Correlation Analysis and Prediction of Genes Expression from Amino Acid Sequence of Proteins
This server allows user to analsis the expresion data (Microarray Data) where
it calculate correlation coefficient between amino acid residue and gene expression level. This will facilitate users in understanding which residues are prefered and vice verse in a organism in given condition. This server also allows to learn from known expression data and to predict expression level of other genes of same organism in that condition from their protein sequence. The method uses SVM for learning and prediction and dipeptide composition of protein as input feature for SVM.
Please cite following article if you are using this server
The LGEpred may be useful to you, if you have microarray or gene expression data and wish to extract more information from this data. The server provide following two facilities for users
Data analysis: This server allows various type analysis on microarray analysis which may help user in understanding relationship between expression of genes and amaino acid composition of their proteins. Following is the briefdescription of options.
Correlation coefficient: This option allows user to compute correlation between amino acid composition and gene expression. It first compute the % composition of an amino acid (e.g. ALA) for each gene. Then it computes correlation coefficient between amino acid composition of an amino acid gene expression data.
Bin wise analysis : This option allows user to compute the average gene expression of genes whoes protein have amino acid composition in given range. User can specify the range of amino acid composition.
Standard plot of gene expression: This option allows user to create standard plots between gene expression and composition of an amino acid.
Specific plots of gene expression: This option allows user to create standard plots between gene expression and composition of an amino acid. In addition to simple plot it also allow to see range and average on graph.
SVM Based Prediction Method: One of the major features of LGEpred is to allows user to develop SVM based prediction method from gene expression method of user. This have three major routines for the prediction of gene or ORF expression.
Training and Prediction of Gene Expression: This routine allows one to predict the expression level of genes from of known/microarray expression data. This routine build SVM model from users microarray data and then predict the expression of unknown genes using this SVM model.
Evaluation and Prediction : This allows user to evaluate the SVM method developed on users data using LGEpred server. The evaluatio is very important in are of prediction because it provides confidance to the user in using a method.
Prediction From Model: This allow user to predict expression of genes from amino acid sequences using SVM model build using LGEpred's options "Training and Prediction of Gene Expression" or "Evaluation and Prediction".
How I can use LGEpred server ?
We have provided example data/information on each submission form which will help you in understanding the format and type of data required for using an option of LGEpred server. In order to run on example file/data you need to download the data from example section and then sumit/upload this data. In order to analysis your data using LGEpred you need to have name of orf/gene and corresponding amino acid sequence in FASTA format. In case of prediction you also need your sequence data in fasta format.