Abstract:The recent advancement in spatial transcriptomics technology has enabled multiplexed profiling of cellular transcriptomes and spatial locations. As the capacity and efficiency of the experimental technologies continue to improve, there is an emerging need for the development of analytical approaches. Furthermore, with the continuous evolution of sequencing protocols, the underlying assumptions of current analytical methods need to be re-evaluated and adjusted to harness the increasing data complexity. To motiv… Show more
“…On the other hand, the LDA, SVM, and logistic regression classifiers were shown to be robust to the perturbation methods in the framework. The developed method is generally intended for use on biological datasets such as RNA expressions, metabolite concentrations, or protein concentration data because these types of datasets involve similar noise characteristics to the ones investigated here [ 43 , 44 , 45 ].…”
There has been a rapid increase in the number of artificial intelligence (AI)/machine learning (ML)-based biomarker diagnostic classifiers in recent years. However, relatively little work has focused on assessing the robustness of these biomarkers, i.e., investigating the uncertainty of the AI/ML models that these biomarkers are based upon. This paper addresses this issue by proposing a framework to evaluate the already-developed classifiers with regard to their robustness by focusing on the variability of the classifiers’ performance and changes in the classifiers’ parameter values using factor analysis and Monte Carlo simulations. Specifically, this work evaluates (1) the importance of a classifier’s input features and (2) the variability of a classifier’s output and model parameter values in response to data perturbations. Additionally, it was found that one can estimate a priori how much replacement noise a classifier can tolerate while still meeting accuracy goals. To illustrate the evaluation framework, six different AI/ML-based biomarkers are developed using commonly used techniques (linear discriminant analysis, support vector machines, random forest, partial-least squares discriminant analysis, logistic regression, and multilayer perceptron) for a metabolomics dataset involving 24 measured metabolites taken from 159 study participants. The framework was able to correctly predict which of the classifiers should be less robust than others without recomputing the classifiers itself, and this prediction was then validated in a detailed analysis.
“…On the other hand, the LDA, SVM, and logistic regression classifiers were shown to be robust to the perturbation methods in the framework. The developed method is generally intended for use on biological datasets such as RNA expressions, metabolite concentrations, or protein concentration data because these types of datasets involve similar noise characteristics to the ones investigated here [ 43 , 44 , 45 ].…”
There has been a rapid increase in the number of artificial intelligence (AI)/machine learning (ML)-based biomarker diagnostic classifiers in recent years. However, relatively little work has focused on assessing the robustness of these biomarkers, i.e., investigating the uncertainty of the AI/ML models that these biomarkers are based upon. This paper addresses this issue by proposing a framework to evaluate the already-developed classifiers with regard to their robustness by focusing on the variability of the classifiers’ performance and changes in the classifiers’ parameter values using factor analysis and Monte Carlo simulations. Specifically, this work evaluates (1) the importance of a classifier’s input features and (2) the variability of a classifier’s output and model parameter values in response to data perturbations. Additionally, it was found that one can estimate a priori how much replacement noise a classifier can tolerate while still meeting accuracy goals. To illustrate the evaluation framework, six different AI/ML-based biomarkers are developed using commonly used techniques (linear discriminant analysis, support vector machines, random forest, partial-least squares discriminant analysis, logistic regression, and multilayer perceptron) for a metabolomics dataset involving 24 measured metabolites taken from 159 study participants. The framework was able to correctly predict which of the classifiers should be less robust than others without recomputing the classifiers itself, and this prediction was then validated in a detailed analysis.
“…We focus on methods specialized for ST data analysis. While a detailed description of all the methods mentioned here is beyond the scope of this review, more detailed descriptions of the ST data analysis methods can be found in the original research articles or the recent reviews [27] , [28] , [29] , [83] , [101] , [102] . Fig.…”
Section: Advanced Solutions In the Analysis Of Spatial Transcriptomic...mentioning
“…In addition to domain recognition, the enhancement of spatial gene expression data also presents a significant challenge. Though great progress has been made in spatial technologies, the major problems such as missing values, data sparsity, low coverage, and noises 2,15 encountered in spatial transcriptomics profiles are impeding the effective use and the elucidation of biology insights 16,17 . Meanwhile, the multi-channel spatial images in single-cell spatial data consist of high-resolution, high-content features detected in the tissue, such as cell types, functions, and morphologies of cellular compartments, as well as the spatial distributions of cells.…”
The recent advances in high throughput molecular imaging push the spatial transcriptomics technologies to the subcellular resolution, which breaks the limitations of both single cell RNA seq and array based spatial profiling. The latest released single cell spatial transcriptomics data from NanoString CosMx and MERSCOPE platforms contains multi channel immunohistochemistry images with rich information of cell types, functions, and morphologies of cellular compartments. In this work, we developed a novel method, Single cell spatial elucidation through image augmented Graph transformer (SiGra), to reveal spatial domains and enhance the substantially sparse and noisy transcriptomics data. SiGra applies hybrid graph transformers over a spatial graph that comprises high-content images and gene expressions of individual cells. SiGra outperformed state of the art methods on both single cell spatial profiles and spot level spatial transcriptomics data from complex tissues. The inclusion of immunohistochemistry images improved the model performance by 37% (95%CI: 27% to 50%). SiGra improves the characterization of intratumor heterogeneity and intercellular communications in human lung cancer samples, meanwhile recovers the known microscopic anatomy in both human brain and mouse liver tissues. Overall, SiGra effectively integrates different spatial modality data to gain deep insights into the spatial cellular ecosystems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
