Characterization of gastric cancer stem-like molecular features, immune and pharmacogenomic landscapes

2021 ◽  
Author(s):  
Chen Wei ◽  
Mingkai Chen ◽  
Wenying Deng ◽  
Liangyu Bie ◽  
Yijie Ma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gastric Cancer ◽  
Stem Cell ◽  
Immune Escape ◽  
Learning Approaches ◽  
Step Process ◽  
Molecular Features ◽  
Immune Escape Mechanism ◽  
New Strategies

Abstract Cancer stem cells (CSCs) actively reprogram their tumor microenvironment (TME) to sustain a supportive niche, which may have a dramatic impact on prognosis and immunotherapy. However, our knowledge of the landscape of the gastric cancer stem-like cell (GCSC) microenvironment needs to be further improved. A multi-step process of machine learning approaches was performed to develop and validate the prognostic and predictive potential of the GCSC-related score (GCScore). The high GCScore subgroup was not only associated with stem cell characteristics, but also with a potential immune escape mechanism. Furthermore, we experimentally demonstrated the upregulated infiltration of CD206+ tumor-associated macrophages (TAMs) in the invasive margin region, which in turn maintained the stem cell properties of tumor cells. Finally, we proposed that the GCScore showed a robust capacity for prediction for immunotherapy, and investigated potential therapeutic targets and compounds for patients with a high GCScore. The results indicate that the proposed GCScore can be a promising predictor of prognosis and responses to immunotherapy, which provides new strategies for the precision treatment of GCSCs.

scholarly journals Characterization of TGFβ-Associated Molecular Features and Drug Responses in Gastrointestinal Adenocarcinoma

2021 ◽  
Author(s):  
Qiaofeng Zhang ◽  
Furong Liu ◽  
Lu Qin ◽  
Zhibin Liao ◽  
Jia Song ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Transforming Growth Factor Beta ◽  
Transforming Growth Factor ◽  
Genomic Analysis ◽  
Molecular Characteristics ◽  
Genomic Changes ◽  
Molecular Features ◽  
Highly Correlated ◽  
Worse Prognosis

Abstract Background: Gastrointestinal adenocarcinoma (GIAD) has caused a serious disease burden globally. Targeted therapy for the transforming growth factor beta (TGF-β) signaling pathway is becoming a reality. However, the molecular characterization of TGF-β in GIAD requires further exploration.Results: The TGF-β­­high group had a worse prognosis in overall GIAD patients, and had a worse prognosis trend in gastric cancer and colon cancer specifically. Signatures (including mRNA and proteins) of the TGF-β­­high group is highly correlated with EMT. According to miRNA analysis, miR-215-3p, miR-378a-5p, and miR-194-3p may block the effect of TGF-β. Further genomic analysis showed that TGF-β­­low group had more genomic changes in gastric cancer, such as TP53 mutation, EGFR amplification, and SMAD4 deletion. And drug response dataset revealed sensitive drugs or drug resistant drugs corresponding to TGF-β associated mRNAs. Finally, the DNN model showed an excellent predictive effect in predicting TGF-β status in different GIAD datasets.Conclusions: Our study provided a comprehensive analysis of the molecular characteristics associated with TGF-β and provides possible therapeutic targets in GIAD.

scholarly journals Validation of a Derived International Patient Severity Algorithm to Support COVID-19 Analytics from Electronic Health Record Data

2020 ◽  
Author(s):  
Jeffrey G Klann ◽  
Griffin M Weber ◽  
Hossein Estiri ◽  
Bertrand Moal ◽  
Paul Avillach ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chart Review ◽  
Learning Approach ◽  
Learning Approaches ◽  
Electronic Health Record Data ◽  
Icu Admission ◽  
Machine Learning Approach ◽  
Proxy Measure ◽  
Definition Of

AbstractIntroductionThe Consortium for Clinical Characterization of COVID-19 by EHR (4CE) includes hundreds of hospitals internationally using a federated computational approach to COVID-19 research using the EHR.ObjectiveWe sought to develop and validate a standard definition of COVID-19 severity from readily accessible EHR data across the Consortium.MethodsWe developed an EHR-based severity algorithm and validated it on patient hospitalization data from 12 4CE clinical sites against the outcomes of ICU admission and/or death. We also used a machine learning approach to compare selected predictors of severity to the 4CE algorithm at one site.ResultsThe 4CE severity algorithm performed with pooled sensitivity of 0.73 and specificity 0.83 for the combined outcome of ICU admission and/or death. The sensitivity of single code categories for acuity were unacceptably inaccurate - varying by up to 0.65 across sites. A multivariate machine learning approach identified codes resulting in mean AUC 0.956 (95% CI: 0.952, 0.959) compared to 0.903 (95% CI: 0.886, 0.921) using expert-derived codes. Billing codes were poor proxies of ICU admission, with 49% precision and recall compared against chart review at one partner institution.DiscussionWe developed a proxy measure of severity that proved resilient to coding variability internationally by using a set of 6 code classes. In contrast, machine-learning approaches may tend to overfit hospital-specific orders. Manual chart review revealed discrepancies even in the gold standard outcomes, possibly due to pandemic conditions.ConclusionWe developed an EHR-based algorithm for COVID-19 severity and validated it at 12 international sites.

scholarly journals Comparative Characterization of Crofelemer Samples Using Data Mining and Machine Learning Approaches With Analytical Stability Data Sets

2017 ◽  
Vol 106 (11) ◽  
pp. 3270-3279 ◽  
Author(s):  
Maulik K. Nariya ◽  
Jae Hyun Kim ◽  
Jian Xiong ◽  
Peter A. Kleindl ◽  
Asha Hewarathna ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Data Sets ◽  
Learning Approaches ◽  
Comparative Characterization ◽  
Analytical Stability ◽  
Stability Data ◽  
Using Data

Immunobiological Characterization of N-Nitrosomethylurea-Induced Rat Breast Carcinomas: Tumoral IL-10 Expression as a Possible Immune Escape Mechanism

2004 ◽  
Vol 84 (2) ◽  
pp. 107-116 ◽  
Author(s):  
Marcelo Hill ◽  
María Bausero ◽  
Daniel Mazal ◽  
Séverine Ménoret ◽  
Jamal Khalife ◽  
...  
Keyword(s):  
Immune Escape ◽  
Breast Carcinomas ◽  
Escape Mechanism ◽  
Immune Escape Mechanism

scholarly journals Characterization of TGFβ-associated molecular features and drug responses in gastrointestinal adenocarcinoma

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Qiaofeng Zhang ◽  
Furong Liu ◽  
Lu Qin ◽  
Zhibin Liao ◽  
Jia Song ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Transforming Growth Factor Beta ◽  
Drug Response ◽  
Transforming Growth Factor ◽  
Genomic Analysis ◽  
Copy Number Variations ◽  
Molecular Features ◽  
Different Levels ◽  
Worse Prognosis

Abstract Background Gastrointestinal adenocarcinoma (GIAD) has caused a serious disease burden globally. Targeted therapy for the transforming growth factor beta (TGF-β) signaling pathway is becoming a reality. However, the molecular characterization of TGF-β associated signatures in GIAD requires further exploration. Methods Multi-omics data were collected from TCGA and GEO database. A pivotal unsupervised clustering for TGF-β level was performed by distinguish status of TGF-β associated genes. We analyzed differential mRNAs, miRNAs, proteins gene mutations and copy number variations in both clusters for comparison. Enrichment of pathways and gene sets were identified in each type of GIAD. Then we performed differential mRNA related drug response by collecting data from GDSC. At last, a summarized deep neural network for TGF-β status and GIADs was constracted. Results The TGF-βhigh group had a worse prognosis in overall GIAD patients, and had a worse prognosis trend in gastric cancer and colon cancer specifically. Signatures (including mRNA and proteins) of the TGF-βhigh group is highly correlated with EMT. According to miRNA analysis, miR-215-3p, miR-378a-5p, and miR-194-3p may block the effect of TGF-β. Further genomic analysis showed that TGF-βlow group had more genomic changes in gastric cancer, such as TP53 mutation, EGFR amplification, and SMAD4 deletion. And drug response dataset revealed tumor-sensitive or tumor-resistant drugs corresponding to TGF-β associated mRNAs. Finally, the DNN model showed an excellent predictive effect in predicting TGF-β status in different GIAD datasets. Conclusions We provide molecular signatures associated with different levels of TGF-β to deepen the understanding of the role of TGF-β in GIAD and provide potential drug possibilities for therapeutic targets in different levels of TGF-β in GIAD.

scholarly journals Metaviromic identification of genetic hotspots of coronavirus pathogenicity using machine learning

2020 ◽  
Author(s):  
Jonathan J. Park ◽  
Sidi Chen
Keyword(s):  
Machine Learning ◽  
Vaccine Development ◽  
Cell Epitope ◽  
Learning Approaches ◽  
Systematic Map ◽  
Functional Studies ◽  
Major Threat ◽  
Pathogenic Viruses ◽  
Rapid Characterization

AbstractThe COVID-19 pandemic caused by SARS-CoV-2 has become a major threat across the globe. Here, we developed machine learning approaches to identify key pathogenic regions in coronavirus genomes. We trained and evaluated 7,562,625 models on 3,665 genomes including SARS-CoV-2, MERS-CoV, SARS-CoV and other coronaviruses of human and animal origins to return quantitative and biologically interpretable signatures at nucleotide and amino acid resolutions. We identified hotspots across the SARS-CoV-2 genome including previously unappreciated features in spike, RdRp and other proteins. Finally, we integrated pathogenicity genomic profiles with B cell and T cell epitope predictions for enrichment of sequence targets to help guide vaccine development. These results provide a systematic map of predicted pathogenicity in SARS-CoV-2 that incorporates sequence, structural and immunological features, providing an unbiased collection of genetic elements for functional studies. This metavirome-based framework can also be applied for rapid characterization of new coronavirus strains or emerging pathogenic viruses.

Machine Learning Applications in Nanomedicine and Nanotoxicology

2019 ◽  
Vol 4 (1) ◽  
pp. 1-7
Author(s):  
Gerardo M. Casañola-Martin ◽  
Hai Pham-The
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Cloud Computing ◽  
Machine Learning Algorithms ◽  
Learning Approaches ◽  
Future Perspectives ◽  
Computational Tools ◽  
Machine Learning Applications ◽  
Nanoparticles Characterization

The development of machine learning algorithms together with the availability of computational tools nowadays have given an increase in the application of artificial intelligence methodologies in different fields. However, the use of these machine learning approaches in nanomedicine remains still underexplored in certain areas, despite the development in hardware and software tools. In this review, the recent advances in the conjunction of machine learning with nanomedicine are shown. Examples dealing with biomedical properties of nanoparticles, characterization of nanomaterials, text mining, and image analysis are also presented. Finally, some future perspectives in the integration of nanomedicine with cloud computing, deep learning and other techniques are discussed.

scholarly journals Machine learning approaches to identify and design low thermal conductivity oxides for thermoelectric applications

2020 ◽  
Vol 1 ◽  
Author(s):  
Abhishek Tewari ◽  
Siddharth Dixit ◽  
Niteesh Sahni ◽  
Stéphane P.A. Bordas
Keyword(s):  
Machine Learning ◽  
Thermal Conductivity ◽  
Transition Metal ◽  
Predictive Accuracy ◽  
Mass Density ◽  
Learning Approaches ◽  
Tree Model ◽  
Step Process ◽  
Tree Classifier ◽  
Boosted Tree

Abstract The search space for new thermoelectric oxides has been limited to the alloys of a few known systems, such as ZnO, SrTiO3, and CaMnO3. Notwithstanding the high power factor, their high thermal conductivity is a roadblock in achieving higher efficiency. In this paper, we apply machine learning (ML) models for discovering novel transition metal oxides with low lattice thermal conductivity ( $ {k}_L $ ). A two-step process is proposed to address the problem of small datasets frequently encountered in material informatics. First, a gradient-boosted tree classifier is learnt to categorize unknown compounds into three categories of $ {k}_L $ : low, medium, and high. In the second step, we fit regression models on the targeted class (i.e., low $ {k}_L $ ) to estimate $ {k}_L $ with an $ {R}^2>0.9 $ . Gradient boosted tree model was also used to identify key material properties influencing classification of $ {k}_L $ , namely lattice energy per atom, atom density, band gap, mass density, and ratio of oxygen by transition metal atoms. Only fundamental materials properties describing the crystal symmetry, compound chemistry, and interatomic bonding were used in the classification process, which can be readily used in the initial phases of materials design. The proposed two-step process addresses the problem of small datasets and improves the predictive accuracy. The ML approach adopted in the present work is generic in nature and can be combined with high-throughput computing for the rapid discovery of new materials for specific applications.

Sign in / Sign up

Export Citation Format

Share Document