scholarly journals ERpred: a web server for the prediction of subtype-specific estrogen receptor antagonists

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11716
Author(s):  
Nalini Schaduangrat ◽  
Aijaz Ahmad Malik ◽  
Chanin Nantasenamat
Keyword(s):  
Large Scale ◽  
Cancer Metastasis ◽  
Model Building ◽  
Hormone Replacement ◽  
Web Server ◽  
Breast Cancer Metastasis ◽  
Data Set ◽  
Therapy Targets ◽  
Subtype Specificity ◽  
Increased Risk

Estrogen receptors alpha and beta (ERα and ERβ) are responsible for breast cancer metastasis through their involvement of clinical outcomes. Estradiol and hormone replacement therapy targets both ERs, but this often leads to an increased risk of breast and endometrial cancers as well as thromboembolism. A major challenge is posed for the development of compounds possessing ER subtype specificity. Herein, we present a large-scale classification structure-activity relationship (CSAR) study of inhibitors from the ChEMBL database which consisted of an initial set of 11,618 compounds for ERα and 7,810 compounds for ERβ. The IC50 was selected as the bioactivity unit for further investigation and after the data curation process, this led to a final data set of 1,593 and 1,281 compounds for ERα and ERβ, respectively. We employed the random forest (RF) algorithm for model building and of the 12 fingerprint types, models built using the PubChem fingerprint was the most robust (Ac of 94.65% and 92.25% and Matthews correlation coefficient (MCC) of 89% and 76% for ERα and ERβ, respectively) and therefore selected for feature interpretation. Results indicated the importance of features pertaining to aromatic rings, nitrogen-containing functional groups and aliphatic hydrocarbons. Finally, the model was deployed as the publicly available web server called ERpred at http://codes.bio/erpred where users can submit SMILES notation as the input query for prediction of the bioactivity against ERα and ERβ.

SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network

2019 ◽  
Vol 7 (3) ◽  
pp. SE113-SE122 ◽  
Author(s):  
Yunzhi Shi ◽  
Xinming Wu ◽  
Sergey Fomel
Keyword(s):  
Large Scale ◽  
Model Building ◽  
Ground Truth ◽  
Velocity Model ◽  
Training Data ◽  
Data Sets ◽  
Validation Data ◽  
Data Set ◽  
Seismic Image ◽  
Data Generator

Salt boundary interpretation is important for the understanding of salt tectonics and velocity model building for seismic migration. Conventional methods consist of computing salt attributes and extracting salt boundaries. We have formulated the problem as 3D image segmentation and evaluated an efficient approach based on deep convolutional neural networks (CNNs) with an encoder-decoder architecture. To train the model, we design a data generator that extracts randomly positioned subvolumes from large-scale 3D training data set followed by data augmentation, then feed a large number of subvolumes into the network while using salt/nonsalt binary labels generated by thresholding the velocity model as ground truth labels. We test the model on validation data sets and compare the blind test predictions with the ground truth. Our results indicate that our method is capable of automatically capturing subtle salt features from the 3D seismic image with less or no need for manual input. We further test the model on a field example to indicate the generalization of this deep CNN method across different data sets.

scholarly journals Multiple-Membership Survival Analysis and Its Applications in Organizational Behavior and Management Research

2019 ◽  
pp. 109442811987745
Author(s):  
Hans Tierens ◽  
Nicky Dries ◽  
Mike Smet ◽  
Luc Sels
Keyword(s):  
Organizational Behavior ◽  
Large Scale ◽  
Model Building ◽  
Real Life ◽  
Hierarchical Structures ◽  
Survival Model ◽  
Survival Models ◽  
Data Set ◽  
Potential Applications ◽  
Multiple Membership

Multilevel paradigms have permeated organizational research in recent years, greatly advancing our understanding of organizational behavior and management decisions. Despite the advancements made in multilevel modeling, taking into account complex hierarchical structures in data remains challenging. This is particularly the case for models used for predicting the occurrence and timing of events and decisions—often referred to as survival models. In this study, the authors construct a multilevel survival model that takes into account subjects being nested in multiple environments—known as a multiple-membership structure. Through this article, the authors provide a step-by-step guide to building a multiple-membership survival model, illustrating each step with an application on a real-life, large-scale, archival data set. Easy-to-use R code is provided for each model-building step. The article concludes with an illustration of potential applications of the model to answer alternative research questions in the organizational behavior and management fields.

scholarly journals Prediction of Bone Metastasis in Breast Cancer Based on Minimal Driver Gene Set in Gene Dependency Network

Genes ◽  
2019 ◽  
Vol 10 (6) ◽  
pp. 466
Author(s):  
Li ◽  
Zhong ◽  
Zhou
Keyword(s):  
Breast Cancer ◽  
Bone Metastasis ◽  
Cancer Metastasis ◽  
Breast Cancer Metastasis ◽  
Driver Gene ◽  
Data Set ◽  
Gene Set ◽  
Signature Genes ◽  
Dependency Network ◽  
Better Than

Bone is the most frequent organ for breast cancer metastasis, and thus it is essential to predict the bone metastasis of breast cancer. In our work, we constructed a gene dependency network based on the hypothesis that the relation between one gene and the risk of bone metastasis might be affected by another gene. Then, based on the structure controllability theory, we mined the driver gene set which can control the whole network in the gene dependency network, and the signature genes were selected from them. Survival analysis showed that the signature could distinguish the bone metastasis risks of cancer patients in the test data set and independent data set. Besides, we used the signature genes to construct a centroid classifier. The results showed that our method is effective and performed better than published methods.

scholarly journals The histone H3K9 demethylase KDM3A promotes anoikis by transcriptionally activating pro-apoptotic genes BNIP3 and BNIP3L

eLife ◽  
2016 ◽  
Vol 5 ◽  
Author(s):  
Victoria E Pedanou ◽  
Stéphane Gobeil ◽  
Sébastien Tabariès ◽  
Tessa M Simone ◽  
Lihua Julie Zhu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Epithelial Cells ◽  
Transcriptional Activation ◽  
Large Scale ◽  
Cancer Metastasis ◽  
Ectopic Expression ◽  
Metastatic Potential ◽  
Breast Cancer Metastasis ◽  
Integrin Signaling ◽  
Breast Cancer Cell Lines

Epithelial cells that lose attachment to the extracellular matrix undergo a specialized form of apoptosis called anoikis. Here, using large-scale RNA interference (RNAi) screening, we find that KDM3A, a histone H3 lysine 9 (H3K9) mono- and di-demethylase, plays a pivotal role in anoikis induction. In attached breast epithelial cells, KDM3A expression is maintained at low levels by integrin signaling. Following detachment, integrin signaling is decreased resulting in increased KDM3A expression. RNAi-mediated knockdown of KDM3A substantially reduces apoptosis following detachment and, conversely, ectopic expression of KDM3A induces cell death in attached cells. We find that KDM3A promotes anoikis through transcriptional activation of BNIP3 and BNIP3L, which encode pro-apoptotic proteins. Using mouse models of breast cancer metastasis we show that knockdown of Kdm3a enhances metastatic potential. Finally, we find defective KDM3A expression in human breast cancer cell lines and tumors. Collectively, our results reveal a novel transcriptional regulatory program that mediates anoikis.

scholarly journals Family aggregation analysis reveals a heritable background of equine grass sickness (dysautonomia)

2019 ◽  
Author(s):  
Boglárka Vincze ◽  
Márta Varga ◽  
András Gáspárdy ◽  
Orsolya Kutasi ◽  
Petra Zenke ◽  
...  
Keyword(s):  
Large Scale ◽  
Intestinal Microbiome ◽  
Pedigree Data ◽  
Data Set ◽  
Grass Sickness ◽  
Disease Occurrence ◽  
Increased Risk ◽  
Life Threatening ◽  
Family Aggregation ◽  
Close Relatives

AbstractEquine grass sickness (also known as dysautonomia) is a life-threatening polyneuropathic disease affecting horses with approx. 80% mortality. Since it’s first description over a hundred years ago, several factors including phenotypic, environmental, management, climate, and intestinal microbiome) have been associated with increased risk of dysautonomia. But despite the extensive research on dysautonomia, it’s causative factors have yet been identified. A retrospective pedigree and phenotype based genetic epidemiological study was performed to analyze the associations of disease occurrence and the kinship in a Hungarian large scale stud. The pedigree data set containing 1233 horses with 49 affected animals was used in the analysis. The first finding was that among the descendants of some stallions the proportion of affected animals are unexpectedly high, with a maximum of 25% of a stallions descendants affected. Animals with affected siblings have higher odds to be a case (OR: 1.27, 95% CI: 1.01-1.57, p=0.033). Among males in the affected population the odds of dysautonomia is higher than in females (OR: 1.76, 95% CI: 0.95-3.29, p=0.057). Significant familial clustering was observed among the affected animals (GIF p=0.001). Further subgroups were identified with significant (p<0.001) aggregation among close relatives using kinship-based methods. Our analysis of the data and the observed higher disease frequency in males suggests that dysautonomia may have X-linked recessive inheritance as a causal factor. This is the first study providing ancestry data and suggesting a genetic contribution to the likely multifactorial causes of the disease.

Hrd in ovarian cancer: Defined today, evolving for the future.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e18052-e18052
Author(s):  
Markus Eckstein ◽  
Kenneth Joel Bloom ◽  
Peter Riccelli ◽  
Frank Policht ◽  
Derry Mae Keeling ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Homologous Recombination ◽  
Genomic Instability ◽  
Large Scale ◽  
Gene Mutations ◽  
Therapy Response ◽  
State Transitions ◽  
Data Set ◽  
Gene Target ◽  
Increased Risk

e18052 Background: Homologous Recombination Repair (HRR) gene mutations result in Homologous Recombination Deficiency (HRD) associated with increased risk of high grade serous ovarian (HGOC) cancer and subsequent response to PARP inhibitors (PARPi). Traditionally, HRD has been determined by testing for germline and/or somatic BRCA1/2 mutations. Today, a growing number of HRR gene mutations are known to result in HRD and genomic instability, thus being a suitable target for PARPi. Therapy response to PARPi is highest in BRCA-mutant followed by HRD+/non-BRCA-mutant HGOC. Today, no standard HRD testing methods exist, causing confusion for physicians, and leading to poor outcomes for missed PARPi eligible patients. Thus, there is need to understand HRD testing utilization and methods in HGOC to inform best practices and optimize HRD testing in the clinic. Methods: We assessed the testing landscape for determining HRD status in ovarian cancer using a data set of 8,400 newly diagnosed and metastatic ovarian cancer patients in the US from Q3-2018 through Q2-2019 identified from Diaceutics’ proprietary Global Diagnostic Index (GDI). Analysis of real-world BRCA1/2 and NGS associated testing data and laboratory profile mapping exercise of 82 US labs was carried out using Diaceutics proprietary methods and data sources to evaluate BRCA1/2 and/or HRD germline/somatic testing rates, test availability, and test panel HRR gene composition. Results: Overall, germline mutation testing rates were 3x greater than somatic testing rates. Excluding BRCA1/2, 67 labs offered comprehensive solid tumor NGS panels capable of measuring HRD with varied HRR gene target composition. Across 34 labs, 5 HRR genes were commonly found on panels: PALB2, ATM, BARD1, BRIP1 and CHEK2. 3 labs currently offering panels explicitly intended for HRD determination only include BRCA1/2 and at least one genomic instability marker (loss of heterozygosity, large-scale state transitions or telomeric allelic imbalance). Conclusions: Lack of standardized HRD panels and low testing rate identifying patients with somatic mutations in BRCA1/2 and other HRR genes is leading to poorer outcomes for missed patients eligible for PARPi’s. As clinical evidence linking HRD status with PARPi efficacy grows in ovarian as well as prostate and pancreatic cancer, Diaceutics recommends organizations such as ASCO, CAP or AMP establish defined universal HRD testing panels including relevant somatic/germline HRR genes and BRCA1/2 as well as genomic instability markers and educate stake holders aiding harmonization and ultimately, better treatment outcomes.

scholarly journals Metabolite profiling reveals a connection between aldehyde dehydrogenase 1A3 and GABA metabolism in breast cancer metastasis

Metabolomics ◽  
2022 ◽  
Vol 18 (1) ◽  
Author(s):  
Margaret L. Dahn ◽  
Hayley R. Walsh ◽  
Cheryl A. Dean ◽  
Michael A. Giacomantonio ◽  
Wasundara Fernando ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Aldehyde Dehydrogenase ◽  
Cancer Progression ◽  
Cancer Metastasis ◽  
Triple Negative ◽  
Breast Cancer Metastasis ◽  
Transcriptome Data ◽  
Thin Sections ◽  
Gaba Metabolism ◽  
Increased Risk

Abstract Introduction Aldehyde dehydrogenase 1A3 (ALDH1A3) is a cancer stem cell (CSC) marker and in breast cancer it is associated with triple-negative/basal-like subtypes and aggressive disease. Studies on the mechanisms of ALDH1A3 in cancer have primarily focused on gene expression changes induced by the enzyme; however, its effects on metabolism have thus far been unstudied and may reveal novel mechanisms of pathogenesis. Objective Determine how ALDH1A3 alters the metabolite profile in breast cancer cells and assess potential impacts. Method Triple-negative MDA-MB-231 tumors and cells with manipulated ALDH1A3 levels were assessed by HPLC–MS metabolomics and metabolite data was integrated with transcriptome data. Mice harboring MDA-MB-231 tumors with or without altered ALDH1A3 expression were treated with γ-aminobutyric acid (GABA) or placebo. Effects on tumor growth, and lungs and brain metastasis were quantified by staining of fixed thin sections and quantitative PCR. Breast cancer patient datasets from TCGA, METABRIC and GEO were used to assess the co-expression of GABA pathway genes with ALDH1A3. Results Integrated metabolomic and transcriptome data identified GABA metabolism as a primary dysregulated pathway in ALDH1A3 expressing breast tumors. Both ALDH1A3 and GABA treatment enhanced metastasis. Patient dataset analyses revealed expression association between ALDH1A3 and GABA pathway genes and corresponding increased risk of metastasis. Conclusion This study revealed a novel pathway affected by ALDH1A3, GABA metabolism. Like ALDH1A3 expression, GABA treatment promotes metastasis. Given the clinical use of GABA mimics to relieve chemotherapy-induced peripheral nerve pain, further study of the effects of GABA in breast cancer progression is warranted.

scholarly journals DeepOMe: A Web Server for the Prediction of 2′-O-Me Sites Based on the Hybrid CNN and BLSTM Architecture

2021 ◽  
Vol 9 ◽  
Author(s):  
Hongyu Li ◽  
Li Chen ◽  
Zaoli Huang ◽  
Xiaotong Luo ◽  
Huiqin Li ◽  
...  
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Short Term Memory ◽  
Learning Algorithm ◽  
Web Server ◽  
High Sensitivity ◽  
Computational Method ◽  
Regulatory Control ◽  
Data Set ◽  
Deep Learning Algorithm

2′-O-methylations (2′-O-Me or Nm) are one of the most important layers of regulatory control over gene expression. With increasing attentions focused on the characteristics, mechanisms and influences of 2′-O-Me, a revolutionary technique termed Nm-seq were established, allowing the identification of precise 2′-O-Me sites in RNA sequences with high sensitivity. However, as the costs and complexities involved with this new method, the large-scale detection and in-depth study of 2′-O-Me is still largely limited. Therefore, the development of a novel computational method to identify 2′-O-Me sites with adequate reliability is urgently needed at the current stage. To address the above issue, we proposed a hybrid deep-learning algorithm named DeepOMe that combined Convolutional Neural Networks (CNN) and Bidirectional Long Short-term Memory (BLSTM) to accurately predict 2′-O-Me sites in human transcriptome. Validating under 4-, 6-, 8-, and 10-fold cross-validation, we confirmed that our proposed model achieved a high performance (AUC close to 0.998 and AUPR close to 0.880). When testing in the independent data set, DeepOMe was substantially superior to NmSEER V2.0. To facilitate the usage of DeepOMe, a user-friendly web-server was constructed, which can be freely accessed at http://deepome.renlab.org.

Sign in / Sign up

Export Citation Format

Share Document