Using machine learning approaches for multi-omics data analysis: A review
Open accessAbstract
With the development of modern high-throughput omic measurement platforms, it has become essential for biomedical studies to undertake an integrative (combined) approach to fully utilise these data to gain insights into biological systems. Data from various omics sources such as genetics, proteomics, and metabolomics can be integrated to unravel the intricate working of systems biology using machine learning-based predictive algorithms. Machine learning methods offer novel techniques to integrate and analyse the various omics data enabling the discovery of new biomarkers. These biomarkers have the potential to help in accurate disease prediction, patient stratification and delivering of precision medicine. This review paper explores different integrative machine learning methods which have been used to provide an in-depth understanding of biological systems during normal physiological functioning and in the presence of a disease. It provides insight and recommendations for interdisciplinary professionals who envisage employing machine learning skills in multi-omics studies.
AI snapshot
Written from the paper’s full text.
TL;DR
This review surveys machine learning approaches for integrating multi-omics data, organizing methods into concatenation-, model-, and transformation-based strategies for supervised and unsupervised learning. It provides background, application examples, challenges, and a recommendation flowchart for interdisciplinary method selection.
Key findings
- Multi-omics integration methods are grouped into three main classes: concatenation-based, model-based, and transformation-based, each with distinct advantages and disadvantages for combining omics data.
- The review reports that most multi-omics studies focus on cancer, especially breast and ovarian cancer, and that integration can improve understanding of disease complexity beyond single-omics analysis.
- It cites examples including an ADNI study using neuroimaging, biochemical, and genetic biomarkers to discriminate early Alzheimer’s patients from healthy volunteers with 98% accuracy, and notes class imbalance examples such as primary hypertension at 95% prevalence versus endocrine hypertension at 5%.
- A recommendation flowchart is proposed to help interdisciplinary teams choose an appropriate integration method, but the paper states that no “one-size-fits-all” approach is feasible.
Methods
- Narrative review of supervised and unsupervised ML strategies for multi-omics integration, explicitly excluding reinforcement, hybrid, multi-view, and self-supervised learning because they have not gained enough momentum in multi-omics analysis.
- Summarizes integration methods, published multi-omics studies, ML terminology, algorithms, and advantages/disadvantages in tables, and presents a recommendation flowchart.
- No primary dataset or experimental analysis is reported; the paper synthesizes existing literature and examples.
Limitations
- The authors state that existing literature does not provide many direct comparisons between methods using the same publicly available datasets, and that empirical investigation guided by ML practitioners is recommended.
- The review’s scope excludes several emerging ML specializations, including reinforcement, hybrid, multi-view, and self-supervised learning.
- Evident from the text: this is a narrative review without a systematic search protocol or quantitative synthesis, and the provided version is a journal pre-proof with production artifacts.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 164 cited sources checked · 0 supported · 0 flagged
- Findingcitation
Commonly used machine learning algorithms differ in their attributes.
“The commonly used ML algorithms have different attributes (Table 4) and therefore it is crucial to choose an appropriate algorithm for the multi-omics analysis.”
Quote in the paperSubstantial claim0 of 3 sources checked - Findingown data
Most multi-omics studies focus on different forms of cancer.
“It is evident from Table 8 that most of the multi-omics studies focus on different forms of cancer.”
Quote in the paperNot a substantial claim - Findingnone given
Many intra-omics studies have successfully explored integration of gene expression and DNA methylation.
“Many intra-omics studies have successfully explored the integration of gene expression and DNA methylation.”
Quote in the paperNot a substantial claim - Premisecitation
Many multi-omic reviews concentrate on narrow sub-topics, including study design, workflows, software selection, and overfitting evaluation.
“Currently, many of the multi-omic reviews are focussed on individual sub-topics.For example, designing studies (Haas et al., 2017;Hasin et al., 2017), setting up workflows (Kohl et al., 2014), choosing software tools (Misra et al., 2019) and evaluating overfitted performance (McCabe et al., 2020).”
Quote in the paperSubstantial claim0 of 3 sources checked - Premisecitation
Patient clinical and omics data, as part of health-related big data, is now more widely accessible.
“Health-based big data including linked information for patients, such as their clinical data (for example gender, age, pathological and physiological history) and omics data (such as genetics, proteomics and metabolomics) has now become more widely available (Canuel et al., 2015;Singhal et al., 2016).”
Quote in the paperSubstantial claim0 of 2 sources checked
- Premisecitation
Precision medicine has grown greatly with support from machine learning and data mining tools.
“There has been unprecedented growth in the development of precision medicine supported by ML (machine learning) approaches (Delavan et al., 2017;Peterson et al., 2013;Zou et al., 2017) and data mining tools (Chawla and Davis, 2013;Cheng et al., 2015;Margolies et al., 2016).”
Quote in the paperNot a substantial claim0 of 3 sources checked - Premisecitation
High-throughput omics data has been central to developing precision medicine biomarkers for Alzheimer's, diabetes, cancer, hypertension, cardiovascular and chronic respiratory diseases.
“High-throughput generated omics data (Lightbody et al., 2019) has played a pivotal role in developing precision medicine biomarkers for diseases such as Alzheimer's (Hampel et al., 2017(Hampel et al., , 2016;;Kovacs, 2016), diabetes (Capobianco, 2017;McCarthy, 2017;Mutie et al., 2017), cancer (Borad and LoRusso, 2017;Senft et al., 2017), hypertension (Barnes et al., 2016;Dominiczak et al., 2017),”
Quote in the paperNot a substantial claim0 of 3 sources checked - Premisecitation
Deep learning has improved classifier performance over traditional machine learning, particularly for large, high-dimensional datasets.
“It has pushed the performance of classifiers beyond that of traditional ML algorithms, especially in scenarios involving large-scale datasets with high dimensionality.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites LeCun et al., 2015 source
Not checked in the free run.
- Premisecitation
Health data of this kind has been applied in precision medicine to deliver customised care.
“Recently, such data has been used for precision (also called personalised or stratified) medicine to provide customised healthcare, i.e. providing a bespoke treatment for individuals (Gibson et al., 2015;Kalaitzopoulos, 2016;Malod-Dognin et al., 2017).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Gibson et al., 2015
Not checked in the free run.
- cites Kalaitzopoulos, 2016
Not checked in the free run.
- cites Malod-Dognin et al., 2017
Not checked in the free run.
- Premisecitation
For some single omics, such as gene data, machine learning performance can be worse because of intrinsic properties.
“However, ML may have deteriorated performance for certain single omics such as gene data due to inherent characteristics (Kim et al., 2020).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Kim et al., 2020 source
Not checked in the free run.
- Premisecitation
Machine learning is now used on multi-omics data to study and interpret links between data and phenotypes.
“ML methods are now also being applied to with multi-omics data (Bersanelli et al., 2016), to investigate and interpret the relationships between data and phenotypes (Kim and Tagkopoulos, 2018).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Bersanelli et al., 2016 source
Not checked in the free run.
- cites Kim and Tagkopoulos, 2018
Not checked in the free run.
- Premisecitation
Most FDA-approved and CE-marked machine learning products are in radiology.
“A recent in-depth analysis by Muehlematter showed most of the FDA approved and -Conformité Européenne”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Muehlematter et al., 2021
Not checked in the free run.
- Premisecitation
Transparency and explainability are key issues that hinder clinical deployment of machine learning methods.
“One of the key issue which hinders the clinical deployment of ML methods is transparency and explainability (Black box medicine and transparency, 2020).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Black box medicine and transparency, 2020
Not checked in the free run.
- Premisecitation
In disease classification, rarer disease classes can create class imbalance in multi-omics datasets.
“In disease classification, certain disease classes are rarer than others which can cause a class imbalance in the multi-omics dataset (Haas et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Haas et al., 2017 source
Not checked in the free run.
- Premisenone given
Most machine learning algorithms need substantial computation power and large storage capacity.
“Most ML algorithms require high computation power and large volumes of storage capacity to save the logs, results and analysis.”
Quote in the paperNot a substantial claim - Premisenone given
Most of these reviews use a systematic workflow that evaluates several algorithms at the same time on a common dataset.
“Most of them use a systematic workflow which involves simultaneous performance evaluation of different algorithms using a common dataset.”
Quote in the paperNot a substantial claim - Premisecitation
Multi-omic data from different high-throughput sources are typically heterogeneous.
“Multi-omic data from different high-throughput sources are usually heterogeneous (Bersanelli et al., 2016).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Bersanelli et al., 2016 source
Not checked in the free run.
- Premisecitation
Some omics types are more likely to produce sparse data than others.
“Also, some omics are more prone to generating sparse data (e.g. in the case of metabolomics, some values might be below the limit of detection and hence assigned null value (Antonelli et al., 2019)) than others.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Antonelli et al., 2019 source
Not checked in the free run.
- Premisecitation
Very few machine learning multi-omics publications have been translated into clinical practice.
“Still, only very few have been translated into clinical practice, for example, Idx (diabetic retinopathy detection), FerriSmart (measure liver iron concentration) and SubtleMR (image processing software for radiology) (Benjamens et al., 2020;Hamamoto et al., 2020).”
Quote in the paperSubstantial claim0 of 2 sources checked - Premisecitation
Most multi-omics datasets have the curse of dimensionality, with far fewer samples than features.
“Most multi-omics datasets suffer from the classical ‗curse of dimensionality' problem, i.e. having much fewer observation samples (n) than multi-omics features (p) (Misra et al., 2019).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Misra et al., 2019 source
Not checked in the free run.
- Premisecitation
The resulting high-dimensional space often contains correlated, redundant features that can mislead algorithm training.
“The resulting high-dimensional space often contains correlated features which are redundant and can mislead the algorithm training (James et al., 2017).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites James et al., 2017
Not checked in the free run.
- Premisenone given
A machine learning model trained on an imbalanced dataset can become overfitted, showing high training accuracy but poor performance on unseen test data.
“The ML model trained using an imbalanced dataset may be overfitted i.e. high accuracy for training data but underperformance for unseen test data.”
Quote in the paperNot a substantial claim - Premisecitation
Most current literature applies deep learning to large-scale multi-omics datasets from open sources such as TCGA, CCLE and GDSC for cancer prognosis and anti-cancer drug response.
“This fact is reinforced by the evidence that most of the current literature employs deep learning on large-scale multi-omics datasets from open sources such as TCGA 3 , CCLE 4 and GDSC 5 for cancer prognosis (Poirion et al., 2018;Seal et al., 2020;Tong et al., 2020;Lee et al., 2020;Zhu et al., 2020) and anti-cancer drug response (Sharifi-Noghabi et al., 2019;Li et al., 2019;Deng et al., 2020).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Poirion et al., 2018
Not checked in the free run.
- cites Seal et al., 2020 source
Not checked in the free run.
- cites Tong et al., 2020
Not checked in the free run.
- Premisecitation
Applying machine learning to multi-omics analysis incurs computational and data storage costs.
“The use of ML for multi-omics analysis comes with computational and data storage cost (Herrmann et al., 2020).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Herrmann et al., 2020
Not checked in the free run.
- Premisecitation
Feature extraction and feature selection can reduce the dimensionality of the data space.
“The dimensional space of the data can be reduced by employing dimensionality reduction techniques such as feature extraction and feature selection.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Jolliffe, 2002
Not checked in the free run.
- cites Martinez and Kak, 2001 source
Not checked in the free run.
- cites Guyon and Elisseeff, 2003
Not checked in the free run.
- Interpretationreasoning
Multi-omics studies are difficult to deploy because they need specialised high-throughput omics infrastructure.
“This is because multi-omics studies are challenging to deploy as they require specialised high-throughput omic infrastructure (as highlighted earlier in section 2).”
Quote in the paperNot a substantial claim - Premisecitation
iCluster was demonstrated using copy number, mRNA expression and methylation data for cancer subtype discovery in glioblastoma.
“They showed the functioning of the framework by using copy number, mRNA expression and methylation data to conduct a cancer subtype discovery in glioblastoma.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shen et al., 2009 source
Not checked in the free run.
- Premisecitation
Deep learning methods have been adopted for model-based supervised learning.
“Deep learning methods have also been adopted for model-based supervised learning (Poirion et al., 2020).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Poirion et al., 2020
Not checked in the free run.
- Premisecitation
A joint matrix of multi-omics features including gene expression, copy number variation and mutation was used with random forest and support vector machine to predict anti-cancer drug response.
“For example, a joint matrix of multi-omics features (which included gene expression, copy number variation and mutation) was used with classical RF and SVM to predict anti-cancer drug response (Stetson et al., 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Stetson et al., 2014 source
Not checked in the free run.
- Premisecitation
In the literature, concatenated multi-omics data in a joint matrix is used as input to classical machine learning methods such as decision trees, naive Bayes, artificial neural networks, support vector machines, k-nearest neighbours, random forests and K-Star.
“The concatenated multi-omics data (in the form of a joint matrix) is provided as input to different classical ML methods such as DT (decision tree) (Quinlan, 1993), NB (naive Bayes) (Domingos and Pazzani, 1997), ANN (artificial neural networks) (Bishop, 1995), SVM (support vector machine) (Vapnik, 1995), KNN (k-nearest neighbors) (Altman, 1992), RF (random forest) (Breiman, 2001) and K-Star (Cle”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Kim and Tagkopoulos, 2018
Not checked in the free run.
- cites Lin and Lane, 2017
Not checked in the free run.
- cites Auslander et al., 2016 source
Not checked in the free run.
- Premisecitation
Boosted trees and support vector regression have been studied for finding longitudinal predictors of glycaemic health.
“Also, Boosted trees (Elith et al., 2008) and SVR (support vector regression) (Awad and Khanna, 2015) have been investigated for finding the longitudinal predictors of glycaemic health (L et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Elith et al., 2008 source
Not checked in the free run.
- cites Awad and Khanna, 2015
Not checked in the free run.
- cites L et al., 2018
Not checked in the free run.
- Premisecitation
Deep neural networks have been widely used to analyse concatenated multi-omics data.
“Other than classical ML algorithms, deep neural networks (Tang et al., 2019) have also been widely used to analyse concatenated multi-omics data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Tang et al., 2019 source
Not checked in the free run.
- Premisecitation
MoCluster used multi-block multivariate analysis to highlight patterns across input omics and find joint clusters.
“The MoCluster proposed by Meng (Meng et al., 2016a), used multi-block multivariate analysis for highlighting the patterns across different input omics data and then finds the joint clusters amongst them.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Meng et al., 2016a
Not checked in the free run.
- Premisecitation
Deep neural networks have been studied to identify robust survival subgroups of liver cancer using RNA, miRNA and methylation data.
“They have been studied to identify robust survival subgroups of liver cancer using RNA, miRNA and methylation data (Chaudhary et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Chaudhary et al., 2017
Not checked in the free run.
- Premisecitation
iCluster+ offered a significant enhancement over iCluster.
“Later, the iCluster+ framework by Mo (Mo et al., 2013), offered a significant enhancement over iCluster framework.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2013
Not checked in the free run.
- Premisecitation
JBF improved the sparsity problem in JIVE.
“The sparsity problem in JIVE was improved by JBF (Joint Bayes Factor) (Ray et al., 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ray et al., 2014 source
Not checked in the free run.
- Premisecitation
MOFA can integrate partially overlapping datasets.
“It can integrate partially overlapping datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Argelaguet et al., 2018 source
Not checked in the free run.
- Premisecitation
Different concatenation-based supervised learning methods have been used to predict phenotypes.
“Different concatenation-based supervised learning methods have been used for phenotypic prediction.”
Quote in the paperNot a substantial claim - Premisecitation
Joint NMF decomposes the joint matrix into loadings and factors, bringing different omics into a common basis matrix.
“It involved decomposing the joint matrix into loadings and factors, bringing the different omics into a common basis matrix.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zhang et al., 2012 source
Not checked in the free run.
- Premisereasoning
The main advantage of concatenation-based methods is that machine learning can be applied simply to continuous or categorical data after all individual omics are concatenated.
“The main advantage of using concatenation-based methods is the simplicity of employing ML for analysing continuous or categorical data, once the concatenation of all individual omics is completed.”
Quote in the paperNot a substantial claim - Premisereasoning
Model-based integration approaches facilitate understanding of interactions among different omics for a certain phenotype.
“Model-based integration approaches facilitate the understanding of interactions amongst different omics for a certain phenotype (for example, survival in pancreatic cancer).”
Quote in the paperSubstantial claim - Premisecitation
iCluster+ was demonstrated by combining genomic data from colorectal cancer datasets.
“and was demonstrated by combining genomic data from the colorectal cancer datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2013
Not checked in the free run.
- Premisecitation
Model-based integration methods can merge models based on different omic types, where each model is developed from a different patient group with the same disease information.
“The major advantage of model-based integration methods is that they can be used for merging models based on different omic types, where each model is developed from a different patient group having the same disease information (He et al., 2016;Ritchie et al., 2015).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites He et al., 2016
Not checked in the free run.
- cites Ritchie et al., 2015 source
Not checked in the free run.
- Premisecitation
MOFA disentangles heterogeneity shared across different omics to discover the principal source of variability.
“Also, Argelaguet (Argelaguet et al., 2018) have developed MOFA (Multi-Omics Factor Analysis) which disentangles the heterogeneity shared across different omics to discover the principal source of variability.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Argelaguet et al., 2018 source
Not checked in the free run.
- Premisecitation
Joint NMF was proposed to integrate multi-omics data with non-negative values.
“Joint NMF (non-negative matrix factorisation) (Zhang et al., 2012) was proposed to integrate multi-omics data with non-negative values.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zhang et al., 2012 source
Not checked in the free run.
- Premisecitation
iCluster was employed in a study using genomic and transcriptomic data from 2,000 breast tumours that discovered novel subgroups.
“This framework was also employed for a landmark study which used genomic and transcriptomic data from 2,000 breast tumours and discovered novel subgroups amongst them (Curtis et al., 2012).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curtis et al., 2012 source
Not checked in the free run.
- Premisecitation
rMKL-LPP used an individual kernel for each omics with a graph embedding framework to identify biologically meaningful subgroups for five cancer types.
“It used an individual kernel for each omics along with graph embedding framework to identify biologically meaningful subgroups for five different cancer types.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Speicher and Pfeifer, 2015
Not checked in the free run.
- Premisecitation
HI-DFNForest uses a stacked auto-encoder to learn high-level representations from three omic datasets.
“Also, HI-DFNForest (hierarchical integration deep flexible neural forest) framework (J.Xu et al., 2019) was developed which uses stacked auto-encoder (Vincent et al., 2010) to learn high-level representations from three omic datasets.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites J.Xu et al., 2019
Not checked in the free run.
- cites Vincent et al., 2010
Not checked in the free run.
- Premisecitation
PSDF is a non-parametric Bayesian model for clustering prognostic cancer subtypes by combining gene expression and copy number variation data.
“PSDF (Patient-Specific Data Fusion) (Yuan et al., 2011) is a non-parametric Bayesian model for clustering prognostic cancer subtypes by combining gene expression and copy number variation data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yuan et al., 2011 source
Not checked in the free run.
- Premisecitation
Chaudhary used autoencoders with SVM for survival prediction in hepatocellular carcinoma subgroups.
“Similarly, Chaudhary (Chaudhary et al., 2017) has used autoencoders along with SVM for survival prediction in subgroups of hepatocellular carcinoma.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Chaudhary et al., 2017
Not checked in the free run.
- Premisecitation
Yan provided an extensive comparison of graph- and kernel-based integration approaches in supervised learning using standardised test datasets.
“Yan (Yan et al., 2017) provide an extensive comparison between different graph-and kernel-based integration approaches in a supervised learning context using various standardised test datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yan et al., 2017 source
Not checked in the free run.
- Premisecitation
NEMO can work on partial datasets without imputation where measurements are available for only a subset of omics.
“It can work on partial data sets (no imputation needed), where measurements are only available for a subset of omics data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Rappoport and Shamir, 2019 source
Not checked in the free run.
- Premisecitation
MORONET uses graph convolutional networks leveraging omics features and patient associations from similarity networks for better classification.
“Recently, MORONET (Multi-Omics gRaph cOnvolutional NETworks) (Wang et al., 2020) is introduced, which use graph convolutional networks taking benefit of the omics features and the associations among patients (as defined by the patient similarity networks) for better classification results.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al., 2020
Not checked in the free run.
- Premisecitation
fMKL-DR has been used with SVM for combining gene expression, miRNA expression, and DNA methylation data.
“Moreover, fMKL-DR (fast multiple kernel learning for dimensionality reduction) (Giang et al., 2020) has been used along with SVM for combining gene expression, miRNA expression, and DNA methylation data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Giang et al., 2020 source
Not checked in the free run.
- Premisecitation
Lee proposed a deep learning-based auto-encoding approach for integrating four omics to create a survival prediction model.
“Lee (Lee et al., 2020) has proposed a deep learning-based auto-encoding approach for integrating four omics to create a survival prediction model.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lee et al., 2020 source
Not checked in the free run.
- Premisecitation
CONEXIC uses a Bayesian network to integrate gene expression and copy number variation from tumour samples to identify driver mutations.
“Similarly, CONEXIC (Akavia et al., 2010) also uses a BN to integrate gene expression and copy number variation from tumour samples to identify driver mutations.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Akavia et al., 2010 source
Not checked in the free run.
- Premisecitation
SNF combines mRNA expression, DNA methylation and miRNA expression data from cancer datasets.
“It combines mRNA expression, DNA methylation and microRNA (miRNA) expression data from cancer datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al., 2014 source
Not checked in the free run.
- Premisecitation
PAMOGK used somatic mutations, transcriptomics and proteomics data to find subgroups of kidney cancer.
“It used somatic mutations, transcriptomics and proteomics data to find subgroups of kidney cancer.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Tepeli et al., 2019
Not checked in the free run.
- Premisecitation
PAMOGK integrates multi-omics data with pathways using a graph kernel, SmSPK.
“Similarly, PAMOGK (Tepeli et al., 2019) is developed for integrating multi-omics data with pathways using graph kernel, SmSPK (smoothed shortest path graph kernel).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Tepeli et al., 2019
Not checked in the free run.
- Premisecitation
The comparison highlights better classification performance of RVM, Ada-boost RVM and SDP-SVM compared to SSL, graph sharpening, composite network and BN.
“It highlights the better classification performance of RVM, Ada-boost RVM and SDP-SVM in comparison to SSL, graph sharpening, composite network and BN.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yan et al., 2017 source
Not checked in the free run.
- Premisenone given
Transformation-based integration methods can combine a wide range of omics if unique information such as patient ID is available.
“The primary advantage of the transformation-based integration methods is that they can be used to combine a wide range of omics if unique information (such as patient ID) is available.”
Quote in the paperNot a substantial claim - Premisecitation
Glycomics and epigenomics have only appeared once in multi-omics context, along with mRNA and metabolomics, in Zierer's study of age-related comorbidities using graphical RF.
“On the other hand, glycomics and epigenomics have only appeared once in the multi-omics context (along with mRNA and metabolomics) and used by Zierer (Zierer et al., 2016) for the study of age-related comorbidities using a graphical variant of RF.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zierer et al., 2016 source
Not checked in the free run.
- Premisecitation
SVM has been used for oral squamous cell carcinoma by integrating mRNA, miRNA and lncRNA.
“SVM has also been used for oral squamous cell carcinoma study by integrating different transcriptomics namely mRNA, miRNA and IncRNA (Li et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Li et al., 2017
Not checked in the free run.
- Premisecitation
Metabolomics and proteomics have been integrated with lipidomics to evaluate COVID-19 patients using PLS-DA and Extra Trees.
“Recently, metabolomics and proteomics have also been integrated with lipidomics to evaluate COVID-19 patients using PLS-DA (Partial Least Squares Discriminant Analysis) and Extra Trees (Overmyer et al., 2020;Thomas et al., 2020).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Overmyer et al., 2020
Not checked in the free run.
- cites Thomas et al., 2020
Not checked in the free run.
- Premisecitation
LASSO has also been employed for cancer prognosis.
“LASSO has also been employed for cancer prognosis”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zhao et al., 2015 source
Not checked in the free run.
- Classified as probably not a substantial claim. 56
- May combine two claims. 41
- The quote only partly states this claim. 1
Probably not a substantial claim: may not pass S3 (load-bearing).
FindingcitationWeb of Science publication counts show that machine learning use in medical science has grown faster over the last ten years.
“Figure 1 shows the number of publications indexed on the Web of Science website (Clarivate Analytics, 2020) with different key topics.This information was collected from the Web of Science by entering a different keyword and searching across all databases 2 .Although the use of ML in medical science can be dated back to 1970s (Davenport and Kalakota, 2019), more rapid growth is evident in the past”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Clarivate Analytics, 2020
Not checked in the free run.
- cites Davenport and Kalakota, 2019 source
Not checked in the free run.
May combine two claims.
FindingcitationPublications on multi-omics integration and on multi-omics with machine learning began appearing in the last five years and have become popular in precision and computational medicine.
“Moreover, publications based on ‗multi-omics integration' and ‗multi-omics and machine learning' have started to emerge in the last 5 years and have gained popularity in precision and computational medicine domain.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Clarivate Analytics, 2020
Not checked in the free run.
Classified as probably not a substantial claim.
Findingown dataA plethora of multi-omic integration methods are available for both supervised and unsupervised learning.
“Today a plethora of multi-omic integration methods are available for both supervised and unsupervised learning as evident in the current review.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S4 (based).
Findingnone givenExisting literature does not provide many direct comparisons between methods using the same publicly available datasets.
“Also, unfortunately, the existing literature does not provide many direct comparisons between methods using the same publicly available datasets.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationDeep learning has become the leading class of machine learning algorithms.
“Deep learning has emerged in recent years as the leading class of ML algorithms.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites LeCun et al., 2015 source
Not checked in the free run.
May combine two claims.
PremisecitationSeveral machine learning specialisations, including reinforcement, hybrid, multi-view and self-supervised learning, are appearing in general healthcare but have not yet gained sufficient traction in multi-omics analysis.
“Although various ML specialisations such as reinforcement (Coronato et al., 2020), hybrid (Zhou et al., 2019), multi-view (Zhao et al., 2017) and selfsupervised learning (Chen et al., 2019) are now emerging in generic health-care applications, they have not yet gained enough momentum in multi-omics analysis, hence they remain beyond the scope of this review.”
Quote in the paperSubstantial claim0 of 3 sources checkedMay combine two claims.
PremisecitationMulti-omics machine learning is still at an early stage, yet it has been explored across many application areas.
“Although ML analysis of multi-omics is still in its embryonic stage, it has already been explored for a wide range of applications, as reported in recent reviews on brain diseases (Garali et al., 2018;Young et al., 2013), diabetes (Kavakiotis et al., 2017), cancers (Borad and LoRusso, 2017;Chaudhary et al., 2017;Wong et al., 2016) cardiovascular disease (Weng et al., 2017), medical imaging (Ericks”
Quote in the paperSubstantial claim0 of 3 sources checkedProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationMachine learning has become popular in health sciences because computing power and high-throughput omics data are more available and AI has succeeded in many fields.
“In recent years, with the increasing availability of affordable computing power and high-throughput omics data and the success of artificial intelligence technology in various fields, the use of ML has become popular in health sciences (Lee and Yoon, 2017;Clifton et al., 2015;Hung, 2019;Barnett-Itzhaki et al., 2020;Kirchebner et al., 2020).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Lee and Yoon, 2017
Not checked in the free run.
- cites Clifton et al., 2015
Not checked in the free run.
- cites Hung, 2019 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationOmics data have recently been integrated in COVID-19 research.
“Recently, these omics have also been integrated for COVID-19 studies (Barh et al., 2020;Overmyer et al., 2020;Zhou et al., 2020).”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationTaken together, omics data give a complete view of cell biology and cellular function.
“Overall, these omics provide a complete picture of cell biology and related cellular function (Cox, 2009).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Cox, 2009 source
Not checked in the free run.
May combine two claims.
PremisecitationDeep learning is computationally demanding, needs high-throughput or high-performance hardware, and is not transparent in feature selection.
“On the other hand, it is very computationally intensive, requiring highthroughput or high-performance hardware, and lacks explainability (transparency) in feature selection (black-box approach), in the sense that it is difficult to extract from the network the features that the network has found as mainly responsible for the task, e.g.classification (LeCun et al., 2015).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites LeCun et al., 2015 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationPrimary hypertension has a prevalence of 95%, whereas endocrine hypertension has a prevalence of only 5%.
“For example, primary hypertension is the most common form of hypertension with 95% prevalence while endocrine hypertension occurs in only 5% (Rimoldi et al., 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Rimoldi et al., 2014 source
Not checked in the free run.
May combine two claims.
PremisecitationRegularisation, bagging, hyperparameter tuning and cross-validation can help balance the bias-variance trade-off.
“Similarly, techniques such as regularisation, bagging, hyperparameter tuning and cross-validation can used to balance bias-variance trade-off (Lee, 2010).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lee, 2010
Not checked in the free run.
May combine two claims.
PremisecitationOther non-machine-learning challenges affect multi-omics studies, including study design, multi-site sample collection and management, data sharing and governance, visualisation, ethical standards, reproducibility and translation.
“However, there are few other challenges related to multi-omics studies which are not ML related such as study design (Haas et al., 2017), multi-site sample collection & management (Pinu et al., 2019), multi-site data sharing and governance (Saulnier et al., 2019), visualisation (Mougin et al., 2018), ethical standards (Lévesque et al., 2018), and finally making the research reproducible (Conesa”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim: may not pass S2 (checkable). May combine two claims.
InterpretationreasoningBecause every multi-omics dataset is unique, a similar workflow could help choose the most suitable algorithm.
“Since each multi-omics dataset is unique, using a similar workflow could allow the selection of the best-suited algorithm.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisereasoningDeep learning is widely used in other areas such as medical imaging and clinical natural language processing, but its use in multi-omics analysis has been more limited.
“Although deep learning is widely popular in other related domains (such as medical imaging (Erickson et al., 2017) and clinical natural language processing (Wu et al., 2020)), the interest has been more limited for multi-omics analysis (X.Tan et al., 2020).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Erickson et al., 2017
Not checked in the free run.
- cites Wu et al., 2020
Not checked in the free run.
- cites X.Tan et al., 2020
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationMost reviews have introduced categorical terminologies to group integration methods by different factors or parameters.
“Most of these reviews have strived to introduce different categorical terminologies (for example: ‗'early', ‗late' and ‗intermediate' in (Gligorijević and Pržulj, 2015) or ‗bottom-up' and ‗top-down' in (Yu and Zeng, 2018)) which enable them to group the integration methods based on different factors/parameters.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Gligorijević and Pržulj, 2015
Not checked in the free run.
- cites Yu and Zeng, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisenone givenNew data integration methods have been introduced in recent years from mathematical, statistical and computational sciences.
“In recent years, various new data integration methods have been introduced from the modern developments in mathematical, statistical and computational sciences.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationMachine learning models can be run on dedicated graphics processing units and cloud computing platforms.
“In recent years, ML models can be deployed on dedicated graphics processing units (Schmidhuber, 2015) and cloud computing platforms (Armbrust et al., 2010) such as Amazon EC2 (-Amazon EC2,‖ n.d.), Microsoft Azure (-Cloud Computing Services | Microsoft Azure,‖ n.d.) and Google Cloud Platform (-Cloud Computing Services,‖ n.d.).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Schmidhuber, 2015
Not checked in the free run.
- cites Armbrust et al., 2010 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone givenAll the challenges discussed above directly affect the use of machine learning for multi-omics analysis.
“All the above challenges directly impact the use of ML for multi-omics analysis.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisenone givenTranscriptomics and proteomics apply different normalisation and scaling before analysis, which produces different dynamic ranges and distributions.
“For example, transcriptomics and proteomics use different normalisation and scaling techniques before omics analysis.This leads to different dynamic ranges and data distribution.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationAI-driven automated machine learning platforms and tools have appeared that can search exhaustively for the best model and parameter tuning, but they are computationally expensive.
“Recently, various artificial intelligence-driven automated ML platforms and tools (Feurer et al., 2015;Olson et al., 2018;Waring et al., 2020) have also emerged which can be utilised to exhaustively search for best ML model and corresponding parameter tuning, however, they are computationally expensive.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Feurer et al., 2015
Not checked in the free run.
- cites Olson et al., 2018
Not checked in the free run.
- cites Waring et al., 2020 source
Not checked in the free run.
May combine two claims.
PremisecitationMany machine learning multi-omics publications have appeared in the past five years, and some use decision curve and calibration analytics to assess diagnostic utility.
“Various ML based multi-omics publications have emerged in the past 5 years (see Figure 1) and some use performance metrics such as decision curve (Vickers and Elkin, 2006) and calibration (Dankers et al., 2019) analytics to evaluate their diagnostic utility.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Vickers and Elkin, 2006
Not checked in the free run.
- cites Dankers et al., 2019
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationMany reviews examine the strengths and weaknesses of different machine learning algorithms on single-omics and multi-omics datasets.
“In the literature, many reviews cover the key strengths and weaknesses of different ML algorithms using single omics (Amancio et al., 2014;López Pineda et al., 2015;Sakr et al., 2017;Uddin et al., 2019) and multi-omics (Ma et al., 2016;Francescatto et al., 2018;J. Xu et al., 2019;Sathyanarayanan et al., 2020) datasets.”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Premisenone givenJoint NMF is computationally slow and requires large memory allocation.
“Joint NMF is computationally slow and needs large memory allocation.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisecitationiCluster uses principles similar to NMF but allows integration of datasets with negative values.
“Similarly, Shen (Shen et al., 2009) proposed iCluster framework which used principles similar to NMF but allows integration of datasets having negative values.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shen et al., 2009 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationFridley studied genomic effects of gemcitabine using mRNA expression and SNP high-throughput data.
“Fridley (Fridley et al., 2012) has studied the genomic effects due to the gemcitabine drug using high-throughput data from mRNA expression and SNPs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Fridley et al., 2012 source
Not checked in the free run.
May combine two claims.
PremisecitationiCluster+ can discover patterns and combine omics with binary, categorical and continuous values.
“The iCluster+ framework can discover patterns and combine a range of omics having binary, categorical and continuous values and was demonstrated by combining genomic data from the colorectal cancer datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2013
Not checked in the free run.
May combine two claims.
PremisecitationFridley integrated mRNA expression and SNP data into one large input matrix and developed a Bayesian pathway analysis using stochastic search variable selection.
“They integrated these two datasets into one large input matrix and developed a Bayesian pathway analysis which uses a stochastic search variable selection.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Fridley et al., 2012 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConcatenation-based integration usually needs no preprocessing.
“Commonly, concatenation-based integration does not require any preprocessing and hence does not have a Stage 2.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationJBF used joint factor analysis to evaluate the feature space and converted it into shared and datatype-specific components.
“joint factor analysis to evaluate the feature space and converted it into shared and datatype-specific components.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ray et al., 2014 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationWhen the joint matrix has many features, feature selection methods can be used during concatenation.
“In scenarios where the number of features in the joint matrix are higher, different feature selection methods described in Section 3 can be employed during concatenation (Sorzano et al., 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Sorzano et al., 2014
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationMultivariate LASSO models have been studied.
“Similarly, multivariate LASSO models (Zou, 2006;Nicolai and Bühlmann Peter, 2010;Mankoo et al., 2011) have been investigated.”
Quote in the paperNot a substantial claim0 of 3 sources checkedProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationJIVE was used to investigate gene expression and miRNA data on brain tumour samples.
“It was used to investigate gene expression and miRNA data on brain tumour samples.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lock et al., 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationThe Bayesian integrative model offers better performance in detecting genomic effects than conventional single-omics analysis.
“Their proposed that the Bayesian integrative model offers better performance in detecting the genomic effects in comparison to using conventional single-omics analysis.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Fridley et al., 2012 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationiClusterBayes includes a binary indicator prior for variable selection and generalises for binary and count data.
“iClusterBayes includes a binary indicator prior for selection of variable and generalises for binary data and count data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2018
Not checked in the free run.
May combine two claims.
PremisecitationiClusterBayes overcomes iCluster+ limitations in statistical inference and computational speed.
“It overcomes the limitations of iCluster+, in terms of statistical inference and computational speed.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationZhu explored Bayesian networks to understand cell regulation in yeast using metabolomics and transcriptomics data.
“Similarly, Zhu (Zhu et al., 2012) has also explored BN (Bayesian network) to understand cell regulation in yeast using metabolomics and transcriptomics data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zhu et al., 2012 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Premisenone givenThese methods treat all concatenated features equally and can select the most discriminating features for a phenotype.
“These methods use all the concatenated features equally and can select the most discriminating features for a given phenotype.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationLRAcluster was developed to integrate high-dimensional multi-omics data and find a low-dimensional manifold to identify molecular subtypes of cancer.
“Also, LRAcluster (Wu et al., 2015) was developed to integrate high-dimensional multi-omics data and find low-dimensional manifold to identify molecular subtypes of cancer.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wu et al., 2015
Not checked in the free run.
May combine two claims.
PremisecitationMoCluster showed noticeably higher clustering accuracy and lower computation cost than Cluster and iCluster+ when validated on proteomic and transcriptomic data.
“MoCluster was validated by integrating proteomic and transcriptomic data and shows a noticeably higher clustering accuracy and lower computation cost in comparison to both Cluster and iCluster+.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Meng et al., 2016a
Not checked in the free run.
May combine two claims.
PremisecitationJIVE captures joint variation across integrated data types, structural variation of each data type, and residual noise.
“Another adaptation of NMF was evaluated as JIVE (Joint and Individual Variation Explained) which captures joint variation across integrating data types and structural variation of each data type along with the residual noise (Lock et al., 2013).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lock et al., 2013
Not checked in the free run.
May combine two claims.
PremisereasoningThe model-based approach allows analysis of improvement in predictive power for individual models and finds the best discriminating features.
“This approach allows the analysis of the improvement in the predictive power for individual models and also finds the best discriminating features.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationiClusterBayes is a fully Bayesian latent variable model.
“Recently, iClusterBayes was introduced by Mo (Mo et al., 2018), which is a fully Bayesian latent variable model.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mo et al., 2018
Not checked in the free run.
May combine two claims.
PremisecitationMOSAE was developed for pan-cancer analysis and compared with conventional ML methods such as SVM, DT, naïve Bayes, KNN, RF and AdaBoost.
“Recently, MOSAE (Multi-omics Supervised Autoencoder) (K.Tan et al., 2020) was developed for pan-cancer analysis and compared with conventional ML methods such as SVM, DT, naïve Bayes, KNN, RF and AdaBoost.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites K.Tan et al., 2020
Not checked in the free run.
May combine two claims.
InterpretationcitationKernel-based algorithms have superior performance to graph-based approaches but usually need more time for training.
“Overall, it is evident from the literature that kernel-based algorithms have superior performance to graph-based approaches, but they usually need more time for the training phase.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConcatenation-based integration ideally requires all omics data for all patients.
“Ideally, requires all omics data for all patients.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationATHENA uses grammatical evolution neural networks with Biofilter and Random Jungle to investigate categorical and quantitative variables and develop prediction models.
“It uses grammatical evolution neural networks along with Biofilter (Bush et al., 2009) and Random Jungle (Schwarz et al., 2010) to investigate different categorical and quantitative variables and develop prediction models.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Bush et al., 2009
Not checked in the free run.
- cites Schwarz et al., 2010 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConcatenation-based integration does not consider the unique distribution of each omics.
“Does not consider the unique distribution of each omics.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationLemon-Tree implemented ensemble methods for reconstructing module networks using somatic copy number alterations and gene expression in brain tumour samples.
“Lemon-Tree (Bonnet et al., 2015) implemented ensemble methods for reconstructing module networks which used somatic copy number alterations and gene expression in brain tumour samples.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Bonnet et al., 2015 source
Not checked in the free run.
May combine two claims.
PremisecitationMeta-SVM integrates multiple omics data and can detect consensus genes associated with diseases across studies such as breast cancer and idiopathic pulmonary fibrosis.
“Meta-SVM (Meta-analytic SVM) is proposed by Kim (Kim et al., 2017), which integrates multiple omics data and able to detect consensus genes associated with diseases across studies such as breast cancer and idiopathic pulmonary fibrosis.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kim et al., 2017 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationDenoising autoencoder has been incorporated with L1-penalized logistic regression for identifying ovarian cancer subtypes.
“Similarly, Denoising autoencoder has been incorporated along with L1-penalized logistic regression for identifying ovarian cancer subtypes (Guo et al., 2020).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Guo et al., 2020 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationNEMO uses an inter-patient similarity matrix-based distance metric to evaluate input omic datasets individually.
“Recently, NEMO (NEighborhood based Multi-Omics clustering) (Rappoport and Shamir, 2019) is introduced which uses an inter-patient similarity matrix-based distance metric for evaluating the input omic datasets individually.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Rappoport and Shamir, 2019 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConcatenation-based integration needs proper normalisation before concatenation.
“Need proper normalisation before concatenation.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenModel-based integration does not increase dimensional complexity.
“Does not increase dimensional complexity.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationrMKL-LPP was implemented for clustering analysis.
“Lately, rMKL-LPP (regularised multiple kernel learning for Locality Preserving Projections) (Speicher and Pfeifer, 2015) was implemented for clustering analysis.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Speicher and Pfeifer, 2015
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationMost transformation-based supervised learning methods are kernel and graph-based algorithms.
“Most of them are kernel and graph-based algorithms (Yan et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yan et al., 2017 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenModel-based integration is not effective if omics data is extremely heterogeneous.
“Not effective if omics data is extremely heterogeneous.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationATHENA was developed for analysing multi-omics data.
“In the past years, ATHENA (Analysis Tool for Heritable and Environmental Network Associations) was developed for analysing multi-omics data (Chung and Kang, 2019;Holzinger et al., 2014).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Chung and Kang, 2019
Not checked in the free run.
- cites Holzinger et al., 2014 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Premisenone givenTransformation-based graph representation is easy to understand and computationally less intensive.
“Graph representation easy to understand and computationally less intensive.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Premisenone givenModel-based integration facilitates understanding of interactions among different omics.
“Facilitates the understanding of interactions amongst different omics.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). The quote only partly states this claim.
Premisenone givenTransformation-based kernel methods provide superior performance.
“Kernel methods provide superior performance.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationPSDF uses a two-step process and limits integration to only two datatypes.
“It uses a two-step process and limits the integration to only two datatypes.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Yuan et al., 2011 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenModel-based integration allows omics data from different sets of patients with a similar phenotype.
“Omics data can be from a different set of patients with a similar phenotype.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Premisenone givenTransformation can sometimes be challenging.
“Transformation can be sometimes challenging.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationHI-DFNForest integrates learned representations to predict cancer subtype classification.
“Later, these representations are integrated to predict cancer subtype classification.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites J.Xu et al., 2019
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenConcatenation-based integration is memory and computation-intensive when the concatenated matrix is large.
“Memory and computation-intensive when the concatenated matrix is large.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
PremisecitationMOLI used type-specific encoding sub-networks to learn features from somatic mutation, CNA and gene expression data independently and then concatenated them for drug response prediction.
“MOLI (multi-omics late integration) (Sharifi-Noghabi et al., 2019) method used type-specific encoding sub-networks to learn features from somatic mutation, CNA and gene expression data independently and then later concatenated them for predicting the response to a given drug.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Sharifi-Noghabi et al., 2019 source
Not checked in the free run.
May combine two claims.
Interpretationnone givenGraph-based approaches can disclose relations between samples while taking less computation time.
“In contrast, graph-based approaches can disclose the relations between samples while taking less computation time.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenTransformation-based integration allows multi-omics data for the same patient to be used for disease subgroup analysis.
“Multi-omics data for the same patient can be used for their disease subgroup analysis.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
PremisecitationNEMO combines omics matrices into one matrix and analyses it using spectral-based clustering.
“These omics matrices are then combined into one matrix and then analysed using spectral-based clustering.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Rappoport and Shamir, 2019 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
InterpretationreasoningMany multi-omics studies related to breast and ovarian cancer highlight research thrust by the scientific community in these domains.
“In particular, the presence of many multi-omics studies related to breast (Chen et al., 2017;Lee et al., 2017;List et al., 2014;Ma et al., 2016;Nam et al., 2009) and ovarian (Anděl et al., 2015;Mankoo et al., 2011;Paik et al., 2017;Zhang et al., 2014) cancer highlights the research thrust by the scientific community in these domains.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Chen et al., 2017 source
Not checked in the free run.
- cites Anděl et al., 2015
Not checked in the free run.
May combine two claims.
PremisecitationSNF constructs networks of samples for each data type and fuses them into a joint network representing the complete range of original data.
“Furthermore, SNF (Similarity Network Fusion) (Wang et al., 2014) constructs networks of samples for respective data type and then effectively fuse them into a joint network which denotes the complete range of original data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wang et al., 2014 source
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenModel-based integration could lose weak signals.
“Weak signals could be lost.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenKernel methods are computationally more intensive than graph methods.
“Kernel methods are computationally more intensive than graph methods.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Premisenone givenModel-based integration could lead to an overfitted solution.
“Could lead to an overfitted solution”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationnone givenRecent multi-omics studies highlight superiority of integration methods in understanding disease complexity and uncovering abnormalities from multi-omics data, which is not always possible with individual omics analysis.
“Overall, the different recent multi-omics studies highlight the superiority of integration methods in understanding the complexity of different diseases and uncovering the underlying abnormalities from the vastly generated multi-omics data, which is not always possible with individual omics analysis.”
Quote in the paperSubstantial claimMay combine two claims.
PremisecitationMetabolomics and proteomics have been integrated using RF for prostate cancer and thyroid functioning.
“Metabolomics and proteomics have been integrated using RF for analysis of prostate cancer (Fan et al., 2011) and thyroid functioning (Pietzner et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checkedMay combine two claims.
PremisecitationMetabolomics is integrated with mRNA for studying ulcerative colitis and cancer survival.
“Similarly, metabolomics is integrated with mRNA for studying ulcerative colitis (Bjerrum et al., 2014) and cancer survival (Kim et al., 2014).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Bjerrum et al., 2014
Not checked in the free run.
- cites Kim et al., 2014 source
Not checked in the free run.
May combine two claims.
PremisecitationLASSO methods have been used for integrating gene expression and DNA methylation by Taskesen and Lee for acute myeloid leukaemia and breast cancer respectively.
“LASSO methods have been used for this particular integration by Taskesen (Taskesen et al., 2015) and Lee (Lee et al., 2017) for acute myeloid leukaemia and breast cancer respectively.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Taskesen et al., 2015 source
Not checked in the free run.
- cites Lee et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable).
Interpretationnone givenA one-size-fits-all approach is not feasible.
“Clearly, a ‗one-size-fits-all' approach is not feasible.”
Quote in the paperNot a substantial claimMay combine two claims.
PremisecitationMulti-omics studies have been successfully conducted in plants and animals.
“Multi-omics studies have also been successfully conducted in plants (potato (Acharjee et al., 2016(Acharjee et al., , 2011))) and animals (such as canine heart disease (Li et al., 2015)).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Acharjee et al., 2016 source
Not checked in the free run.
- cites Li et al., 2015
Not checked in the free run.
May combine two claims.
PremisecitationmRNA-miRNA integration was investigated using Neural Fuzzy Network for colorectal cancer, SVM for pancreatic cancer, and RF for cardiac tissue ageing and ovarian cancer.
“Similarly, mRNA -miRNA integration was investigated using Neural Fuzzy Network for colorectal cancer (Vineetha et al., 2013), SVM for pancreatic cancer (Kwon et al., 2015), and RF for cardiac tissue ageing (Dimitrakopoulos et al., 2014) and ovarian cancer (Anděl et al., 2015) respectively.”
Quote in the paperNot a substantial claim0 of 3 sources checked
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
With increasingly sophisticated -omics technologies, dimensionality of data increases rapidly, surpassing the number of cases, which remains similar over time (curse of dimensionality).
“With increasingly sophisticated -omics technologies, the dimensionality of data increases rapidly, thereby surpassing the number of cases, which remains similar over time. This phenomenon is described as the “curse of dimensionality”44.”
From Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging (2024) · cites this paper as [44]
Section 3.3, “More features than data (p >> n)” (page not supplied), describes the curse of dimensionality as multi-omics datasets having far fewer samples than features. It does not say that feature counts rise rapidly as technologies improve or that the number of cases remains similar over time. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Concatenation is described as both needing and not needing preprocessing
MinorSection 4.1 says concatenation-based integration commonly requires no preprocessing, but Table 6 says it needs proper normalisation before concatenation.
“Commonly, concatenation-based integration does not require any preprocessing and hence does not have a Stage 2.”
“ Need proper normalisation before concatenation.”
Model-based workflow assigns individual models to different stages
MinorThe workflow says individual omics models are developed in Stage 2 and integrated in Stage 3, but the later description places the individual omics models in Stage 3.
“The final multi-dimensional joint model in Stage 4 can be built using an ML algorithm (such as neural networks) which uses the most relevant variables from each omics models (from Stage 3).”
“In Stage 2, individual models are developed for each of the omics which are later integrated into a joint model in Stage 3.”
mRNA is classified as a microRNA despite being defined as messenger RNA
MinorThe paper expands mRNA as messenger RNA, but later places it within "microRNAs (mRNA and miRNA)."
“Similarly, transcriptomics is further classed into lncRNAs (long non-coding RNAs) and microRNAs (mRNA and miRNA).”
“mRNA (messenger ribo-nucleic acid)”
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
DNA sequencing with chain-terminating inhibitors
Sanger, F., Nicklen, S., & Coulson, A. R. (1977) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.74.12.5463 · Cited by 68,572 · see citing works
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138 · see citing works
KEGG: Kyoto Encyclopedia of Genes and Genomes
Kanehisa, M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.27 · Cited by 37,077 · see citing works
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · see citing works
KEGG: Kyoto Encyclopedia of Genes and Genomes
Ogata, H., Goto, S., Sato, K., Fujibuchi, W., Bono, H., & Kanehisa, M. (1999) · Nucleic Acids Research · doi:10.1093/nar/27.1.29 · Cited by 31,232 · see citing works
(1992) · Cited by 23,431 · see citing works
Seel, N. M. (2012) · Springer eBooks · doi:10.1007/978-1-4419-1428-6_5195 · Cited by 19,525 · see citing works
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · see citing works
Neural networks for pattern recognition
Bishop, C. (1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,537 · see citing works
Jolliffe, I. T. (2005) · Wiley eBooks · doi:10.1002/0470013192.bsa501 · Cited by 14,522 · see citing works
The Pfam Protein Families Database
Bateman, A. G. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.276 · Cited by 14,062 · see citing works
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423 · see citing works
Gene selection for cancer classification using support vector machines
Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002) · Machine Learning · doi:10.1023/a:1012487302797 · Cited by 9,954 · see citing works
Armbrust, M., Fox, A., Griffith, R., Joseph, A. D., Katz, R., Konwinski, A., Lee, G., Patterson, D., Rabkin, A., Stoica, I., et al. (2010) · Communications of the ACM · doi:10.1145/1721654.1721672 · Cited by 9,464 · see citing works
(2006) · Springer eBooks · Cited by 8,123 · see citing works
An introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,843 · see citing works
UniProt: a worldwide hub of protein knowledge
The UniProt Consortium (2019) · Nucleic Acids Research · doi:10.1093/nar/gky1049 · Cited by 7,698 · see citing works
The adaptive lasso and its oracle properties
Zou, H. (2006) · Journal of the American Statistical Association · doi:10.1198/016214506000000735 · Cited by 7,470 · see citing works
Chiang, L. H., Russell, E. L., & Braatz, R. D. (2001) · Advanced textbooks in control and signal processing · doi:10.1007/978-1-4471-0347-9_4 · Cited by 6,684 · see citing works
A working guide to boosted regression trees
Elith, J., Leathwick, J. R., & Hastie, T. (2008) · Journal of Animal Ecology · doi:10.1111/j.1365-2656.2008.01390.x · Cited by 6,484 · see citing works
Decision curve analysis: a novel method for evaluating prediction models
Vickers, A. J., & Elkin, E. B. (2006) · Medical Decision Making · doi:10.1177/0272989x06295361 · Cited by 6,341 · see citing works
The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups
METABRIC Group, Curtis, C., Shah, S. P., Chin, S.-F., Turashvili, G., Rueda, O. M., Dunning, M. J., Speed, D., Lynch, A. G., Samarajiwa, S., et al. (2012) · Nature · doi:10.1038/nature10983 · Cited by 6,097 · see citing works
An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression
Altman, N. (1992) · The American Statistician · doi:10.1080/00031305.1992.10475879 · Cited by 5,721 · see citing works
Radiomics: the bridge between medical imaging and personalized medicine
Lambin, P., Leijenaar, R. T. H., Deist, T. M., Peerlings, J., de Jong, E. E. C., van Timmeren, J., Sanduleanu, S., Larue, R. T. H. M., Even, A. J. G., Jochems, A., et al. (2017) · Nature Reviews Clinical Oncology · doi:10.1038/nrclinonc.2017.141 · Cited by 5,688 · see citing works
Lodish, H. F. (1986) · Cited by 5,640 · see citing works
ADASYN: Adaptive synthetic sampling approach for imbalanced learning
He, H., Bai, Y., Garcia, E. A., & Shutao Li, A. (2008) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2008.4633969 · Cited by 4,945 · see citing works
miRBase: from microRNA sequences to function
Kozomara, A., Birgaoanu, M., & Griffiths-Jones, S. (2019) · Nucleic Acids Research · doi:10.1093/nar/gky1141 · Cited by 4,684 · see citing works
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · see citing works
The potential for artificial intelligence in healthcare
Davenport, T., & Kalakota, R. (2019) · Future Healthcare Journal · doi:10.7861/futurehosp.6-2-94 · Cited by 3,800 · see citing works
Abe, S. (2001) · Springer eBooks · doi:10.1007/978-1-4471-0285-4 · Cited by 3,740 · see citing works
Predicting the future - big data, machine learning, and clinical medicine
Obermeyer, Z., & Emanuel, E. J. (2016) · New England Journal of Medicine · doi:10.1056/nejmp1606181 · Cited by 3,652 · see citing works
Meyer, F., Paarmann, D., D'Souza, M., Olson, R., Glass, E., Kubal, M., Paczian, T., Rodriguez, A., Stevens, R. L., Wilke, A., et al. (2008) · BMC Bioinformatics · doi:10.1186/1471-2105-9-386 · Cited by 3,565 · see citing works
Multiple imputation by chained equations: what is it and how does it work?
Azur, M. J., Stuart, E. A., Frangakis, C., & Leaf, P. J. (2011) · International Journal of Methods in Psychiatric Research · doi:10.1002/mpr.329 · Cited by 3,542 · see citing works
HMDB 4.0: the human metabolome database for 2018
Wishart, D. S., Feunang, Y. D., Marcu, A., Guo, A. C., Liang, K., Vázquez-Fresno, R., Sajed, T., Johnson, D., Li, C., Karu, N., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gkx1089 · Cited by 3,438 · see citing works
Martinez, A. M., & Kak, A. C. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.908974 · Cited by 3,249 · see citing works
Floating search methods in feature selection
Pudil, P., Novovičová, J., & Kittler, J. (1994) · Pattern Recognition Letters · doi:10.1016/0167-8655(94)90127-9 · Cited by 3,129 · see citing works
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
Domingos, P., & Pazzani, M. J. (1997) · Machine Learning · doi:10.1023/a:1007413511361 · Cited by 3,115 · see citing works
Multi-omics approaches to disease
Hasin, Y., Seldin, M., & Lusis, A. (2017) · Genome Biology · doi:10.1186/s13059-017-1215-1 · Cited by 2,953 · see citing works
The Pfam protein families database
Finn, R. D., Mistry, J., Tate, J., Coggill, P., Heger, A., Pollington, J. E., Gavin, O. L., Gunasekaran, P., Ceric, G., Forslund, K., et al. (2010) · Nucleic Acids Research · doi:10.1093/nar/gkp985 · Cited by 2,694 · see citing works
Towards a knowledge-based Human Protein Atlas
Uhlen, M., Oksvold, P., Fagerberg, L., Lundberg, E., Jonasson, K., Forsberg, M., Zwahlen, M., Kampf, C., Wester, K., Hober, S., et al. (2010) · Nature Biotechnology · doi:10.1038/nbt1210-1248 · Cited by 2,440 · see citing works
Meinshausen, N., & Bühlmann, P. (2010) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/j.1467-9868.2010.00740.x · Cited by 2,314 · see citing works
Strimbu, K., & Tavel, J. A. (2010) · Current Opinion in HIV and AIDS · doi:10.1097/coh.0b013e32833ed177 · Cited by 2,062 · see citing works
XAI—Explainable artificial intelligence
Gunning, D., Stefik, M., Choi, J., Miller, T., Stumpf, S., & Yang, G.-Z. (2019) · Science Robotics · doi:10.1126/scirobotics.aay7120 · Cited by 2,053 · see citing works
Similarity network fusion for aggregating data types on a genomic scale
Wang, B., Mezlini, A. M., Demir, F., Fiume, M., Tu, Z., Brudno, M., Haibe-Kains, B., & Goldenberg, A. (2014) · Nature Methods · doi:10.1038/nmeth.2810 · Cited by 2,036 · see citing works
Handelsman, J., Rondon, M. R., Brady, S. F., Clardy, J., & Goodman, R. M. (1998) · Chemistry & Biology · doi:10.1016/s1074-5521(98)90108-9 · Cited by 2,007 · see citing works
A Comprehensive Survey of Clustering Algorithms
Xu, D., & Tian, Y. (2015) · Annals of Data Science · doi:10.1007/s40745-015-0040-1 · Cited by 1,939 · see citing works
Neural networks for pattern recognition
Marshall, J. A. (1995) · Neural Networks · doi:10.1016/0893-6080(95)90002-0 · Cited by 1,888 · see citing works
Single-cell RNA sequencing technologies and bioinformatics pipelines
Hwang, B., Lee, J. H., & Bang, D. (2018) · Experimental & Molecular Medicine · doi:10.1038/s12276-018-0071-8 · Cited by 1,793 · see citing works
Comparing different supervised machine learning algorithms for disease prediction
Uddin, S., Khan, A. M., Hossain, M. E., & Moni, M. A. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-1004-8 · Cited by 1,687 · see citing works
Machine learning for medical imaging
Erickson, B. J., Korfiatis, P., Akkus, Z., & Kline, T. L. (2017) · RadioGraphics · doi:10.1148/rg.2017160130 · Cited by 1,672 · see citing works
Awad, M., & Khanna, R. (2015) · Apress eBooks · doi:10.1007/978-1-4302-5990-9 · Cited by 1,569 · see citing works
Awad, M., & Khanna, R. (2015) · Apress eBooks · doi:10.1007/978-1-4302-5990-9_4 · Cited by 1,519 · see citing works
Multi-Omics Factor Analysis—a framework for unsupervised integration of multi-omics data sets
Argelaguet, R., Velten, B., Arnol, D., Dietrich, S., Zenz, T., Marioni, J. C., Buettner, F., Huber, W., & Stegle, O. (2018) · Molecular Systems Biology · doi:10.15252/msb.20178124 · Cited by 1,510 · see citing works
Machine learning and data mining methods in diabetes research
Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., & Chouvarda, I. (2017) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2016.12.005 · Cited by 1,445 · see citing works
LMSD: LIPID MAPS structure database
Sud, M., Fahy, E., Cotter, D., Brown, A., Dennis, E. A., Glass, C. K., Merrill, A. H., Murphy, R. C., Raetz, C. R. H., Russell, D. W., et al. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkl838 · Cited by 1,388 · see citing works
Can machine-learning improve cardiovascular risk prediction using routine clinical data?
Weng, S. F., Reps, J., Kai, J., Garibaldi, J. M., & Qureshi, N. (2017) · PLOS ONE · doi:10.1371/journal.pone.0174944 · Cited by 1,346 · see citing works
High-Throughput Sequencing Technologies
Reuter, J., Spacek, D. V., & Snyder, M. P. (2015) · Molecular Cell · doi:10.1016/j.molcel.2015.05.004 · Cited by 1,330 · see citing works
(2015) · neural information processing systems · Cited by 1,305 · see citing works
Badue, C. S., Guidolini, R., Carneiro, R. V., Azevedo, P., Cardoso, V. B., Forechi, A., Jesus, L. F. R., Berriel, R. F., Paixão, T. M., Mutz, F. W., et al. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113816 · Cited by 1,257 · see citing works
Benjamens, S., Dhunnoo, P., & Meskó, B. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00324-0 · Cited by 1,215 · see citing works
Lowe, R. G. T., Shirley, N. J., Bleackley, M. R., Dolan, S., & Shafee, T. M. A. (2017) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1005457 · Cited by 1,186 · see citing works
Protein Data Bank: the single global archive for 3D macromolecular structure data
wwPDB consortium, Burley, S. K., Berman, H. M., Bhikadiya, C., Bi, C., Chen, L., Costanzo, L. D., Christie, C., Duarte, J. M., Dutta, S., et al. (2019) · Nucleic Acids Research · doi:10.1093/nar/gky949 · Cited by 1,163 · see citing works
(1987) · Comparative Biochemistry and Physiology Part A Physiology · doi:10.1016/0300-9629(87)90455-5 · Cited by 1,130 · see citing works
Deep Learning vs. Traditional Computer Vision
O’Mahony, N., Campbell, S., Carvalho, A. L. D., Harapanahalli, S., Velasco-Hernandez, G., Krpálková, L., Riordan, D., & Walsh, J. L. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-17795-9_10 · Cited by 1,104 · see citing works
Deep learning-based multi-omics integration robustly predicts survival in liver cancer
Chaudhary, K., Poirion, O. B., Lu, L., & Garmire, L. X. (2018) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-17-0853 · Cited by 1,091 · see citing works
Methods of integrating data to uncover genotype-phenotype interactions
Ritchie, M. D., Holzinger, E. R., Li, R., Pendergrass, S. A., & Kim, D. (2015) · Nature Reviews Genetics · doi:10.1038/nrg3868 · Cited by 1,085 · see citing works
Proteomics: Technologies and Their Applications
Aslam, B., Basit, M., Nisar, M. A., Khurshid, M., & Rasool, M. H. (2016) · Journal of Chromatographic Science · doi:10.1093/chromsci/bmw167 · Cited by 1,010 · see citing works
Multi-view learning overview: Recent progress and new challenges
Zhao, J., Xie, X., Xu, X., & Sun, S. (2017) · Information Fusion · doi:10.1016/j.inffus.2017.02.007 · Cited by 1,002 · see citing works
Comparison of RNA-Seq and Microarray in Transcriptome Profiling of Activated T Cells
Zhao, S., Fung‐Leung, W., Bittner, A., Ngo, K., & Liu, X. (2014) · PLoS ONE · doi:10.1371/journal.pone.0078644 · Cited by 945 · see citing works
Metabolomics by Gas Chromatography–Mass Spectrometry: Combined Targeted and Untargeted Profiling
Fiehn, O. (2016) · Current Protocols in Molecular Biology · doi:10.1002/0471142727.mb3004s114 · Cited by 917 · see citing works
The sequence read archive: explosive growth of sequencing data
Kodama, Y., Shumway, M., Leinonen, R., & on behalf of the International Nucleotide Sequence Database Collaboration (2012) · Nucleic Acids Research · doi:10.1093/nar/gkr854 · Cited by 894 · see citing works
Supervised Machine Learning: A Brief Primer
Jiang, T., Gradus, J. L., & Rosellini, A. J. (2020) · Behavior Therapy · doi:10.1016/j.beth.2020.05.002 · Cited by 880 · see citing works
Shen, R., Olshen, A. B., & Ladanyi, M. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp543 · Cited by 849 · see citing works
An Introduction to Machine Learning
Badillo, S., Bánfai, B., Birzele, F., Davydov, I. I., Hutchinson, L. G., Kam‐Thong, T., Siebourg‐Polster, J., Steiert, B., & Zhang, J. D. (2020) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.1796 · Cited by 836 · see citing works
Automated machine learning: Review of the state-of-the-art and opportunities for healthcare
Waring, J., Lindvall, C., & Umeton, R. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101822 · Cited by 834 · see citing works
Facing Imbalanced Data--Recommendations for the Use of Performance Metrics
Jeni, L. A., Cohn, J. F., & de la Torre, F. N. (2013) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii.2013.47 · Cited by 826 · see citing works
Systems biology and multi-omics integration: viewpoints from the metabolomics research community
Pinu, F. R., Beale, D. J., Paten, A. M., Kouremenos, K., Swarup, S., Schirra, H. J., & Wishart, D. (2019) · Metabolites · doi:10.3390/metabo9040076 · Cited by 723 · see citing works
The European nucleotide archive
Leinonen, R., Akhtar, R., Birney, E., Bower, L., Cerdeno-Tarraga, A., Cheng, Y., Cleland, I., Faruque, N., Goodgame, N., Gibson, R., et al. (2011) · Nucleic Acids Research · doi:10.1093/nar/gkq967 · Cited by 690 · see citing works
Integrated omics: tools, advances and future approaches
Misra, B. B., Langefeld, C., Olivier, M., & Cox, L. A. (2019) · Journal of Molecular Endocrinology · doi:10.1530/jme-18-0055 · Cited by 686 · see citing works
Wang, T., Shao, W., Huang, Z., Tang, H., Zhang, J., Ding, Z., & Huang, K. (2021) · Nature Communications · doi:10.1038/s41467-021-23774-w · Cited by 671 · see citing works
A statistical framework for genomic data fusion
Lanckriet, G. R. G., Bie, T. D., Cristianini, N., Jordan, M. I., & Noble, W. S. (2004) · Bioinformatics · doi:10.1093/bioinformatics/bth294 · Cited by 667 · see citing works
Muehlematter, U. J., Daniore, P., & Vokinger, K. N. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30292-2 · Cited by 665 · see citing works
Zhou, B., Xiao, J. F., Tuli, L., & Ressom, H. W. (2011) · Molecular BioSystems · doi:10.1039/c1mb05350g · Cited by 652 · see citing works
More Is Better: Recent Progress in Multi-Omics Data Integration Methods
Huang, S., Chaudhary, K., & Garmire, L. (2017) · Frontiers in Genetics · doi:10.3389/fgene.2017.00084 · Cited by 637 · see citing works
Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)
Memon, J., Sami, M., Khan, R. A., & Uddin, M. (2020) · IEEE Access · doi:10.1109/access.2020.3012542 · Cited by 608 · see citing works
Lipidomics: Techniques, Applications, and Outcomes Related to Biomedical Sciences
Yang, K., & Han, X. (2016) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2016.08.010 · Cited by 596 · see citing works
Medical big data: promise and challenges
Lee, C. H., & Yoon, H. (2017) · Kidney Research and Clinical Practice · doi:10.23876/j.krcp.2017.36.1.3 · Cited by 596 · see citing works
Large-Scale Multi-omic Analysis of COVID-19 Severity
Overmyer, K. A., Shishkova, E., Miller, I. J., Balnis, J., Bernstein, M. N., Peters-Clarke, T. M., Meyer, J. G., Quan, Q., Muehlbauer, L. K., Trujillo, E. A., et al. (2020) · Cell Systems · doi:10.1016/j.cels.2020.10.003 · Cited by 584 · see citing works
Self-supervised learning for medical image analysis using image context restoration
Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., & Rueckert, D. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.101539 · Cited by 575 · see citing works
Shen, R., Olshen, A. B., & Ladanyi, M. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btp659 · Cited by 566 · see citing works
MGnify: the microbiome analysis resource in 2020
Mitchell, A. L., Almeida, A., Beracochea, M., Boland, M., Burgin, J., Cochrane, G., Crusoe, M. R., Kale, V., Potter, S. C., Richardson, L. J., et al. (2019) · Nucleic Acids Research · doi:10.1093/nar/gkz1035 · Cited by 562 · see citing works
Joint and individual variation explained (JIVE) for integrated analysis of multiple data types
Lock, E. F., Hoadley, K. A., Marron, J. S., & Nobel, A. B. (2013) · The Annals of Applied Statistics · doi:10.1214/12-aoas597 · Cited by 554 · see citing works
Benson, D. A., Karsch‐Mizrachi, I., Lipman, D. J., Ostell, J., & Sayers, E. W. (2010) · Nucleic Acids Research · doi:10.1093/nar/gkq1079 · Cited by 552 · see citing works
Multi-omic and multi-view clustering algorithms: review and cancer benchmark
Rappoport, N., & Ron Shamir, A. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky889 · Cited by 549 · see citing works
Deep learning in clinical natural language processing: a methodical review
Wu, S., Roberts, K. E., Datta, S., Du, J., Ji, Z., Si, Y., Soni, S., Wang, Q., Wei, Q., Xiang, Y., et al. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocz200 · Cited by 495 · see citing works
Targeted RNA sequencing reveals the deep complexity of the human transcriptome
Mercer, T. R., Gerhardt, D. J., Dinger, M. E., Crawford, J., Trapnell, C., Jeddeloh, J. A., Mattick, J. S., & Rinn, J. L. (2011) · Nature Biotechnology · doi:10.1038/nbt.2024 · Cited by 490 · see citing works
Machine learning for email spam filtering: review, approaches and open research problems
Dada, E., Bassi, J. S., Chiroma, H., Abdulhamid, S., Adetunmbi, A., & Ajibuwa, O. (2019) · Heliyon · doi:10.1016/j.heliyon.2019.e01802 · Cited by 490 · see citing works
An integrated approach to uncover drivers of cancer
Akavia, U. D., Litvin, O., Kim, J., Sanchez-Garcia, F., Kotliar, D., Causton, H. C., Pochanard, P., Mozes, E., Garraway, L. A., & Pe'er, D. (2010) · Cell · doi:10.1016/j.cell.2010.11.013 · Cited by 484 · see citing works
Pattern discovery and cancer gene identification in integrated cancer genomic data
Mo, Q., Wang, S., Seshan, V. E., Olshen, A. B., Schultz, N., Sander, C., Powers, R. S., Ladanyi, M., & Shen, R. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1208949110 · Cited by 474 · see citing works
Multidimensional Scaling: History, Theory and Applications.
Pigden, N., Young, F. W., & Hamer, R. M. (1988) · Journal of the Royal Statistical Society Series D (The Statistician) · doi:10.2307/2348396 · Cited by 473 · see citing works
Zhou, J. Z., He, Z., Yang, Y., Deng, Y., Tringe, S. G., & Alvarez‐Cohen, L. (2015) · mBio · doi:10.1128/mbio.02288-14 · Cited by 473 · see citing works
Genome sequencing of the sweetpotato whitefly Bemisia tabaci MED/Q
Xie, W., Chen, C., Yang, Z., Guo, L., Yang, X., Wang, D., Chen, M., Huang, J., Wen, Y., Zeng, Y., et al. (2017) · GigaScience · doi:10.1093/gigascience/gix018 · Cited by 473 · see citing works
Overview of DNA Microarrays: Types, Applications, and Their Future
Bumgarner, R. E. (2013) · Current Protocols in Molecular Biology · doi:10.1002/0471142727.mb2201s101 · Cited by 467 · see citing works
A comparative evaluation of outlier detection algorithms: Experiments and analyses
Domingues, R., Filippone, M., Pietro Michiardi, A., & Zouaoui, J. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.09.037 · Cited by 457 · see citing works
A comprehensive survey of anomaly detection techniques for high dimensional big data
Thudumu, S., Branch, P., Jin, J., & Singh, J. (2020) · Journal Of Big Data · doi:10.1186/s40537-020-00320-x · Cited by 454 · see citing works
Methods for the integration of multi-omics data: mathematical aspects
Bersanelli, M., Mosca, E., Remondini, D., Giampieri, E., Sala, C., Castellani, G., & Milanesi, L. (2016) · BMC Bioinformatics · doi:10.1186/s12859-015-0857-9 · Cited by 449 · see citing works
Bringing Big Data to Personalized Healthcare: A Patient-Centered Framework
Chawla, N. V., & Davis, D. A. (2013) · Journal of General Internal Medicine · doi:10.1007/s11606-013-2455-8 · Cited by 440 · see citing works
Hugenholtz, P., & Tyson, G. W. (2008) · Nature · doi:10.1038/455481a · Cited by 433 · see citing works
yaImpute : An R Package for k NN Imputation
Crookston, N. L., & Finley, A. O. (2008) · Journal of Statistical Software · doi:10.18637/jss.v023.i10 · Cited by 428 · see citing works
MOLI: multi-omics late integration with deep neural networks for drug response prediction
Sharifi-Noghabi, H., Zolotareva, O., Collins, C. C., & Ester, M. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz318 · Cited by 421 · see citing works
Probabilistic model of the human protein-protein interaction network
Rhodes, D. R., Tomlins, S. A., Varambally, S., Mahavisno, V., Barrette, T. R., Sundaram, S. K., Ghosh, D., Pandey, A., & Chinnaiyan, A. M. (2005) · Nature Biotechnology · doi:10.1038/nbt1103 · Cited by 411 · see citing works
Non-coding RNA analysis using the Rfam database
Kalvari, I., Nawrocki, E. P., Argasinska, J., Quinones-Olvera, N., Finn, R., Bateman, A., & Petrov, A. I. (2018) · Current Protocols in Bioinformatics · doi:10.1002/cpbi.51 · Cited by 401 · see citing works
Secondary arterial hypertension: when, who, and how to screen?
Rimoldi, S. F., Scherrer, U., & Messerli, F. H. (2014) · European Heart Journal · doi:10.1093/eurheartj/eht534 · Cited by 393 · see citing works
Machine learning, medical diagnosis, and biomedical engineering research - commentary
Foster, K. R., Koprowski, R., & Skufca, J. D. (2014) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-13-94 · Cited by 384 · see citing works
The Application of Deep Learning in Cancer Prognosis Prediction
Zhu, W., Xie, L., Han, J., & Guo, X. (2020) · Cancers · doi:10.3390/cancers12030603 · Cited by 384 · see citing works
Dimension reduction techniques for the integrative analysis of multi-omics data
Meng, C., Zeleznik, O. A., Thallinger, G., Küster, B., Gholami, A. M., & Culhane, A. C. (2016) · Briefings in Bioinformatics · doi:10.1093/bib/bbv108 · Cited by 383 · see citing works
Rashidi, H. H., Tran, N. K., Betts, E. V., Howell, L. P., & Green, R. (2019) · Academic Pathology · doi:10.1177/2374289519873088 · Cited by 381 · see citing works
Machine learning and integrative analysis of biomedical big data
Mirza, B., Wang, W., Wang, J., Choi, H., Chung, N. C., & Ping, P. (2019) · Genes · doi:10.3390/genes10020087 · Cited by 380 · see citing works
The Handbook of Metabonomics and Metabolomics
Lindon, J. C., Nicholson, J., & Holmes, E. (2007) · Elsevier eBooks · doi:10.1016/b978-0-444-52841-4.x5000-0 · Cited by 374 · see citing works
Discovery of multi-dimensional modules by integrative analysis of cancer genomic data
Zhang, S., Liu, C.-C., Li, W., Shen, H., Laird, P. W., & Zhou, X. J. (2012) · Nucleic Acids Research · doi:10.1093/nar/gks725 · Cited by 374 · see citing works
Ensemble classifier for protein fold pattern recognition
Shen, H., & Chou, K. (2006) · Bioinformatics · doi:10.1093/bioinformatics/btl170 · Cited by 357 · see citing works
C-reactive protein, inflammation and coronary heart disease
Shrivastava, A. K., Singh, H. V., Raizada, A., & Singh, S. K. (2014) · The Egyptian Heart Journal · doi:10.1016/j.ehj.2014.11.005 · Cited by 321 · see citing works
Kovács, G. G. (2016) · International Journal of Molecular Sciences · doi:10.3390/ijms17020189 · Cited by 321 · see citing works
A survey of dimensionality reduction techniquesPreprint
Sorzano, C. Ó. S., Vargas, J., & Pascual-Montano, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.2877 · Cited by 320 · see citing works
Reinforcement learning for intelligent healthcare applications: A survey
Coronato, A., Naeem, M., De Pietro, G., & Paragliola, G. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101964 · Cited by 320 · see citing works
Pérez-Cobas, A. E., Gomez-Valero, L., & Buchrieser, C. (2020) · Microbial Genomics · doi:10.1099/mgen.0.000409 · Cited by 314 · see citing works
A reference human genome dataset of the BGISEQ-500 sequencer
Huang, J., Liang, X., Xuan, Y., Geng, C., Li, Y., Lu, H., Qu, S., Mei, X., Chen, H., Yu, T., et al. (2017) · GigaScience · doi:10.1093/gigascience/gix024 · Cited by 313 · see citing works
Lock, E. F., & Dunson, D. B. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt425 · Cited by 308 · see citing works
Poirion, O., Jing, Z., Chaudhary, K., Huang, S., & Garmire, L. X. (2021) · Genome Medicine · doi:10.1186/s13073-021-00930-x · Cited by 299 · see citing works
Prospects and challenges of multi-omics data integration in toxicology
Canzler, S., Schor, J., Busch, W., Schubert, K. A., Rolle-Kampczyk, U. E., Seitz, H., Kamp, H., von Bergen�, M., Buesen, R., & Hackermüller, J. (2020) · Archives of Toxicology · doi:10.1007/s00204-020-02656-y · Cited by 291 · see citing works
NEMO: cancer subtyping by integration of partial multi-omic data
Rappoport, N., & Shamir, R. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz058 · Cited by 286 · see citing works
Thomas, T. A., Stefanoni, D., Dzieciątkowska, M., Issaian, A., Nemkov, T. G., Hill, R. C., Francis, R. O., Hudson, K. E., Buehler, P. W., Zimring, J. C., et al. (2020) · Journal of Proteome Research · doi:10.1021/acs.jproteome.0c00606 · Cited by 285 · see citing works
Integrated Multi-Omics Analyses in Oncology: A Review of Machine Learning Methods and Tools
Nicora, G., Vitali, F., Dagliati, A., Geifman, N., & Bellazzi, R. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.01030 · Cited by 284 · see citing works
A fully Bayesian latent variable model for integrative clustering analysis of multi-type omics data
Mo, Q., Shen, R., Guo, C., Vannucci, M., Chan, K. S., & Hilsenbeck, S. G. (2017) · Biostatistics · doi:10.1093/biostatistics/kxx017 · Cited by 281 · see citing works
Zhou, Z., Chawla, N. V., Jin, Y., & Williams, G. J. (2014) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2014.2350953 · Cited by 275 · see citing works
Methods for biological data integration: perspectives and challenges
Gligorijević, V., & Pržulj, N. (2015) · Journal of The Royal Society Interface · doi:10.1098/rsif.2015.0571 · Cited by 274 · see citing works
Integrative Methods and Practical Challenges for Single-Cell Multi-omics
Ma, A., McDermaid, A., Xu, J., Chang, Y., & Ma, Q. (2020) · Trends in biotechnology · doi:10.1016/j.tibtech.2020.02.013 · Cited by 272 · see citing works
On safari to Random Jungle: a fast implementation of Random Forests for high-dimensional data
Schwarz, D. F., König, I. R., & Ziegler, A. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq257 · Cited by 269 · see citing works
Novel advances in shotgun lipidomics for biology and medicine
Wang, M., Wang, C., Han, R. H., & Han, X. (2015) · Progress in Lipid Research · doi:10.1016/j.plipres.2015.12.002 · Cited by 269 · see citing works
Painting a new picture of personalised medicine for diabetes
McCarthy, M. I. (2017) · Diabetologia · doi:10.1007/s00125-017-4210-x · Cited by 256 · see citing works
Beyond mass spectrometry, the next step in proteomics
Timp, W., & Timp, G. (2020) · Science Advances · doi:10.1126/sciadv.aax8978 · Cited by 254 · see citing works
Young, J., Modat, M., Cardoso, M. J., Mendelson, A., Cash, D., & Ourselin, S. (2013) · NeuroImage Clinical · doi:10.1016/j.nicl.2013.05.004 · Cited by 249 · see citing works
Criteria for the use of omics-based predictors in clinical trials
McShane, L. M., Cavenagh, M. M., Lively, T., Eberhard, D. A., Bigbee, W. L., Williams, P. M., Mesirov, J. P., Polley, M. C., Kim, K. Y., Tricoli, J. V., et al. (2013) · Nature · doi:10.1038/nature12564 · Cited by 245 · see citing works
Fundamentals of Clinical Data Science
Kubben, P., Dumontier, M., & Dekker, A. L. A. J. (2018) · Springer eBooks · doi:10.1007/978-3-319-99713-1 · Cited by 240 · see citing works
Recent advances of deep learning in bioinformatics and computational biology
Tang, B., Pan, Z., Yin, K., & Khateeb, A. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00214 · Cited by 233 · see citing works
Wu, D., Wang, D., Zhang, M. Q., & Gu, J. (2015) · BMC Genomics · doi:10.1186/s12864-015-2223-8 · Cited by 229 · see citing works
Bayesian correlated clustering to integrate multiple datasets
Kirk, P., Griffin, J. E., Savage, R. S., Zoubin Ghahramani, A., & Wild, D. L. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts595 · Cited by 228 · see citing works
A post-genomic challenge: learning to read patterns of protein synthesis
Abbott, A. (1999) · Nature · doi:10.1038/45350 · Cited by 227 · see citing works
60 years ago, Francis Crick changed the logic of biology
Cobb, M. A. (2017) · PLoS Biology · doi:10.1371/journal.pbio.2003243 · Cited by 227 · see citing works
Mamoshina, P., Volosnikova, M., Ozerov, I. V., Lane, E., Skibina, E., Cortese, F., & Zhavoronkov, A. A. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00242 · Cited by 227 · see citing works
A systematic comparison of supervised classifiers
Amancio, D. R., Comin, C. H., Casanova, D., Travieso, G., Bruno, O. M., Rodrigues, F. A., & da Fontoura Costa, L. (2014) · PLoS ONE · doi:10.1371/journal.pone.0094137 · Cited by 225 · see citing works
Zhang, L., Dong, X., Lee, M., Maslov, A. Y., Wang, T., & Vijg, J. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1902510116 · Cited by 222 · see citing works
Diagnostic classification of cancers using extreme gradient boosting algorithm and multi-omics data
Ma, B., Meng, F., Ge, Y., Yan, H., Chai, B., & Song, F. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103761 · Cited by 221 · see citing works
Liquid chromatography mass spectrometry-based proteomics: Biological and technological aspects
Karpievitch, Y. V., Polpitiya, A. D., Anderson, G., Smith, R. D., & Dabney, A. R. (2010) · The Annals of Applied Statistics · doi:10.1214/10-aoas341 · Cited by 219 · see citing works
High-Sensitivity C-Reactive Protein as Cardiovascular Risk Marker in Patients with Diabetes Mellitus
Pfützner, A., & Forst, T. M. (2006) · Diabetes Technology & Therapeutics · doi:10.1089/dia.2006.8.28 · Cited by 218 · see citing works
Liew, A. W., Law, N.-F., & Yan, H. (2010) · Briefings in Bioinformatics · doi:10.1093/bib/bbq080 · Cited by 218 · see citing works
Fast protein classification with multiple networks
Tsuda, K., Shin, H., & Schölkopf, B. (2005) · Bioinformatics · doi:10.1093/bioinformatics/bti1110 · Cited by 217 · see citing works
Integrative methods for analyzing big data in precision medicine
Gligorijević, V., Malod‐Dognin, N., & Pržulj, N. (2015) · PROTEOMICS · doi:10.1002/pmic.201500396 · Cited by 216 · see citing works
A Selective Review of Multi-Level Omics Data Integration Using Variable Selection
Wu, C., Zhou, F., Ren, J., Li, X., Jiang, Y., & Ma, S. (2019) · Microarrays · doi:10.3390/ht8010004 · Cited by 213 · see citing works
Systematic Multi-Omics Integration (MOI) Approach in Plant Systems Biology
Jamil, I. N., Remali, J., Azizan, K. A., Muhammad, N. A. N., Arita, M., Goh, H., & Aizat, W. M. (2020) · Frontiers in Plant Science · doi:10.3389/fpls.2020.00944 · Cited by 210 · see citing works
Hamamoto, R., Suvarna, K., Yamada, M., Kobayashi, K., Shinkai, N., Miyake, M., Takahashi, M., Jinnai, S., Shimoyama, R., Sakai, A., et al. (2020) · Cancers · doi:10.3390/cancers12123532 · Cited by 207 · see citing works
Zhu, J., Sova, P., Xu, Q., Dombek, K. M., Xu, E. Y., Vu, H., Tu, Z., Brem, R. B., Bumgarner, R. E., & Schadt, E. E. (2012) · PLoS Biology · doi:10.1371/journal.pbio.1001301 · Cited by 205 · see citing works
Zhang, L., Lv, C., Jin, Y., Cheng, G., Fu, Y., Yuan, D., Tao, Y., Guo, Y., Ni, X., & Shi, T. (2018) · Frontiers in Genetics · doi:10.3389/fgene.2018.00477 · Cited by 203 · see citing works
Systems Biology of Metabolism: A Driver for Developing Personalized and Precision Medicine
Nielsen, J. (2017) · Cell Metabolism · doi:10.1016/j.cmet.2017.02.002 · Cited by 197 · see citing works
Machine learning in cybersecurity: A review
Handa, A., Sharma, A., & Shukla, S. K. (2019) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1306 · Cited by 196 · see citing works
Machine learning and systems genomics approaches for multi-omics data
Lin, E., & Lane, H. (2017) · Biomarker Research · doi:10.1186/s40364-017-0082-y · Cited by 192 · see citing works
Precision Oncology: The Road Ahead
Senft, D., Leiserson, M. D. M., Ruppin, E., & Ronai, Z. A. (2017) · Trends in Molecular Medicine · doi:10.1016/j.molmed.2017.08.003 · Cited by 192 · see citing works
Ding, M. Q., Chen, L., Cooper, G. F., Young, J. D., & Lu, X. (2017) · Molecular Cancer Research · doi:10.1158/1541-7786.mcr-17-0378 · Cited by 191 · see citing works
Prognostic and Predictive Biomarkers: Tools in Personalized Oncology
Nalejska, E., Mączyńska, E., & Lewandowska, M. A. (2014) · Molecular Diagnosis & Therapy · doi:10.1007/s40291-013-0077-9 · Cited by 189 · see citing works
Speicher, N. K., & Pfeifer, N. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv244 · Cited by 186 · see citing works
Metabolomics and Multi-Omics Integration: A Survey of Computational Methods and Resources
Eicher, T., Kinnebrew, G. H., Patt, A. C., Spencer, K., Ying, K. L., Ma, Q., Machiraju, R., & Mathé, E. A. (2020) · Metabolites · doi:10.3390/metabo10050202 · Cited by 185 · see citing works
Big Data and Biomedical Informatics: A Challenging Opportunity
Bellazzi, R. (2014) · Yearbook of Medical Informatics · doi:10.15265/iy-2014-0024 · Cited by 184 · see citing works
Mass Spectrometry Based Lipidomics: An Overview of Technological Platforms
Köfeler, H. C., Fauland, A., Rechberger, G. N., & Trötzmüller, M. (2012) · Metabolites · doi:10.3390/metabo2010019 · Cited by 181 · see citing works
Comparing machine learning classifiers in potential distribution modelling
Lorena, A. C., Jacintho, L. F. O., de Siqueira, M. F., Giovanni, R. D., Lohmann, L. G., de Carvalho, A. C. P. L. F., & Yamamoto, M. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2010.10.031 · Cited by 180 · see citing works
Zhou, Y., Hou, Y., Shen, J., Mehra, R., Kallianpur, A., Culver, D. A., Gack, M. U., Farha, S., Zein, J., Comhair, S., et al. (2020) · PLoS Biology · doi:10.1371/journal.pbio.3000970 · Cited by 180 · see citing works
A novel approach for data integration and disease subtypingPreprint
Nguyen, T., Tagett, R., Diaz, D., & Drăghici, S. (2017) · Genome Research · doi:10.1101/gr.215129.116 · Cited by 178 · see citing works
Lightbody, G., Haberland, V., Browne, F., Taggart, L., Zheng, H., Parkes, E., & Blayney, J. K. (2019) · Briefings in Bioinformatics · doi:10.1093/bib/bby051 · Cited by 173 · see citing works
Making multi-omics data accessible to researchers
Conesa, A., & Beck, S. (2019) · Scientific Data · doi:10.1038/s41597-019-0258-4 · Cited by 173 · see citing works
Frontiers of high-throughput metabolomics
Zampieri, M., Sekar, K., Zamboni, N., & Sauer, U. (2017) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2016.12.006 · Cited by 169 · see citing works
A versatile ultra-high performance LC-MS method for lipid profiling
Knittelfelder, O. L., Weberhofer, B. P., Eichmann, T. O., Kohlwein, S. D., & Rechberger, G. N. (2014) · Journal of Chromatography B · doi:10.1016/j.jchromb.2014.01.011 · Cited by 161 · see citing works
DeepDSC: A Deep Learning Method to Predict Drug Sensitivity of Cancer Cell Lines
Li, M., Wang, Y., Zheng, R., Shi, X. M., Li, Y., Wu, F., & Wang, J. (2019) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2919581 · Cited by 160 · see citing works
Bzdok, D. (2017) · HAL · Cited by 160 · see citing works
Meta-analytic support vector machine for integrating multiple omics data
Kim, S., Jhong, J.-H., Lee, J., & Koo, J.-Y. (2017) · BioData Mining · doi:10.1186/s13040-017-0126-8 · Cited by 159 · see citing works
Classical Statistics and Statistical Learning in Imaging Neuroscience
Bzdok, D. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00543 · Cited by 159 · see citing works
GlyTouCan: an accessible glycan structure repository
Tiemeyer, M., Aoki, K., Paulson, J. C., Cummings, R. D., York, W. S., Karlsson, N. G., Lisacek, F., Packer, N. H., Campbell, M. P., Aoki, N. P., et al. (2017) · Glycobiology · doi:10.1093/glycob/cwx066 · Cited by 158 · see citing works
Gupta, Y., Lama, R. K., Kwon, G., & Initiative, A. D. N. (2019) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2019.00072 · Cited by 157 · see citing works
Zhao, Q., Shi, X., Xie, Y., Huang, J., Shia, B., & Ma, S. (2015) · Briefings in Bioinformatics · doi:10.1093/bib/bbu003 · Cited by 154 · see citing works
Combining tissue transcriptomics and urine metabolomics for breast cancer biomarker identification
Nam, H., Chung, B. C., Kim, Y.-H., Lee, K., & Lee, D. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp558 · Cited by 154 · see citing works
Applications and analysis of targeted genomic sequencing in cancer studies
Bewicke‐Copley, F., Kumar, E. A., Palladino, G., Korfi, K., & Wang, J. (2019) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2019.10.004 · Cited by 154 · see citing works
Challenges in the Integration of Omics and Non-Omics Data
de Maturana, E. L., Alonso, L., Moreno, P. A., Martín‐Antoniano, I. A., Pineda, S., Piorno, L., Calle, M. L., & Malats, N. (2019) · Genes · doi:10.3390/genes10030238 · Cited by 150 · see citing works
DNA Data Bank of Japan (DDBJ) for genome scale research in life science
Tateno, Y. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.27 · Cited by 149 · see citing works
Hampel, H., O’Bryant, S. E., Durrleman, S., Younesi, E., Rojkova, K., Escott-Price, V., Corvol, J.-C., Broich, K., Dubois, B., Lista, S., et al. (2017) · Climacteric · doi:10.1080/13697137.2017.1287866 · Cited by 147 · see citing works
Multi-omics integration—a comparison of unsupervised clustering methodologies
Tini, G., Marchetti, L., Priami, C., & Scott‐Boyer, M. (2017) · Briefings in Bioinformatics · doi:10.1093/bib/bbx167 · Cited by 147 · see citing works
Proteome-Scale Human Interactomics
Luck, K., Sheynkman, G., Zhang, I., & Vidal, M. (2017) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2017.02.006 · Cited by 146 · see citing works
Xu, X., Liang, T., Zhu, J., Zheng, D., & Sun, T. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.100 · Cited by 146 · see citing works
moCluster: Identifying Joint Patterns Across Multiple Omics Data Sets
Meng, C., Helm, D., Frejno, M., & Küster, B. (2015) · Journal of Proteome Research · doi:10.1021/acs.jproteome.5b00824 · Cited by 141 · see citing works
Criteria for the use of omics-based predictors in clinical trials: explanation and elaboration
McShane, L. M., Cavenagh, M. M., Lively, T., Eberhard, D. A., Bigbee, W. L., Williams, P. M., Mesirov, J. P., Polley, M. C., Kim, K. Y., Tricoli, J. V., et al. (2013) · BMC Medicine · doi:10.1186/1741-7015-11-220 · Cited by 140 · see citing works
PINSPlus: a tool for tumor subtype discovery in integrated genomic data
Nguyen, H., Shrestha, S., Drăghici, S., & Nguyen, T. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty1049 · Cited by 140 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- Clarivate Analytics, 2020, Web of science [v.5.35] - web of science core collection basic search [WWW Document], Web Sci.
- Tipping, 2001, Sparse bayesian learning and the relevance vector machine, J. Mach. Learn. Res., 1, 211
- Wang, 2020, MORONET: multi-omics integration via graph convolutional networks for biomedical data classification, bioRxiv
Cited by
Sorted by citations
AI for life: Trends in artificial intelligence for biotechnology
Holzinger, A., Keiblinger, K., Holub, P., Zatloukal, K., & Müller, H. (2023) · New Biotechnology · doi:10.1016/j.nbt.2023.02.001 · Cited by 438 · see citing works
Single-cell and spatial transcriptomics: deciphering brain complexity in health and disease
Piwecka, M., Rajewsky, N., & Rybak-Wolf, A. (2023) · Nature Reviews Neurology · doi:10.1038/s41582-023-00809-y · Cited by 320 · see citing works
Missing data in multi-omics integration: Recent advances through artificial intelligence
Flores, J. E., Claborne, D. M., Weller, Z. D., Webb-Robertson, B.-J. M., Waters, K. M., & Bramer, L. M. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1098308 · Cited by 181 · see citing works
“…of subsets of general AI and ML approaches to multi-omics data integration (e.g., Li et al., 2016; Huang et al., 2017; Kim and Tagkopoulos, 2018; Picard et al., 2021; Reel et al., 2021; Lee and Kim, 2022) with some attention given to limitations of methods, such as interpretability of models.”
MethodPahud de Mortanges, A., Luo, H., Shu, S. Z., Kamath, A., Suter, Y., Shelan, M., Pöllinger, A., & Reyes, M. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01190-w · Cited by 93 · see citing works
“Additional organizational or technical challenges regarding multi-modal machine learning and AI in healthcare have previously been pointed out 20,44,52 .”
Scientific novelty beyond the experiment
Hallsworth, J. E., Udaondo, Z., Pedrós‐Alió, C., Höfer, J., Benison, K. C., Lloyd, K. G., Cordero, R. J. B., de Campos, C. B. L., Yakimov, M. M., & Amils, R. (2023) · Microbial Biotechnology · doi:10.1111/1751-7915.14222 · Cited by 62 · see citing works
Kaur, A., Mittal, M., Bhatti, J. S., Thareja, S., & Singh, S. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102928 · Cited by 54 · see citing works
Li, J., Li, L., You, P., Wei, Y., & Xu, B. (2023) · Seminars in Cancer Biology · doi:10.1016/j.semcancer.2023.02.009 · Cited by 55 · see citing works
Samadishadlou, M., Rahbarghazi, R., Piryaei, Z., Esmaeili, M., Avcı, Ç. B., Bani, F., & Kavousi, K. (2023) · Cardiovascular Diabetology · doi:10.1186/s12933-023-01957-7 · Cited by 26 · see citing works
Cui, X., Chang, Y., Yang, C., Cong, Z., Wang, B., & Leng, Y. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm13010050 · Cited by 19 · see citing works
- Authors
- Reel, P. S., Reel, S., Pearson, E., Trucco, E., & Jefferson, E.
- Affiliations
- University of Dundee (GB)
- Corresponding author
- Jefferson, Emily
- Venue
- Biotechnology Advances
- Publisher
- Elsevier BV
- Published
- 2021-07
- Volume
- 49
- Pages
- 107739
- ISSN
- 0734-9750 (ISSN-L)
- OpenAlex
- W3139601120
- Semantic Scholar
- adb2c80911fbb5c273279afa79f6a766700a1040
- Cited by
- 903
- References
- 357
- Citations by year
- 2026: 186 · 2025: 239 · 2024: 227 · 2023: 148 · 2022: 89 · 2021: 14
- FWCI
- 13.04
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Biotechnology Advances (publishedVersion)
- PubMed (publishedVersion)
- Discovery Research Portal (University of Dundee) (publishedVersion, cc-by-nc-nd)
- Funders
- Horizon 2020
- University of Dundee (16/136/102)
- Horizon 2020 Framework Programme (633983)
- National Institute for Health Research
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- multi-omics integration, machine learning, biomarker discovery, disease prediction, patient stratification, precision medicine, systems biology, genomics, proteomics, metabolomics, predictive algorithms
- MeSH terms
- Machine Learning, Algorithms, Humans, Proteomics, Systems Biology, Metabolomics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
