Artificial Neural Networks (ANNs) are “biologically-inspired” mathematical models and algorithms that have been designed to mimic the sophisticated information processing and knowledge acquisition methods of the human brain. The application of ANNs toward predicting complex biological processes – ranging from simple cellular responses to disease progression and outcomes – could expedite the discovery of novel cellular mechanisms underlying a range of diseases. Using Neural Network Toolbox™ in MATLAB®, an ANN prototype was constructed and trained for use to test a set of genetic sequences to determine if they promote splicing in nuclear extract complemented by human SC35. SC35 belongs to the evolutionarily conserved family of serine-and-arginine-rich (SR) proteins, which play a critical role in controlling gene expression in all organisms and plants by regulating general splicing factors, alternative splicing, mRNA nuclear export, as well as multiple other factors.

Identification of genetic sequences recognized by human SC35 protein using artificial neural networks: A deep learning approach

251st National Meeting (2016)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.