Breast cancer identification via modeling of peripherally circulating miRNAs.

Prolonged life expectancy in humans has been accompanied by an increase in the prevalence of cancers. Breast cancer (BC) is the leading cause of cancer-related deaths. It accounts for one-fourth of all diagnosed cancers and affects one in eight females worldwide. Given the high BC prevalence, there is a practical need for demographic screening of the disease. In the present study, we re-analyzed a large microRNA (miRNA) expression dataset (GSE73002), with the goal of optimizing miRNA biomarker selection using neural network cascade (NNC) modeling. Our results identified numerous candidate miRNA biomarkers that are technically suitable for BC detection. We combined three miRNAs (miR-1246, miR-6756-5p, and miR-8073) into a single panel to generate an NNC model, which successfully detected BC with 97.1% accuracy in an independent validation cohort comprising 429 BC patients and 895 healthy controls. In contrast, at least seven miRNAs were merged in a multiple linear regression model to obtain equivalent diagnostic performance (96.4% accuracy in the independent validation set). Our findings suggested that suitable modeling can effectively reduce the number of miRNAs required in a biomarker panel without compromising prediction accuracy, thereby increasing the technical possibility of early detection of BC.

Medical examination powers miR-194-5p as a biomarker for postmenopausal osteoporosis.

An important attribute of microRNAs is their potential use as disease biomarkers. However, such applications may be restricted because of unsatisfactory performance of the microRNA of interest. Owing to moderate correlation with spine T-score, miR-194-5p was identified as a potential biomarker for postmenopausal osteoporosis. Here, we determined whether medical examination could improve its characteristic as a biomarker for postmenopausal osteoporosis. We recruited 230 postmenopausal Chinese women to measure circulating levels of miR-194-5p, determine the spine bone status, and perform a 42-item medical examination. No obvious information redundancy was observed between miR-194-5p and any one item. However, on examining miR-194-5p alone, the sensitivity at fixed specificity of 0.9 (SESP=0.9) was 0.27, implying poor identification of at-risk individuals. Model integration of the microRNA and multiple medical items strengthened this property; in addition, model complexity greatly contributed to performance improvement. Using a model composed of two artificial neural networks, the ability of miR-194-5p to identify at-risk individuals significantly improved (SESP=0.9 = 0.54) when correlated with five medical items: weight, age, left ventricular end systolic diameter, alanine aminotransferase, and urine epithelial cell count. We present a feasible way to achieve a more accurate microRNA-based biomarker for a disease of interest.

Constructing an ovarian cancer metastasis index by dissecting medical records.

Globally, ovarian cancer (OC) is the leading cause of gynecological cancer-associated deaths. Metastasis, especially multi-organ metastasis, determines the speed of disease progression. A multicenter retrospective study was performed to identify the factors that drive metastasis, from medical records of 534 patients with OC. The average number of target organs per patient was 3.66, indicating multi-organ metastasis. The most common sites of metastasis were large intestine and greater omentum, which were prone to co-metastasis. Results indicated that ascites and laterality, rather than age and menopausal status, were the potential drivers for multi-organ metastasis. Cancer antigen (CA) 125 (CA-125) and nine other blood indicators were found to show a significant, but weak correlation with multi-organ metastasis. A neural network cascade-multiple linear regression hybrid model was built to create an ovarian cancer metastasis index (OCMI) by integration of six multi-organ metastasis drivers including CA-125, blood platelet count, lymphocytes percentage, prealbumin, ascites, and laterality. In an independent set of 267 OC medical records, OCMI showed a moderate correlation with multi-organ metastasis (Spearman ρ = 0.67), the value being 0.72 in premenopausal patients, and good performance in identifying multi-organ metastasis (area under the receiver operating characteristic curve = 0.832), implying a potential prognostic marker for OC.

Modeling using clinical examination indicators predicts interstitial lung disease among patients with rheumatoid arthritis.

Interstitial lung disease (ILD) is a severe extra-articular manifestation of rheumatoid arthritis (RA) that is well-defined as a chronic systemic autoimmune disease. A proportion of patients with RA-associated ILD (RA-ILD) develop pulmonary fibrosis (PF), resulting in poor prognosis and increased lifetime risk. We investigated whether routine clinical examination indicators (CEIs) could be used to identify RA patients with high PF risk. A total of 533 patients with established RA were recruited in this study for model building and 32 CEIs were measured for each of them. To identify PF risk, a new artificial neural network (ANN) was built, in which inputs were generated by calculating Euclidean distance of CEIs between patients. Receiver operating characteristic curve analysis indicated that the ANN performed well in predicting the PF risk (Youden index = 0.436) by only incorporating four CEIs including age, eosinophil count, platelet count, and white blood cell count. A set of 218 RA patients with healthy lungs or suffering from ILD and a set of 87 RA patients suffering from PF were used for independent validation. Results showed that the model successfully identified ILD and PF with a true positive rate of 84.9% and 82.8%, respectively. The present study suggests that model integration of multiple routine CEIs contributes to identification of potential PF risk among patients with RA.

Five-descriptor model to predict the chromatographic sequence of natural compounds.

Despite the recent introduction of mass detection techniques, ultraviolet detection is still widely applied in the field of the chromatographic analysis of natural medicines. Here, a neural network cascade model consisting of nine small artificial neural network units was innovatively developed to predict the chromatographic sequence of natural compounds by integrating five molecular descriptors as the input. A total of 117 compounds of known structure were collected for model building. The order of appearance of each compound was determined in gradient chromatography. Strong linear correlation was found between the predicted and actual chromatographic position orders (Spearman's rho = 0.883, p < 0.0001). Application of the model to the external validation set of nine natural compounds was shown to dramatically increase the prediction accuracy of the real chromatographic order of multiple compounds. A case study shows that chromatographic sequence prediction based on a neural network cascade facilitated compound identification in the chromatographic fingerprint of Radix Salvia miltiorrhiza. For natural medicines of known compound composition, our method provides a feasible means for identifying the constituents of interest when only ultraviolet detection is available.

Artificial neural network cascade identifies multi-P450 inhibitors in natural compounds.

Substantial evidence has shown that most exogenous substances are metabolized by multiple cytochrome P450 (P450) enzymes instead of by merely one P450 isoform. Thus, multi-P450 inhibition leads to greater drug-drug interaction risk than specific P450 inhibition. Herein, we innovatively established an artificial neural network cascade (NNC) model composed of 23 cascaded networks in a ladder-like framework to identify potential multi-P450 inhibitors among natural compounds by integrating 12 molecular descriptors into a P450 inhibition score (PIS). Experimental data reporting in vitro inhibition of five P450 isoforms (CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4) were obtained for 8,148 compounds from the Cytochrome P450 Inhibitors Database (CPID). The results indicate significant positive correlation between the PIS values and the number of inhibited P450 isoforms (Spearman's ρ = 0.684, p < 0.0001). Thus, a higher PIS indicates a greater possibility for a chemical to inhibit the enzyme activity of at least three P450 isoforms. Ten-fold cross-validation of the NNC model suggested an accuracy of 78.7% for identifying whether a compound is a multi-P450 inhibitor or not. Using our NNC model, 22.2% of the approximately 160,000 natural compounds in TCM Database@Taiwan were identified as potential multi-P450 inhibitors. Furthermore, chemical similarity calculations suggested that the prevailing parent structures of natural multi-P450 inhibitors were alkaloids. Our findings show that dissection of chemical structure contributes to confident identification of natural multi-P450 inhibitors and provides a feasible method for virtually evaluating multi-P450 inhibition risk for a known structure.