Using Machine Learning to Predict Novel Gene Regulatory Interactions During Candida albicans Biofilm Development

Candida albicans is a common fungal pathogen of humans, capable of forming biofilms which are surface-adhered fungal cells within an extracellular matrix. C. albicans biofilms are attributed for over 50% hospital acquired infections. Previously, our lab identified six core transcription factors (TFs) required for the formation of mature biofilms in C. albicans. In this study, we utilize previously published data sets to identify the transcriptional network controlling C. albicans biofilm formation. We implemented a support vector machine classifier to identify novel TF binding sites by utilizing binding site 3D DNA shape and motif features. For each of the six TFs, novel TF-gene interactions were observed. Finally, active and inactive TF-gene interactions were identified by integrating novel TF-gene interactions with time-series gene expression data. This work, using interdisciplinary approaches, provides insights into potential molecular targets for therapeutic applications.