Dataset Information

Environmental properties of cells improve machine learning-based phenotype recognition accuracy.

ABSTRACT: To answer major questions of cell biology, it is often essential to understand the complex phenotypic composition of cellular systems precisely. Modern automated microscopes produce vast amounts of images routinely, making manual analysis nearly impossible. Due to their efficiency, machine learning-based analysis software have become essential tools to perform single-cell-level phenotypic analysis of large imaging datasets. However, an important limitation of such methods is that they do not use the information gained from the cellular micro- and macroenvironment: the algorithmic decision is based solely on the local properties of the cell of interest. Here, we present how various features from the surrounding environment contribute to identifying a cell and how such additional information can improve single-cell-level phenotypic image analysis. The proposed methodology was tested for different sizes of Euclidean and nearest neighbour-based cellular environments both on tissue sections and cell cultures. Our experimental data verify that the surrounding area of a cell largely determines its entity. This effect was found to be especially strong for established tissues, while it was somewhat weaker in the case of cell cultures. Our analysis shows that combining local cellular features with the properties of the cell's neighbourhood significantly improves the accuracy of machine learning-based phenotyping.

SUBMITTER: Toth T

PROVIDER: S-EPMC6031649 | biostudies-literature | 2018 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Environmental properties of cells improve machine learning-based phenotype recognition accuracy.

Toth Timea T Balassa Tamas T Bara Norbert N Kovacs Ferenc F Kriston Andras A Molnar Csaba C Haracska Lajos L Sukosd Farkas F Horvath Peter P

Scientific reports 20180704 1

To answer major questions of cell biology, it is often essential to understand the complex phenotypic composition of cellular systems precisely. Modern automated microscopes produce vast amounts of images routinely, making manual analysis nearly impossible. Due to their efficiency, machine learning-based analysis software have become essential tools to perform single-cell-level phenotypic analysis of large imaging datasets. However, an important limitation of such methods is that they do not use ...[more]

PMID: 29973621

Similar Datasets

Project description:Human pluripotent stem cells have the potential for unlimited proliferation and controlled differentiation into various somatic cells, making them a unique tool for regenerative and personalized medicine. Determining the best clone selection is a challenging problem in this field and requires new sensing instruments and methods able to automatically assess the state of a growing colony ('phenotype') and make decisions about its destiny. One possible solution for such label-free, non-invasive assessment is to make phase-contrast images and/or videos of growing stem cell colonies, process the morphological parameters ('morphological portrait', or signal), link this information to the colony phenotype, and initiate an automated protocol for the colony selection. As a step in implementing this strategy, we used machine learning methods to find an effective model for classifying the human pluripotent stem cell colonies of three lines according to their morphological phenotype ('good' or 'bad'), using morphological parameters from the previously published data as predictors. We found that the model using cellular morphological parameters as predictors and artificial neural networks as the classification method produced the best average accuracy of phenotype prediction (67%). When morphological parameters of colonies were used as predictors, logistic regression was the most effective classification method (75% average accuracy). Combining the morphological parameters of cells and colonies resulted in the most effective model, with a 99% average accuracy of phenotype prediction. Random forest was the most efficient classification method for the combined data. We applied feature selection methods and showed that different morphological parameters were important for phenotype recognition via either cellular or colonial parameters. Our results indicate a necessity for retaining both cellular and colonial morphological information for predicting the phenotype and provide an optimal choice for the machine learning method. The classification models reported in this study could be used as a basis for developing and/or improving automated solutions to control the quality of human pluripotent stem cells for medical purposes.

Project description:PurposePrompt diagnosis and treatment of septic arthritis of the knee is crucial. Nevertheless, the quality of evidence for the diagnosis of septic arthritis is low. In this study, the authors developed a machine learning-based diagnostic algorithm for septic arthritis of the native knee using clinical data in an emergency department and validated its diagnostic accuracy.MethodsPatients (n = 326) who underwent synovial fluid analysis at the emergency department for suspected septic arthritis of the knee were enrolled. Septic arthritis was diagnosed in 164 of the patients (50.3%) using modified Newman criteria. Clinical characteristics of septic and inflammatory arthritis were compared. Area under the receiver-operating characteristic (ROC) curve (AUC) statistics was applied to evaluate the efficacy of each variable for the diagnosis of septic arthritis. The dataset was divided into independent training and test sets (comprising 80% and 20%, respectively, of the data). Supervised machine-learning techniques (random forest and eXtreme Gradient Boosting: XGBoost) were applied to develop a diagnostic model using the training dataset. The test dataset was subsequently used to validate the developed model. The ROC curves of the machine-learning model and each variable were compared.ResultsSynovial white blood cell (WBC) count was significantly higher in septic arthritis than in inflammatory arthritis in the multivariate analysis (P = 0.001). In the ROC comparison analysis, synovial WBC count yielded a significantly higher AUC than all other single variables (P = 0.002). The diagnostic model using the XGBoost algorithm yielded a higher AUC (0.831, 95% confidence interval 0.751-0.923) than synovial WBC count (0.740, 95% confidence interval 0.684-0.791; P = 0.033). The developed algorithm was deployed as a free access web-based application ( www.septicknee.com ).ConclusionThe diagnosis of septic arthritis of the knee might be improved using a machine learning-based prediction model.Level of evidenceDiagnostic study Level III (Case-control study).

Project description:BackgroundRecently, machine learning (ML) has become attractive in genomic prediction, but its superiority in genomic prediction over conventional (ss) GBLUP methods and the choice of optimal ML methods need to be investigated.ResultsIn this study, 2566 Chinese Yorkshire pigs with reproduction trait records were genotyped with the GenoBaits Porcine SNP 50 K and PorcineSNP50 panels. Four ML methods, including support vector regression (SVR), kernel ridge regression (KRR), random forest (RF) and Adaboost.R2 were implemented. Through 20 replicates of fivefold cross-validation (CV) and one prediction for younger individuals, the utility of ML methods in genomic prediction was explored. In CV, compared with genomic BLUP (GBLUP), single-step GBLUP (ssGBLUP) and the Bayesian method BayesHE, ML methods significantly outperformed these conventional methods. ML methods improved the genomic prediction accuracy of GBLUP, ssGBLUP, and BayesHE by 19.3%, 15.0% and 20.8%, respectively. In addition, ML methods yielded smaller mean squared error (MSE) and mean absolute error (MAE) in all scenarios. ssGBLUP yielded an improvement of 3.8% on average in accuracy compared to that of GBLUP, and the accuracy of BayesHE was close to that of GBLUP. In genomic prediction of younger individuals, RF and Adaboost.R2_KRR performed better than GBLUP and BayesHE, while ssGBLUP performed comparably with RF, and ssGBLUP yielded slightly higher accuracy and lower MSE than Adaboost.R2_KRR in the prediction of total number of piglets born, while for number of piglets born alive, Adaboost.R2_KRR performed significantly better than ssGBLUP. Among ML methods, Adaboost.R2_KRR consistently performed well in our study. Our findings also demonstrated that optimal hyperparameters are useful for ML methods. After tuning hyperparameters in CV and in predicting genomic outcomes of younger individuals, the average improvement was 14.3% and 21.8% over those using default hyperparameters, respectively.ConclusionOur findings demonstrated that ML methods had better overall prediction performance than conventional genomic selection methods, and could be new options for genomic prediction. Among ML methods, Adaboost.R2_KRR consistently performed well in our study, and tuning hyperparameters is necessary for ML methods. The optimal hyperparameters depend on the character of traits, datasets etc.

Dataset Information

Environmental properties of cells improve machine learning-based phenotype recognition accuracy.

Publications

Environmental properties of cells improve machine learning-based phenotype recognition accuracy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets