Genome-wide functional analysis of the cotton transcriptome by creating an integrated EST database

Abstract

A total of 28,432 unique contigs (25,371 in consensus contigs and 3,061 as singletons) were assembled from all 268,786 cotton ESTs currently available. Several in silico approaches [comparative genomics, Blast, Gene Ontology (GO) analysis, and pathway enrichment by Kyoto Encyclopedia of Genes and Genomes (KEGG)] were employed to investigate global functions of the cotton transcriptome. Cotton EST contigs were clustered into 5,461 groups with a maximum cluster size of 196 members. A total of 27,956 indel mutants and 149,616 single nucleotide polymorphisms (SNPs) were identified from consensus contigs. Interestingly, many contigs with significantly high frequencies of indels or SNPs encode transcription factors and protein kinases. In a comparison with six model plant species, cotton ESTs show the highest overall similarity to grape. A total of 87 cotton miRNAs were identified; 59 of these have not been reported previously from experimental or bioinformatics investigations. We also predicted 3,260 genes as miRNAs targets, which are associated with multiple biological functions, including stress response, metabolism, hormone signal transduction and fiber development. We identified 151 and 4,214 EST-simple sequence repeats (SSRs) from contigs and raw ESTs respectively. To make these data widely available, and to facilitate access to EST-related genetic information, we integrated our results into a comprehensive, fully downloadable web-based cotton EST database (www.leonxie.com).

Figure 1. Sequence size distribution of consensus contigs and singletons in cotton.

Figure 2. Schematic pipeline for cotton EST assembly, data analysis and database development.

Figure 3. Gene Ontology (GO) analysis of 28,432 cotton annotated contigs.

The three GO categories are presented: cellular component (A), biological process (B), and molecular function (C).

Figure 4. Cluster size distribution of cotton contigs.

Figure 5. Homologous genomic comparison using several blast E-value cutoffs.

A. Distribution of percent cotton contigs finding a hit in each genome. B. Distribution of cotton homologous proteins identified in other plant species. C. Comparison of number of homologs identified between cotton and Vitis vinifera with a BLASTx E-value cutoff of 1e-30. D. The same comparison between cotton and Arabidopsis thaliana.

Figure 6

A. Distribution of length of miRNAs in cotton. B. Size distribution of cotton miRNA families with more than one member.

Figure 7. Interface of cotton EST database for querying raw ESTs (A), and assembled contigs (B).