MOTIVATION: Cancer dependencies provide potential drug targets. Unfortunately, dependencies differ among cancers and even individuals. To this end, visible neural networks (VNNs) are promising due to robust performance and the interpretability required for the biomedical field. RESULTS: We design Biological visible neural network (BioVNN) using pathway knowledge to predict cancer dependencies. Despite having fewer parameters, BioVNN marginally outperforms traditional neural networks (NNs) and converges faster. BioVNN also outperforms an NN based on randomized pathways. More importantly, dependency predictions can be explained by correlating with the neuron output states of relevant pathways, which suggest dependency mechanisms. In feature importance analysis, BioVNN recapitulates known reaction partners and proposes new ones. Such robust and interpretable VNNs may facilitate the understanding of cancer dependency and the development of targeted therapies. AVAILABILITY AND IMPLEMENTATION: Code and data are available at https://github.com/LichtargeLab/BioVNN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: In light of the massive growth of the scientific literature, text mining is increasingly used to extract biological pathways. Though multiple tools explore individual connections between genes, diseases and drugs, few extensively synthesize pathways for specific diseases and drugs. RESULTS: Through community detection of a literature network, we extracted 3444 functional gene groups that represented biological pathways for specific diseases and drugs. The network linked Medical Subject Headings (MeSH) terms of genes, diseases and drugs that co-occurred in publications. The resulting communities detected highly associated genes, diseases and drugs. These significantly matched current knowledge of biological pathways and predicted future ones in time-stamped experiments. Likewise, disease- and drug-specific communities also recapitulated known pathways for those given diseases and drugs. Moreover, diseases sharing communities had high comorbidity with each other and drugs sharing communities had many common side effects, consistent with related mechanisms. Indeed, the communities robustly recovered mutual targets for drugs [area under Receiver Operating Characteristic curve (AUROC)=0.75] and shared pathogenic genes for diseases (AUROC=0.82). These data show that literature communities inform not only just known biological processes but also suggest novel disease- and drug-specific mechanisms that may guide disease gene discovery and drug repurposing. AVAILABILITY AND IMPLEMENTATION: Application tools are available at http://meteor.lichtargelab.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Bioinformatics (2019) doi: 10.1093/bioinformatics/btz857 The first version of this article contained the following errors: Equation 1 was missing the absolute-value notion bars in the denominator. Equation 2 contained an equal sign (=) instead of a minus sign (-), and an incorrect subscript (Rj instead of Ri). A column heading in Table 3 incorrectly contained subscript instead of regular script (Sz instead of Sz). These have now been corrected.

MOTIVATION: Precision medicine is an emerging field with hopes to improve patient treatment and reduce morbidity and mortality. To these ends, computational approaches have predicted associations among genes, chemicals and diseases. Such efforts, however, were often limited to using just some available association types. This lowers prediction coverage and, since prior evidence shows that integrating heterogeneous data is likely beneficial, it may limit accuracy. Therefore, we systematically tested whether using more association types improves prediction. RESULTS: We study multimodal networks linking diseases, genes and chemicals (drugs) by applying three diffusion algorithms and varying information content. Ten-fold cross-validation shows that these networks are internally consistent, both within and across association types. Also, diffusion methods recovered missing edges, even if all the edges from an entire mode of association were removed. This suggests that information is transferable between these association types. As a realistic validation, time-stamped experiments simulated the predictions of future associations based solely on information known prior to a given date. The results show that many future published results are predictable from current associations. Moreover, in most cases, using more association types increases prediction coverage without significantly decreasing sensitivity and specificity. In case studies, literature-supported validation shows that these predictions mimic human-formulated hypotheses. Overall, this study suggests that diffusion over a more comprehensive multimodal network will generate more useful hypotheses of associations among diseases, genes and chemicals, which may guide the development of precision therapies. AVAILABILITY AND IMPLEMENTATION: Code and data are available at https://github.com/LichtargeLab/multimodal-network-diffusion. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Ambiguity in genetic codes exists in cases where certain stop codons are alternatively used to encode non-canonical amino acids. In selenoprotein transcripts, the UGA codon may either represent a translation termination signal or a selenocysteine (Sec) codon. Translating UGA to Sec requires selenium and specialized Sec incorporation machinery such as the interaction between the SECIS element and SBP2 protein, but how these factors quantitatively affect alternative assignments of UGA has not been fully investigated. We developed a model simulating the UGA decoding process. Our model is based on the following assumptions: (1) charged Sec-specific tRNAs (Sec-tRNASec) and release factors compete for a UGA site, (2) Sec-tRNASec abundance is limited by the concentrations of selenium and Sec-specific tRNA (tRNASec) precursors, and (3) all synthesis reactions follow first-order kinetics. We demonstrated that this model captured two prominent characteristics observed from experimental data. First, UGA to Sec decoding increases with elevated selenium availability, but saturates under high selenium supply. Second, the efficiency of Sec incorporation is reduced with increasing selenoprotein synthesis. We measured the expressions of four selenoprotein constructs and estimated their model parameters. Their inferred Sec incorporation efficiencies did not correlate well with their SECIS-SBP2 binding affinities, suggesting the existence of additional factors determining the hierarchy of selenoprotein synthesis under selenium deficiency. This model provides a framework to systematically study the interplay of factors affecting the dual definitions of a genetic codon.