Predicting Biological Activity from Biosynthetic Gene Clusters Using Neural Networks

Microorganisms such as bacteria and fungi have been used for natural products that translate to drugs. However, assessing the bioactivity of extract from culture to identify novel natural molecules remains a strenuous process due to the cumbersome order of production, purification, and assaying. Thus, extensive genome mining of microbiomes is underway to identify biosynthetic gene clusters or BGCs that can be profiled as particular natural products, and computational methods have been developed to address this problem using machine learning. However, existing tools are ineffective due to a small training data set, dependence on old genome mining tools, lack of relevant genomic descriptors, and prevalent class imbalance. This work presents a new tool, NPBdetect, that can detect multiple bioactivities and has been designed through rigorous experiments. First, we composed a larger training set using the MIBiG database and a test set through literature mining to build and assess the model, respectively. Second, the latest antiSMASH genome mining tool was used to obtain BGCs and introduced new sequence-based descriptors. Third, neural networks are used to build the model by dealing with class imbalance issues through the class weighting technique. Finally, we compared the NPBdetect tool with an existing tool to show its efficacy and real-world utility in detecting several bioactivities with high confidence.