Histopathological Image QTL Discovery of Immune Infiltration Variants.
Ontology highlight
ABSTRACT:
SUBMITTER: Barry JD
PROVIDER: S-EPMC6123851 | biostudies-literature | 2018 Jul
REPOSITORIES: biostudies-literature
Publications
Histopathological Image QTL Discovery of Immune Infiltration Variants.
Barry Joseph D JD Fagny Maud M Paulson Joseph N JN Aerts Hugo J W L HJWL Platig John J Quackenbush John J
iScience 20180706
Genotype-to-phenotype association studies typically use macroscopic physiological measurements or molecular readouts as quantitative traits. There are comparatively few suitable quantitative traits available between cell and tissue length scales, a limitation that hinders our ability to identify variants affecting phenotype at many clinically informative levels. Here we show that quantitative image features, automatically extracted from histopathological imaging data, can be used for image quant ...[more]
Similar Datasets
Project description:Abundant accumulation of digital histopathological images has led to the increased demand for their analysis, such as computer-aided diagnosis using machine learning techniques. However, digital pathological images and related tasks have some issues to be considered. In this mini-review, we introduce the application of digital pathological image analysis using machine learning algorithms, address some problems specific to such analysis, and propose possible solutions.
| S-EPMC6158771 | biostudies-other
Project description:Dense SNP genotypes are often combined with complex trait phenotypes to map causal variants, study genetic architecture and provide genomic predictions for individuals with genotypes but no phenotype. A single method of analysis that jointly fits all genotypes in a Bayesian mixture model (BayesR) has been shown to competitively address all 3 purposes simultaneously. However, BayesR and other similar methods ignore prior biological knowledge and assume all genotypes are equally likely to affect the trait. While this assumption is reasonable for SNP array genotypes, it is less sensible if genotypes are whole-genome sequence variants which should include causal variants.We introduce a new method (BayesRC) based on BayesR that incorporates prior biological information in the analysis by defining classes of variants likely to be enriched for causal mutations. The information can be derived from a range of sources, including variant annotation, candidate gene lists and known causal variants. This information is then incorporated objectively in the analysis based on evidence of enrichment in the data. We demonstrate the increased power of BayesRC compared to BayesR using real dairy cattle genotypes with simulated phenotypes. The genotypes were imputed whole-genome sequence variants in coding regions combined with dense SNP markers. BayesRC increased the power to detect causal variants and increased the accuracy of genomic prediction. The relative improvement for genomic prediction was most apparent in validation populations that were not closely related to the reference population. We also applied BayesRC to real milk production phenotypes in dairy cattle using independent biological priors from gene expression analyses. Although current biological knowledge of which genes and variants affect milk production is still very incomplete, our results suggest that the new BayesRC method was equal to or more powerful than BayesR for detecting candidate causal variants and for genomic prediction of milk traits.BayesRC provides a novel and flexible approach to simultaneously improving the accuracy of QTL discovery and genomic prediction by taking advantage of prior biological knowledge. Approaches such as BayesRC will become increasing useful as biological knowledge accumulates regarding functional regions of the genome for a range of traits and species.
| S-EPMC4769584 | biostudies-literature
Project description:IntroductionCancerous Tissue Recognition (CTR) methodologies are continuously integrating advancements at the forefront of machine learning and computer vision, providing a variety of inference schemes for histopathological data. Histopathological data, in most cases, come in the form of high-resolution images, and thus methodologies operating at the patch level are more computationally attractive. Such methodologies capitalize on pixel level annotations (tissue delineations) from expert pathologists, which are then used to derive labels at the patch level. In this work, we envision a digital connected health system that augments the capabilities of the clinicians by providing powerful feature descriptors that may describe malignant regions.Material and methodsWe start with a patch level descriptor, termed Covariance-Kernel Descriptor (CKD), capable of compactly describing tissue architectures associated with carcinomas. To leverage the recognition capability of the CKDs to larger slide regions, we resort to a multiple instance learning framework. In that direction, we derive the Weakly Annotated Image Descriptor (WAID) as the parameters of classifier decision boundaries in a Multiple Instance Learning framework. The WAID is computed on bags of patches corresponding to larger image regions for which binary labels (malignant vs. benign) are provided, thus obviating the necessity for tissue delineations.ResultsThe CKD was seen to outperform all the considered descriptors, reaching classification accuracy (ACC) of 92.83%. and area under the curve (AUC) of 0.98. The CKD captures higher order correlations between features and was shown to achieve superior performance against a large collection of computer vision features on a private breast cancer dataset. The WAID outperform all other descriptors on the Breast Cancer Histopathological database (BreakHis) where correctly classified malignant (CCM) instances reached 91.27 and 92.00% at the patient and image level, respectively, without resorting to a deep learning scheme achieves state-of-the-art performance.DiscussionOur proposed derivation of the CKD and WAID can help medical experts accomplish their work accurately and faster than the current state-of-the-art.
| S-EPMC7749086 | biostudies-literature
Project description:Lung adenocarcinoma (LUAD) has a high mortality rate and is difficult to diagnose and treat in its early stage. Previous studies have demonstrated that small nucleolar RNAs (snoRNAs) play a critical role in tumor immune infiltration and the development of a variety of solid tumors. However, there have been no studies on the correlation between tumor-infiltrating immune-related snoRNAs (TIISRs) and LUAD. In this study, we filtered six immune-related snoRNAs based on the tissue specificity index (TSI) and expression profile of all snoRNAs between all LUAD cell lines from the Cancer Cell Line Encyclopedia and 21 types of immune cells from the Gene Expression Omnibus database. Further, we performed real-time quantitative polymerase chain reaction (RT-qPCR) to validate the expression status of these snoRNAs on peripheral blood mononuclear cells (PBMCs) and lung cancer cell lines. Next, we developed a TIISR signature based on the expression profiles of snoRNAs from 479 LUAD patients filtered by the random survival forest algorithm. We then analyzed the value of this TIISR signature (TIISR risk score) for assessing tumor immune infiltration, immune checkpoint inhibitor (ICI) treatment response, and the prognosis of LUAD between groups with high and low TIISR risk score. Further, we found that the TIISR risk score groups showed significant differences in biological characteristics and that the risk score could be used to assess the level of tumor immune cell infiltration, thereby predicting prognosis and responsiveness to immunotherapy in LUAD patients.
| S-EPMC8649667 | biostudies-literature
Project description:BackgroundIt has been proposed that the use of gene expression microarrays in nonrecombinant parental or congenic strains can accelerate the process of isolating individual genes underlying quantitative trait loci (QTL). However, the effectiveness of this approach has not been assessed.ResultsThirty-seven studies that have implemented the QTL/microarray approach in rodents were reviewed. About 30% of studies showed enrichment for QTL candidates, mostly in comparisons between congenic and background strains. Three studies led to the identification of an underlying QTL gene. To complement the literature results, a microarray experiment was performed using three mouse congenic strains isolating the effects of at least 25 biometric QTL. Results show that genes in the congenic donor regions were preferentially selected. However, within donor regions, the distribution of differentially expressed genes was homogeneous once gene density was accounted for. Genes within identical-by-descent (IBD) regions were less likely to be differentially expressed in chromosome 2, but not in chromosomes 11 and 17. Furthermore, expression of QTL regulated in cis (cis eQTL) showed higher expression in the background genotype, which was partially explained by the presence of single nucleotide polymorphisms (SNP).ConclusionsThe literature shows limited successes from the QTL/microarray approach to identify QTL genes. Our own results from microarray profiling of three congenic strains revealed a strong tendency to select cis-eQTL over trans-eQTL. IBD regions had little effect on rate of differential expression, and we provide several reasons why IBD should not be used to discard eQTL candidates. In addition, mismatch probes produced false cis-eQTL that could not be completely removed with the current strains genotypes and low probe density microarrays. The reviewed studies did not account for lack of coverage from the platforms used and therefore removed genes that were not tested. Together, our results explain the tendency to report QTL candidates as differentially expressed and indicate that the utility of the QTL/microarray as currently implemented is limited. Alternatives are proposed that make use of microarray data from multiple experiments to overcome the outlined limitations.
| S-EPMC2919467 | biostudies-literature
Project description:Digital pathology coupled with advanced machine learning (e.g., deep learning) has been changing the paradigm of whole-slide histopathological images (WSIs) analysis. Major applications in digital pathology using machine learning include automatic cancer classification, survival analysis, and subtyping from pathological images. While most pathological image analyses are based on patch-wise processing due to the extremely large size of histopathology images, there are several applications that predict a single clinical outcome or perform pathological diagnosis per slide (e.g., cancer classification, survival analysis). However, current slide-based analyses are task-dependent, and a general framework of slide-based analysis in WSI has been seldom investigated. We propose a novel slide-based histopathology analysis framework that creates a WSI representation map, called HipoMap, that can be applied to any slide-based problems, coupled with convolutional neural networks. HipoMap converts a WSI of various shapes and sizes to structured image-type representation. Our proposed HipoMap outperformed existing methods in intensive experiments with various settings and datasets. HipoMap showed the Area Under the Curve (AUC) of 0.96±0.026 (5% improved) in the experiments for lung cancer classification, and c-index of 0.787±0.013 (3.5% improved) and coefficient of determination ([Formula: see text]) of 0.978±0.032 (24% improved) in survival analysis and survival prediction with TCGA lung cancer data respectively, as a general framework of slide-based analysis with a flexible capability. The results showed significant improvement comparing to the current state-of-the-art methods on each task. We further discussed experimental results of HipoMap as pathological viewpoints and verified the performance using publicly available TCGA datasets. A Python package is available at https://pypi.org/project/hipomap , and the package can be easily installed using Python PIP. The open-source codes in Python are available at: https://github.com/datax-lab/HipoMap .
| S-EPMC9646838 | biostudies-literature
Project description:Computational analysis of histopathological images can identify sub-visual objective image features that may not be visually distinguishable by human eyes, and hence provides better modeling of disease phenotypes. This study aims to investigate whether specific image features are associated with somatic mutations and patient survival in gastric adenocarcinoma (sample size = 310). An automated image analysis pipeline was developed to extract quantitative morphological features from H&E stained whole-slide images. We found that four frequently somatically mutated genes (TP53, ARID1A, OBSCN, and PIK3CA) were significantly associated with tumor morphological changes. A prognostic model built on the image features significantly stratified patients into low-risk and high-risk groups (log-rank test p-value = 2.6e-4). Multivariable Cox regression showed the model predicted risk index was an additional prognostic factor besides tumor grade and stage. Gene ontology enrichment analysis showed that the genes whose expressions mostly correlated with the contributing features in the prognostic model were enriched on biological processes such as cell cycle and muscle contraction. These results demonstrate that histopathological image features can reflect underlying somatic mutations and identify high-risk patients that may benefit from more precise treatment regimens. Both the image features and pipeline are highly interpretable to enable translational applications.
| S-EPMC8045755 | biostudies-literature
Project description:With the exception of intestinal lymphoma, surgery is the most commonly recommended treatment for solitary feline intestinal tumours. However, there is a lack of evidence to substantiate resection margin recommendations for these tumours. The aim of this study was to add knowledge concerning resection margins for discrete intestinal masses in cats. Thirty confirmed feline intestinal tumours removed at veterinary centres across the UK from March 2017 to March 2018 underwent histological assessment at the palpable edge of the intestinal tumour and then at every 1 cm increment to the surgeon-cut tissue border in oral, aboral and mesenteric directions. Histological margin recommendations were developed for carcinoma and lymphoma tumour types and non-lymphoma intestinal tumours collectively. Seventeen intestinal lymphomas, nine carcinomas, two sarcomas and two mast cell tumours were evaluated in this study. Seven of the nine intestinal carcinomas would have been completely removed with histological margins of 4 cm in oral and aboral directions. Both sarcomas and one mast cell tumour would have been removed in their entirety with 4 cm histological margins in oral and aboral directions. There was extensive and varied microscopic invasion of intestinal tissue away from discrete intestinal lymphomas in the majority of the cases in this study. There is increasing evidence in veterinary as well as human literature supporting the role of surgical resection in the treatment of discrete intestinal lymphoma. If surgery is to be considered this study supports the removal of the gross tumour only. A histological margin of 4 cm should be considered, where possible, for intestinal masses other than lymphomas.
| S-EPMC6682799 | biostudies-literature
Project description:Uterine leiomyomas, or fibroids, are the most common human tumors. Based on histopathology, they can be divided into common leiomyomas and various relatively rare subtypes that mimic malignancy in one or more aspects. Recently, we showed that exon 2 of mediator complex subunit 12 (MED12) is mutated in up to 70% of common fibroids. To investigate the frequency of MED12 exon 2 mutations in histopathological uterine leiomyoma variants, we screened altogether 206 lesions, including 69 histopathologically common leiomyomas, 59 cellular (23 cellular and 36 highly cellular), 18 atypical and 26 mitotically active leiomyomas, as well as 34 uterine fibroid samples from 14 hereditary leiomyomatosis and renal cell cancer patients with a heterozygous germ line mutation in fumarate hydratase (FH). The uterine leiomyoma variants harbored MED12 exon 2 mutations significantly less frequently than common leiomyomas (P=2.93 × 10(-8)). In all, 6 mutations were detected among cellular fibroids (6/67; 8.96%), 3 among atypical fibroids (3/18; 16.67%) and 10 among mitotically active fibroids (10/26; 38.46%). Only mitotically active fibroids displayed a mutation frequency that was not statistically different from common leiomyomas (P=0.11). Three MED12 exon 2 mutations were detected among 34 tumors with a heterozygous germ line FH mutation (P=5.28 × 10(-7)). None of these tumors displayed biallelic inactivation of FH. Our results suggest that MED12 mutation positivity is a key characteristic of common leiomyomas. Cellular and atypical fibroids, in particular, may arise through different molecular mechanisms. The results also propose that MED12 and biallelic FH mutations may be mutually exclusive.
| S-EPMC3798840 | biostudies-literature
Project description:Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.
| S-EPMC6778075 | biostudies-literature