ABSTRACT
Understanding protein-protein interactions (PPIs) helps to identify protein functions and develop other important applications such as drug preparation and protein-disease relationship identification. Deep-learning-based approaches are being intensely researched for PPI determination to reduce the cost and time of previous testing methods. In this work, we integrate deep learning with feature fusion, harnessing the strengths of both approaches, handcrafted features, and protein sequence embedding. The accuracies of the proposed model using five-fold cross-validation on Yeast core and Human datasets are 96.34% and 99.30%, respectively. In the task of predicting interactions in important PPI networks, our model correctly predicted all interactions in one-core, Wnt-related, and cancer-specific networks. The experimental results on cross-species datasets, including Caenorhabditis elegans, Helicobacter pylori, Homo sapiens, Mus musculus, and Escherichia coli, also show that our feature fusion method helps increase the generalization capability of the PPI prediction model.
Subject(s)
Deep Learning , Protein Interaction Mapping , Humans , Animals , Protein Interaction Mapping/methods , Caenorhabditis elegans/metabolism , Caenorhabditis elegans/genetics , Mice , Computational Biology/methods , Protein Interaction Maps , Databases, ProteinABSTRACT
The selective detection of ultratrace amounts of aflatoxin M1 (AFM1) is extremely important for food safety since it is the most toxic mycotoxin class that is allowed to be present on cow milk with strictly low regulatory levels. In this work, Fe3O4 incorporated polyaniline (Fe3O4/PANi) film has been polymerized on interdigitated electrode (IDE) as sensitive film for AFM1 electrochemical biosensor. The immobilized aptamers as an affinity capture reagent and magnetic nanoparticles for signal amplification element have been employed in the sensing platform. Label-free and direct detection of the aptamer-AFM1 on Fe3O4/PANi interface were performed via electrochemical signal change, acquired by cyclic and square wave voltammetries. With a simplified strategy, this electrochemical aptasensor shows a good sensitivity to AFM1 in the range of 6-60 ng·L(-1), with the detection limit of 1.98 ng·L(-1). The results open up the path for designing cost effective aptasensors for other biomedical applications.