selecting-multiple-biomarker-subsets-with-similarly-effective-binary

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Biomarker detection is one of the more important biomedical questions for high-throughput &#39;omics&#39; researchers, and almost all existing biomarker ...

Jilin University

Glutathione peroxidase (GPX) is one of the important members of the antioxidant enzyme family. It can catalyze the reduction of hydroperoxides with glutathione to protect cells against oxidative damage. In previous studies, we have prepared the human catalytic antibody Se-scFv-B3 (selenium-containing single-chain Fv fragment of clone B3) with GPX activity by incorporating a catalytic group Sec (selenocysteine) into the binding site using chemical mutation; however, its activity was not very satisfying. In order to try to improve its GPX activity, structural analysis of the scFv-B3 was carried out. A three-dimensional (3D) structure of scFv-B3 was constructed by means of homology modeling and binding site analysis was carried out. Computer-aided docking and energy minimization (EM) calculations of the antibody-GSH (glutathione) complex were also performed. From these simulations, Ala44 and Ala180 in the candidate binding sites were chosen to be mutated to serines respectively, which can be subsequently converted into the catalytic Sec group. The two mutated protein and wild type of the scFv were all expressed in soluble form in Escherichia coli Rosetta and purified by Ni(2+)-immobilized metal affinity chromatography (IMAC), then transformed to selenium-containing catalytic antibody with GPX activity by chemical modification of the reactive serine residues. The GPX activity of the mutated catalytic antibody Se-scFv-B3-A180S was significantly increased compared to the original Se-scFv-B3.

Improving GPX activity of selenium-containing human single-chain Fv antibody by site-directed mutation based on the structural analysis.

In this paper, we propose two potential risk indicators to define and evaluate the safety of bicycle path at the microscopic level. Field bicycle data were collected from three survey sites under different traffic conditions. These two risk indicators based on speed dispersion were proposed and calculated during each 5-min interval. The risk influences of various widths of bicycle path and traffic conditions were analyzed by using one-way ANOVA. We further proposed a generalized linear model (GLM) for modeling and analyzing the relationships between bicycle risks and v/c ratio and percentages of electric bicycles, male cyclists, young cyclists, and loaded cyclists. The stepwise regression models were applied for determination of coefficients. The results show that the influences of gender and age of cyclists on potential risks are not significant. The risks increase with the width of bicycle path and percentage of electric bicycles, while only for wider bicycle path (4-lane case in this study), the risks are associated with whether or not cyclists are loaded. The findings could contribute for analysis and evaluation of the safety for bicycle path. 

Potential risk and its influencing factors for separated bicycle paths.

Different therapeutic methods have been developed for the B-cell and T-cell subtypes of acute lymphoblastic leukemia (ALL). The identification of molecular biomarkers that can accurately discriminate between B-cell and T-cell ALLs will facilitate the quick determination of therapeutic plans, as well as reveal the intrinsic mechanisms underlining the two different ALL subtypes. This study computationally screened the high-throughput transcriptome dataset for multiple candidate biomarkers and verified their discrimination abilities in an independent sample set using quantitative real-time polymerase chain reaction (PCR) technology. Both technologies suggest that the two genes CD3D and PKRCQ together provided a good model for classification of B-cell and T-cell ALLs, whereas the individual genes did not show consistent discrimination between the two ALL subtypes. Supplementary material is available at http://healthinformaticslab.org/supp/.

CD3D and PRKCQ work together to discriminate between B-cell and T-cell acute lymphoblastic leukemia.

Binary classification is a widely employed problem to facilitate the decisions on various biomedical big data questions, such as clinical drug trials between treated participants and controls, and genome-wide association studies (GWASs) between participants with or without a phenotype. A machine learning model is trained for this purpose by optimizing the power of discriminating samples from two groups. However, most of the classification algorithms tend to generate one locally optimal solution according to the input dataset and the mathematical presumptions of the dataset. Here we demonstrated from the aspects of both disease classification and feature selection that multiple different solutions may have similar classification performances. So the existing machine learning algorithms may have ignored a horde of fishes by catching only a good one. Since most of the existing machine learning algorithms generate a solution by optimizing a mathematical goal, it may be essential for understanding the biological mechanisms for the investigated classification question, by considering both the generated solution and the ignored ones.

Multiple similarly-well solutions exist for biomedical feature selection and classification problems.

A correction to this article has been published and is linked from the HTML version of this paper. The error has been fixed in the paper.

Author Correction: Multiple similarly effective solutions exist for biomedical feature selection and classification problems.

Transcriptomic and methylomic patterns represent two major OMIC data sources impacted by both inheritable genetic information and environmental factors, and have been widely used as disease diagnosis and prognosis biomarkers.

An OMIC biomarker detection algorithm TriVote and its application in methylomic biomarker detection.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has been fixed in the paper.

Cheng Xu

College of Software

Jilin University

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances