Computational classification models for predicting the interaction of drugs with P-glycoprotein and breast cancer resistance protein

P-glycoprotein (P-gp/ABCB1) and breast cancer resistance protein (BCRP/ABCG2) are two members of the adenosine triphosphate (ATP) binding cassette (ABC) family of transporters which function as membrane efflux transporters and display considerable substrate promiscuity. Both are known to significantly influence the absorption, distribution and elimination of drugs, mediate drug-drug interactions and contribute to multiple drug resistance (MDR) of cancer cells. Correspondingly, timely characterization of the interaction of novel leads and drug candidates with these two transporters is of great importance. In this study, several computational classification models for prediction of transport and inhibition of P-gp and BCRP, respectively, were developed based on newly compiled and critically evaluated experimental data. Artificial neural network (ANN) and support vector machine (SVM) ensemble based models were explored, as well as knowledge-based approaches to descriptor selection. The average overall classification accuracy of best performing models was 82% for P-gp transport, 88% for BCRP transport, 89% for P-gp inhibition and 87% for BCRP inhibition, determined across an array of different test sets. An analysis of substrate overlap between P-gp and BCRP was also performed. The accuracy, simplicity and interpretability of the proposed models suggest that they could be of significant utility in the drug discovery and development settings.

Radiomics Approaches for Predicting Liver Fibrosis With Nonenhanced T1 -Weighted Imaging: Comparison of Different Radiomics Models

BACKGROUND

Liver fibrosis is a common process resulting from various etiologies. Sustained progression of liver fibrosis leads to cirrhosis, even hepatocellular carcinoma. Thus, noninvasive staging of liver fibrosis is of clinical importance. Radiomics is an emerging approach for staging liver fibrosis. However, the feature selection methods and classifier models are complicated, and may result in a discrepancy of diagnostic performance owing to different radiomics models.

PURPOSE

To identify the optimal feature selection and classifier methods for predicting liver fibrosis by using nonenhanced T₁ -weighted imaging.

STUDY TYPE

Prospective.

ANIMAL MODEL

Wistar rats, total 97.

FIELD STRENGTH/SEQUENCE

3T, 3D T₁ -weighted images with fast-spoiled gradient echo (FSPGR).

ASSESSMENT

Liver fibrosis rats were induced via subcutaneous injection of a mixture of carbon tetrachloride. Rats in the control group were injected with saline. Segmentation and feature extraction were performed by 3D slicer and the image biomarker explorer (IBEX) software package. Data preprocessing, feature selection, model building, and model comparative evaluation were conducted with Python. The liver fibrosis stage was determined by pathological examination.

STATISTICAL TESTS

Receiver operating characteristic curve, fuzzy comprehensive evaluation.

RESULTS

For discriminating between F0 and F1-2, F0 and F3-4, F0 and F1-4, F0-1 and F2-4, F0-2 and F3-4, and F0-3 and F4, the accuracies of 12 radiomics models were 77.27-90.91%, 73.33-86.67%, 80.56-91.67%, 74.07-88.89%, 76.47-88.24%, and 79.49-92.31%, respectively. The AUCs of the radiomics models were 0.86-0.97, 0.85-0.95, 0.89-0.97, 0.81-0.96, 0.82-0.93, and 0.85-0.96, respectively. The least absolute shrinkage and selection operator / support vector machine (LASSO-SVM) model had high AUCs of 0.93-0.97. For discriminating between F0 and F1-2, F0 and F3-4, F0 and F1-4, F0-1 and F2-4, and F0-2 and F3-4, the fuzzy comprehensive evaluation showed that the LASSO-SVM model had a high fuzzy score/order of 0.087-0.091/1.

DATA CONCLUSION

LASSO-SVM appears to be the optimal model for predicting liver fibrosis by using nonenhanced T₁ -weighted imaging in a rodent model of liver fibrosis.

LEVEL OF EVIDENCE

2.

TECHNICAL EFFICACY STAGE

2.

Development and Internal Validation of a Prognostic Model of the Probability of Death or Lung Transplantation Within 2 Years for Patients With Cystic Fibrosis and FEV1 ≤ 50% Predicted

BACKGROUND

Improved methods are needed to risk-stratify patients with cystic fibrosis (CF) and reduced FEV1.

RESEARCH QUESTIONS

What are the predictors of death or lung transplantation (LTx) within 2 years among patients with CF whose FEV1 ≤ 50% predicted? Do these markers similarly predict outcomes among G551D patients taking ivacaftor since 2012?

STUDY DESIGN AND METHODS

Patients with CF, age ≥ 6 years with FEV1 ≤ 50% predicted as of December 31, 2014, were identified in a data set that merged Cystic Fibrosis Foundation and United Network for Organ Sharing (UNOS) registries. The least absolute shrinkage and selection operator (LASSO) method was applied to a randomly selected training set to select important prognostic variables. Accuracy and association of the model with death or LTx with 2 years (2-year death or LTx) were validated via logistic regression on an independent test set. Sensitivity analyses explored predictors for patients with UNOS data.

RESULTS

FEV1 percent predicted (OR, 1.51 for 5% decrease; 95% CI, 1.27-1.81), number of pulmonary exacerbations treated with IV antibiotics (OR, 1.35; 95% CI, 1.11-1.65), and continuous or nocturnal oxygen (OR, 3.71; 95% CI, 1.81-7.59) were significantly associated with 2-year death or LTx. Our model predicted outcomes with greater sensitivity (ratio of sensitivity, 1.26; 95% CI, 1.02-1.54), ratio of positive predictive value (1.25; 95% CI, 1.05-1.51), and ratio of negative predictive value (1.04; 95% CI, 1.01-1.07) than FEV1 < 30% predicted. Among those taking ivacaftor in 2014, only FEV1 remained associated with 2-year death or LTx. For patients with UNOS data, LASSO identified additional covariates of interest, including noninvasive ventilation use, low hemoglobin, pulmonary arterial systolic pressure, supplemental oxygen, mechanical ventilation, FEV1 percent predicted, and cardiac index.

INTERPRETATION

Among individuals with CF and FEV1 ≤ 50% predicted, FEV1 percent predicted, oxygen therapy, and number of pulmonary exacerbations predicted 2-year death or LTx. Although limited by small sample size, only FEV1 remained predictive in patients receiving highly effective modulator therapy. Additional physiologic variables could improve prognostication in CF.

A Clinicogenetic Prognostic Classifier for Prediction of Recurrence and Survival in Asian Breast Cancer Patients

Background

Several prognostic factors affect the recurrence of breast cancer in patients who undergo mastectomy. Assays of the expression profiles of multiple genes increase the probability of overexpression of certain genes and thus can potentially characterize the risk of metastasis.

Methods

We propose a 20-gene classifier for predicting patients with high/low risk of recurrence within 5 years. Gene expression levels from a quantitative PCR assay were used to screen 473 luminal breast cancer patients treated at Taiwan Hospital (positive for estrogen and progesterone receptors, negative for human epidermal growth factor receptor 2). Gene expression scores, along with clinical information (age, tumor stage, and nodal stage), were evaluated for risk prediction. The classifier could correctly predict patients with and without relapse (logistic regression, P<0.05).

Results

A Cox proportional hazards regression analysis showed that the 20-gene panel was prognostic with hazard ratios of 5.63 (95% confidence interval 2.77-11.5, univariate) and 5.56 (2.62-11.8, multivariate) for the “genetic” model, and of 8.02 (3.52-18.3, univariate) and 19.8 (5.96-65.87, multivariate) for the “clinicogenetic” model during a 5-year follow-up.

Conclusions

The proposed 20-gene classifier can successfully separate the patients into two risk groups, and the two risk group had significantly different relapse rate and prognosis. This 20-gene classifier can provide better estimation of prognosis, which can help physicians to make better personalized treatment plans.

A 23-gene prognostic classifier for prediction of recurrence and survival for Asian breast cancer patients

We report a 23- gene-classifier profiled from Asian women, with the primary purpose of assessing its clinical utility towards improved risk stratification for relapse for breast cancer patients from Asian cohorts within 10 years’ following mastectomy. Four hundred and twenty-two breast cancer patients underwent mastectomy and were used to train the classifier on a logistic regression model. A subset of 197 patients were chosen to be entered into the follow-up studies post mastectomy who were examined to determine the patterns of recurrence and survival analysis based on gene expression of the gene classifier, age at diagnosis, tumor stage and lymph node status, over a 5 and 10 years follow-up period. Metastasis to lymph node (N2-N3) with N0 as the reference (N2 vs. N0 hazard ratio: 2.02 (1.05–8.70), N3 vs. N0 hazard ratio: 4.32 (1.41–13.22) for 5 years) and gene expression of the 23-gene panel (P=0.06, 5 years and 0.02, 10 years, log-rank test) were found to have significant discriminatory effects on the risk of relapse (HR (95%CI):2.50 (0.95–6.50)). Furthermore, survival curves for subgroup analysis with N0-N1 and T1-T2 predicted patients with higher risk scores. The study provides robust evidence of the effectiveness of the 23-gene-classifier and could be used to determine the risk of relapse event (locoregional and distant recurrence) in Asian patients, leading to a meaningful reduction in chemotherapy recommendations.

Cerebellar nuclei cells produce distinct pathogenic spike signatures in mouse models of ataxia, dystonia, and tremor

The cerebellum contributes to a diverse array of motor conditions, including ataxia, dystonia, and tremor. The neural substrates that encode this diversity are unclear. Here, we tested whether the neural spike activity of cerebellar output neurons is distinct between movement disorders with different impairments, generalizable across movement disorders with similar impairments, and capable of causing distinct movement impairments. Using in vivo awake recordings as input data, we trained a supervised classifier model to differentiate the spike parameters between mouse models for ataxia, dystonia, and tremor. The classifier model correctly assigned mouse phenotypes based on single-neuron signatures. Spike signatures were shared across etiologically distinct but phenotypically similar disease models. Mimicking these pathophysiological spike signatures with optogenetics induced the predicted motor impairments in otherwise healthy mice. These data show that distinct spike signatures promote the behavioral presentation of cerebellar diseases.

Selecting Accurate Classifier Models for a MERS-CoV Dataset

The Middle East Respiratory Syndrome Coronavirus (MERS-CoV) is a viral respiratory disease that is spreading worldwide necessitating to have an accurate diagnosis system that accurately predicts infections. As data mining classifiers can greatly assist in enhancing the prediction accuracy of diseases in general. In this paper, classifier model performance for two classification types: (1) binary and (2) multi-class were tested on a MERS-CoV dataset that consists of all reported cases in Saudi Arabia between 2013 and 2017. A cross-validation model was applied to measure the accuracy of the Support Vector Machine (SVM), Decision Tree, and k-Nearest Neighbor (k-NN) classifiers. Experimental results demonstrate that SVM and Decision Tree classifiers achieved the highest accuracy of 86.44% for binary classification based on healthcare personnel class. On the other hand, for multiclass classification based on city class, the decision tree classifier had the highest accuracy among the remaining classifiers; although it did not reach a satisfactory accuracy level (42.80%). This work is intended to be a part of a MERS-CoV prediction system to enhance the diagnosis of MERS-CoV disease.

Combining the Fecal Immunochemical Test with a Logistic Regression Model for Screening Colorectal Neoplasia

Background: The fecal immunochemical test (FIT) is a widely used strategy for colorectal cancer (CRC) screening with moderate sensitivity. To further increase the sensitivity of FIT in identifying colorectal neoplasia, in this study, we established a classifier model by combining FIT result and other demographic and clinical features.

Methods: A total of 4,477 participants were examined with FIT and those who tested positive (over 100 ng/ml) were followed up by a colonoscopy examination. Demographic and clinical information of participants including four domains (basic information, clinical history, diet habits and life styles) that consist of 15 features were retrieved from questionnaire surveys. A mean decrease accuracy (MDA) score was used to select features that are mostly related to CRC. Five different algorithms including logistic regression (LR), classification and regression tree (CART), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) were used to generate a classifier model, through a 10X cross validation process. Area under curve (AUC) and normalized mean squared error (NMSE) were used in the evaluation of the performance of the model.

Results: The top six features that are mostly related to CRC include age, gender, history of intestinal adenoma or polyposis, smoking history, gastrointestinal discomfort symptom and fruit eating habit were selected. LR algorithm was used in the generation of the model. An AUC score of 0.92 and an NMSE score of 0.076 were obtained by the final classifier model in separating normal individuals from participants with colorectal neoplasia.

Conclusion: Our results provide a new “Funnel” strategy in colorectal neoplasia screening via adding a classifier model filtering step between FIT and colonoscopy examination. This strategy minimizes the need of colonoscopy examination while increases the sensitivity of FIT-based CRC screening.