Track topics on Twitter Track topics that are important to you
DNA methylation plays an important role in the regulation of some biological processes. Up to now, with the development of machine learning models, there are several sequence-based deep learning models designed to predict DNA methylation states, which gain better performance than traditional methods like random forest and SVM. However, convolutional network based deep learning models that use one-hot encoding DNA sequence as input may discover limited information and cause unsatisfactory prediction performance, so more data and model structures of diverse angles should be considered. In this work, we proposed a hybrid sequence-based deep learning model with both MeDIP-seq data and Histone information to predict DNA methylated CpG states (MHCpG). We combined both MeDIP-seq data and histone modification data with sequence information and implemented convolutional network to discover sequence patterns. In addition, we used statistical data gained from previous three input data and adopted a 3-layer feedforword neuron network to extract more high-level features. We compared our method with traditional predicting methods using random forest and other previous methods like CpGenie and DeepCpG, the result showed that MHCpG exceeded the other approaches and gained more satisfactory performance.
This article was published in the following journal.
Name: IEEE/ACM transactions on computational biology and bioinformatics
The Oxford Nanopore sequencing enables to directly detect methylation states of bases in DNA from reads without extra laboratory techniques. Novel computational methods are required to improve the acc...
Hybrid vigour, or heterosis, refers to the increased productivity and growth rate of hybrid offsprings relative to the parents. Various heterosis have been well exploited in fish for fisheries. Howeve...
Protein secondary structure and backbone torsion angle prediction can provide important information for predicting protein 3D structures and protein functions. Our new methods MUFold-SS, MUFold-Angle,...
Recently there have been significant advances in the field of machine learning and artificial intelligence (AI) centered around imaging-based applications such as computer vision. In particular, the t...
DNA methylation profiling has previously uncovered biologically and clinically meaningful subgroups within many tumor types, but was not yet performed in angiosarcoma (AS). AS is a rare sarcoma with v...
The main aim of this study is to determine whether the assessment of the invasive pattern based on NBI with dual focus/magnification or BLI with magnification ± chromoendoscopy (NBI+CE) f...
The overarching goal of this proposal is to determine whether DNA methylation of the mitochondrial DNA impairs mitochondrial function in insulin resistant states such as obesity and type 2...
The primary objective of this study is to compare the testing of DNA methylation, high-risk HPV subtypes, and cytology with the definite histological results for uterine cervical lesions i...
The primary objective of this study is to compare the testing of DNA methylation, high-risk HPV subtypes, and cytology with the definite histological results in a case-control study, so as...
The purpose of the study is to demonstrate that the SynergEyes SA Hybrid Contact Lens clinical performance is substantially equivalent to that of the SynergEyes A Hybrid Lens when studied:...
Screening techniques first developed in yeast to identify genes encoding interacting proteins. Variations are used to evaluate interplay between proteins and other molecules. Two-hybrid techniques refer to analysis for protein-protein interactions, one-hybrid for DNA-protein interactions, three-hybrid interactions for RNA-protein interactions or ligand-based interactions. Reverse n-hybrid techniques refer to analysis for mutations or other small molecules that dissociate known interactions.
Addition of methyl groups. In histo-chemistry methylation is used to esterify carboxyl groups and remove sulfate groups by treating tissue sections with hot methanol in the presence of hydrochloric acid. (From Stedman, 25th ed)
An educational process that provides information and advice to individuals or families about a genetic condition that may affect them. The purpose is to help individuals make informed decisions about marriage, reproduction, and other health management issues based on information about the genetic disease, the available diagnostic tests, and management programs. Psychosocial support is usually offered.
A system for the collection and/or processing of data from various sources, and using the information for policy making and management of health services. It could be paper-based or electronic. (From http://web.worldbank.org/WBSITE/EXTERNAL/TOPICS/EXTHEALTHNUTRITIONANDPOPULATION/EXTHSD/0,,contentMDK:22239824~menuPK:376799~pagePK:148956~piPK:216618~theSitePK:376793,00.html. http://www.who.int/healthinfo/systems/en/)
The specific patterns of POST-TRANSLATIONAL PROTEIN MODIFICATION of HISTONES, i.e. histone ACETYLATION; METHYLATION; PHOSPHORYLATION; and ubiquitination, at specific amino acid residues, that are involved in assembly, maintenance, and modification of different chromatin structural states, such as EUCHROMATIN and HETEROCHROMATIN.
Bioinformatics is the application of computer software and hardware to the management of biological data to create useful information. Computers are used to gather, store, analyze and integrate biological and genetic information which can then be applied...
Biological therapy involves the use of living organisms, substances derived from living organisms, or laboratory-produced versions of such substances to treat disease. Some biological therapies for cancer use vaccines or bacteria to stimulate the body&rs...