Breast cancer is a highly aggressive type of with very low median survival. Accurate prognosis prediction breast can spare significant number patients from receiving unnecessary adjuvant systemic treatment and its related expensive medical costs. Previous work relies mostly on selected gene expression data to create predictive model. The emergence deep learning methods multi-dimensional offers opportunities for more comprehensive analysis the molecular characteristics therefore improve...

Phosphorylation is the most studied post-translational modification, which crucial for multiple biological processes. Recently, many efforts have been taken to develop computational predictors phosphorylation site prediction, but of them are based on feature selection and discriminative classification. Thus, it useful a novel highly accurate predictor that can unveil intricate patterns automatically protein sites.In this study we present DeepPhos, deep learning architecture prediction...

Abstract Background As a reversible and dynamic post-translational modification (PTM) of proteins, phosphorylation plays essential regulatory roles in broad spectrum the biological processes. Although many studies have been contributed on molecular mechanism dynamics, intrinsic feature substrates specificity is still elusive remains to be delineated. Results In this work, we present novel, versatile comprehensive program, PPSP (Prediction PK-specific Phosphorylation site), deployed with...

Abstract An enduring challenge in personalized medicine lies selecting a suitable drug for each individual patient. Here we concentrate on predicting responses based cohort of genomic, chemical structure, and target information. Therefore, recently study such as GDSC has provided an unprecedented opportunity to infer the potential relationships between cell line drug. While existing approach rely primarily regression, classification or multiple kernel learning predict responses. Synthetic...

As one large class of non-coding RNAs (ncRNAs), long ncRNAs (lncRNAs) have gained considerable attention in recent years. Mutations and dysfunction lncRNAs been implicated human disorders. Many exert their effects through interactions with the corresponding RNA-binding proteins. Several computational approaches developed, but only few are able to perform prediction these from a network-based point view. Here, we introduce method named lncRNA-protein bipartite network inference (LPBNI). LPBNI...

Accumulating evidences have indicated that lncRNAs play an important role in various human complex diseases. However, known disease-related are still comparatively small number, and experimental identification is time-consuming labor-intensive. Therefore, developing a useful computational method for inferring potential associations between diseases has become hot topic, which can significantly help people to explore at the molecular level effectively advance quality of disease diagnostics,...

Breast cancer is a very heterogeneous disease and there an urgent need to design computational methods that can accurately predict the prognosis of breast for appropriate therapeutic regime. Recently, deep learning-based have achieved great success in prediction, but many them directly combine features from different modalities may ignore complex inter-modality relations. In addition, existing do not take intra-modality relations into consideration are also beneficial prediction. Therefore,...

Cancer survival prediction can greatly assist clinicians in planning patient treatments and improving their life quality. Recent evidence suggests the fusion of multimodal data, such as genomic data pathological images, is crucial for understanding cancer heterogeneity enhancing prediction. As a powerful technique, Kronecker product has shown its superiority predicting survival. However, this technique introduces large number parameters that may lead to high computational cost risk...

Abstract Background Gene expression profiling has become a useful biological resource in recent years, and it plays an important role broad range of areas biology. The raw gene data, usually the form large matrix, may contain missing values. downstream analysis methods that postulate complete matrix input are thus not applicable. Several have been developed to solve this problem, such as K nearest neighbor impute method, Bayesian principal components etc . In paper, we introduce novel...

Abstract Background Over 200 published studies of more than 30 plant species have reported a role for miRNAs in regulating responses to abiotic stresses. However, data from these individual reports has not been collected into single database. The lack curated database stress-related limits research this field, and thus cohesive system should necessarily be constructed deposit further application. Description PASmiR , literature-curated web-accessible database, was developed provide detailed,...

There is an increasing interest in using single nucleotide polymorphism (SNP) genotyping arrays for profiling chromosomal rearrangements tumors, as they allow simultaneous detection of copy number and loss heterozygosity with high resolution. Critical issues such signal baseline shift due to aneuploidy, normal cell contamination, the presence GC content bias have been reported dramatically alter SNP array signals complicate accurate identification aberrations cancer genomes. To address these...

Breast cancer is a common disease in elderly women. With the development of microarray technique, discovering gene signature became powerful approach predicting survival breast cancer. Previously, 70-gene had been discovered for prognosis prediction and received good performance. In this study we adopted an efficient feature selection method: support vector machine-based recursive elimination (SVM-RFE) prediction. Using leave-one-out evaluation procedure on expression dataset including 295...

Recent study shows that long noncoding RNAs (lncRNAs) are participating in diverse biological processes and complex diseases. However, at present the functions of lncRNAs still rarely known. In this study, we propose a network-based computational method, which is called lncRNA-protein interaction prediction based on Heterogeneous Network Model (LPIHN), to predict potential interactions. First, construct heterogeneous network by integrating lncRNA-lncRNA similarity network, protein-protein...

Glioblastoma multiforme (GBM) is a highly aggressive type of brain cancer with very low median survival. In order to predict the patient's prognosis, researchers have proposed rules classify different glioma cell subtypes. However, survival time subtypes GBM often various due individual basis. Recent development in gene testing has evolved classic subtype more specific classification based on single biomolecular features. These methods are proven perform better than traditional simple...

Recently, accumulating studies have indicated that microRNAs (miRNAs) play an important role in exploring the pathogenesis of various human diseases at molecular level and may result design specific tools for diagnosis, treatment evaluation prevention.

Abstract Motivation Detecting driver genes from gene mutation data is a fundamental task for tumorigenesis research. Due to the fact that cancer heterogeneous disease with various subgroups, subgroup-specific are key factors in development of precision medicine cancer. However, existing detection methods not designed identify subgroup specificities their detected genes, and therefore cannot indicate which group patients associated difficult provide specifically clinical guidance individual...

Abstract Motivation Prediction of cancer patient’s response to therapeutic agent is important for personalized treatment. Because experimental verification reactions between large cohort patients and drugs time-intensive, expensive impractical, preclinical prediction model based on large-scale pharmacogenomic cell line highly expected. However, most the existing computational studies are primarily genomic profiles lines while ignoring relationships among genes failing capture functional...

Survival analysis is a branch of statistics to analyze the time duration that expected until some events interest happen, like death in organisms biology. Currently, survival based on pathological images has turned out be truly energetic area research healthcare for making primary decisions therapy and improving patients' quality treatment. In this regard, design convolutional neural networks with increasing greatly at present. Furthermore, consider important spatial hierarchies between...

Abstract Motivation Phosphorylation is one of the most studied post-translational modifications, which plays a pivotal role in various cellular processes. Recently, deep learning methods have achieved great success prediction phosphorylation sites, but them are based on convolutional neural network that may not capture enough information about long-range dependencies between residues protein sequence. In addition, existing only make use sequence for predicting and it highly desirable to...

: Next-Generation Sequencing (NGS) technology has revealed that microRNAs (miRNAs) are capable of exhibiting frequent differences from their corresponding mature reference sequences, generating multiple variants: the isoforms miRNAs (isomiRs). These isomiRs mainly originate via imprecise and alternative cleavage during pre-miRNA processing post-transcriptional modifications influence miRNA stability, sub-cellular localization target selection. Although several tools for identification isomiR...