Phenomapping of Patients with Primary Breast Cancer Using Machine Learning-Based Unsupervised Cluster Analysis

Machine Learning Methods for Small Data Challenges in Molecular Science

Small data are often used in scientific and engineering research due to the presence of various constraints, such as time, cost, ethics, privacy, security, and technical limitations in data acquisition. However, big data have been the focus for the past decade, small data and their challenges have received little attention, even though they are technically more severe in machine learning (ML) and deep learning (DL) studies. Overall, the small data challenge is often compounded by issues, such as data diversity, imputation, noise, imbalance, and high-dimensionality. Fortunately, the current big data era is characterized by technological breakthroughs in ML, DL, and artificial intelligence (AI), which enable data-driven scientific discovery, and many advanced ML and DL technologies developed for big data have inadvertently provided solutions for small data problems. As a result, significant progress has been made in ML and DL for small data challenges in the past decade. In this review, we summarize and analyze several emerging potential solutions to small data challenges in molecular science, including chemical and biological sciences. We review both basic machine learning algorithms, such as linear regression, logistic regression (LR), k-nearest neighbor (KNN), support vector machine (SVM), kernel learning (KL), random forest (RF), and gradient boosting trees (GBT), and more advanced techniques, including artificial neural network (ANN), convolutional neural network (CNN), U-Net, graph neural network (GNN), Generative Adversarial Network (GAN), long short-term memory (LSTM), autoencoder, transformer, transfer learning, active learning, graph-based semi-supervised learning, combining deep learning with traditional machine learning, and physical model-based data augmentation. We also briefly discuss the latest advances in these methods. Finally, we conclude the survey with a discussion of promising trends in small data challenges in molecular science.

Vitamin D Deficiency in Women with Breast Cancer: A Correlation with Osteoporosis? A Machine Learning Approach with Multiple Factor Analysis

Breast cancer (BC) is the most frequent malignant tumor in women in Europe and North America, and the use of aromatase inhibitors (AIs) is recommended in women affected by estrogen receptor-positive BCs. AIs, by inhibiting the enzyme that converts androgens into estrogen, cause a decrement in bone mineral density (BMD), with a consequent increased risk of fragility fractures. This study aimed to evaluate the role of vitamin D3 deficiency in women with breast cancer and its correlation with osteoporosis and BMD modifications. This observational cross-sectional study collected the following data regarding bone health: osteoporosis and osteopenia diagnosis, lumbar spine (LS) and femoral neck bone mineral density (BMD), serum levels of 25-hydroxyvitamin D3 (25(OH)D3), calcium and parathyroid hormone. The study included 54 women with BC, mean age 67.3 ± 8.16 years. Given a significantly low correlation with the LS BMD value (r2 = 0.30, p = 0.025), we assessed the role of vitamin D3 via multiple factor analysis and found that BMD and vitamin D3 contributed to the arrangement of clusters, reported as vectors, providing similar trajectories of influence to the construction of the machine learning model. Thus, in a cohort of women with BC undergoing Ais, we identified a very low prevalence (5.6%) of patients with adequate bone health and a normal vitamin D3 status. According to our cluster model, we may conclude that the assessment and management of bone health and vitamin D3 status are crucial in BC survivors.