Integrating Heterogeneous omics Data via Statistical Inference and Learning Techniques

Ahmad, Ashar; Fröhlich, Holger

doi:10.18547/gcb.2016.vol2.iss1.e32

Cited by 20 publications

(14 citation statements)

References 77 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This aspect is in turn widely believed to be key for enhancing the prediction performance of stratification algorithms up to a level that is useful for clinical practice. Accordingly, there has been a lot of work in methods that combine data from different (omics-) modalities, see [ 49 ] for a review.…”

Section: What Is Possible Today?mentioning

confidence: 99%

From hype to reality: data science enabling personalized medicine

Fröhlich

Balling

Beerenwinkel

et al. 2018

BMC Med

Self Cite

324

256

View full text Add to dashboard Cite

BackgroundPersonalized, precision, P4, or stratified medicine is understood as a medical approach in which patients are stratified based on their disease subtype, risk, prognosis, or treatment response using specialized diagnostic tests. The key idea is to base medical decisions on individual patient characteristics, including molecular and behavioral biomarkers, rather than on population averages. Personalized medicine is deeply connected to and dependent on data science, specifically machine learning (often named Artificial Intelligence in the mainstream media). While during recent years there has been a lot of enthusiasm about the potential of ‘big data’ and machine learning-based solutions, there exist only few examples that impact current clinical practice. The lack of impact on clinical practice can largely be attributed to insufficient performance of predictive models, difficulties to interpret complex model predictions, and lack of validation via prospective clinical trials that demonstrate a clear benefit compared to the standard of care. In this paper, we review the potential of state-of-the-art data science approaches for personalized medicine, discuss open challenges, and highlight directions that may help to overcome them in the future.ConclusionsThere is a need for an interdisciplinary effort, including data scientists, physicians, patient advocates, regulatory agencies, and health insurance organizations. Partially unrealistic expectations and concerns about data science-based solutions need to be better managed. In parallel, computational methods must advance more to provide direct benefit to clinical practice.

show abstract

Section: What Is Possible Today?mentioning

confidence: 99%

From hype to reality: data science enabling personalized medicine

Fröhlich

Balling

Beerenwinkel

et al. 2018

BMC Med

Self Cite

324

256

View full text Add to dashboard Cite

show abstract

“…Multi-modal data fusion is a field of active research, and there is not a universal best performing approach. In the data science literature classically three general strategies for multi-modal data fusion are distinguished 98 , 99 , see Ahmad and Fröhlich 100 for a more extensive review 100 . Early data fusion methods focus on extraction of common features from several data modalities, resulting into one integrated data matrix.…”

Section: Methodsmentioning

confidence: 99%

Using Multi-Scale Genetic, Neuroimaging and Clinical Data for Predicting Alzheimer’s Disease and Reconstruction of Relevant Biological Mechanisms

Khanna

Domingo‐Fernándéz

Iyappan

et al. 2018

Sci Rep

Self Cite

View full text Add to dashboard Cite

Alzheimer’s Disease (AD) is among the most frequent neuro-degenerative diseases. Early diagnosis is essential for successful disease management and chance to attenuate symptoms by disease modifying drugs. In the past, a number of cerebrospinal fluid (CSF), plasma and neuro-imaging based biomarkers have been proposed. Still, in current clinical practice, AD diagnosis cannot be made until the patient shows clear signs of cognitive decline, which can partially be attributed to the multi-factorial nature of AD. In this work, we integrated genotype information, neuro-imaging as well as clinical data (including neuro-psychological measures) from ~900 normal and mild cognitively impaired (MCI) individuals and developed a highly accurate machine learning model to predict the time until AD is diagnosed. We performed an in-depth investigation of the relevant baseline characteristics that contributed to the AD risk prediction. More specifically, we used Bayesian Networks to uncover the interplay across biological scales between neuro-psychological assessment scores, single genetic variants, pathways and neuro-imaging related features. Together with information extracted from the literature, this allowed us to partially reconstruct biological mechanisms that could play a role in the conversion of normal/MCI into AD pathology. This in turn may open the door to novel therapeutic options in the future.

show abstract

“…Bayesian method is preferred when the analysis requires integrating known knowledge (ie, pathway or network structure) 45 but it requires larger computer memories and can be time-consuming to achieve better precisions in the estimation.…”

Section: Bayesian Versus Non-bayesian Computationmentioning

confidence: 99%

Review of Statistical Learning Methods in Integrated Omics Studies (An Integrated Information Science)

Zeng

Lumley

2018

Bioinform Biol Insights

View full text Add to dashboard Cite

Integrated omics is becoming a new channel for investigating the complex molecular system in modern biological science and sets a foundation for systematic learning for precision medicine. The statistical/machine learning methods that have emerged in the past decade for integrated omics are not only innovative but also multidisciplinary with integrated knowledge in biology, medicine, statistics, machine learning, and artificial intelligence. Here, we review the nontrivial classes of learning methods from the statistical aspects and streamline these learning methods within the statistical learning framework. The intriguing findings from the review are that the methods used are generalizable to other disciplines with complex systematic structure, and the integrated omics is part of an integrated information science which has collated and integrated different types of information for inferences and decision making. We review the statistical learning methods of exploratory and supervised learning from 42 publications. We also discuss the strengths and limitations of the extended principal component analysis, cluster analysis, network analysis, and regression methods. Statistical techniques such as penalization for sparsity induction when there are fewer observations than the number of features and using Bayesian approach when there are prior knowledge to be integrated are also included in the commentary. For the completeness of the review, a table of currently available software and packages from 23 publications for omics are summarized in the appendix.

show abstract

Integrating Heterogeneous omics Data via Statistical Inference and Learning Techniques

Cited by 20 publications

References 77 publications

From hype to reality: data science enabling personalized medicine

From hype to reality: data science enabling personalized medicine

Using Multi-Scale Genetic, Neuroimaging and Clinical Data for Predicting Alzheimer’s Disease and Reconstruction of Relevant Biological Mechanisms

Review of Statistical Learning Methods in Integrated Omics Studies (An Integrated Information Science)

Contact Info

Product

Resources

About