ABSTRACT
Standard clinicopathological parameters (age, growth pattern, tumor size, margin status, and grade) have been shown to have limited value in predicting recurrence in ductal carcinoma in situ (DCIS) patients. Early and accurate recurrence prediction would facilitate a more aggressive treatment policy for high-risk patients (mastectomy or adjuvant radiation therapy), and simultaneously reduce over-treatment of low-risk patients. Generative adversarial networks (GAN) are a class of DL models in which two adversarial neural networks, generator and discriminator, compete with each other to generate high quality images. In this work, we have developed a deep learning (DL) classification network that predicts breast cancer events (BCEs) in DCIS patients using hematoxylin and eosin (H & E) images. The DL classification model was trained on 67 patients using image patches from the actual DCIS cores and GAN generated image patches to predict breast cancer events (BCEs). The hold-out validation dataset (n = 66) had an AUC of 0.82. Bayesian analysis further confirmed the independence of the model from classical clinicopathological parameters. DL models of H & E images may be used as a risk stratification strategy for DCIS patients to personalize therapy.
ABSTRACT
BACKGROUND: Four previously reported studies have tested for association of blood proteins with neocortical amyloid-ß burden (NAB). If shown to be robust, these proteins could have utility as a blood test for enrichment in clinical trials of Alzheimer's disease (AD) therapeutics. OBJECTIVE: This study aimed to investigate whether previously identified blood proteins also show evidence for association with NAB in serum samples from the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL). The study considers candidate proteins seen in cohorts other than AIBL and candidates previously discovered in the AIBL cohort. METHODS: Our study used the SOMAscan platform for protein quantification in blood serum. Linear and logistic regressions were used to model continuous NAB and dichotomized NAB respectively using single proteins as a predictor. Multiple protein models were built using stepwise regression techniques and support vectors machines. Age and APOEÉ4 carriage were used as covariates for all analysis. RESULTS: Of the 41 proteins previously reported, 15 AIBL candidates and 20 non-AIBL candidates were available for testing. Of these candidates, pancreatic polypeptide (PPY) and IgM showed a significant association with NAB. Notably, IgM was found to associate with continuous NAB across cognitively normal control subjects. CONCLUSIONS: We have further demonstrated the association of PPY and IgM with NAB, despite technical differences between studies. There are several reasons for a lack of significance for the other candidates including platform differences and the use of serum rather than plasma samples. To investigate the possibility of technical differences causing lack of replication, further studies are required.
Subject(s)
Alzheimer Disease/blood , Alzheimer Disease/pathology , Amyloid beta-Peptides/metabolism , Blood Proteins/metabolism , Neocortex/metabolism , Aged , Aged, 80 and over , Aging/blood , Aging/pathology , Aniline Compounds/metabolism , Apolipoproteins E/genetics , Australia , Cohort Studies , Female , Humans , Male , Middle Aged , Positron-Emission Tomography , Proteins , Proteomics , Thiazoles/metabolismABSTRACT
BACKGROUND: Measures of neocortical amyloid burden (NAB) identify individuals who are at substantially greater risk of developing Alzheimer's disease (AD). Blood-based biomarkers predicting NAB would have great utility for the enrichment of AD clinical trials, including large-scale prevention trials. METHODS: Nontargeted proteomic discovery was applied to 78 subjects from the Australian Imaging, Biomarkers and Lifestyle Flagship Study of Ageing with a range of NAB values. Technical and independent replications were performed by immunoassay. RESULTS: Seventeen discovery candidates were selected for technical replication. α2-Macroglobulin, fibrinogen γ-chain (FGG), and complement factor H-related protein 1 were confirmed to be associated with NAB. In an independent cohort, FGG plasma levels combined with age predicted NAB had a sensitivity of 59% and specificity of 78%. CONCLUSION: A single blood protein, FGG, combined with age, was shown to relate to NAB and therefore could have potential for enrichment of clinical trial populations.
ABSTRACT
BACKGROUND: Host-microbe interactions at the intestinal mucosal-luminal interface (MLI) are critical factors in the biology of inflammatory bowel disease (IBD). METHODS: To address this issue, we performed a series of investigations integrating analysis of the bacteria and metaproteome at the MLI of Crohn's disease, ulcerative colitis, and healthy human subjects. After quantifying these variables in mucosal specimens from a first sample set, we searched for bacteria exhibiting strong correlations with host proteins. This assessment identified a small subset of bacterial phylotypes possessing this host interaction property. Using a second and independent sample set, we tested the association of disease state with levels of these 14 "host interaction" bacterial phylotypes. RESULTS: A high frequency of these bacteria (35%) significantly differentiated human subjects by disease type. Analysis of the MLI metaproteomes also yielded disease classification with exceptional confidence levels. Examination of the relationships between the bacteria and proteins, using regularized canonical correlation analysis (RCCA), sorted most subjects by disease type, supporting the concept that host-microbe interactions are involved in the biology underlying IBD. Moreover, this correlation analysis identified bacteria and proteins that were undetected by standard means-based methods such as analysis of variance, and identified associations of specific bacterial phylotypes with particular protein features of the innate immune response, some of which have been documented in model systems. CONCLUSIONS: These findings suggest that computational mining of mucosa-associated bacteria for host interaction provides an unsupervised strategy to uncover networks of bacterial taxa and host processes relevant to normal and disease states. (Inflamm Bowel Dis 2012;).
Subject(s)
Bacteria/genetics , Colitis, Ulcerative/microbiology , Crohn Disease/microbiology , Proteins/metabolism , RNA, Bacterial/analysis , RNA, Ribosomal/analysis , Bacteria/metabolism , Cecum/metabolism , Cecum/microbiology , Colitis, Ulcerative/metabolism , Colon, Sigmoid/metabolism , Colon, Sigmoid/microbiology , Crohn Disease/metabolism , Humans , Intestinal Mucosa/metabolism , Intestinal Mucosa/microbiology , ProteomicsABSTRACT
Clustering is rapidly becoming a powerful data mining technique, and has been broadly applied to many domains such as bioinformatics and text mining. However, the existing methods can only deal with a data matrix of scalars. In this paper, we introduce a hierarchical clustering procedure that can handle a data matrix of scatter plots. To more accurately reflect the nature of data, we introduce a dissimilarity statistic based on "data depth" to measure the discrepancy between two bivariate distributions without oversimplifying the nature of the underlying pattern. We then combine hypothesis testing with hierarchical clustering to simultaneously cluster the rows and columns of the data matrix of scatter plots. We also propose novel painting metrics and construct heat maps to allow visualization of the clusters. We demonstrate the utility and power of our new clustering method through simulation studies and application to a microbe-host-interaction study.