Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci
Genome-wide association studies (GWAS) have revealed thousands of genetic loci that underpin the complex biology of many human traits. However, the strength of GWAS – the ability to detect genetic association by linkage disequilibrium (LD) – is also its limitation. Whilst the ever-increasing study s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-04-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fgene.2020.00350/full |
| _version_ | 1819111912602861568 |
|---|---|
| author | Hannah L. Nicholls Hannah L. Nicholls Christopher R. John Christopher R. John David S. Watson David S. Watson Patricia B. Munroe Patricia B. Munroe Michael R. Barnes Michael R. Barnes Michael R. Barnes Michael R. Barnes Claudia P. Cabrera Claudia P. Cabrera Claudia P. Cabrera |
| author_facet | Hannah L. Nicholls Hannah L. Nicholls Christopher R. John Christopher R. John David S. Watson David S. Watson Patricia B. Munroe Patricia B. Munroe Michael R. Barnes Michael R. Barnes Michael R. Barnes Michael R. Barnes Claudia P. Cabrera Claudia P. Cabrera Claudia P. Cabrera |
| author_sort | Hannah L. Nicholls |
| collection | DOAJ |
| description | Genome-wide association studies (GWAS) have revealed thousands of genetic loci that underpin the complex biology of many human traits. However, the strength of GWAS – the ability to detect genetic association by linkage disequilibrium (LD) – is also its limitation. Whilst the ever-increasing study size and improved design have augmented the power of GWAS to detect effects, differentiation of causal variants or genes from other highly correlated genes associated by LD remains the real challenge. This has severely hindered the biological insights and clinical translation of GWAS findings. Although thousands of disease susceptibility loci have been reported, causal genes at these loci remain elusive. Machine learning (ML) techniques offer an opportunity to dissect the heterogeneity of variant and gene signals in the post-GWAS analysis phase. ML models for GWAS prioritization vary greatly in their complexity, ranging from relatively simple logistic regression approaches to more complex ensemble models such as random forests and gradient boosting, as well as deep learning models, i.e., neural networks. Paired with functional validation, these methods show important promise for clinical translation, providing a strong evidence-based approach to direct post-GWAS research. However, as ML approaches continue to evolve to meet the challenge of causal gene identification, a critical assessment of the underlying methodologies and their applicability to the GWAS prioritization problem is needed. This review investigates the landscape of ML applications in three parts: selected models, input features, and output model performance, with a focus on prioritizations of complex disease associated loci. Overall, we explore the contributions ML has made towards reaching the GWAS end-game with consequent wide-ranging translational impact. |
| first_indexed | 2024-12-22T04:05:09Z |
| format | Article |
| id | doaj.art-d25406a98a014738a499143e68bbf8d2 |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-12-22T04:05:09Z |
| publishDate | 2020-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-d25406a98a014738a499143e68bbf8d22022-12-21T18:39:39ZengFrontiers Media S.A.Frontiers in Genetics1664-80212020-04-011110.3389/fgene.2020.00350521712Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease LociHannah L. Nicholls0Hannah L. Nicholls1Christopher R. John2Christopher R. John3David S. Watson4David S. Watson5Patricia B. Munroe6Patricia B. Munroe7Michael R. Barnes8Michael R. Barnes9Michael R. Barnes10Michael R. Barnes11Claudia P. Cabrera12Claudia P. Cabrera13Claudia P. Cabrera14Clinical Pharmacology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Translational Bioinformatics, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Translational Bioinformatics, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Experimental Medicine and Rheumatology, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Translational Bioinformatics, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomOxford Internet Institute, University of Oxford, Oxford, United KingdomClinical Pharmacology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomNIHR Barts Biomedical Research Centre, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomClinical Pharmacology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Translational Bioinformatics, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomNIHR Barts Biomedical Research Centre, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomThe Alan Turing Institute, British Library, London, United KingdomClinical Pharmacology, William Harvey Research Institute, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomCentre for Translational Bioinformatics, William Harvey Research Institute, Barts and the London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomNIHR Barts Biomedical Research Centre, Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United KingdomGenome-wide association studies (GWAS) have revealed thousands of genetic loci that underpin the complex biology of many human traits. However, the strength of GWAS – the ability to detect genetic association by linkage disequilibrium (LD) – is also its limitation. Whilst the ever-increasing study size and improved design have augmented the power of GWAS to detect effects, differentiation of causal variants or genes from other highly correlated genes associated by LD remains the real challenge. This has severely hindered the biological insights and clinical translation of GWAS findings. Although thousands of disease susceptibility loci have been reported, causal genes at these loci remain elusive. Machine learning (ML) techniques offer an opportunity to dissect the heterogeneity of variant and gene signals in the post-GWAS analysis phase. ML models for GWAS prioritization vary greatly in their complexity, ranging from relatively simple logistic regression approaches to more complex ensemble models such as random forests and gradient boosting, as well as deep learning models, i.e., neural networks. Paired with functional validation, these methods show important promise for clinical translation, providing a strong evidence-based approach to direct post-GWAS research. However, as ML approaches continue to evolve to meet the challenge of causal gene identification, a critical assessment of the underlying methodologies and their applicability to the GWAS prioritization problem is needed. This review investigates the landscape of ML applications in three parts: selected models, input features, and output model performance, with a focus on prioritizations of complex disease associated loci. Overall, we explore the contributions ML has made towards reaching the GWAS end-game with consequent wide-ranging translational impact.https://www.frontiersin.org/article/10.3389/fgene.2020.00350/fullmachine learningartificial intelligencegenome-wide association studygenomicscandidate geneclinical translation |
| spellingShingle | Hannah L. Nicholls Hannah L. Nicholls Christopher R. John Christopher R. John David S. Watson David S. Watson Patricia B. Munroe Patricia B. Munroe Michael R. Barnes Michael R. Barnes Michael R. Barnes Michael R. Barnes Claudia P. Cabrera Claudia P. Cabrera Claudia P. Cabrera Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci Frontiers in Genetics machine learning artificial intelligence genome-wide association study genomics candidate gene clinical translation |
| title | Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci |
| title_full | Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci |
| title_fullStr | Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci |
| title_full_unstemmed | Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci |
| title_short | Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci |
| title_sort | reaching the end game for gwas machine learning approaches for the prioritization of complex disease loci |
| topic | machine learning artificial intelligence genome-wide association study genomics candidate gene clinical translation |
| url | https://www.frontiersin.org/article/10.3389/fgene.2020.00350/full |
| work_keys_str_mv | AT hannahlnicholls reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT hannahlnicholls reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT christopherrjohn reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT christopherrjohn reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT davidswatson reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT davidswatson reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT patriciabmunroe reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT patriciabmunroe reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT michaelrbarnes reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT michaelrbarnes reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT michaelrbarnes reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT michaelrbarnes reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT claudiapcabrera reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT claudiapcabrera reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci AT claudiapcabrera reachingtheendgameforgwasmachinelearningapproachesfortheprioritizationofcomplexdiseaseloci |