Survival-supervised latent Dirichlet allocation models for genomic analysis of time-to-event outcomes

Two challenging problems in the clinical study of cancer are the characterization of cancer subtypes and the classification of individual patients according to those subtypes. Statistical approaches addressing these problems are hampered by population heterogeneity and challenges inherent in data integration across high-dimensional, diverse covariates. We have developed a survival-supervised latent Dirichlet allocation (survLDA) modeling framework to address these concerns. LDA models have proven extremely effective at identifying themes common across large collections of text, but applications to genomics have been limited. Our framework extends LDA to the genome by considering each patient as a `document' with `text' constructed from clinical and high-dimensional genomic measurements. We then further extend the framework to allow for supervision by a time-to-event response. The model enables the efficient identification of collections of clinical and genomic features that co-occur within patient subgroups, and then characterizes each patient by those features. An application of survLDA to The Cancer Genome Atlas (TCGA) ovarian project identifies informative patient subgroups that are characterized by different propensities for exhibiting abnormal mRNA expression and methylations, corresponding to differential rates of survival from primary therapy.

• Publication year

  2012

• Venue

  arXiv: Methodology

• Publication date

  2012-02-27

• Fields of study

  Biology, Medicine, Computer Science, Mathematics

• Identifiers
  arXiv 1202.5999
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Retinoid X receptor alpha (RXRα) and peroxisome proliferator-activated receptor gamma (PPARγ) expression in breast cancer: an immunohistochemical study.

  2012cited by this paper
• Expression analysis of mitotic spindle checkpoint genes in breast carcinoma: role of NDC80/HEC1 in early breast tumorigenicity, and a two-gene signature for aneuploidy

  2011cited by this paper
• Integrated Genomic Analyses of Ovarian Carcinoma

  2011cited by this paper
• Combining multiple models with survival data: the PHASE algorithm

  2010cited by this paper
• Pathway analysis using random forests with bivariate node-split for survival outcomes

  2010cited by this paper
• An Integrative Pathway-based Clinical-genomic Model for Cancer Survival Prediction.

  2010cited by this paper
• Latent Dirichlet Allocation

  2009cited by this paper
• Latent Dirichlet Allocation with Topic-in-Set Knowledge

  2009cited by this paper
• INTS6/DICE1 inhibits growth of human androgen-independent prostate cancer cells by altering the cell cycle profile and Wnt signaling

  2009cited by this paper
• Survival Prediction and Gene Identification with Penalized Global AUC Maximization

  2009influential reference
• Sparse canonical correlation analysis, with applications to genomic data

  2009cited by this paper
• Integrating Biological Knowledge with Gene Expression Profiles for Survival Prediction of Cancer

  2009influential reference
• Graphical Models, Exponential Families, and Variational Inference

  2008cited by this paper
• Core Signaling Pathways in Human Pancreatic Cancers Revealed by Global Genomic Analyses

  2008cited by this paper
• Novel Molecular Subtypes of Serous and Endometrioid Ovarian Cancer Linked to Clinical Outcome

  2008cited by this paper
• Latent dirichlet allocation in web spam filtering

  2008cited by this paper
• Fast collapsed gibbs sampling for latent dirichlet allocation

  2008cited by this paper
• Nonparametric pathway-based regression models for analysis of genomic data.

  2007cited by this paper
• A gene expression bar code for microarray data

  2007influential reference
• Supervised Topic Models

  2007influential reference
• MCLUST Version 3 for R: Normal Mixture Modeling and Model-Based Clustering †

  2007cited by this paper
• Hierarchical Dirichlet Processes

  2006cited by this paper
• Partial Cox regression analysis for high-dimensional microarray gene expression data

  2004cited by this paper
• Dimension reduction methods for microarrays with application to censored survival data

  2004cited by this paper
• Truncated product method for combining P‐values

  2002cited by this paper
• Supervised clustering of genes

  2002cited by this paper
• Model-Based Clustering, Discriminant Analysis, and Density Estimation

  2002cited by this paper
• Kernel Cox Regression Models for Linking Gene Expression Profiles to Censored Survival Data

  2002influential reference
• An Introduction to Variational Methods for Graphical Models

  1999cited by this paper
• A high-risk lesion for invasive breast cancer, ductal carcinoma in situ, exhibits frequent overexpression of retinoid X receptor.

  1998cited by this paper
• Mutations in the arginine-rich protein gene (ARP) in pancreatic cancer

  1997cited by this paper
• Mutations in the arginine-rich protein gene, in lung, breast, and prostate cancers, and in squamous cell carcinoma of the head and neck.

  1996cited by this paper
• Heterogeneity in survival analysis.

  1988cited by this paper
• Covariance analysis of censored survival data.

  1974cited by this paper
• Regression Models and Life-Tables

  1972cited by this paper
• Regression Models and Life-Tables

  year unknowninfluential reference

• Recent Advancements in Topic Modeling Techniques for Healthcare, Bioinformatics, and Other Potential Applications

  2026cites this paper
• Enabling near real time use of wildlife necropsy data: Text-mining approaches to derive interactive dashboard displays

  2025cites this paper
• Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

  2025cites this paper
• MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records

  2023cites this paper
• Machine learning analysis of topic modeling re-ranking of clinical records

  2020cites this paper
• Neural topic models with survival supervision: Jointly predicting time-to-event outcomes and learning how clinical features relate

  2020influential citation
• Artificial Intelligence in Medicine - 18th International Conference on Artificial Intelligence in Medicine, AIME 2020, Minneapolis, MN, USA, August 25-28, 2020, Proceedings

  2020cites this paper
• Gene expression based survival prediction for cancer patients—A topic modeling approach

  2019cites this paper
• Temporal Comorbidity-Adjusted Risk of Emergency Readmission (T-CARER): A tool for comorbidity risk assessment

  2019cites this paper
• Survival Prediction using Gene Expression Data - A Topic Modeling Approach

  2017cites this paper
• Fuzzy Approach Topic Discovery in Health and Medical Corpora

  2017cites this paper
• Survival-Supervised Topic Modeling with Anchor Words: Characterizing Pancreatitis Outcomes

  2017cites this paper
• An overview of topic modeling and its current applications in bioinformatics

  2016cites this paper
• Biomedical Text Mining: State-of-the-Art, Open Problems and Future Challenges

  2014cites this paper
• Journal of Biomedical Informatics

  year unknowncites this paper