Search

Drug-induced liver injury (DILI) is a class of adverse drug reactions (ADR) that causes problems in both clinical and research settings. It is the most frequent cause of acute liver failure in the majority of Western countries and is a major cause of attrition of novel drug candidates. Manual trawling of the literature is the main route of deriving information on DILI from research studies. This makes it an inefficient process prone to human error. Therefore, an automatized AI model capable of retrieving DILI-related articles from the huge ocean of literature could be invaluable for the drug discovery community. In this study, we built an artificial intelligence (AI) model combining the power of natural language processing (NLP) and machine learning (ML) to address this problem. This model uses NLP to filter out meaningless text (e.g., stop words) and uses customized functions to extract relevant keywords such as singleton, pair, and triplet. These keywords are processed by an apriori pattern mining algorithm to extract relevant patterns which are used to estimate initial weightings for a ML classifier. Along with pattern importance and frequency, an FDA-approved drug list mentioning DILI adds extra confidence in classification. The combined power of these methods builds a DILI classifier (DILI C ), with 94.91% cross-validation and 94.14% external validation accuracy. To make DILI C as accessible as possible, including to researchers without coding experience, an R Shiny app capable of classifying single or multiple entries for DILI is developed to enhance ease of user experience and made available at https://researchmind.co.uk/diliclassifier/. Additionally, a GitHub link (https://github.com/sanjaysinghrathi/DILI-Classifier) for app source code and ISMB extended video talk (https://www.youtube.com/watch?v=j305yIVi_f8) are available as supplementary materials.

Constitutive heterochromatin undergoes a dynamic clustering and spatial reorganization during myogenic differentiation. However the detailed mechanisms and its role in cell differentiation remain largely elusive. Here, we report the identification of a muscle-specific long non-coding RNA, ChRO1, involved in constitutive heterochromatin reorganization. ChRO1 is induced during terminal differentiation of myoblasts, and is specifically localized to the chromocenters in myotubes. ChRO1 is required for efficient cell differentiation, with global impacts on gene expression. It influences DNA methylation and chromatin compaction at peri/centromeric regions. Inhibition of ChRO1 leads to defects in the spatial fusion of chromocenters, and mislocalization of H4K20 trimethylation, Suv420H2, HP1, MeCP2 and cohesin. In particular, ChRO1 specifically associates with ATRX/DAXX/H3.3 complex at chromocenters to promote H3.3 incorporation and transcriptional induction of satellite repeats, which is essential for chromocenter clustering. Thus, our results unveil a mechanism involving a lncRNA that plays a role in large-scale heterochromatin reorganization and cell differentiation., Individual Basic Researcher Program [2018R1D1A1B070 48056 to E.-J.C., 2017R1D1A1B03035883 to J.P.]; Advanced Research Center Program [NRF-2010-0029359 to E.-J.C.]; National Creative Research Laboratory Program [2012R1A3A2048767 to H.-D.Y.]; NRF-2012-Fostering Core Leaders of the Future Basic Science Program through the National Research Foundation of Korea [2012H1A8003093 to J.P.].

DDX3X is a multifunctional RNA helicase with documented roles in different cancer types. Here, we demonstrate that DDX3X plays an oncogenic role in breast cancer cells by modulating the cell cycle. Depletion of DDX3X in MCF7 cells slows cell proliferation by inducing a G1 phase arrest. Notably, DDX3X inhibits expression of Kruppel-like factor 4 (KLF4), a transcription factor and cell cycle repressor. Moreover, DDX3X directly interacts with KLF4 mRNA and regulates its splicing. We show that DDX3X-mediated repression of KLF4 promotes expression of S-phase inducing genes in MCF7 breast cancer cells. These findings provide evidence for a novel function of DDX3X in regulating expression and downstream functions of KLF4, a master negative regulator of the cell cycle.

Background Survival rates for oesophageal adenocarcinoma (OAC) remain disappointingly poor and current conventional treatment modalities have minimal impact on long-term survival. This is partly due to a lack of understanding of the molecular changes that occur in this disease. Previous studies have indicated that the transcription factor FOXM1 is commonly upregulated in this cancer type but the impact of this overexpression on gene expression in the context of OAC is largely unknown. FOXM1 does not function alone but works alongside the antagonistically-functioning co-regulatory MMB and DREAM complexes. Methods To establish how FOXM1 affects gene expression in OAC we have identified the FOXM1 target gene network in OAC-derived cells using ChIP-seq and determined the expression of both its coregulatory partners and members of this target gene network in OAC by digital transcript counting using the Nanostring gene expression assay. Results We find co-upregulation of FOXM1 with its target gene network in OAC. Furthermore, we find changes in the expression of its coregulatory partners, including co-upregulation of LIN9 and, surprisingly, reduced expression of LIN54. Mechanistically, we identify LIN9 as the direct binding partner for FOXM1 in the MMB complex. In the context of OAC, both coregulator (eg LIN54) and target gene (eg UHRF1) expression levels are predictive of disease stage. Conclusions Together our data demonstrate that there are global changes to the FOXM1 regulatory network in OAC and the expression of components of this network help predict cancer prognosis. Electronic supplementary material The online version of this article (doi:10.1186/s12943-015-0339-8) contains supplementary material, which is available to authorized users.