Gsslasso Cox: a Bayesian hierarchical model for predicting survival and detecting associated genes by incorporating pathway information.

BACKGROUND: Group structures among genes encoded in functional relationships or biological pathways are valuable and unique features in large-scale molecular data for survival analysis. However, most of previous approaches for molecular data analysis ignore such group structures. It is desirable to develop powerful analytic methods for incorporating valuable pathway information for predicting disease survival outcomes and detecting associated genes. RESULTS: We here propose a Bayesian hierarchical Cox survival model, called the group spike-and-slab lasso Cox (gsslasso Cox), for predicting disease survival outcomes and detecting associated genes by incorporating group structures of biological pathways. Our hierarchical model employs a novel prior on the coefficients of genes, i.e., the group spike-and-slab double-exponential distribution, to integrate group structures and to adaptively shrink the effects of genes. We have developed a fast and stable deterministic algorithm to fit the proposed models. We performed extensive simulation studies to assess the model fitting properties and the prognostic performance of the proposed method, and also applied our method to analyze three cancer data sets. CONCLUSIONS: Both the theoretical and empirical studies show that the proposed method can induce weaker shrinkage on predictors in an active pathway, thereby incorporating the biological similarity of genes within a same pathway into the hierarchical modeling. Compared with several existing methods, the proposed method can more accurately estimate gene effects and can better predict survival outcomes. For the three cancer data sets, the results show that the proposed method generates more powerful models for survival prediction and detecting associated genes. The method has been implemented in a freely available R package BhGLM at https://github.com/nyiuab/BhGLM .

Pathway-structured predictive modeling for multi-level drug response in multiple myeloma.

Motivation: Molecular analyses suggest that myeloma is composed of distinct sub-types that have different molecular pathologies and various response rates to certain treatments. Drug responses in multiple myeloma (MM) are usually recorded as a multi-level ordinal outcome. One of the goals of drug response studies is to predict which response category any patients belong to with high probability based on their clinical and molecular features. However, as most of genes have small effects, gene-based models may provide limited predictive accuracy. In that case, methods for predicting multi-level ordinal drug responses by incorporating biological pathways are desired but have not been developed yet. Results: We propose a pathway-structured method for predicting multi-level ordinal responses using a two-stage approach. We first develop hierarchical ordinal logistic models and an efficient quasi-Newton algorithm for jointly analyzing numerous correlated variables. Our two-stage approach first obtains the linear predictor (called the pathway score) for each pathway by fitting all predictors within each pathway using the hierarchical ordinal logistic approach, and then combines the pathway scores as new predictors to build a predictive model. We applied the proposed method to two publicly available datasets for predicting multi-level ordinal drug responses in MM using large-scale gene expression data and pathway information. Our results show that our approach not only significantly improved the predictive performance compared with the corresponding gene-based model but also allowed us to identify biologically relevant pathways. Availability and implementation: The proposed approach has been implemented in our R package BhGLM, which is freely available from the public GitHub repository https://github.com/abbyyan3/BhGLM.

High Sensitive and Stable UV-Vis Photodetector Based on MoS2/MoO3 vdW Heterojunction.

The development of new high-performance photodetectors (PDs) is currently focused on achieving small size, low power consumption, low cost, and large bandwidth. Two-dimensional (2D) materials and heterostructures offer promising approaches for the future development of optoelectronic devices. However, there has been limited research on 2D wide-bandgap semiconductor heterostructures. In this study, we successfully constructed a MoS2/MoO3 vdW heterojunction PD. This PD exhibited excellent response and significant photovoltaic behavior in the ultraviolet (UV) to visible (Vis) range. Under 365 nm UV light and 1 V bias voltage, the PD demonstrated a high responsivity of 645 mA/W, a high specific detectivity of 8.98 × 1010 Jones, and fast response speeds of 55.9/59.6 ms. At 0 V bias voltage, the responsivity reached as high as 157 mA/W. Furthermore, the PD exhibited remarkable stability in its performance. These outstanding characteristics can be attributed to the strong internal electric field created by the type II heterojunction structure and the chemical stability of the materials. This work opens a route for the application of 2D wide-bandgap semiconductor materials in optoelectronic devices.

An Ensemble Model for Tumor Type Identification and Cancer Origins Classification.

Tissue biopsy can be wildly used in cancer diagnosis. However, manually classifying the cancerous status of biopsies and tissue origin of tumors for cancerous ones requires skilled specialists and sophisticated equipment. As a result, a data-based model is urgently needed. In this paper, we propose a data-based ensemble model for tumor type identification and cancer origins classification. Our model is an ensemble model that combines different models based on mRNA groups which serve distinct functions. The experiment on the TCGA dataset exhibits a promising result on both tasks - 98% on tumor type identification and 96.1% on cancer origin classification. We also test our model on external validation datasets, which prove the robustness of our model.

A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma.

BACKGROUND: Neuroblastoma is one of the most devastating forms of childhood cancer. Despite large amounts of attempts in precise survival prediction in neuroblastoma, the prediction efficacy remains to be improved. METHODS: Here, we applied a deep-learning (DL) model with the attention mechanism to predict survivals in neuroblastoma. We utilized 2 groups of features separated from 172 genes, to train 2 deep neural networks and combined them by the attention mechanism. RESULTS: This classifier could accurately predict survivals, with areas under the curve of receiver operating characteristic (ROC) curves and time-dependent ROC reaching 0.968 and 0.974 in the training set respectively. The accuracy of the model was further confirmed in a validation cohort. Importantly, the two feature groups were mapped to two groups of patients, which were prognostic in Kaplan-Meier curves. Biological analyses showed that they exhibited diverse molecular backgrounds which could be linked to the prognosis of the patients. CONCLUSIONS: In this study, we applied artificial intelligence methods to improve the accuracy of neuroblastoma survival prediction based on gene expression and provide explanations for better understanding of the molecular mechanisms underlying neuroblastoma.

Slow-release delivery enhances the pharmacological properties of oral 5-hydroxytryptophan: mouse proof-of-concept.

5-hydroxytryptophan (5-HTP) has shown therapeutic promise in a range of human CNS disorders. But native 5-HTP immediate release (IR) is poorly druggable, as rapid absorption causes rapid onset of adverse events, and rapid elimination causes fluctuating exposure. Recently, we reported that 5-HTP delivered as slow-release (SR) in mice augmented the brain pro-serotonergic effect of selective serotonin reuptake inhibitors (SSRIs), without the usual adverse events associated with 5-HTP IR. However, our previous study entailed translational limitations, in terms of route, dose, and duration. Here we modeled oral 5-HTP SR in mice by administering 5-HTP via the food. We modeled oral SSRI treatment via fluoxetine in the water, in a regimen recapitulating clinical pharmacokinetics and pharmacodynamics. 5-HTP SR produced plasma 5-HTP levels well within the range enhancing brain 5-HT function in humans. 5-HTP SR robustly increased brain 5-HT synthesis and levels. When administered with an SSRI, 5-HTP SR enhanced 5-HT-sensitive behaviors and neurotrophic mRNA expression. 5-HTP SR's pro-serotonergic effects were stronger in mice with endogenous brain 5-HT deficiency. In a comprehensive screen, 5-HTP SR was devoid of overt toxicological effects. The present preclinical data, appreciated in the context of published 5-HTP clinical data, suggest that 5-HTP SR could represent a new therapeutic approach to the plethora of CNS disorders potentially treatable with a pro-serotonergic drug. 5-HTP SR might in particular be therapeutically relevant when brain 5-HT deficiency is pathogenic and as an adjunctive augmentation therapy to SSRI therapy.