Analyzing the similarity of samples and genes by MG-PCC algorithm, t-SNE-SS and t-SNE-SG maps

Abstract

BackgroundFor analyzing these gene expression data sets under different samples, clustering and visualizing samples and genes are important methods. However, it is difficult to integrate clustering and visualizing techniques when the similarities of samples and genes are defined by PCC(Person correlation coefficient) measure.ResultsHere, for rare samples of gene expression data sets, we use MG-PCC (mini-groups that are defined by PCC) algorithm to divide them into mini-groups, and use t-SNE-SSP maps to display these mini-groups, where the idea of MG-PCC algorithm is that the nearest neighbors should be in the same mini-groups, t-SNE-SSP map is selected from a series of t-SNE(t-statistic Stochastic Neighbor Embedding) maps of standardized samples, and these t-SNE maps have different perplexity parameter. Moreover, for PCC clusters of mass genes, they are displayed by t-SNE-SGI map, where t-SNE-SGI map is selected from a series of t-SNE maps of standardized genes, and these t-SNE maps have different initialization dimensions. Here, t-SNE-SSP and t-SNE-SGI maps are selected by A-value, where A-value is modeled from areas of clustering projections, and t-SNE-SSP and t-SNE-SGI maps are such t-SNE map that has the smallest A-value.ConclusionsFrom the analysis of cancer gene expression data sets, we demonstrate that MG-PCC algorithm is able to put tumor and normal samples into their respective mini-groups, and t-SNE-SSP(or t-SNE-SGI) maps are able to display the relationships between mini-groups(or PCC clusters) clearly. Furthermore, t-SNE-SS(m)(or t-SNE-SG(n)) maps are able to construct independent tree diagrams of the nearest sample(or gene) neighbors, where each tree diagram is corresponding to a mini-group of samples(or genes).Electronic supplementary materialThe online version of this article (10.1186/s12859-018-2495-5) contains supplementary material, which is available to authorized users.

In Stallion Spermatozoa, Superoxide Dismutase (Cu–Zn) (SOD1) and the Aldo-Keto-Reductase Family 1 Member b (AKR1B1) Are the Proteins Most Significantly Reduced by Cryopreservation

“…Hierarchical clustering and heat maps were used to display protein expression patterns 27 and t-SNE (t-statistic Stochastic Neighbor Embedding) maps of standardized samples were used to identify relations between samples. 28 , 29 …”

“…The optimal filter threshold was established using the projection score. , Qlucore Omics Explorer version 3.6 Lund Sweden () bioinformatics software was used for analysis. Hierarchical clustering and heat maps were used to display protein expression patterns and t-SNE (t-statistic Stochastic Neighbor Embedding) maps of standardized samples were used to identify relations between samples. , …”

Separating Phages From Other Virus Families and Classifying the Different Phage Families By GI-Clusters

“…For the i-th virus of data-s, we use X(i) to represent its complete genome, and F k (i) to represent its F k -feature, where MG-Euclidean and Icc-cluster algorithms MG-Euclidean algorithm does not directly divide viruses into clusters, but put the nearest neighbor viruses to the same mini-groups [15]. That is, when a virus belongs to a mini-group, its nearest neighbors are in the mini-group also.…”

“…To search appropriate methods that were able to separate phages from other virus families and classify the different phage families, we constructed 4 data sets to verify our methods, where Data-1 mixed phages and other 9 different virus families, Data-2 contained 6 different phage families, Data-3 owned 9 different virus families that deleted phages of Data-1, Data-4 contained 5 different Ebolavirus families, Data-3 and Data-4 mainly illustrated the complexity of phages. Here, we used t-SNE maps to select efficient features, where t-SNE was able to map nearest neighbor samples onto adjacent points on the plane [15,16]. That is, if t-SNE projections of the different virus families distributed in different regions, the used features were reliable to define the similarity of viruses.…”

“…But for t-SNE map of any type of F-features, results showed that the different phage families mixed together on almost all of regions. Then, Gfeatures were constructed by the comprehensive application of these 15 types of F-features, training data and MG-Euclidean algorithm, where MG-Euclidean algorithm was able to put the nearest neighbors in the same mini-groups [15], and viruses of training data were used to define the families of mini-groups. However, t-SNE map of G-features showed that the different phage families still had slight mixture on their boundaries.…”