QuantumTox: Utilizing quantum chemistry with ensemble learning for molecular toxicity prediction

Molecular toxicity prediction plays an important role in drug discovery, which is directly related to human health and drug fate. Accurately determining the toxicity of molecules can help weed out low-quality molecules in the early stage of drug discovery process and avoid depletion later in the drug development process. Nowadays, more and more researchers are starting to use machine learning methods to predict the toxicity of molecules, but these models do not fully exploit the 3D information of molecules. Quantum chemical information, which provides stereo structural information of molecules, can influence their toxicity. To this end, we propose QuantumTox, the first application of quantum chemistry in the field of drug molecule toxicity prediction compared to existing work. We extract the quantum chemical information of molecules as their 3D features. In the downstream prediction phase, we use Gradient Boosting Decision Tree and Bagging ensemble learning methods together to improve the accuracy and generalization of the model. A series of experiments on various tasks show that our model consistently outperforms the baseline model and that the model still performs well on small datasets of less than 300.

GBDTLRL2D Predicts LncRNA-Disease Associations Using MetaGraph2Vec and K-Means Based on Heterogeneous Network

In recent years, the long noncoding RNA (lncRNA) has been shown to be involved in many disease processes. The prediction of the lncRNA-disease association is helpful to clarify the mechanism of disease occurrence and bring some new methods of disease prevention and treatment. The current methods for predicting the potential lncRNA-disease association seldom consider the heterogeneous networks with complex node paths, and these methods have the problem of unbalanced positive and negative samples. To solve this problem, a method based on the Gradient Boosting Decision Tree (GBDT) and logistic regression (LR) to predict the lncRNA-disease association (GBDTLRL2D) is proposed in this paper. MetaGraph2Vec is used for feature learning, and negative sample sets are selected by using K-means clustering. The innovation of the GBDTLRL2D is that the clustering algorithm is used to select a representative negative sample set, and the use of MetaGraph2Vec can better retain the semantic and structural features in heterogeneous networks. The average area under the receiver operating characteristic curve (AUC) values of GBDTLRL2D obtained on the three datasets are 0.98, 0.98, and 0.96 in 10-fold cross-validation.

Machine Learning Methods for the Diagnosis of Chronic Obstructive Pulmonary Disease in Healthy Subjects: Retrospective Observational Cohort Study

BACKGROUND

Airflow limitation is a critical physiological feature in chronic obstructive pulmonary disease (COPD), for which long-term exposure to noxious substances, including tobacco smoke, is an established risk. However, not all long-term smokers develop COPD, meaning that other risk factors exist.

OBJECTIVE

This study aimed to predict the risk factors for COPD diagnosis using machine learning in an annual medical check-up database.

METHODS

In this retrospective observational cohort study (ARTDECO [Analysis of Risk Factors to Detect COPD]), annual medical check-up records for all Hitachi Ltd employees in Japan collected from April 1998 to March 2019 were analyzed. Employees who provided informed consent via an opt-out model were screened and those aged 30 to 75 years without a prior diagnosis of COPD/asthma or a history of cancer were included. The database included clinical measurements (eg, pulmonary function tests) and questionnaire responses. To predict the risk factors for COPD diagnosis within a 3-year period, the Gradient Boosting Decision Tree machine learning (XGBoost) method was applied as a primary approach, with logistic regression as a secondary method. A diagnosis of COPD was made when the ratio of the prebronchodilator forced expiratory volume in 1 second (FEV₁) to prebronchodilator forced vital capacity (FVC) was <0.7 during two consecutive examinations.

RESULTS

Of the 26,101 individuals screened, 1213 met the exclusion criteria, and thus, 24,815 individuals were included in the analysis. The top 10 predictors for COPD diagnosis were FEV₁/FVC, smoking status, allergic symptoms, cough, pack years, hemoglobin A_1c, serum albumin, mean corpuscular volume, percent predicted vital capacity, and percent predicted value of FEV₁. The areas under the receiver operating characteristic curves of the XGBoost model and the logistic regression model were 0.956 and 0.943, respectively.

CONCLUSIONS

Using a machine learning model in this longitudinal database, we identified a number of parameters as risk factors other than smoking exposure or lung function to support general practitioners and occupational health physicians to predict the development of COPD. Further research to confirm our results is warranted, as our analysis involved a database used only in Japan.

A Novel KGP Algorithm for Improving INS/GPS Integrated Navigation Positioning Accuracy

The fusion of multi-source sensor data is an effective method for improving the accuracy of vehicle navigation. The generalization abilities of neural-network-based inertial devices and GPS integrated navigation systems weaken as the nonlinearity in the system increases, resulting in decreased positioning accuracy. Therefore, a KF-GDBT-PSO (Kalman Filter-Gradient Boosting Decision Tree-Particle Swarm Optimization, KGP) data fusion method was proposed in this work. This method establishes an Inertial Navigation System (INS) error compensation model by integrating Kalman Filter (KF) and Gradient Boosting Decision Tree (GBDT). To improve the prediction accuracy of the GBDT, we optimized the learning algorithm and the fitness parameter using Particle Swarm Optimization (PSO). When the GPS signal was stable, the KGP method was used to solve the nonlinearity issue between the vehicle feature and positioning data. When the GPS signal was unstable, the training model was used to correct the positioning error for the INS, thereby improving the positioning accuracy and continuity. The experimental results show that our method increased the positioning accuracy by 28.20–59.89% compared with the multi-layer perceptual neural network and random forest regression.

Crash injury severity analysis using a two-layer Stacking framework

Crash injury severity analysis is useful for traffic management agency to further understand severity of crashes. A two-layer Stacking framework is proposed in this study to predict the crash injury severity: The fist layer integrates advantages of three base classification methods: RF (Random Forests), AdaBoost (Adaptive Boosting), and GBDT (Gradient Boosting Decision Tree); the second layer completes classification of crash injury severity based on a Logistic Regression model. A total of 5538 crashes were recorded at 326 freeway diverge areas. In the model calibration, several parameters including the number of trees in three base classification methods, learning rate, and regularization coefficient are optimized via a systematic grid search approach. In the model validation, the performance of the Stacking model is compared with several traditional models including the Support Vector Machine (SVM), Multi-Layer Perceptron (MLP) and Random Forests (RF) in the multi classification experiments. The prediction results show that Stacking model achieves superior performance evaluated by two indicators: accuracy and recall. Furthermore, all the factors used in severity prediction are classified into different categories according to their influence on the results, and sensitivity analysis of several significant factors is finally implemented to explore the impact of their value variation on the prediction accuracy.