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.

Genome-wide 5hmC profiles to enable cancer detection and tissue of origin classification in breast, colorectal, lung, ovarian, and pancreatic cancers.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 3044-3044
Author(s):  
David Haan ◽  
Anna Bergamaschi ◽  
Yuhong Ning ◽  
William Gibb ◽  
Michael Kesling ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Cancer Detection ◽  
Normal Tissue ◽  
Cross Validation ◽  
Tissue Type ◽  
Normal Tissues ◽  
Pancreatic Cancers ◽  
Tissue Of Origin ◽  
Fold Cross Validation

3044 Background: Epigenomics assays have recently become popular tools for identification of molecular biomarkers, both in tissue and in plasma. In particular 5-hydroxymethyl-cytosine (5hmC) method, has been shown to enable the epigenomic regulation of gene expression and subsequent gene activity, with different patterns, across several tumor and normal tissues types. In this study we show that 5hmC profiles enable discrete classification of tumor and normal tissue for breast, colorectal, lung ovary and pancreas. Such classification was also recapitulated in cfDNA from patient with breast, colorectal, lung, ovarian and pancreatic cancers. Methods: DNA was isolated from 176 fresh frozen tissues from breast, colorectal, lung, ovary and pancreas (44 per tumor per tissue type and up to 11 tumor tissues for each stage (I-IV)) and up to 10 normal tissues per tissue type. cfDNA was isolated from plasma from 783 non-cancer individuals and 569 cancer patients. Plasma-isolated cfDNA and tumor genomic DNA, were enriched for the 5hmC fraction using chemical labelling, sequenced, and aligned to a reference genome to construct features sets of 5hmC patterns. Results: 5hmC multinomial logistic regression analysis was employed across tumor and normal tissues and identified a set of specific and discrete tumor and normal tissue gene-based features. This indicates that we can classify samples regardless of source, with a high degree of accuracy, based on tissue of origin and also distinguish between normal and tumor status.Next, we employed a stacked ensemble machine learning algorithm combining multiple logistic regression models across diverse feature sets to the cfDNA dataset composed of 783 non cancers and 569 cancers comprising 67 breast, 118 colorectal, 210 Lung, 71 ovarian and 100 pancreatic cancers. We identified a genomic signature that enable the classification of non-cancer versus cancers with an outer fold cross validation sensitivity of 49% (CI 45%-53%) at 99% specificity. Further, individual cancer outer fold cross validation sensitivity at 99% specificity, was measured as follows: breast 30% (CI 119% -42%); colorectal 41% (CI 32%-50%); lung 49% (CI 42%-56%); ovarian 72% (CI 60-82%); pancreatic 56% (CI 46%-66%). Conclusions: This study demonstrates that 5hmC profiles can distinguish cancer and normal tissues based on their origin. Further, 5hmC changes in cfDNA enables detection of the several cancer types: breast, colorectal, lung, ovarian and pancreatic cancers. Our technology provides a non-invasive tool for cancer detection with low risk sample collection enabling improved compliance than current screening methods. Among other utilities, we believe our technology could be applied to asymptomatic high-risk individuals thus enabling enrichment for those subjects that most need a diagnostic imaging follow up.

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

2019 ◽  
Vol 12 (S1) ◽  
Author(s):  
William Z. D. Zeng ◽  
Benjamin S. Glicksberg ◽  
Yangyan Li ◽  
Bin Chen
Keyword(s):  
Cancer Research ◽  
Deep Learning ◽  
Normal Tissue ◽  
Learning Approach ◽  
Tissue Samples

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 Interaction Between Host MicroRNAs and the Gut Microbiota in Colorectal Cancer

2017 ◽  
Author(s):  
Ce Yuan ◽  
Michael Burns ◽  
Subbaya Subramanian ◽  
Ran Blekhman
Keyword(s):  
Colorectal Cancer ◽  
Gut Microbiome ◽  
Normal Tissue ◽  
Microbial Community Composition ◽  
Taxonomic Composition ◽  
Integrated Analysis ◽  
Tissue Samples ◽  
Microbiome Composition ◽  
Normal Tissues ◽  
Mirnas Expression

AbstractBackgroundAlthough variation in gut microbiome composition has been linked with colorectal cancer (CRC), the factors that mediate the interactions between CRC tumors and the microbiome are poorly understood. MicroRNAs (miRNAs) are known to regulate CRC progression and patient survival outcomes. In addition, recent studies suggested that host miRNAs can also regulate bacterial growth and influence the composition of the gut microbiome. Here, we investigated the association between miRNAs expression in human CRC tumor and normal tissues and the microbiome composition associated with these same tissues.MethodWe sequenced the small RNAs from patient-matched tumor and normal tissue samples collected from 44 human CRC patients performed an integrated analysis with microbiome taxonomic composition data from these same samples. We then interrogated the functions of the bacteria correlated with miRNAs that were differentially expressed (DE) between tumor and matched normal tissues, as well as the functions of miRNAs correlated with bacterial taxa that have been previously associated with CRC, including Fusobacterium, Providencia, Bacteroides, Akkermansia, Roseburia, Porphyromonas, and Peptostreptococcus.ResultsWe identified 76 miRNAs as DE between CRC and normal tissue, including known oncogenic miRNAs miR-182, miR-503, and miR-17∼92. These DE miRNAs were correlated with the relative abundance of several bacterial taxa, including Firmicutes, Bacteroidetes, and Proteobacteria. Bacteria correlated with DE miRNAs were enriched with distinct predicted metabolic categories. Additionally, we found that miRNAs correlated with CRC-associated bacteria are predicted to regulate targets that are relevant for host-microbiome interactions, and highlight a possible role for miRNA-driven glycan production in the recruitment of pathogenic microbial taxa.ConclusionsOur work characterized a global relationship between microbial community composition and miRNA expression in human CRC tissues. Our results support a role for miRNAs in mediating a bi-directional host-microbiome interaction in CRC. In addition, we highlight sets of potentially interacting microbes and host miRNAs, suggesting several pathways that can be targeted via future therapies.

scholarly journals c-Jun-like Immunoreactivity in Apoptosis Is the Result of a Crossreaction with Neoantigenic Sites Exposed by Caspase-3-mediated Proteolysis

2002 ◽  
Vol 50 (7) ◽  
pp. 961-972 ◽  
Author(s):  
Joan Ribera ◽  
Victoria Ayala ◽  
Josep E. Esquerda
Keyword(s):  
Normal Tissue ◽  
Caspase 3 ◽  
Tunel Staining ◽  
Apoptotic Cells ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Tissue Sections ◽  
Dying Cells ◽  
Active Caspase

Previous reports in various cells and species have shown that apoptotic cells are specifically and strongly labeled by certain c-Jun/N-terminal antibodies, such as c-Jun/sc45. This kind of immunoreactivity is confined to the cytoplasm. It is not due to c-Jun but appears to be related to c-Jun-like neoepitopes generated during apoptosis. This study was planned to gain further information about c-Jun-like immunostaining during apoptosis and to evaluate these antibodies as possible tools for characterizing cell death. Most of the experiments were performed in chick embryo spinal cord. When the apoptotic c-Jun-like immunoreactivity and caspase-3 immunostaining patterns were compared, we found that both antibodies immunostained the same dying cells in a similar pattern. In contrast to TUNEL staining, which reveals a positive reaction in both apoptotic and necrotic dying cells, active caspase-3 and c-Jun/sc45 antibodies are more selective because they stained only apoptotic cells. When cytosolic extracts from normal tissues were digested in vitro with caspase-3, c-Jun/sc45 immunoreactivity was strongly induced in several proteins, as demonstrated by Western blotting. Similar results were found when normal tissue sections were treated with caspase-3. Our results show that c-Jun/sc45 antibodies react with neoepitopes generated from cell proteins cleaved by activated caspases during apoptosis. We conclude that c-Jun/sc45 antibodies may be useful for detecting apoptosis. They can even be used in archival paraffin-embedded tissue samples.

scholarly journals A deep learning-based model of normal histology

2019 ◽  
Author(s):  
Tobias Sing ◽  
Holger Hoefling ◽  
Imtiaz Hossain ◽  
Julie Boisclair ◽  
Arno Doelemeyer ◽  
...  
Keyword(s):  
Deep Learning ◽  
Rat Tissues ◽  
Learning Models ◽  
Tissue Samples ◽  
Normal Tissues ◽  
Scientific Disciplines ◽  
The Individual ◽  
Rat Tissue ◽  
Human Primate ◽  
Abnormal Tissue

AbstractDeep learning models have been applied on various tissues in order to recognize malignancies. However, these models focus on relatively narrow tissue context or well-defined pathologies. Here, instead of focusing on pathologies, we introduce models characterizing the diversity of normal tissues. We obtained 1,690 slides with rat tissue samples from the control groups of six preclinical toxicology studies, on which tissue regions were outlined and annotated by pathologists into 46 different tissue classes. From these annotated regions, we sampled small patches of 224 × 224 pixels at six different levels of magnification. Using four studies as training set and two studies as test set, we trained VGG-16, ResNet-50, and Inception-v3 networks separately at each of these magnification levels. Among these models, Inception-v3 consistently outperformed the other networks and attained accuracies up to 83.4% (top-3 accuracy: 96.3%). Further analysis showed that most tissue confusions occurred within clusters of histologically similar tissues. Investigation of the embedding layer using the UMAP method revealed not only pronounced clusters corresponding to the individual tissues, but also subclusters corresponding to histologically meaningful structures that had neither been annotated nor trained for. This suggests that the histological representation learned by the normal histology network could also be used to flag abnormal tissue as outliers in the embedding space without a need to explicitly train for specific types of abnormalities. Finally, we found that models trained on rat tissues can be used on non-human primate and minipig tissues with minimal retraining.Author contributionT.S. and H.H. contributed equally to this work.Significance statementLike many other scientific disciplines, histopathology has been profoundly impacted by recent advances in machine learning with deep neural networks. In this field, most deep learning models reported in the literature are trained on pathologies in specific tissues/contexts. Here, we aim to establish a model of normal tissues as a foundation for future models of histopathology. We build models that are specific to histopathology images and we show that their embeddings are better feature vectors for describing the underlying images than those of off-the shelf CNN models. Therefore, our models could be useful for transfer learning to improve the accuracy of other histopathology models.

Strahlenwirkung am Normalgewebe

2010 ◽  
Vol 49 (S 01) ◽  
pp. S53-S58 ◽  
Author(s):  
W. Dörr
Keyword(s):  
Radiation Exposure ◽  
Normal Tissue ◽  
Radiation Effects ◽  
A Priori ◽  
Cell Loss ◽  
Turnover Time ◽  
Complete Healing ◽  
Internal Radiotherapy ◽  
Normal Tissues ◽  
Chronic Radiation

SummaryThe curative effectivity of external or internal radiotherapy necessitates exposure of normal tissues with significant radiation doses, and hence must be associated with an accepted rate of side effects. These complications can not a priori be considered as an indication of a too aggressive therapy. Based on the time of first diagnosis, early (acute) and late (chronic) radiation sequelae in normal tissues can be distinguished. Early reactions per definition occur within 90 days after onset of the radiation exposure. They are based on impairment of cell production in turnover tissues, which in face of ongoing cell loss results in hypoplasia and eventually a complete loss of functional cells. The latent time is largely independent of dose and is defined by tissue biology (turnover time). Usually, complete healing of early reactions is observed. Late radiation effects can occur after symptom-free latent times of months to many years, with an inverse dependence of latency on dose. Late normal tissue changes are progressive and usually irreversible. They are based on a complex interaction of damage to various cell populations (organ parenchyma, connective tissue, capillaries), with a contribution from macrophages. Late effects are sensitive for a reduction in dose rate (recovery effects).A number of biologically based strategies for protection of normal tissues or for amelioration of radiation effects was and still is tested in experimental systems, yet, only a small fraction of these approaches has so far been introduced into clinical studies. One advantage of most of the methods is that they may be effective even if the treatment starts way after the end of radiation exposure. For a clinical exploitation, hence, the availability of early indicators for the progression of subclinical damage in the individual patient would be desirable. Moreover, there is need to further investigate the molecular pathogenesis of normal tissue effects in more detail, in order to optimise biology based preventive strategies, as well as to identify the precise mechanisms of already tested approaches (e. g. stem cells).

Resveratrol as an Adjuvant for Normal Tissues Protection and Tumor Sensitization

2020 ◽  
Vol 20 (2) ◽  
pp. 130-145 ◽  
Author(s):  
Keywan Mortezaee ◽  
Masoud Najafi ◽  
Bagher Farhood ◽  
Amirhossein Ahmadi ◽  
Dheyauldeen Shabeeb ◽  
...  
Keyword(s):  
Targeted Therapy ◽  
Cancer Treatment ◽  
Cancer Cells ◽  
Clinical Studies ◽  
Normal Tissue ◽  
Medical Science ◽  
Treatment Modalities ◽  
Radiation Toxicity ◽  
Normal Tissues ◽  
Normal Tissue Toxicity

Cancer is one of the most complicated diseases in present-day medical science. Yearly, several studies suggest various strategies for preventing carcinogenesis. Furthermore, experiments for the treatment of cancer with low side effects are ongoing. Chemotherapy, targeted therapy, radiotherapy and immunotherapy are the most common non-invasive strategies for cancer treatment. One of the most challenging issues encountered with these modalities is low effectiveness, as well as normal tissue toxicity for chemo-radiation therapy. The use of some agents as adjuvants has been suggested to improve tumor responses and also alleviate normal tissue toxicity. Resveratrol, a natural flavonoid, has attracted a lot of attention for the management of both tumor and normal tissue responses to various modalities of cancer therapy. As an antioxidant and anti-inflammatory agent, in vitro and in vivo studies show that it is able to mitigate chemo-radiation toxicity in normal tissues. However, clinical studies to confirm the usage of resveratrol as a chemo-radioprotector are lacking. In addition, it can sensitize various types of cancer cells to both chemotherapy drugs and radiation. In recent years, some clinical studies suggested that resveratrol may have an effect on inducing cancer cell killing. Yet, clinical translation of resveratrol has not yielded desirable results for the combination of resveratrol with radiotherapy, targeted therapy or immunotherapy. In this paper, we review the potential role of resveratrol for preserving normal tissues and sensitization of cancer cells in combination with different cancer treatment modalities.

scholarly journals Association between colorectal cancer and Fusobacterium nucleatum and Bacteroides fragilis bacteria in Iranian patients: a preliminary study

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Aref Shariati ◽  
Shabnam Razavi ◽  
Ehsanollah Ghaznavi-Rad ◽  
Behnaz Jahanbin ◽  
Abolfazl Akbari ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Relative Abundance ◽  
Normal Tissue ◽  
Bacteroides Fragilis ◽  
Fusobacterium Nucleatum ◽  
Normal Mucosa ◽  
Clinicopathologic Characteristics ◽  
Tissue Samples ◽  
Adjacent Normal Mucosa ◽  
Iranian Patients

Abstract Background and aim Recent studies have proposed that commensal bacteria might be involved in the development and progression of gastrointestinal disorders such as colorectal cancer (CRC). Therefore, in this study, the relative abundance of Fusobacterium nucleatum, Bacteroides fragilis, Streptococcus bovis/gallolyticus, and Enteropathogenic Escherichia coli (EPEC) in CRC tissues, and their association with clinicopathologic characteristics of CRC was investigated in Iranian patients. Moreover, the role of these bacteria in the CRC-associated mutations including PIK3CA, KRAS, and BRAF was studied. Method To these ends, the noted bacteria were quantified in paired tumors and normal tissue specimens of 30 CRC patients, by TaqMan quantitative Real-Time Polymerase Chain Reaction (qPCR). Next, possible correlations between clinicopathologic factors and mutations in PIK3CA, KRAS, and BRAF genes were analyzed. Results In studied samples, B. fragilis was the most abundant bacteria that was detected in 66 and 60% of paired tumor and normal samples, respectively. Furthermore, 15% of the B. fragilis-positive patients were infected with Enterotoxigenic B. fragilis (ETBF) in both adenocarcinoma and matched adjacent normal samples. F. nucleatum was also identified in 23% of tumors and 13% of adjacent normal tissue samples. Moreover, the relative abundance of these bacteria determined by 2-ΔCT was significantly higher in CRC samples than in adjacent normal mucosa (p < 0.05). On the other hand, our findings indicated that S. gallolyticus and EPEC, compared to adjacent normal mucosa, were not prevalent in CRC tissues. Finally, our results revealed a correlation between F. nucleatum-positive patients and the KRAS mutation (p = 0.02), while analyses did not show any association between bacteria and mutation in PIK3CA and BRAF genes. Conclusion The present study is the first report on the analysis of different bacteria in CRC tissue samples of Iranian patients. Our findings revealed that F. nucleatum and B. fragilis might be linked to CRC. However, any link between gut microbiome dysbiosis and CRC remains unknown.

scholarly journals Two Ensemble-CNN Approaches for Colorectal Cancer Tissue Type Classification

2021 ◽  
Vol 7 (3) ◽  
pp. 51
Author(s):  
Emanuela Paladini ◽  
Edoardo Vantaggiato ◽  
Fares Bougourzi ◽  
Cosimo Distante ◽  
Abdenour Hadid ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Deep Learning ◽  
Digital Pathology ◽  
Texture Features ◽  
Tissue Type ◽  
Cancer Tissue ◽  
Learning Methods ◽  
Feature Based ◽  
Type Classification ◽  
Whole Slide Images

In recent years, automatic tissue phenotyping has attracted increasing interest in the Digital Pathology (DP) field. For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. The development of Whole Slide Images (WSIs) has provided the required data for creating automatic tissue phenotyping systems. In this paper, we study different hand-crafted feature-based and deep learning methods using two popular multi-classes CRC-tissue-type databases: Kather-CRC-2016 and CRC-TP. For the hand-crafted features, we use two texture descriptors (LPQ and BSIF) and their combination. In addition, two classifiers are used (SVM and NN) to classify the texture features into distinct CRC tissue types. For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). Moreover, we propose two Ensemble CNN approaches: Mean-Ensemble-CNN and NN-Ensemble-CNN. The experimental results show that the proposed approaches outperformed the hand-crafted feature-based methods, CNN architectures and the state-of-the-art methods in both databases.

Sign in / Sign up

Export Citation Format

Share Document