Potential protein markers in children with Autistic Spectrum Disorder (ASD) revealed by salivary proteomics

Salivary Diagnostics in Pediatrics and the Status of Saliva-Based Biosensors

Salivary biomarkers are increasingly being used as an alternative to diagnose and monitor the progression of various diseases due to their ease of use, on site application, non-invasiveness, and most likely improved patient compliance. Here, we highlight the role of salivary biosensors in the general population, followed by the application of saliva as a diagnostic tool in the pediatric population. We searched the literature for pediatric applications of salivary biomarkers, more specifically, in children from 0 to 18 years old. The use of those biomarkers spans autoimmune, developmental disorders, oncology, neuropsychiatry, respiratory illnesses, gastrointestinal disorders, and oral diseases. Four major applications of salivary proteins as biomarkers are: (1) dental health (caries, stress from orthodontic appliances, and gingivitis); (2) gastrointestinal conditions (eosinophilic esophagitis, acid reflux, appendicitis); (3) metabolic conditions (obesity, diabetes); and (4) respiratory conditions (asthma, allergic rhinitis, small airway inflammation, pneumonia). Genomics, metabolomics, microbiomics, proteomics, and transcriptomics, are various other classifications for biosensing based on the type of biomarkers used and reviewed here. Lastly, we describe the recent advances in pediatric biosensing applications using saliva. This work guides scientists in fabricating saliva-based biosensors by comprehensively overviewing the potential markers and techniques that can be employed.

Saliva - a new opportunity for fluid biopsy

Saliva is a complex biological fluid with a variety of biomolecules, such as DNA, RNA, proteins, metabolites and microbiota, which can be used for the screening and diagnosis of many diseases. In addition, saliva has the characteristics of simple collection, non-invasive and convenient storage, which gives it the potential to replace blood as a new main body of fluid biopsy, and it is an excellent biological diagnostic fluid. This review integrates recent studies and summarizes the research contents of salivaomics and the research progress of saliva in early diagnosis of oral and systemic diseases. This review aims to explore the value and prospect of saliva diagnosis in clinical application.

Machine learning algorithms based on proteomic data mining accurately predicting the recurrence of hepatitis B-related hepatocellular carcinoma

BACKGROUND AND AIM

Over 10% of hepatocellular carcinoma (HCC) cases recur each year, even after surgical resection. Currently, there is a lack of knowledge about the causes of recurrence and the effective prevention. Prediction of HCC recurrence requires diagnostic markers endowed with high sensitivity and specificity. This study aims to identify new key proteins for HCC recurrence and to build machine learning algorithms for predicting HCC recurrence.

METHODS

The proteomics data for analysis in this study were obtained from the Clinical Proteomics Tumor Analysis Consortium (CPTAC) database. We analyzed different proteins based on cases with or without recurrence of HCC. Survival analysis, Cox regression analysis, and area under the ROC curves (AUROC > 0.7) were used to screen for more significant differential proteins. Predictive models for HCC recurrence were developed using four machine learning algorithms.

RESULTS

A total of 690 differentially expressed proteins between 50 relapsed and 77 non-relapsed hepatitis B-related HCC patients were identified. Seven of these proteins had an AUROC > 0.7 for 5-year survival in HCC, including BAHCC1, ESF1, RAP1GAP, RUFY1, SCAMP3, STK3, and TMEM230. Among the machine learning algorithms, the random forest algorithm showed the highest AUROC values (AUROC: 0.991, 95% CI 0.962-0.999) for identifying HCC recurrence, followed by the support vector machine (AUROC: 0.893, 95% Cl 0.824-0.956), the logistic regression (AUROC: 0.774, 95% Cl 0.672-0.868), and the multi-layer perceptron algorithm (AUROC: 0.571, 95% Cl 0.459-0.682).

CONCLUSIONS

Our study identifies seven novel proteins for predicting HCC recurrence and the random forest algorithm as the most suitable predictive model for HCC recurrence.