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.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6198861PMC
http://dx.doi.org/10.1093/bioinformatics/bty436DOI Listing

Publication Analysis

Top Keywords

multi-level ordinal
16
drug responses
12
predicting multi-level
12
drug response
8
multiple myeloma
8
ordinal drug
8
two-stage approach
8
hierarchical ordinal
8
ordinal logistic
8
ordinal
6

Similar Publications

Introduction: Anemia is a significant health problem that has a profound impact on young children under the age of five. It can result in severe consequences, such as stunted growth, impaired cognitive and motor development, increased illness, and even death. In Ghana, anemia is the leading cause of child mortality, yet there is a lack of information available on the prevalence of anemia and the factors associated with its severity in children under five in the country.

View Article and Find Full Text PDF

Objective: Alcohol expectancy theory proposes that beliefs about drinking motivate or deter drinking. Although expectancies influence drinking, less is known about how the consequences of drinking influence expectancies. We modeled a feedback conceptualization of how the experience of specific consequences influenced people's beliefs about how likely a consequence will occur (i.

View Article and Find Full Text PDF

A nationwide mixed-methods study of gaps and barriers to implementation of antimicrobial stewardship programmes in hospitals in Indonesia.

J Hosp Infect

December 2024

Centre for Tropical Medicine and Global Health, Nuffield Department of Medicine, University of Oxford, Oxford, UK; Oxford University Clinical Research Unit Indonesia, Faculty of Medicine Universitas Indonesia, Jakarta, Indonesia.

Background: There is an urgent need to understand the implementation barriers of antimicrobial stewardship programmes (ASPs) in low- and middle-income countries.

Methods: We conducted a mixed-methods study in public and private hospitals across all provinces in Indonesia (March-December 2023). We used a self-assessment questionnaire with a scoring system, and multi-level ordinal regression to assess associations with hospital and district-level characteristics.

View Article and Find Full Text PDF

Air pollution, traffic noise, mental health, and cognitive development: A multi-exposure longitudinal study of London adolescents in the SCAMP cohort.

Environ Int

September 2024

Department of Epidemiology and Biostatistics, School of Public Health, Imperial College London, UK; MRC Centre for Environment and Health, School of Public Health, Imperial College London, UK; Mohn Centre for Children's Health and Wellbeing, School of Public Health, Imperial College London, UK; NIHR HPRU in Environmental Exposures and Health, School of Public Health, Imperial College London, UK; NIHR HPRU in Chemical and Radiation Threats and Hazards, School of Public Health, Imperial College London, UK. Electronic address:

Background: There is increasing evidence that air pollution and noise may have detrimental psychological impacts, but there are few studies evaluating adolescents, ground-level ozone exposure, multi-exposure models, or metrics beyond outdoor residential exposure. This study aimed to address these gaps.

Methods: Annual air pollution and traffic noise exposure at home and school were modelled for adolescents in the Greater London SCAMP cohort (N=7555).

View Article and Find Full Text PDF

Background: Best practice of infection prevention and control (IPC) is a hallmark for the patient care in health care settings, but it is a major problem in developing countries like Ethiopia where resources are limited. Ethiopia Federal Ministry of Health working to strengthen its IPC program, but still it there is no organized study conducted on assessment of performance gaps and implementation challenges of IPC practice faced by hospital staffs particularly among sanitary workers (SWs) at public hospitals inline to national and international guidelines.

Aim: This study focuses on compliance and determinants of IPC among sanitary worker in public hospitals in eastern Ethiopia: A cross sectional study design.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!