A deep learning approach for medication disposition and corresponding attributes extraction.

OBJECTIVE: This article summarizes our approach to extracting medication and corresponding attributes from clinical notes, which is the focus of track 1 of the 2022 National Natural Language Processing (NLP) Clinical Challenges(n2c2) shared task. METHODS: The dataset was prepared using Contextualized Medication Event Dataset (CMED), including 500 notes from 296 patients. Our system consisted of three components: medication named entity recognition (NER), event classification (EC), and context classification (CC). These three components were built using transformer models with slightly different architecture and input text engineering. A zero-shot learning solution for CC was also explored. RESULTS: Our best performance systems achieved micro-average F1 scores of 0.973, 0.911, and 0.909 for the NER, EC, and CC, respectively. CONCLUSION: In this study, we implemented a deep learning-based NLP system and demonstrated that our approach of (1) utilizing special tokens helps our model to distinguish multiple medications mentions in the same context; (2) aggregating multiple events of a single medication into multiple labels improves our model's performance.

Increased MTH1-specific 8-oxodGTPase activity is a hallmark of cancer in colon, lung and pancreatic tissue.

Cellular homeostasis is dependent on a balance between DNA damage and DNA repair mechanisms. Cells are constantly assaulted by both exogenous and endogenous stimuli leading to high levels of reactive oxygen species (ROS) that cause oxidation of the nucleotide dGTP to 8-oxodGTP. If this base is incorporated into DNA and goes unrepaired, it can result in G > T transversions, leading to genomic DNA damage. MutT Homolog 1 (MTH1) is a nucleoside diphosphate X (Nudix) pyrophosphatase that can remove 8-oxodGTP from the nucleotide pool before it is incorporated into DNA by hydrolyzing it into 8-oxodGMP. MTH1 expression has been shown to be elevated in many cancer cells and is thought to be a survival mechanism by which a cancer cell can stave off the effects of high ROS that can result in cell senescence or death. It has recently become a target of interest in cancer because it is thought that inhibiting MTH1 can increase genotoxic damage and cytotoxicity. Determining the role of MTH1 in normal and cancer cells is confounded by an inability to reliably and directly measure its native enzymatic activity. We have used the chimeric ATP-releasing guanine-oxidized (ARGO) probe that combines 8-oxodGTP and ATP to measure MTH1 enzymatic activity in colorectal cancer (CRC), non-small cell lung cancer (NSCLC) and pancreatic ductal adenocarcinoma (PDAC) along with patient-matched normal tissue. MTH1 8-oxodGTPase activity is significantly increased in tumors across all three tissue types, indicating that MTH1 is a marker of cancer. MTH1 activity measured by ARGO assay was compared to mRNA and protein expression measured by RT-qPCR and Western blot in the CRC tissue pairs, revealing a positive correlation between ARGO assay and Western blot, but little correlation with RT-qPCR in these samples. The adoption of the ARGO assay will help in establishing the level of MTH1 activity in model systems and in assessing the effects of MTH1 modulation in the treatment of cancer.