Tyrosine Kinase Ligand-Receptor Pair Prediction by Using Support Vector Machine

Stacked classifiers for individualized prediction of glycemic control following initiation of metformin therapy in type 2 diabetes

OBJECTIVE

Metformin is the preferred first-line medication for management of type 2 diabetes and prediabetes. However, over a third of patients experience primary or secondary therapeutic failure. We developed machine learning models to predict which patients initially prescribed metformin will achieve and maintain control of their blood glucose after one year of therapy.

MATERIALS AND METHODS

We performed a retrospective analysis of administrative claims data for 12,147 commercially-insured adults and Medicare Advantage beneficiaries with prediabetes or diabetes. Several machine learning models were trained using variables available at the time of metformin initiation to predict achievement and maintenance of hemoglobin A_1c (HbA_1c) < 7.0% after one year of therapy.

RESULTS

AUC performances based on five-fold cross-validation ranged from 0.58 to 0.75. The most influential variables driving the predictions were baseline HbA_1c, starting metformin dosage, and presence of diabetes with complications.

CONCLUSIONS

Machine learning models can effectively predict primary or secondary metformin treatment failure within one year. This information can help identify effective individualized treatment strategies. Most of the implemented models outperformed traditional logistic regression, highlighting the potential for applying machine learning to problems in medicine.

A machine learning approach towards the prediction of protein–ligand binding affinity based on fundamental molecular properties

There is an exigency of transformation of the enormous amount of biological data available in various forms into some significant knowledge. We have tried to implement Machine Learning (ML) algorithm models on the protein–ligand binding affinity data already available to predict the binding affinity of the unknown. ML methods are appreciably faster and cheaper as compared to traditional experimental methods or computational scoring approaches. The prerequisites of this prediction are sufficient and unbiased features of training data and a prediction model which can fit the data well. In our study, we have applied Random forest and Gaussian process regression algorithms from the Weka package on protein–ligand binding affinity, which encompasses protein and ligand binding information from PdbBind database. The models are trained on the basis of selective fundamental information of both proteins and ligand, which can be effortlessly fetched from online databases or can be calculated with the availability of structure. The assessment of the models was made on the basis of correlation coefficient (R²) and root mean square error (RMSE). The Random forest model gave R² and RMSE of 0.76 and 1.31 respectively. We have also used our features and prediction models on the dataset used by others and found that our model with our features outperformed the existing ones.

There is an exigency of transformation of the enormous amount of biological data available in various forms into some significant knowledge.

Machine Learning and Data Mining Methods in Diabetes Research

The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.