scholarly journals Topology preserving stratification of tissue neoplasticity using Deep Neural Maps and microRNA signatures

2022 ◽  
Vol 23 (1) ◽  
Author(s):  
Emily Kaczmarek ◽  
Jina Nanayakkara ◽  
Alireza Sedghi ◽  
Mehran Pesteie ◽  
Thomas Tuschl ◽  
...  
Keyword(s):  
Deep Learning ◽  
Expression Profiles ◽  
Treatment Selection ◽  
Cancer Classification ◽  
Common Disease ◽  
Cancer Tissue ◽  
Topological Map ◽  
Tissue Samples ◽  
Learning Framework ◽  
Tissue Of Origin

Abstract Background Accurate cancer classification is essential for correct treatment selection and better prognostication. microRNAs (miRNAs) are small RNA molecules that negatively regulate gene expression, and their dyresgulation is a common disease mechanism in many cancers. Through a clearer understanding of miRNA dysregulation in cancer, improved mechanistic knowledge and better treatments can be sought. Results We present a topology-preserving deep learning framework to study miRNA dysregulation in cancer. Our study comprises miRNA expression profiles from 3685 cancer and non-cancer tissue samples and hierarchical annotations on organ and neoplasticity status. Using unsupervised learning, a two-dimensional topological map is trained to cluster similar tissue samples. Labelled samples are used after training to identify clustering accuracy in terms of tissue-of-origin and neoplasticity status. In addition, an approach using activation gradients is developed to determine the attention of the networks to miRNAs that drive the clustering. Using this deep learning framework, we classify the neoplasticity status of held-out test samples with an accuracy of 91.07%, the tissue-of-origin with 86.36%, and combined neoplasticity status and tissue-of-origin with an accuracy of 84.28%. The topological maps display the ability of miRNAs to recognize tissue types and neoplasticity status. Importantly, when our approach identifies samples that do not cluster well with their respective classes, activation gradients provide further insight in cancer subtypes or grades. Conclusions An unsupervised deep learning approach is developed for cancer classification and interpretation. This work provides an intuitive approach for understanding molecular properties of cancer and has significant potential for cancer classification and treatment selection.

scholarly journals RNA Sequencing in Comparison to Immunohistochemistry for Measuring Cancer Biomarkers in Breast Cancer and Lung Cancer Specimens

Biomedicines ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 114
Author(s):  
Maxim Sorokin ◽  
Kirill Ignatev ◽  
Elena Poddubskaya ◽  
Uliana Vladimirova ◽  
Nurshat Gaifullin ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Lung Cancer ◽  
Rna Sequencing ◽  
Expression Profiles ◽  
Correlation Study ◽  
Cancer Tissue ◽  
Transcriptional Level ◽  
Tissue Samples ◽  
Protein Levels ◽  
Formalin Fixed Paraffin Embedded

RNA sequencing is considered the gold standard for high-throughput profiling of gene expression at the transcriptional level. Its increasing importance in cancer research and molecular diagnostics is reflected in the growing number of its mentions in scientific literature and clinical trial reports. However, the use of different reagents and protocols for RNA sequencing often produces incompatible results. Recently, we published the Oncobox Atlas of RNA sequencing profiles for normal human tissues obtained from healthy donors killed in road accidents. This is a database of molecular profiles obtained using uniform protocol and reagents settings that can be broadly used in biomedicine for data normalization in pathology, including cancer. Here, we publish new original 39 breast cancer (BC) and 19 lung cancer (LC) RNA sequencing profiles obtained for formalin-fixed paraffin-embedded (FFPE) tissue samples, fully compatible with the Oncobox Atlas. We performed the first correlation study of RNA sequencing and immunohistochemistry-measured expression profiles for the clinically actionable biomarker genes in FFPE cancer tissue samples. We demonstrated high (Spearman’s rho 0.65–0.798) and statistically significant (p < 0.00004) correlations between the RNA sequencing (Oncobox protocol) and immunohistochemical measurements for HER2/ERBB2, ER/ESR1 and PGR genes in BC, and for PDL1 gene in LC; AUC: 0.963 for HER2, 0.921 for ESR1, 0.912 for PGR, and 0.922 for PDL1. To our knowledge, this is the first validation that total RNA sequencing of archived FFPE materials provides a reliable estimation of marker protein levels. These results show that in the future, RNA sequencing can complement immunohistochemistry for reliable measurements of the expression biomarkers in FFPE cancer samples.

scholarly journals Selecting precise reference normal tissue samples for cancer research using a deep learning approach

2018 ◽  
Author(s):  
William Zeng ◽  
Benjamin S. Glicksberg ◽  
Yangyan Li ◽  
Bin Chen
Keyword(s):  
Cancer Research ◽  
Deep Learning ◽  
Normal Tissue ◽  
Principal Component ◽  
Tissue Type ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Tissue Of Origin ◽  
Disease Signature ◽  
Disease Signatures

AbstractBackgroundNormal tissue samples are often employed as a control for understanding disease mechanisms, however, collecting matched normal tissues from patients is difficult in many instances. In cancer research, for example, the open cancer resources such as TCGA and TARGET do not provide matched tissue samples for every cancer or cancer subtype. The recent GTEx project has profiled samples from healthy individuals, providing an excellent resource for this field, yet the feasibility of using GTEx samples as the reference remains unanswered.MethodsWe analyze RNA-Seq data processed from the same computational pipeline and systematically evaluate GTEx as a potential reference resource. We use those cancers that have adjacent normal tissues in TCGA as a benchmark for the evaluation. To correlate tumor samples and normal samples, we explore top varying genes, reduced features from principal component analysis, and encoded features from an autoencoder neural network. We first evaluate whether these methods can identify the correct tissue of origin from GTEx for a given cancer and then seek to answer whether disease expression signatures are consistent between those derived from TCGA and from GTEx.ResultsAmong 32 TCGA cancers, 18 cancers have less than 10 matched adjacent normal tissue samples. Among three methods, autoencoder performed the best in predicting tissue of origin, with 12 of 14 cancers correctly predicted. The reason for misclassification of two cancers is that none of normal samples from GTEx correlate well with any tumor samples in these cancers. This suggests that GTEx has matched tissues for the majority cancers, but not all. While using autoencoder to select proper normal samples for disease signature creation, we found that disease signatures derived from normal samples selected via an autoencoder from GTEx are consistent with those derived from adjacent samples from TCGA in many cases. Interestingly, choosing top 50 mostly correlated samples regardless of tissue type performed reasonably well or even better in some cancers.ConclusionsOur findings demonstrate that samples from GTEx can serve as reference normal samples for cancers, especially those do not have available adjacent tissue samples. A deep-learning based approach holds promise to select proper normal samples.

scholarly journals Gene Expression Profiling forIn SilicoMicrodissection of Hodgkin's Lymphoma Microenvironment and Identification of Prognostic Features

2011 ◽  
Vol 2011 ◽  
pp. 1-8 ◽  
Author(s):  
François Bertucci ◽  
Bruno Chetaille ◽  
Luc Xerri
Keyword(s):  
Gene Expression ◽  
Gene Expression Profiling ◽  
Expression Profiling ◽  
Dna Microarrays ◽  
Tissue Sample ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Cancer Tissue ◽  
Tissue Samples ◽  
Prognostic Features

Gene expression profiling studies based on DNA microarrays have demonstrated their ability to define the interaction pathways between neoplastic and nonmalignant stromal cells in cancer tissues. During the past ten years, a number of approaches including microdissection have tried to resolve the variability in DNA microarray measurements stemming from cancer tissue sample heterogeneity. Another approach, designated as virtual orin silicomicrodissection, avoids the laborious and time-consuming step of anatomic microdissection. It consists of confronting the gene expression profiles of complex tissue samples to those of cell lines representative of different cell lineages, different differentiation stages, or different signaling pathways. This strategy has been used in recent studies aiming to analyze microenvironment alterations using gene expression profiling of nonmicrodissected classical Hodgkin lymphoma tissues in order to generate new prognostic factors. These recent contributions are detailed and discussed in the present paper.

scholarly journals MatchMaker: A Deep Learning Framework for Drug Synergy Prediction

2020 ◽  
Author(s):  
Halil Ibrahim Kuru ◽  
Oznur Tastan ◽  
A. Ercument Cicek
Keyword(s):  
Deep Learning ◽  
Drug Combination ◽  
Mean Squared Error ◽  
Expression Profiles ◽  
Search Space ◽  
Computational Techniques ◽  
Combinatorial Search ◽  
Structure Information ◽  
Drug Synergy ◽  
Learning Framework

AbstractDrug combination therapies have been a viable strategy for the treatment of complex diseases such as cancer due to increased efficacy and reduced side effects. However, experimentally validating all possible combinations for synergistic interaction even with high-throughout screens is intractable due to vast combinatorial search space. Computational techniques can reduce the number of combinations to be evaluated experimentally by prioritizing promising candidates. We present MatchMaker that predicts drug synergy scores using drug chemical structure information and gene expression profiles of cell lines in a deep learning framework. For the first time, our model utilizes the largest known drug combination dataset to date, DrugComb. We compare the performance of MatchMaker with the state-of-the-art models and observe up to ~ 20% correlation and ~ 40% mean squared error (MSE) improvements over the next best method. We investigate the cell types and drug pairs that are relatively harder to predict and present novel candidate pairs. MatchMaker is built and available at https://github.com/tastanlab/matchmaker

A PILOT STUDY OF HER-2/NEU GENE AMPLIFICATION ASSESSED BY FLUORESCENCE IN SITU HYBRIDIZATION (FISH) IN GASTRIC CANCER

2014 ◽  
pp. 15-20
Author(s):  
Van Huy Tran ◽  
Thi Minh Thi Ha ◽  
Trung Nghia Van ◽  
Viet Nhan Nguyen ◽  
Phan Tuong Quynh Le ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
In Situ Hybridization ◽  
Fluorescence In Situ Hybridization ◽  
Cancer Patients ◽  
Gene Amplification ◽  
Cancer Tissue ◽  
Tissue Samples ◽  
Her 2 ◽  
Gastric Cancer Patients

Background: HER-2/neu is a predictive biomarker for treatment of gastric cancer using trastuzumab in combination with chemotherapy. This study aimed to evaluate the status of HER-2/neu gene amplification using fluorescence in situ hybridization (FISH) in gastric cancer. Patients and methods: thirty six gastric cancer patients were assessed HER-2/neu gene amplification by FISH using PathVysionTM HER-2 DNA Probe kit (including HER-2/neu probe and CEP-17 probe) with biopsy and surgical specimens. Results: The HER-2/neu gene amplification was observed in three cases (8.3%), the HER-2/neu gene amplification rate in Lauren’s intestinal-type and diffuse-type were 11.8% and 5.2%, respectively. Conclusion: We applied successfully FISH technique with gastric cancer tissue samples. This technique could be performed as routine test in gastric cancer in order to select patients that benefit from trastuzumab in combination with chemotherapy.

A Deep Learning Framework for Prediction of Retinal Disorders

2020 ◽  
Author(s):  
Raniyaharini R ◽  
Madhumitha K ◽  
Mishaa S ◽  
Virajaravi R
Keyword(s):  
Deep Learning ◽  
Learning Framework ◽  
Retinal Disorders

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

Sign in / Sign up

Export Citation Format

Share Document