) was achieved on the held-out test set using significantly different proteins between disease and control patients (PR AUC 0.99), followed by input of significant peptides (PR AUC 0.96). Despite no statistically significant proteins between aneurysm and dissection cases, use of all proteins was able to modestly classify between the two disease states (PR AUC 0.77). To overcome correlation in the proteins and enable biological pathway analysis, a disease versus control classifier was optimized using only seven unique protein clusters, which achieved comparable performance to models trained on all/significant proteins (accuracy 0.88, F1-score 0.78, PR AUC 0.90). Model interpretation with permutation importance revealed that proteins in the most important clusters for differentiating disease and control function in coagulation, protein-lipid complex remodeling, and acute inflammatory response.
2024-06-16 | PXD041337 | Pride
Project description:We propose a convolutional neural network (CNN) model predicting HPV-status in head and neck cancer from transcriptome data allowing identification of molecular pathways driving individual classifier decisions. The CNN was trained on transcriptome data from 264 (13% HPV-positive) and tested on 85 (25% HPV-positive) patients after transformation into 2D-treemaps representing molecular pathways. Model stability was assessed by shuffling pathways within 2D-images. Grad-CAM saliency was used to quantify pathways contribution to CNN decisions. For comparison, a logistic regression model was generated. The CNN achieved ROC-AUC/PR-AUC of 0.96/0.90 for all treemap variants. Saliency heatmaps consistently found KRAS-, spermatogenesis-, bile acid metabolism- and inflammatory-signaling as most informative for classification of HPV-positive-, and MYC-targets-, epithelial-mesenchymal transition and protein-secretion pathways for HPV-negative patients. The regression-based 18-gene model achieved a ROC-AUC/PR-AUC of 0.97/0.97. We present a high-performance explainable CNN-model from transcriptome data of a typically sized oncological cohort providing molecular pathway information at the individual level.
2023-04-24 | GSE205308 | GEO
Project description:Posttraumatic stress disorder (PTSD) develops in a substantial minority of emergency room admits. Inexpensive and accurate person-level assessment of PTSD risk after trauma exposure is a critical precursor to large-scale deployment of early interventions that may reduce individual suffering and societal costs. Toward this aim, we applied ensemble machine learning to predict PTSD screening status three months after severe injury using cost-effective and minimally invasive data. Participants (N = 271) were recruited at a Level 1 Trauma Center where they provided variables routinely collected at the hospital, including pulse, injury severity, and demographics, as well as psychological variables, including self-reported current depression, psychiatric history, and social support. Participant zip codes were used to extract contextual variables including population total and density, average annual income, and health insurance coverage rates from publicly available U.S. Census data. Machine learning yielded good prediction of PTSD screening status 3 months post-hospitalization, AUC = 0.85 95% CI [0.83, 0.86], and significantly outperformed all benchmark comparison models in a cross-validation procedure designed to yield an unbiased estimate of performance. These results demonstrate that good prediction can be attained from variables that individually have relatively weak predictive value, pointing to the promise of ensemble machine learning approaches that do not rely on strong isolated risk factors.
| S-EPMC6777842 | biostudies-literature
Project description:BACKGROUND:Prognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission. METHODS AND FINDINGS:This study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission improved the maximum AUC to 0.895 (σ = 0.008). Beyond the second day, predictive ability declined. CONCLUSION:This has implications for decision making in intensive care and provides a justification for time-limited trials of ICU therapy; the assessment of prognosis over more than one day may be a valuable strategy as new information on the second day helps to differentiate outcomes. New ML models based on trend data beyond the first day could greatly improve upon current risk stratification tools.
| S-EPMC6241126 | biostudies-other
Project description:Efforts at finding potential biomarkers of tolerance after kidney transplantation have been hindered by limited sample size, as well as the complicated mechanisms underlying tolerance and the potential risk of rejection after immunosuppressant withdrawal. In this work, three different publicly available genome-wide expression data sets of peripheral blood lymphocyte (PBL) from 63 tolerant patients were used to compare 14 different machine learning models for their ability to predict spontaneous kidney graft tolerance. We found that the Best Subset Selection (BSS) regression approach was the most powerful with a sensitivity of 91.7% and a specificity of 93.8% in the test group, and a specificity of 86.1% and a sensitivity of 80% in the validation group. A feature set with five genes (HLA-DOA, TCL1A, EBF1, CD79B, and PNOC) was identified using the BSS model. EBF1 downregulation was also an independent factor predictive of graft rejection and graft loss. An AUC value of 84.4% was achieved using the two-gene signature (EBF1 and HLA-DOA) as an input to our classifier. Overall, our systematic machine learning exploration suggests novel biological targets that might affect tolerance to renal allografts, and provides clinical insights that can potentially guide patient selection for immunosuppressant withdrawal.
2021-06-04 | GSE166865 | GEO
Project description:Currently, Renal Cell Carcinoma (RCC) is identified through expensive cross-sectional imaging, frequently followed by renal mass biopsy, which is invasive and subject to sampling errors. Hence, there is a critical need for a non-invasive diagnostic assay. RCC is a disease of altered cellular metabolism with the tumor(s) in close proximity to the urine in the kidney suggesting metabolomic profiling would be an excellent choice for assay development. Here, we applied liquid chromatography-mass spectrometry (LC-MS), nuclear magnetic resonance (NMR), and machine learning (ML) for the discovery of candidate metabolic panels for RCC. The study cohort consists of 82 RCC patients and 174 healthy controls, these were separated into two sub-cohorts: model cohort and the test cohort. Discriminatory metabolic features were selected in the model cohort, using univariate, wrapper, and embedded methods of feature selection. Three ML techniques with different induction biases were used for training and hyperparameter tuning. Final assessment of RCC status prediction was made using the test cohort with the selected biomarkers and the tuned ML algorithms. A seven-metabolite panel consisting of endogenous and exogenous metabolites enabled the prediction of RCC with 88% accuracy, 94% sensitivity, and 85% specificity in the test cohort, with an AUC of 0.98.
2021-02-11 | ST001705 | MetabolomicsWorkbench