A Computational Method for Prediction of Saliva-Secretory Proteins and Its Application to Identification of Head and Neck Cancer Biomarkers for Salivary Diagnosis

Abstract

Human saliva is rich in proteins, which have been used for disease detection such as oral diseases and systematic diseases. In this paper, we present a computational method for predicting secretory proteins in human saliva based on two sets of human proteins from published literatures and public databases. One set contains known proteins which can be secreted into saliva, and the other contains the proteins that are deemed to be not extracellular secretion. The protein features with discerning power between two sets were firstly gathered. Then a classifier was trained based on the identified features to predict whether a protein was saliva-secretory one or not. The average values of the sensitivity, specificity, precision, accuracy, and Matthews correlation coefficient value by 10-fold cross validation repeated 100 times were 80.67%, 90.56%, 90.09%, 85.53%, and 0.7168, respectively. These results indicated that our selected features are informative. We applied the classifier for prediction saliva-secretory proteins out of all human proteins, if a known biomarker was likely to enter into saliva, and the potential salivary biomarkers for head and neck squamous cell carcinoma. We also compared the top 1000 proteins predicted by computational methods in different kind of fluids. This work provided a useful tool for effectively identifying the salivary biomarkers for various human diseases and facilitate the development of salivary diagnosis.

The clinical significance of HOXA9 promoter hypermethylation in head and neck squamous cell carcinoma

“…The current study had some limitations. A number of methods have been developed to assess biomarkers in biological fluids to non‐invasively identify early HNSCC . Due to a lack of blood and/or saliva samples, we were unable to explore the diagnostic value of non‐invasive detection of HNSCC methylation.…”

“…A number of methods have been developed to assess biomarkers in biological fluids to non-invasively identify early HNSCC. 49,50 Due to a lack of blood and/ or saliva samples, we were unable to explore the diagnostic value of non-invasive detection of HNSCC methylation. In addition, emerging evidence indicates that a panel of several methylation genes could improve cancer diagnosis, 51 while our study focused on a single gene, which may not completely satisfy the requirements for clinical application.…”

Effect of smoking cessation in saliva compounds by FTIR spectroscopy

“…Greater intensity in former smoker mean spectra shown efficacy for diagnosis [3,22,4]. In addition, studies have shown that the saliva content of the changes is closely related to the onset of oral diseases [2,23,24] and systemic diseases [2]. It is known that substances present in cigarettes, such as nicotine, can be detected in saliva [25], and this occurs because of the solubility properties of the agents present in cigarette smoke [26].…”

“…Saliva is a complex body fluid [1] that contains a large number of different types of proteins, hormones and ions [2]. It is secreted primarily by three pairs of salivary glands (parotid, submandibular and sublingual), as well as numerous minor salivary glands [2], With the continuous advancement of proteomics technology, salivary diagnosis has become a focus of several studies [2] and, mainly because besides being considered a fluid with excellent indicators of plasma levels of various substances [1] its collection is simple and noninvasive. Thus, saliva has been used for the early diagnosis, prevention, and monitoring process of various diseases [2,3,4].…”

High-Throughput Identification of Mammalian Secreted Proteins Using Species-Specific Scheme and Application to Human Proteome

“…Yu et al built a multi-classifier to predict various types of secreted proteins [ 15 ]. Besides simply predicting secreted proteins, Sun et al applied their method in the identification of head and neck cancer biomarkers [ 16 ]. Additionally, in secreted proteins, signal peptides are destined towards the secretory pathway [ 17 ].…”