PATH-45. APOLLO: RAMAN-BASED PATHOLOGY OF MALIGNANT GLIOMA

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi125-vi125
Author(s):  
Adrian Lita ◽  
Joel Sjöberg ◽  
Stefan Filipescu ◽  
Orieta Celiku ◽  
Luigia Petre ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Variable Number ◽  
Prediction Algorithm ◽  
Empirical Observation ◽  
Average Accuracy ◽  
Sample Extraction ◽  
Frequency Criterion ◽  
Model Training ◽  
Spectral Intensities

Abstract BACKGROUND DNA methylation is an essential component for integrative diagnosis in glioma. Methylation subtype prediction of gliomas is currently done via sample extraction of high-quality of reasonable amount of DNA (~1ug), methylome profiling, followed by probe identification, curation and subsequent analysis via different random forest classifiers. However, the DNA methylation classification is not always available for all the samples. METHODS Raman Spectroscopy performed of the regions of interest using 1mm2 FFPE tissue spots from 45 patient samples with LGm1 to LGm6 methylation subtypes. Spectral information was then used to train a convolutional neural network (CNN) and develop a prediction algorithm. 70 % of dataset - model training while the remaining 30% for validation. Supervised wrapper methods and random forests were used to identify the top 109 most discriminatory Raman frequencies out of 1738. RESULTS We identified the most discriminatory features from these analyses and demonstrated that these frequencies show differential spectral intensities for these frequencies depending upon the glioma subtypes across the larger areas of the tissue. We compared the results of the Ward linkage clustering with the separation induced by the “frequency criterion”, an empirical observation that Raman spectra of tumor spots are characterized by intensities higher than 5000 on some of the frequencies from 1463 to 1473. For each of the 45 samples we ran Ward linkage clustering with a variable number of clusters (from 2 to 7), with the majority cluster corresponding to tumor spots and the others corresponding to (various types of) non-tumor spots. We found that the majority cluster matches very well the tumor spots characterized by the frequency criterion, The average accuracy over all samples was 90:3%, the average precision was 99:6% and the average recall was 90:2%. For most samples, two clusters were sufficient to distinguish between tumor and non-tumor spots with accuracy.

scholarly journals TBMT-02. APOLLO: RAMAN-BASED PATHOLOGY OF MALIGNANT GLIOMA

2021 ◽  
Vol 3 (Supplement_1) ◽  
pp. i20-i20
Author(s):  
Adrian Lita ◽  
Joel Sjöberg ◽  
Stefan Filipescu ◽  
Orieta Celiku ◽  
Luigia Petre ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Raman Spectroscopy ◽  
Prediction Algorithm ◽  
Molecular Fingerprinting ◽  
Molecular Fingerprint ◽  
Sample Extraction ◽  
Ffpe Samples ◽  
Coherent Raman ◽  
Model Training ◽  
Non Destructive

Abstract BACKGROUND DNA methylation is an essential component for integrative diagnosis of gliomas. Methylation subtype prediction of gliomas is currently done via sample extraction of high-quality DNA (~1ug), methylome profiling, followed by probe identification, curation and subsequent analysis via different random forest classifiers. However, the DNA methylation classification is not always available for all the samples. Examples include when the existing material is not suitable for methylation profiling or the sample is very limiting. Therefore, we hypothesized that Raman spectroscopy might be suitable to predict the glioma methylome, based upon its ability to create a molecular fingerprint of the tumor and would provide biological insights unknown before. METHODS Coherent Raman Spectroscopy was used for molecular fingerprinting of the regions of interest using 1mm2 FFPE tissue spots from 39 patient samples with LGm1 to LGm6 methylation subtypes. Spectral information was then used to train a convolutional neural network (CNN) and develop a prediction algorithm, capable of detecting the glioma methylation subtypes. 70 % of the dataset was used for model training while the remaining 30% for validation. Oversampling was used to obtain a subtype-balanced data distribution. In addition, supervised wrapper methods and random forests were used to identify the top 50 most discriminatory Raman frequencies out of 1738. RESULTS We demonstrate that Raman spectroscopy can accurately and rapidly classify gliomas according to their methylation subtype from achieved FFPE samples, which are routinely present in pathological laboratories as a complementary mean to obtain this important classification when other analyses are not available. The most discriminatory frequencies show differential spectral intensities depending upon the glioma subtypes across the larger areas of the tissue. CONCLUSIONS The non-destructive nature of this method and the ability to be applied on FFPE samples directly, allows the histopathologist to reuse of the same slide for subsequent staining and downstream analyses.

Klasifikasi Tahap Kematangan Pisang Ambon Berdasarkan Warna Menggunakan Naive Bayes

2018 ◽  
Vol 5 (2) ◽  
pp. 60-67 ◽  
Author(s):  
Dwi Yulianto ◽  
Retno Nugroho Whidhiasih ◽  
Maimunah Maimunah
Keyword(s):  
Naive Bayes ◽  
Fruit Production ◽  
Naïve Bayes ◽  
Primary Data ◽  
Banana Fruit ◽  
Bayes Method ◽  
Classification Image ◽  
Average Accuracy ◽  
The Government

ABSTRACT   Banana fruit is a commodity that contributes a great value to both national and international fruit production achievement. The government through the National Standardization Agency establishes standards to maintain the quality of bananas. The purpose of this Project is to classify the stages of maturity of Ambon banana base on the color index using Naïve Bayes method in accordance with the regulations of SNI 7422:2009. Naive Bayes is used as a method in the classification process by comparing the probability values generated from the variable value of each model to determine the stage of Ambon banana maturity. The data used is the primary data image of 105 pieces of Ambon banana. By using 3 models which consists of different variables obtained the same greatest average accuracy by using the 2nd model which has 9 variable values (r, g, b, v, * a, * b, entropy, energy, and homogeneity) and the 3rd model has 7 variable values (r, g, b, v , * a, entropy and homogeneity) that is 90.48%.   Keywords: banana maturity, classification, image processing     ABSTRAK   Buah pisang merupakan komoditas yang memberikan kontribusi besar terhadap angka produksi buah nasional maupun internasional. Pemerintah melalui Badan Standarisasi Nasional menetapkan standar untuk buah pisang, menjaga mutu  buah pisang. Tujuan dari penelitian ini adalah klasifikasi tahapan kematangan dari buah pisang ambon berdasarkan indeks warna menggunakan metode Naïve Bayes  sesuai dengan SNI 7422:2009. Naive bayes digunakan sebagai metode dalam proses pengklasifikasian dengan cara membandingkan nilai probabilitas yang dihasilkan dari nilai variabel penduga setiap model untuk menentukan tahap kematangan pisang ambon. Data yang digunakan adalah data primer citra pisang ambon sebanyak 105. Dengan menggunakan 3 buah model yang terdiri dari variabel penduga yang berbeda didapatkan akurasi rata-rata terbesar yang sama yaitu dengan menggunakan model ke-2 yang mempunyai 9 nilai variabel (r, g, b, v, *a, *b, entropi, energi, dan homogenitas) dan model ke-3 yang mempunyai 7 nilai variabel (r, g, b, v, *a, entropi dan homogenitas) yaitu sebesar 90.48%.   Kata Kunci : kematangan pisang,  klasifikasi, pengolahan citra

scholarly journals Detection of Myocardial Infarction Using ECG and Multi-Scale Feature Concatenate

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1906
Author(s):  
Jia-Zheng Jian ◽  
Tzong-Rong Ger ◽  
Han-Hua Lai ◽  
Chi-Ming Ku ◽  
Chiung-An Chen ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Network Structure ◽  
Class Imbalance ◽  
Class Imbalance Problem ◽  
Multi Scale ◽  
Imbalance Problem ◽  
Average Accuracy ◽  
Significant Difference ◽  
Electrocardiogram Ecg

Diverse computer-aided diagnosis systems based on convolutional neural networks were applied to automate the detection of myocardial infarction (MI) found in electrocardiogram (ECG) for early diagnosis and prevention. However, issues, particularly overfitting and underfitting, were not being taken into account. In other words, it is unclear whether the network structure is too simple or complex. Toward this end, the proposed models were developed by starting with the simplest structure: a multi-lead features-concatenate narrow network (N-Net) in which only two convolutional layers were included in each lead branch. Additionally, multi-scale features-concatenate networks (MSN-Net) were also implemented where larger features were being extracted through pooling the signals. The best structure was obtained via tuning both the number of filters in the convolutional layers and the number of inputting signal scales. As a result, the N-Net reached a 95.76% accuracy in the MI detection task, whereas the MSN-Net reached an accuracy of 61.82% in the MI locating task. Both networks give a higher average accuracy and a significant difference of p < 0.001 evaluated by the U test compared with the state-of-the-art. The models are also smaller in size thus are suitable to fit in wearable devices for offline monitoring. In conclusion, testing throughout the simple and complex network structure is indispensable. However, the way of dealing with the class imbalance problem and the quality of the extracted features are yet to be discussed.

DNA methylation in human sperm: a systematic review

2020 ◽  
Vol 26 (6) ◽  
pp. 841-873 ◽  
Author(s):  
Fredrika Åsenius ◽  
Amy F Danson ◽  
Sarah J Marzi
Keyword(s):  
Systematic Review ◽  
Dna Methylation ◽  
Environmental Factors ◽  
Pregnancy Outcomes ◽  
Human Sperm ◽  
Semen Parameters ◽  
Dna Methylome ◽  
Sperm Dna ◽  
Offspring Health

Abstract BACKGROUND Studies in non-human mammals suggest that environmental factors can influence spermatozoal DNA methylation, and some research suggests that spermatozoal DNA methylation is also implicated in conditions such as subfertility and imprinting disorders in the offspring. Together with an increased availability of cost-effective methods of interrogating DNA methylation, this premise has led to an increasing number of studies investigating the DNA methylation landscape of human spermatozoa. However, how the human spermatozoal DNA methylome is influenced by environmental factors is still unclear, as is the role of human spermatozoal DNA methylation in subfertility and in influencing offspring health. OBJECTIVE AND RATIONALE The aim of this systematic review was to critically appraise the quality of the current body of literature on DNA methylation in human spermatozoa, summarize current knowledge and generate recommendations for future research. SEARCH METHODS A comprehensive literature search of the PubMed, Web of Science and Cochrane Library databases was conducted using the search terms ‘semen’ OR ‘sperm’ AND ‘DNA methylation’. Publications from 1 January 2003 to 2 March 2020 that studied human sperm and were written in English were included. Studies that used sperm DNA methylation to develop methodologies or forensically identify semen were excluded, as were reviews, commentaries, meta-analyses or editorial texts. The Grading of Recommendations, Assessment, Development and Evaluations (GRADE) criteria were used to objectively evaluate quality of evidence in each included publication. OUTCOMES The search identified 446 records, of which 135 were included in the systematic review. These 135 studies were divided into three groups according to area of research; 56 studies investigated the influence of spermatozoal DNA methylation on male fertility and abnormal semen parameters, 20 studies investigated spermatozoal DNA methylation in pregnancy outcomes including offspring health and 59 studies assessed the influence of environmental factors on spermatozoal DNA methylation. Findings from studies that scored as ‘high’ and ‘moderate’ quality of evidence according to GRADE criteria were summarized. We found that male subfertility and abnormal semen parameters, in particular oligozoospermia, appear to be associated with abnormal spermatozoal DNA methylation of imprinted regions. However, no specific DNA methylation signature of either subfertility or abnormal semen parameters has been convincingly replicated in genome-scale, unbiased analyses. Furthermore, although findings require independent replication, current evidence suggests that the spermatozoal DNA methylome is influenced by cigarette smoking, advanced age and environmental pollutants. Importantly however, from a clinical point of view, there is no convincing evidence that changes in spermatozoal DNA methylation influence pregnancy outcomes or offspring health. WIDER IMPLICATIONS Although it appears that the human sperm DNA methylome can be influenced by certain environmental and physiological traits, no findings have been robustly replicated between studies. We have generated a set of recommendations that would enhance the reliability and robustness of findings of future analyses of the human sperm methylome. Such studies will likely require multicentre collaborations to reach appropriate sample sizes, and should incorporate phenotype data in more complex statistical models.

scholarly journals DeepMAsED: evaluating the quality of metagenomic assemblies

2020 ◽  
Vol 36 (10) ◽  
pp. 3011-3017 ◽  
Author(s):  
Olga Mineeva ◽  
Mateo Rojas-Carulla ◽  
Ruth E Ley ◽  
Bernhard Schölkopf ◽  
Nicholas D Youngblut
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Ground Truth ◽  
Supplementary Information ◽  
Learning Approach ◽  
Wide Range ◽  
Metagenome Assembly ◽  
Model Training ◽  
Reference Genomes

Abstract Motivation Methodological advances in metagenome assembly are rapidly increasing in the number of published metagenome assemblies. However, identifying misassemblies is challenging due to a lack of closely related reference genomes that can act as pseudo ground truth. Existing reference-free methods are no longer maintained, can make strong assumptions that may not hold across a diversity of research projects, and have not been validated on large-scale metagenome assemblies. Results We present DeepMAsED, a deep learning approach for identifying misassembled contigs without the need for reference genomes. Moreover, we provide an in silico pipeline for generating large-scale, realistic metagenome assemblies for comprehensive model training and testing. DeepMAsED accuracy substantially exceeds the state-of-the-art when applied to large and complex metagenome assemblies. Our model estimates a 1% contig misassembly rate in two recent large-scale metagenome assembly publications. Conclusions DeepMAsED accurately identifies misassemblies in metagenome-assembled contigs from a broad diversity of bacteria and archaea without the need for reference genomes or strong modeling assumptions. Running DeepMAsED is straight-forward, as well as is model re-training with our dataset generation pipeline. Therefore, DeepMAsED is a flexible misassembly classifier that can be applied to a wide range of metagenome assembly projects. Availability and implementation DeepMAsED is available from GitHub at https://github.com/leylabmpi/DeepMAsED. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Pervasive cis effects of variation in copy number of large tandem repeats on local epigenetics and gene expression

2020 ◽  
Author(s):  
Paras Garg ◽  
Alejandro Martin-Trujillo ◽  
Oscar L. Rodriguez ◽  
Scott J. Gies ◽  
Bharati Jadhav ◽  
...  
Keyword(s):  
Gene Expression ◽  
Dna Methylation ◽  
Copy Number ◽  
Large Scale ◽  
Tandem Repeats ◽  
Local Variation ◽  
Read Depth ◽  
Variable Number ◽  
Human Populations ◽  
Functional Variation

ABSTRACTVariable Number Tandem Repeats (VNTRs) are composed of large tandemly repeated motifs, many of which are highly polymorphic in copy number. However, due to their large size and repetitive nature, they remain poorly studied. To investigate the regulatory potential of VNTRs, we used read-depth data from Illumina whole genome sequencing to perform association analysis between copy number of ~70,000 VNTRs (motif size ≥10bp) with both gene expression (404 samples in 48 tissues) and DNA methylation (235 samples in peripheral blood), identifying thousands of VNTRs that are associated with local gene expression (eVNTRs) and DNA methylation levels (mVNTRs). Using large-scale replication analysis in an independent cohort we validated 73-80% of signals observed in the two discovery cohorts, providing robust evidence to support that these represent genuine associations. Further, conditional analysis indicated that many eVNTRs and mVNTRs act as QTLs independently of other local variation. We also observed strong enrichments of eVNTRs and mVNTRs for regulatory features such as enhancers and promoters. Using the Human Genome Diversity Panel, we defined sets of VNTRs that show highly divergent copy numbers among human populations, show that these are enriched for regulatory effects on gene expression and epigenetics, and preferentially associate with genes that have been linked with human phenotypes through GWAS. Our study provides strong evidence supporting functional variation at thousands of VNTRs, and defines candidate sets of VNTRs, copy number variation of which potentially plays a role in numerous human phenotypes.

scholarly journals Enhancement of Multilayer Perceptron Model Training Accuracy through the Optimization of Hyperparameters: A Case Study of the Quality Prediction of Injection Molded Parts

2021 ◽  
Author(s):  
Kun-Cheng Ke ◽  
Ming-Shyan Huang
Keyword(s):  
Gradient Descent ◽  
Training Model ◽  
Learning Rate ◽  
Stochastic Gradient Descent ◽  
Activation Functions ◽  
Molded Parts ◽  
Injection Molded ◽  
Testing Accuracy ◽  
Model Training

Abstract Injection molding has been broadly used in the mass production of plastic parts and must meet the requirements of efficiency and quality consistency. Machine learning can effectively predict the quality of injection molded part. However, the performance of machine learning models largely depends on the accuracy of the training. Hyperparameters such as activation functions, momentum, and learning rate are crucial to the accuracy and efficiency of model training. This research further analyzed the influence of hyperparameters on testing accuracy, explored the corresponding optimal learning rate, and provided the optimal training model for predicting the quality of injection molded parts. In this study, stochastic gradient descent (SGD) and stochastic gradient descent with momentum were used to optimize the artificial neural network model. Through optimization of these training model hyperparameters, the width testing accuracy of the injection product improved. The experimental results indicated that in the absence of momentum effects, all five activation functions can achieve more than 90% of the training accuracy with a learning rate of 0.1. Moreover, when optimized with the SGD, the learning rate of the Sigmoid activation function was 0.1, and the testing accuracy reached 95.8%. Although momentum had the least influence on accuracy, it affected the convergence speed of the Sigmoid function, which reduced the number of required learning iterations (82.4% reduction rate). Optimizing hyperparameter settings can improve the accuracy of model testing and markedly reduce training time.

scholarly journals Single sitting multimodality management of hemorrhoid

2021 ◽  
Vol 8 (11) ◽  
pp. 3302
Author(s):  
Mahendra P. Singh
Keyword(s):  
Variable Number ◽  
Concomitant Treatment ◽  
Stage Management ◽  
Group 4 ◽  
Number Of Patients ◽  
Clinical Complexity ◽  
Group 3 ◽  
Group 2 ◽  
Group 1

Background: It is usual to face clinical complexity in piles patients. They usually present with variable number of pile masses and in different grades of progression. This led to the idea of offering concomitant single stage management in our hemorrhoid patients matching to our criteria. We conducted hospital based descriptive study among the patients coming to my clinical practice falling in grade-1-3.Methods: All the patients falling in grade-1-3 and matching to our criteria were included. The study was conducted   from January 2012 to December 2020. Place of study was basically at two centres: Karamdeep medical centre, Kanpur and Mayo health care, Mohali. Total number of patients were 581. Patients having grade-4 piles and with local co-morbidities were excluded from the study. Modalities of treatment used were sclerotherapy, band ligation and hemorrhoidectomy.Results: Patients managed were divided into four groups – group 1 included patients with piles in grade-1; group-2 included patients having piles in grade-1 and 2; group-3 included patients having piles in grade-1 and 3; and group-4 included patients having piles in grade-1, 2 and 3. Total 952 pile masses were treated in 581 patients. Sclerotherapy was required in 732 (77%) masses, banding in 99 (10.3%) masses and surgery in 122 (12.7%) masses.Conclusions: Concomitant treatment policy proved to be comprehensive way to tackle pile patients of grade-1-3. Mixed and matched method using surgical and non-surgical modalities in a single sitting proved to be beneficial. 86.4% cases were cured this way. Cost of the treatment was economical with lesser complications including local mutilation and better quality of life.

Legal Capacity

2011 ◽  
Author(s):  
Timothy Besley ◽  
Torsten Persson
Keyword(s):  
Total Factor Productivity ◽  
Legal Capacity ◽  
Factor Productivity ◽  
Empirical Observation ◽  
Role Of Government ◽  
Doing Business ◽  
The Right ◽  
Productive Role

This chapter focuses on the productive role of government in improving the environment for doing business. Improvements in the performance of government are measured as total factor productivity and differences in income across countries can be explained by differences in the quality of their economic institutions. This makes it essential to understand why some countries make the right investments in legal institutions and deploy such legal capacity effectively. A running theme of the chapter is the possibility of a complementarity between the extractive (taxation) and the productive (supporting markets) roles of government. This is at the heart of the empirical observation that market development and state development move hand in hand. But the key insight from this is that we have to understand the incentives of a government to make investments to improve the workings of the economy.

Sign in / Sign up

Export Citation Format

Share Document