To study the ways in which compounds can induce adverse effects, toxicologists have been constructing Adverse Outcome Pathways (AOPs). An AOP can be considered as a pragmatic tool to capture and visualize mechanisms underlying different types of toxicity inflicted by any kind of stressor, and describes the interactions between key entities that lead to the adverse outcome on multiple biological levels of organization. The construction or optimization of an AOP is a labor intensive process, which currently depends on the manual search, collection, reviewing and synthesis of available scientific literature. This process could however be largely facilitated using Natural Language Processing (NLP) to extract information contained in scientific literature in a systematic, objective, and rapid manner that would lead to greater accuracy and reproducibility. This would support researchers to invest their expertise in the substantive assessment of the AOPs by replacing the time spent on evidence gathering by a critical review of the data extracted by NLP. As case examples, we selected two frequent adversities observed in the liver: namely, cholestasis and steatosis denoting accumulation of bile and lipid, respectively. We used deep learning language models to recognize entities of interest in text and establish causal relationships between them. We demonstrate how an NLP pipeline combining Named Entity Recognition and a simple rules-based relationship extraction model helps screen compounds related to liver adversities in the literature, but also extract mechanistic information for how such adversities develop, from the molecular to the organismal level. Finally, we provide some perspectives opened by the recent progress in Large Language Models and how these could be used in the future. We propose this work brings two main contributions: 1) a proof-of-concept that NLP can support the extraction of information from text for modern toxicology and 2) a template open-source model for recognition of toxicological entities and extraction of their relationships. All resources are openly accessible via GitHub (https://github.com/ontox-project/en-tox).
DOCUMENT
This research article shows that a high intensity exercise program compared to a low intensity exercise program of the same session duration and frequency, increases insulin sensitivity to a larger extend in healthy subjects. It also shows that the short insulin tolerance test can be used to detect differences in insulin sensitivity in intervention studies.
LINK
According to the "membrane sensor" hypothesis, the membrane's physical properties and microdomain organization play an initiating role in the heat shock response. Clinical conditions such as cancer, diabetes and neurodegenerative diseases are all coupled with specific changes in the physical state and lipid composition of cellular membranes and characterized by altered heat shock protein levels in cells suggesting that these "membrane defects" can cause suboptimal hsp-gene expression. Such observations provide a new rationale for the introduction of novel, heat shock protein modulating drug candidates. Intercalating compounds can be used to alter membrane properties and by doing so normalize dysregulated expression of heat shock proteins, resulting in a beneficial therapeutic effect for reversing the pathological impact of disease. The membrane (and lipid) interacting hydroximic acid (HA) derivatives discussed in this review physiologically restore the heat shock protein stress response, creating a new class of "membrane-lipid therapy" pharmaceuticals. The diseases that HA derivatives potentially target are diverse and include, among others, insulin resistance and diabetes, neuropathy, atrial fibrillation, and amyotrophic lateral sclerosis. At a molecular level HA derivatives are broad spectrum, multi-target compounds as they fluidize yet stabilize membranes and remodel their lipid rafts while otherwise acting as PARP inhibitors. The HA derivatives have the potential to ameliorate disparate conditions, whether of acute or chronic nature. Many of these diseases presently are either untreatable or inadequately treated with currently available pharmaceuticals. Ultimately, the HA derivatives promise to play a major role in future pharmacotherapy.
LINK
