MOTIVATION: Essential genes are required for the reproductive success at either cellular or organismal level. The identification of essential genes is important for understanding the core biological processes and identifying effective therapeutic drug targets. However, experimental identification of essential genes is costly, time consuming and labor intensive. Although several machine learning models have been developed to predict essential genes, these models are not readily applicable to lncRNAs. Moreover, the currently available models cannot be used to predict essential genes in a specific cancer type. RESULTS: In this study, we have developed a new machine learning approach, XGEP (eXpression-based Gene Essentiality Prediction), to predict essential genes and candidate lncRNAs in cancer cells. The novelty of XGEP lies in the utilization of relevant features derived from the TCGA transcriptome dataset through collaborative embedding. When evaluated on the pan-cancer dataset, XGEP was able to accurately predict human essential genes and achieve significantly higher performance than previous models. Notably, several candidate lncRNAs selected by XGEP are reported to promote cell proliferation and inhibit cell apoptosis. Moreover, XGEP also demonstrated superior performance on cancer-type-specific datasets to identify essential genes. The comprehensive lists of candidate essential genes in specific cancer types may be used to guide experimental characterization and facilitate the discovery of drug targets for cancer therapy. AVAILABILITY AND IMPLEMENTATION: The source code and datasets used in this study are freely available at https://github.com/BioDataLearning/XGEP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Autism spectrum disorders (ASD) refer to a range of neurodevelopmental conditions, which are genetically complex and heterogeneous with most of the genetic risk factors also found in the unaffected general population. Although all the currently known ASD risk genes code for proteins, long non-coding RNAs (lncRNAs) as essential regulators of gene expression have been implicated in ASD. Some lncRNAs show altered expression levels in autistic brains, but their roles in ASD pathogenesis are still unclear. RESULTS: In this study, we have developed a new machine learning approach to predict candidate lncRNAs associated with ASD. Particularly, the knowledge learnt from protein-coding ASD risk genes was transferred to the prediction and prioritization of ASD-associated lncRNAs. Both developmental brain gene expression data and transcript sequence were found to contain relevant information for ASD risk gene prediction. During the pre-training phase of model construction, an autoencoder network was implemented for a representation learning of the gene expression data, and a random-forest-based feature selection was applied to the transcript-sequence-derived k-mers. Our models, including logistic regression, support vector machine and random forest, showed robust performance based on tenfold cross-validations as well as candidate prioritization with hypothetical loci. We then utilized the models to predict and prioritize a list of candidate lncRNAs, including some reported to be cis-regulators of known ASD risk genes, for further investigation. CONCLUSIONS: Our results suggest that ASD risk genes can be accurately predicted using developmental brain gene expression data and transcript sequence features, and the models may provide useful information for functional characterization of the candidate lncRNAs associated with ASD.

MOTIVATION: Circular RNAs (circRNAs) are a new class of endogenous RNAs in animals and plants. During pre-RNA splicing, the 5' and 3' termini of exon(s) can be covalently ligated to form circRNAs through back-splicing (head-to-tail splicing). CircRNAs can be conserved across species, show tissue- and developmental stage-specific expression patterns, and may be associated with human disease. However, the mechanism of circRNA formation is still unclear although some sequence features have been shown to affect back-splicing. RESULTS: In this study, by applying the state-of-art machine learning techniques, we have developed the first deep learning model, DeepCirCode, to predict back-splicing for human circRNA formation. DeepCirCode utilizes a convolutional neural network (CNN) with nucleotide sequence as the input, and shows superior performance over conventional machine learning algorithms such as support vector machine and random forest. Relevant features learnt by DeepCirCode are represented as sequence motifs, some of which match human known motifs involved in RNA splicing, transcription or translation. Analysis of these motifs shows that their distribution in RNA sequences can be important for back-splicing. Moreover, some of the human motifs appear to be conserved in mouse and fruit fly. The findings provide new insight into the back-splicing code for circRNA formation. AVAILABILITY AND IMPLEMENTATION: All the datasets and source code for model construction are available at https://github.com/BioDataLearning/DeepCirCode. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Autism spectrum disorders (ASD) are a group of neurodevelopmental disorders with clinical heterogeneity and a substantial polygenic component. High-throughput methods for ASD risk gene identification produce numerous candidate genes that are time-consuming and expensive to validate. Prioritization methods can identify high-confidence candidates. Previous ASD gene prioritization methods have focused on a priori knowledge, which excludes genes with little functional annotation or no protein product such as long non-coding RNAs (lncRNAs). RESULTS: We have developed a support vector machine (SVM) model, trained using brain developmental gene expression data, for the classification and prioritization of ASD risk genes. The selected feature model had a mean accuracy of 76.7%, mean specificity of 77.2% and mean sensitivity of 74.4%. Gene lists comprised of an ASD risk gene and adjacent genes were ranked using the model's decision function output. The known ASD risk genes were ranked on average in the 77.4th, 78.4th and 80.7th percentile for sets of 101, 201 and 401 genes respectively. Of 10,840 lncRNA genes, 63 were classified as ASD-associated candidates with a confidence greater than 0.95. Genes previously associated with brain development and neurodevelopmental disorders were prioritized highly within the lncRNA gene list. CONTACT: [email protected] information: Supplementary data are available at Bioinformatics online.

Advances of high-throughput technologies have rapidly produced more and more data from DNAs and RNAs to proteins, especially large volumes of genome-scale data. However, connection of the genomic information to cellular functions and biological behaviours relies on the development of effective approaches at higher systems level. In particular, advances in RNA-Seq technology has helped the studies of transcriptome, RNA expressed from the genome, while systems biology on the other hand provides more comprehensive pictures, from which genes and proteins actively interact to lead to cellular behaviours and physiological phenotypes. As biological interactions mediate many biological processes that are essential for cellular function or disease development, it is important to systematically identify genomic information including genetic mutations from GWAS (genome-wide association study), differentially expressed genes, bidirectional promoters, intrinsic disordered proteins (IDP) and protein interactions to gain deep insights into the underlying mechanisms of gene regulations and networks. Furthermore, bidirectional promoters can co-regulate many biological pathways, where the roles of bidirectional promoters can be studied systematically for identifying co-regulating genes at interactive network level. Combining information from different but related studies can ultimately help revealing the landscape of molecular mechanisms underlying complex diseases such as cancer.

BACKGROUND: Kidney Renal Clear Cell Carcinoma (KIRC) is one of fatal genitourinary diseases and accounts for most malignant kidney tumours. KIRC has been shown resistance to radiotherapy and chemotherapy. Like many types of cancers, there is no curative treatment for metastatic KIRC. Using advanced sequencing technologies, The Cancer Genome Atlas (TCGA) project of NIH/NCI-NHGRI has produced large-scale sequencing data, which provide unprecedented opportunities to reveal new molecular mechanisms of cancer. We combined differentially expressed genes, pathways and network analyses to gain new insights into the underlying molecular mechanisms of the disease development. RESULTS: Followed by the experimental design for obtaining significant genes and pathways, comprehensive analysis of 537 KIRC patients' sequencing data provided by TCGA was performed. Differentially expressed genes were obtained from the RNA-Seq data. Pathway and network analyses were performed. We identified 186 differentially expressed genes with significant p-value and large fold changes (P < 0.01, |log(FC)| > 5). The study not only confirmed a number of identified differentially expressed genes in literature reports, but also provided new findings. We performed hierarchical clustering analysis utilizing the whole genome-wide gene expressions and differentially expressed genes that were identified in this study. We revealed distinct groups of differentially expressed genes that can aid to the identification of subtypes of the cancer. The hierarchical clustering analysis based on gene expression profile and differentially expressed genes suggested four subtypes of the cancer. We found enriched distinct Gene Ontology (GO) terms associated with these groups of genes. Based on these findings, we built a support vector machine based supervised-learning classifier to predict unknown samples, and the classifier achieved high accuracy and robust classification results. In addition, we identified a number of pathways (P < 0.04) that were significantly influenced by the disease. We found that some of the identified pathways have been implicated in cancers from literatures, while others have not been reported in the cancer before. The network analysis leads to the identification of significantly disrupted pathways and associated genes involved in the disease development. Furthermore, this study can provide a viable alternative in identifying effective drug targets. CONCLUSIONS: Our study identified a set of differentially expressed genes and pathways in kidney renal clear cell carcinoma, and represents a comprehensive computational approach to analysis large-scale next-generation sequencing data. The pathway and network analyses suggested that information from distinctly expressed genes can be utilized in the identification of aberrant upstream regulators. Identification of distinctly expressed genes and altered pathways are important in effective biomarker identification for early cancer diagnosis and treatment planning. Combining differentially expressed genes with pathway and network analyses using intelligent computational approaches provide an unprecedented opportunity to identify upstream disease causal genes and effective drug targets.

Lipids perform many vital functions in the cell. Cellular levels of lipids are tightly regulated, and alterations in lipid metabolism can cause various human diseases such as inflammation, cancer and neurological disorders. Here, we present a method that takes an amino acid sequence as the only input and predicts lipid-interacting residues using support vector machines (SVMs). Protein sequence datasets with known lipid-interacting residues were chosen from the protein data bank (PDB). SVM classifiers were then constructed using data instances encoded with three sequence features. The results suggest that lipid-interacting residues can be predicted at 52.78% sensitivity and 70.84% specificity. To the best of our knowledge, this is the first study that utilizes a machine learning approach to predict lipid-interacting residues based on amino acid sequence data. Our study provides useful information for understanding protein-lipid interactions, and may lead to advances in drug discovery.

MOTIVATION: The amplified interest in metabolic profiling has generated the need for additional tools to assist in the rapid analysis of complex data sets. RESULTS: A new program; metabolomics spectral formatting, alignment and conversion tools, (MSFACTs) is described here for the automated import, reformatting, alignment, and export of large chromatographic data sets to allow more rapid visualization and interrogation of metabolomic data. MSFACTs incorporates two tools: one for the alignment of integrated chromatographic peak lists and another for extracting information from raw chromatographic ASCII formatted data files. MSFACTs is illustrated in the processing of GC/MS metabolomic data from different tissues of the model legume plant, Medicago truncatula. The results document that various tissues such as roots, stems, and leaves from the same plant can be easily differentiated based on metabolite profiles. Further, similar types of tissues within the same plant, such as the first to eleventh internodes of stems, could also be differentiated based on metabolite profiles. AVAILABILITY: Freely available upon request for academic and non-commercial use. Commercial use is available through licensing agreement http://www.noble.org/PlantBio/MS/MSFACTs/MSFACTs.html.