Poster or Presentation Title
Identification and Folding of miRNA through Machine Learning
Advisor(s)
Sonika Tyagi
Linda McIver
Subjects
Biology
Abstract
As of writing, there is currently no efficient way to accurately identify miRNA or predict the structure of miRNA without the usage of a lab. The purpose of this work is to provide a framework which allows for efficient identification of mature miRNA and folding of pre-miRNA using a feedforward neural network (FFNN) and probabilistic context-free grammar (PCFG) parsing, respectively. After training, the FFNN developed an accuracy of 98%. Out of all control cases using high confidence miRNA, the PCFG used returned folded structures that matched the canonical structures to an accuracy of 81%. The results of this work indicates definite patterns in miRNA folding and sequences which could facilitate the development and discovery of new strands and their characteristics. Though the current study was done using human data, the probabilistic models are generic and can be trained to work with different organisms.
Included in
Identification and Folding of miRNA through Machine Learning
As of writing, there is currently no efficient way to accurately identify miRNA or predict the structure of miRNA without the usage of a lab. The purpose of this work is to provide a framework which allows for efficient identification of mature miRNA and folding of pre-miRNA using a feedforward neural network (FFNN) and probabilistic context-free grammar (PCFG) parsing, respectively. After training, the FFNN developed an accuracy of 98%. Out of all control cases using high confidence miRNA, the PCFG used returned folded structures that matched the canonical structures to an accuracy of 81%. The results of this work indicates definite patterns in miRNA folding and sequences which could facilitate the development and discovery of new strands and their characteristics. Though the current study was done using human data, the probabilistic models are generic and can be trained to work with different organisms.