More recently, DNA methylation has attracted great attention because of the strong correlation with the abnormal gene activity and informative representation of the status of cancer. As a number of studies focusing on the signature of DNA methylation in cancer, the demand to utilize publicly available datasets methylome been enhanced.
To accomplish this, large scale projects launched to find the biological insights into cancer, provides a collection of datasets. However, public cancer data, especially for certain types of cancer, it is still limited for use in research. Some simulation tools for producing epigenetic dataset has been introduced to alleviate the problem, still, to this day, for the generation of user defined types of cancer datasets have not proposed.
In this paper, we present methCancer-gen, a tool for generating DNA dataset methylome considering this type of cancer. Employing conditional variational autoencoder, generative models based on neural networks, it is estimated that the conditional distribution of latent variables and data, and generate a sample for evaluating the performance of certain cancers type.
To methCancer-gen simulation for user-specified types of cancer, our model is proposed compared with the method benchmark and it could be cancer-wise succeeded in reproducing the types of data with high accuracy helps to alleviate the lack of data problems specific conditions. methCancer-gen is available to the public in https://github.com/cbi-bioinfo/methCancer-gen.
HuVarBase: A human variant database with comprehensive information on the gene and protein level.
human variant database could be better utilized if variant data is available in multiple sources is integrated in a single comprehensive resource with sequence and structural features. The integration will improve the analysis of variance for disease prediction, prevention or treatment.
The HuVarBase (HUmanVARiantdataBASE) Data assimilation human variant available to the public at the level of protein and gene level into a comprehensive resource. The data rate of protein such as amino acid, secondary structure from residues, domain, function, location subcellular mutants and post-translational modifications that are integrated with a data rate of a gene such as the name of the gene, chromosome number and position of the genome, DNA mutations, mutation of origin and rs number ID , classes have been added to a variant disease that causes the disease.
A total of 774 863 records variant, integrated in HuVarBase, can be searched with the option to display, visualize and download the results.
A k-mer-based method for the identification of genomic biomarkers related phenotypes and predict the phenotype of bacterial sequencing.
We have developed a method that is easy to use and saving of memory called PhenotypeSeeker that (a) identify the phenotype special k-mer, (b) generate a statistical model based on k-mer to predict the phenotype; and (c) predict the phenotype of sequencing data from bacteria certain.
This method was validated in 167 isolates of Klebsiella pneumoniae (virulence), 200 isolates of Pseudomonas aeruginosa (ciprofloxacin resistance) and 459 Clostridium difficile isolates (azithromycin resistance). Phenotype prediction model trained on this dataset obtain F1-size 0.88 K. pneumoniae test set, 0.88 in P. aeruginosa test set and 0.97 in C. difficile test set. F1-the same steps to order assembled and raw sequencing data; However, building a model of the assembled genome is significantly faster.
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Hepatitis C virus genotype 1a. This antibody is HRP conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Hepatitis C virus genotype 1a. This antibody is FITC conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Hepatitis C virus genotype 1a. This antibody is Biotin conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human enterovirus 71. This antibody is HRP conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human enterovirus 71. This antibody is FITC conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human enterovirus 71. This antibody is Biotin conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Dengue virus. This antibody is HRP conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Dengue virus. This antibody is FITC conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Dengue virus. This antibody is Biotin conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human rhinovirus A serotype 89. This antibody is HRP conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human rhinovirus A serotype 89. This antibody is FITC conjugated. Tested in the following application: ELISA
Description: A polyclonal antibody against Genome polyprotein. Recognizes Genome polyprotein from Human rhinovirus A serotype 89. This antibody is Biotin conjugated. Tested in the following application: ELISA
Description: Recombinant Sindbis virus Structural polyprotein,partial expressed in in vitro E.coli expression system
×
In this dataset, the model to build a mid-range server Linux takes about 3 to 5 hours per genome assembled phenotype when used and 10 hours per phenotype whether raw sequencing data were used. Phenotype prediction of genome assembly takes less than one second per isolates. Thus, PhenotypeSeeker must be suitable to predict the phenotype of large sequencing datasets.
by 
