Browse Articles

Using a convolution neural network, these authors show machine learning can clinically diagnose breast cancer with high accuracy.

Here, recognizing the significant growth of electronic cigarettes in recent years, the authors sought to test a hypothesis that three main components of the liquid solutions used in e-cigarettes might affect lung cancer cell viability. In a study performed by exposing A549 cells, human lung cancer cells, to different types of smoke extracts, the authors found that increasing levels of nicotine resulted in improve lung cancer cell viability up until the toxicity of nicotine resulted in cell death. They conclude that these results suggest that contrary to conventional thought e-cigarettes may be more dangerous than tobacco cigarettes in certain contexts.

In this article, the authors analyzed ribosome profiling data from amino acid-starved pancreatic cancer cells to explore whether the pattern of ribosome distribution along transcripts under normal conditions can predict the degree of ribosome stalling under stress. The authors found that ribosomes in amino acid-deprived cells stalled more along elongation-limited transcripts. By contrast, they observed no relationship between read density near start and stop and disparities between mRNA sequencing reads and ribosome profiling reads. This research identifies an important relationship between read distribution and propensity for ribosomes to stall, although more work is needed to fully understand the patterns of ribosome distribution along transcripts in ribosome profiling data.

Pancreatic cancer is one of the deadliest cancers, with a 10% 5-year survival rate. The authors studied various dosages of TPEN and zinc in combination with Chloroquine and Gemcitabine as treatments to reduce cell proliferation. Results showed that when combined with Chloroquine and Gemcitabine, zinc and TPEN both significantly lowered cell proliferation compared to Gemcitabine, suggesting a synergistic effect that resulted in a more cytotoxic treatment. Further research and clinical trials on this topic are needed to determine whether this could be a viable treatment for pancreatic cancer.

Machine learning and deep learning techniques can be used to predict the early onset of breast cancer. The main objective of this analysis was to determine whether machine learning algorithms can be used to predict the onset of breast cancer with more than 90% accuracy. Based on research with supervised machine learning algorithms, Gaussian Naïve Bayes, K Nearest Algorithm, Random Forest, and Logistic Regression were considered because they offer a wide variety of classification methods and also provide high accuracy and performance. We hypothesized that all these algorithms would provide accurate results, and Random Forest and Logistic Regression would provide better accuracy and performance than Naïve Bayes and K Nearest Neighbor.

The authors computationally screened potential ALDH1 inhibitors, for use as potential cancer therapeutics.

The authors looked at the ability of different deep learning models to predict the presence of lung cancer from chest CT scans. They found that a pre-trained CNN model performed better than an autoencoder model.

This study used an improved CMS-seq method to profile 5hmC in ormalin-fixed and paraffin-embedded (FFPE) samples from HNC tumors and adjacent normal tissues, identifying three genes (PRKD2, HADHA, and AIPL1) with promising potential as biomarkers for Head and neck cancer (HNC) diagnosis.

Pulmonary diseases like lung cancer and valley fever pose serious health challenges, making accurate and rapid diagnostics essential. This study developed a MATLAB-based software tool that uses computer vision techniques to differentiate between these diseases by analyzing features of lung nodules in CT scans, achieving higher precision than traditional methods.

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.