c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease
Abstract Background Alzheimer’s disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer’s can faci...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-10-01
|
| Series: | BMC Medical Genomics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12920-023-01675-9 |
| _version_ | 1797659752927330304 |
|---|---|
| author | Sherlyn Jemimah Aamna AlShehhi for the Alzheimer’s Disease Neuroimaging Initiative |
| author_facet | Sherlyn Jemimah Aamna AlShehhi for the Alzheimer’s Disease Neuroimaging Initiative |
| author_sort | Sherlyn Jemimah |
| collection | DOAJ |
| description | Abstract Background Alzheimer’s disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer’s can facilitate less-invasive, routine diagnostic tests to aid early intervention. Therefore, we propose “c-Diadem” (constrained dual-input Alzheimer’s disease model), a novel deep learning classifier which incorporates KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway constraints on the input genotyping data to predict disease, i.e., mild cognitive impairment (MCI)/AD or cognitively normal (CN). SHAP (SHapley Additive exPlanations) was used to explain the model and identify novel, potential blood-based genetic markers of MCI/AD. Methods We developed a novel constrained deep learning neural network which utilizes SNPs (single nucleotide polymorphisms) and microarray data from ADNI (Alzheimer’s Disease Neuroimaging Initiative) to predict the disease status of participants, i.e., CN or with disease (MCI/AD), and identify potential blood-based biomarkers for diagnosis and intervention. The dataset contains samples from 626 participants, of which 212 are CN (average age 74.6 ± 5.4 years) and 414 patients have MCI/AD (average age 72.7 ± 7.6 years). KEGG pathway information was used to generate constraints applied to the input tensors, thus enhancing the interpretability of the model. SHAP scores were used to identify genes which could potentially serve as biomarkers for diagnosis and targets for drug development. Results Our model’s performance, with accuracy of 69% and AUC of 70% in the test dataset, is superior to previous models. The SHAP scores show that SNPs in PRKCZ, PLCB1 and ITPR2 as well as expression of HLA-DQB1, EIF1AY, HLA-DQA1, and ZFP57 have more impact on model predictions. Conclusions In addition to predicting MCI/AD, our model has been interrogated for potential genetic biomarkers using SHAP. From our analysis, we have identified blood-based genetic markers related to Ca2+ ion release in affected regions of the brain, as well as depression. The findings from our study provides insights into disease mechanisms, and can facilitate innovation in less-invasive, cost-effective diagnostics. To the best of our knowledge, our model is the first to use pathway constraints in a multimodal neural network to identify potential genetic markers for AD. |
| first_indexed | 2024-03-11T18:20:43Z |
| format | Article |
| id | doaj.art-04e684010d9d4a5d893e0f5d99e697ae |
| institution | Directory Open Access Journal |
| issn | 1755-8794 |
| language | English |
| last_indexed | 2024-03-11T18:20:43Z |
| publishDate | 2023-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Genomics |
| spelling | doaj.art-04e684010d9d4a5d893e0f5d99e697ae2023-10-15T11:31:40ZengBMCBMC Medical Genomics1755-87942023-10-0116S211310.1186/s12920-023-01675-9c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s diseaseSherlyn Jemimah0Aamna AlShehhi1for the Alzheimer’s Disease Neuroimaging InitiativeDepartment of Biomedical Engineering, Khalifa UniversityDepartment of Biomedical Engineering, Khalifa UniversityAbstract Background Alzheimer’s disease (AD) is an incurable, debilitating neurodegenerative disorder. Current biomarkers for AD diagnosis require expensive neuroimaging or invasive cerebrospinal fluid sampling, thus precluding early detection. Blood-based biomarker discovery in Alzheimer’s can facilitate less-invasive, routine diagnostic tests to aid early intervention. Therefore, we propose “c-Diadem” (constrained dual-input Alzheimer’s disease model), a novel deep learning classifier which incorporates KEGG (Kyoto Encyclopedia of Genes and Genomes) pathway constraints on the input genotyping data to predict disease, i.e., mild cognitive impairment (MCI)/AD or cognitively normal (CN). SHAP (SHapley Additive exPlanations) was used to explain the model and identify novel, potential blood-based genetic markers of MCI/AD. Methods We developed a novel constrained deep learning neural network which utilizes SNPs (single nucleotide polymorphisms) and microarray data from ADNI (Alzheimer’s Disease Neuroimaging Initiative) to predict the disease status of participants, i.e., CN or with disease (MCI/AD), and identify potential blood-based biomarkers for diagnosis and intervention. The dataset contains samples from 626 participants, of which 212 are CN (average age 74.6 ± 5.4 years) and 414 patients have MCI/AD (average age 72.7 ± 7.6 years). KEGG pathway information was used to generate constraints applied to the input tensors, thus enhancing the interpretability of the model. SHAP scores were used to identify genes which could potentially serve as biomarkers for diagnosis and targets for drug development. Results Our model’s performance, with accuracy of 69% and AUC of 70% in the test dataset, is superior to previous models. The SHAP scores show that SNPs in PRKCZ, PLCB1 and ITPR2 as well as expression of HLA-DQB1, EIF1AY, HLA-DQA1, and ZFP57 have more impact on model predictions. Conclusions In addition to predicting MCI/AD, our model has been interrogated for potential genetic biomarkers using SHAP. From our analysis, we have identified blood-based genetic markers related to Ca2+ ion release in affected regions of the brain, as well as depression. The findings from our study provides insights into disease mechanisms, and can facilitate innovation in less-invasive, cost-effective diagnostics. To the best of our knowledge, our model is the first to use pathway constraints in a multimodal neural network to identify potential genetic markers for AD.https://doi.org/10.1186/s12920-023-01675-9Alzheimer’s diseaseBiomarkersNeural networkDeep learningBinary classificationGenomics |
| spellingShingle | Sherlyn Jemimah Aamna AlShehhi for the Alzheimer’s Disease Neuroimaging Initiative c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease BMC Medical Genomics Alzheimer’s disease Biomarkers Neural network Deep learning Binary classification Genomics |
| title | c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease |
| title_full | c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease |
| title_fullStr | c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease |
| title_full_unstemmed | c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease |
| title_short | c-Diadem: a constrained dual-input deep learning model to identify novel biomarkers in Alzheimer’s disease |
| title_sort | c diadem a constrained dual input deep learning model to identify novel biomarkers in alzheimer s disease |
| topic | Alzheimer’s disease Biomarkers Neural network Deep learning Binary classification Genomics |
| url | https://doi.org/10.1186/s12920-023-01675-9 |
| work_keys_str_mv | AT sherlynjemimah cdiademaconstraineddualinputdeeplearningmodeltoidentifynovelbiomarkersinalzheimersdisease AT aamnaalshehhi cdiademaconstraineddualinputdeeplearningmodeltoidentifynovelbiomarkersinalzheimersdisease AT forthealzheimersdiseaseneuroimaginginitiative cdiademaconstraineddualinputdeeplearningmodeltoidentifynovelbiomarkersinalzheimersdisease |