With advancements in machine learning a large data scale, high throughput virtual screening has become a more attractive method for screening drug candidates. This study compared the accuracy of molecular descriptors from two cheminformatics Mordred and PaDEL, software libraries, in characterizing the chemo-structural composition of 53 compounds from the non-nucleoside reverse transcriptase inhibitors (NNRTI) class. The classification model built with the filtered set of descriptors from Mordred was superior to the model using PaDEL descriptors. This approach can accelerate the identification of hit compounds and improve the efficiency of the drug discovery pipeline.

Each year, over 100,000 patients die from Sudden Unexpected Death in Epilepsy (SUDEP). A reliable seizure warning system can help patients stay safe. This work presents a comprehensive, comparative analysis of three different signal processing algorithms for automated seizure/ictal detection. The experimental results show that the proposed methods can be effective for accurate automated seizure detection and monitoring in clinical care.

Cosmic rays are high-energy astronomical particles originating from various sources across the universe. Here, The authors sought to understand how surface-level cosmic-ray muon flux is affected by atmospheric attenuation by measuring the variation in relative muon-flux rate relative to zenith angle, testing the hypothesis that muons follow an exponential attenuation model. The attenuation model predicts an attenuation length of 6.3 km. This result implies that only a maximum of 24% of muons can reach the Earth’s surface, due to both decay and atmospheric interactions.

The authors investigate the ability of machine learning models to developing new drug-like molecules by learning desired chemical properties versus simply generating molecules that similar to those in the training set.

Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

In this study, the authors developed a model named DNA Sequence Embedding Network (DNA-SEnet) to classify DNA-asthma associations using their genomic patterns.

Osteosarcoma is a type of bone cancer that affects young adults and children. Early diagnosis of osteosarcoma is crucial to successful treatment. The current methods of diagnosis, which include imaging tests and biopsy, are time consuming and prone to human error. Hence, we used deep learning to extract patterns and detect osteosarcoma from histological images. We hypothesized that the combination of two different technologies (transfer learning and data augmentation) would improve the efficacy of osteosarcoma detection in histological images. The dataset used for the study consisted of histological images for osteosarcoma and was quite imbalanced as it contained very few images with tumors. Since transfer learning uses existing knowledge for the purpose of classification and detection, we hypothesized it would be proficient on such an imbalanced dataset. To further improve our learning, we used data augmentation to include variations in the dataset. We further evaluated the efficacy of different convolutional neural network models on this task. We obtained an accuracy of 91.18% using the transfer learning model MobileNetV2 as the base model with various geometric transformations, outperforming the state-of-the-art convolutional neural network based approach.

In this study, the authors sought to find out how many mathematical solutions there were to the Indian mathematician Ramanujan's formula, which is a³ + b³ + c³ = d³, and also quantify the densities its solutions. They wrote their own computer program to do so and kept values of a, b, and c less than 10,000. While conducting the analysis, they were also looking for perfect power taxicab numbers and their frequency. They were able to find solutions and densities for the equation. Additionally, while they found that most perfect cube taxicab numbers had a frequency of 2 or 3, they also found on number with a frequency of 42!

In this study, the authors studied the ability for bacteria to develop antibiotic resistance over successive generations and modeled the trajectory to predict how antibiotic resistance is developed.

With molecular energy being an integral element to the study of molecules and molecular interactions, computational methods to determine molecular energy are used for the preservation of time and resources. However, these computational methods have high demand for computer resources, limiting their widespread feasibility. The authors of this study employed machine learning to address this disadvantage, utilizing neural networks trained on different representations of molecules to predict molecular properties without the requirement of computationally-intensive processing. In their findings, the authors determined the Feedforward Neural Network, trained by two separate models, as capable of predicting molecular energy with limited prediction error.