Deep learning captures the effect of epistasis in multifactorial diseases
BackgroundPolygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. Howev...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1479717/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841556907447287808 |
|---|---|
| author | Vladislav Perelygin Alexey Kamelin Alexey Kamelin Nikita Syzrantsev Layal Shaheen Layal Shaheen Anna Kim Nikolay Plotnikov Anna Ilinskaya Valery Ilinsky Alexander Rakitko Alexander Rakitko Maria Poptsova |
| author_facet | Vladislav Perelygin Alexey Kamelin Alexey Kamelin Nikita Syzrantsev Layal Shaheen Layal Shaheen Anna Kim Nikolay Plotnikov Anna Ilinskaya Valery Ilinsky Alexander Rakitko Alexander Rakitko Maria Poptsova |
| author_sort | Vladislav Perelygin |
| collection | DOAJ |
| description | BackgroundPolygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer’s disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis.MethodsSimulated data with 2- and 3-loci interactions and tested three different models of epistasis: additive, multiplicative and threshold, were generated using the GAMETES. Penetrance tables were generated using PyTOXO package. For machine learning methods we used multilayer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), Lasso regression, random forest and gradient boosting models. Performance of machine learning models were assessed using accuracy, AUC-ROC, AUC-PR, recall, precision, and F1 score.ResultsFirst, we tested ensemble tree methods and deep learning neural networks against LASSO linear regression model on simulated data with different types and strength of epistasis. The results showed that with the increase of strength of epistasis effect, non-linear models significantly outperform linear. Then the higher performance of non-linear models over linear was confirmed on real genetic data for multifactorial phenotypes such as obesity, type 1 diabetes, and psoriasis. From non-linear models, gradient boosting appeared to be the best model in obesity and psoriasis while deep learning methods significantly outperform linear approaches in type 1 diabetes.ConclusionOverall, our study underscores the efficacy of non-linear models and deep learning approaches in more accurately accounting for the effects of epistasis in simulations with specific configurations and in the context of certain diseases. |
| format | Article |
| id | doaj-art-f7cb4ed1449d4d199f152b7b272c9c0a |
| institution | Kabale University |
| issn | 2296-858X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj-art-f7cb4ed1449d4d199f152b7b272c9c0a2025-01-07T05:24:05ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-01-011110.3389/fmed.2024.14797171479717Deep learning captures the effect of epistasis in multifactorial diseasesVladislav Perelygin0Alexey Kamelin1Alexey Kamelin2Nikita Syzrantsev3Layal Shaheen4Layal Shaheen5Anna Kim6Nikolay Plotnikov7Anna Ilinskaya8Valery Ilinsky9Alexander Rakitko10Alexander Rakitko11Maria Poptsova12International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, RussiaInternational Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, RussiaGenotek Ltd., Moscow, RussiaGenotek Ltd., Moscow, RussiaGenotek Ltd., Moscow, RussiaPhystech School of Biological and Medical Physics, Moscow Institute of Physics and Technology, Moscow, RussiaGenotek Ltd., Moscow, RussiaGenotek Ltd., Moscow, RussiaEligens SIA, Mārupe, LatviaEligens SIA, Mārupe, LatviaInternational Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, RussiaGenotek Ltd., Moscow, RussiaInternational Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, RussiaBackgroundPolygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer’s disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis.MethodsSimulated data with 2- and 3-loci interactions and tested three different models of epistasis: additive, multiplicative and threshold, were generated using the GAMETES. Penetrance tables were generated using PyTOXO package. For machine learning methods we used multilayer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), Lasso regression, random forest and gradient boosting models. Performance of machine learning models were assessed using accuracy, AUC-ROC, AUC-PR, recall, precision, and F1 score.ResultsFirst, we tested ensemble tree methods and deep learning neural networks against LASSO linear regression model on simulated data with different types and strength of epistasis. The results showed that with the increase of strength of epistasis effect, non-linear models significantly outperform linear. Then the higher performance of non-linear models over linear was confirmed on real genetic data for multifactorial phenotypes such as obesity, type 1 diabetes, and psoriasis. From non-linear models, gradient boosting appeared to be the best model in obesity and psoriasis while deep learning methods significantly outperform linear approaches in type 1 diabetes.ConclusionOverall, our study underscores the efficacy of non-linear models and deep learning approaches in more accurately accounting for the effects of epistasis in simulations with specific configurations and in the context of certain diseases.https://www.frontiersin.org/articles/10.3389/fmed.2024.1479717/fullpolygenic risk scoremultifactorial diseasesepistasisobesitytype 1 diabetespsoriasis |
| spellingShingle | Vladislav Perelygin Alexey Kamelin Alexey Kamelin Nikita Syzrantsev Layal Shaheen Layal Shaheen Anna Kim Nikolay Plotnikov Anna Ilinskaya Valery Ilinsky Alexander Rakitko Alexander Rakitko Maria Poptsova Deep learning captures the effect of epistasis in multifactorial diseases Frontiers in Medicine polygenic risk score multifactorial diseases epistasis obesity type 1 diabetes psoriasis |
| title | Deep learning captures the effect of epistasis in multifactorial diseases |
| title_full | Deep learning captures the effect of epistasis in multifactorial diseases |
| title_fullStr | Deep learning captures the effect of epistasis in multifactorial diseases |
| title_full_unstemmed | Deep learning captures the effect of epistasis in multifactorial diseases |
| title_short | Deep learning captures the effect of epistasis in multifactorial diseases |
| title_sort | deep learning captures the effect of epistasis in multifactorial diseases |
| topic | polygenic risk score multifactorial diseases epistasis obesity type 1 diabetes psoriasis |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1479717/full |
| work_keys_str_mv | AT vladislavperelygin deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT alexeykamelin deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT alexeykamelin deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT nikitasyzrantsev deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT layalshaheen deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT layalshaheen deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT annakim deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT nikolayplotnikov deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT annailinskaya deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT valeryilinsky deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT alexanderrakitko deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT alexanderrakitko deeplearningcapturestheeffectofepistasisinmultifactorialdiseases AT mariapoptsova deeplearningcapturestheeffectofepistasisinmultifactorialdiseases |