With the advancement of next generation sequencing technologies, large numbers of sequenced genomes had been generated for many large-scale sequencing projects. Accurate prediction of genes from these genomes is one of the most important steps in the genome annotation process. Many software tools and pipelines developed by various computing techniques are available for gene prediction, but have yet to accurately predict the protein-coding regions. None of them has a universal Hidden Markov Model (HMM) that can perform gene prediction automatically for all organisms equally well. We developed an automated gene prediction program, Seqping that uses self-training HMM models and transcriptomic data.
Main Researcher: Chan Kuang Lim