{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T09:00:45Z","timestamp":1772701245691,"version":"3.50.1"},"reference-count":43,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia","award":["PNURSP2026R346"],"award-info":[{"award-number":["PNURSP2026R346"]}]},{"name":"Prince Sultan University, Riyadh, Saudi Arabia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Parkinson\u2019s disease (PD) progression is clinically heterogeneous, complicating predictive modeling and personalized monitoring. We developed a protein-peptide sequential convolutional neural network (pSCNN) enhanced with kernel density estimation (KDE) to capture nonlinear relationships between cerebrospinal fluid (CSF) biomarkers, clinical features, and longitudinal Unified Parkinson\u2019s Disease Rating Scale (UPDRS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Data from 248 patients in the Accelerating Medicines Partnership\u2013PD (AMP-PD) cohort, including CSF and visit metadata, were aligned\n                      <jats:italic>via<\/jats:italic>\n                      arithmetic averaging of UniProt-level technical replicates within visits, then pivoted into wide-format matrices and merged on visit identifiers to create unified multimodal profiles. Aligned features underwent Box-Cox transformation, filtering, and KDE-based distributional modeling. The trained pSCNN was evaluated using the mean absolute error (MAE) and the symmetric mean absolute percentage error (SMAPE).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>The pSCNN reduced average SMAPE from 125.4% to 92.6% and MAE from 6.60 to 5.35 across UPDRS subscales relative to baseline models, with the largest gains observed for motor symptoms (UPDRS-III: SMAPE 125.5% to 72.9%). SHapley Additive exPlanations (SHAP) analysis identified medication status (upd23b) and temporal progression (visit month) as the strongest predictors, while space-time analysis demonstrated close alignment between predicted and observed molecular trajectories.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Interpretation<\/jats:title>\n                    <jats:p>KDE-enhanced multimodal biomarker integration improves regression-based modeling of PD progression by capturing medication-dependent distributional shifts invisible to linear methods. The pSCNN offers an interpretable and reproducible framework for biomarker-driven disease tracking. However, external validation across independent cohorts with documented disease staging is required before clinical deployment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.7717\/peerj-cs.3639","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T08:18:25Z","timestamp":1772698705000},"page":"e3639","source":"Crossref","is-referenced-by-count":0,"title":["Protein-peptide sequential convolutional network for interpretable prediction of unified Parkinson\u2019s disease rating scale trajectories"],"prefix":"10.7717","volume":"12","author":[{"given":"Tanzila","family":"Saba","sequence":"first","affiliation":[{"name":"Artificial Intelligence & Data Analytics Lab CCIS, Prince Sultan University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunusi Bala","family":"Abdullahi","sequence":"additional","affiliation":[{"name":"Department of Information Systems Engineering, Faculty of Computer and Information Sciences, Sakarya University, Sakarya, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faten S.","family":"Alamri","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, College of Science, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salma","family":"Idris","sequence":"additional","affiliation":[{"name":"Artificial Intelligence & Data Analytics Lab CCIS, Prince Sultan University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saeed Ali","family":"Bahaj","sequence":"additional","affiliation":[{"name":"MIS Department, College of Business Administration, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amjad","family":"Rehman","sequence":"additional","affiliation":[{"name":"Artificial Intelligence & Data Analytics Lab CCIS, Prince Sultan University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"issue":"3","key":"10.7717\/peerj-cs.3639\/ref-1","doi-asserted-by":"publisher","first-page":"3511","DOI":"10.1109\/access.2023.3233969","article-title":"Deep transfer learning based Parkinson\u2019s disease detection using optimized feature selection","volume":"11","author":"Abdullah","year":"2023","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3639\/ref-2","doi-asserted-by":"publisher","first-page":"88511","DOI":"10.1109\/ACCESS.2023.3305255","article-title":"IDF-Sign: addressing inconsistent depth features for dynamic sign word recognition","volume":"11","author":"Abdullahi","year":"2023","journal-title":"IEEE Access"},{"issue":"2018","key":"10.7717\/peerj-cs.3639\/ref-3","doi-asserted-by":"publisher","first-page":"49167","DOI":"10.1109\/access.2022.3171850","article-title":"Biometric information recognition using artificial intelligence algorithms: a performance comparison","volume":"10","author":"Abdullahi","year":"2022","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3639\/ref-4","doi-asserted-by":"publisher","first-page":"55388","DOI":"10.1109\/access.2021.3068215","article-title":"Data-driven AI-based parameters tuning using grid partition algorithm for predicting climatic effect on epidemic diseases","volume":"9","author":"Abdullahi","year":"2021","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-5","doi-asserted-by":"publisher","first-page":"872","DOI":"10.32604\/cmc.2022.024596","article-title":"Parkinson\u2019s detection using RNN-graph-LSTM with optimization based on speech signals","volume":"72","author":"Almasoud","year":"2022","journal-title":"Computers Materials & Continua"},{"issue":"20","key":"10.7717\/peerj-cs.3639\/ref-6","doi-asserted-by":"publisher","first-page":"14499","DOI":"10.1007\/s00521-021-06626-y","article-title":"Automated methods for diagnosis of parkinsons disease and predicting severity level","volume":"35","author":"Ayaz","year":"2023","journal-title":"Neural Computing and Applications"},{"key":"10.7717\/peerj-cs.3639\/ref-7","article-title":"Exploring the potential of gene and cell-based therapies in Parkinsons","author":"Barker","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-8","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1093\/brain\/awac258","article-title":"Extracellular vesicle biomarkers for cognitive impairment in parkinsons disease","volume":"146","author":"Blommer","year":"2023","journal-title":"Brain"},{"issue":"4","key":"10.7717\/peerj-cs.3639\/ref-9","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1111\/ene.15692","article-title":"White matter hyperintensity burden predicts cognitive but not motor decline in Parkinsons disease: results from the Ontario neurodegenerative diseases research initiative","volume":"30","author":"Carvalho de Abreu","year":"2023","journal-title":"European Journal of Neurology"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-10","doi-asserted-by":"publisher","first-page":"118772","DOI":"10.1016\/j.eswa.2022.118772","article-title":"Parkinsons disease effective biomarkers based on hjorth features improved by machine learning","volume":"212","author":"Coelho","year":"2023","journal-title":"Expert Systems with Applications"},{"issue":"4","key":"10.7717\/peerj-cs.3639\/ref-11","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.3390\/s23042085","article-title":"Bayesian optimization with support vector machine model for Parkinson disease classification","volume":"23","author":"Elshewey","year":"2023","journal-title":"Sensors"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-12","doi-asserted-by":"publisher","first-page":"17485","DOI":"10.1038\/s41598-019-54029-w","article-title":"Parkinsons disease prognostic scores for progression of cognitive decline","volume":"9","author":"Gramotnev","year":"2019","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.3639\/ref-13","article-title":"Parkinson\u2019s disease progression prediction with tensorflow decision forests","author":"Gusthema","year":"2023"},{"issue":"9996","key":"10.7717\/peerj-cs.3639\/ref-14","doi-asserted-by":"publisher","first-page":"137435","DOI":"10.1016\/j.neulet.2023.137435","article-title":"Motor progression phenotypes in early-stage Parkinsons disease: a clinical prediction model and the role of glymphatic system imaging biomarkers","volume":"814","author":"He","year":"2023b","journal-title":"Neuroscience Letters"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-15","doi-asserted-by":"publisher","first-page":"105987","DOI":"10.1016\/j.parkreldis.2023.105987","article-title":"The association of CSF biomarkers and cognitive decline with choroid plexus volume in early parkinson\u2019s disease","volume":"120","author":"He","year":"2023c","journal-title":"Parkinsonism & Related Disorders"},{"issue":"3","key":"10.7717\/peerj-cs.3639\/ref-16","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1111\/jnc.15882","article-title":"METTL14 is decreased and regulates m6a modification of \n$\\alpha$\u03b1\n-synuclein in Parkinson\u2019s disease","volume":"166","author":"He","year":"2023a","journal-title":"Journal of Neurochemistry"},{"issue":"10","key":"10.7717\/peerj-cs.3639\/ref-17","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.3390\/diagnostics13101691","article-title":"Prediction of cognitive decline in Parkinsons disease using clinical and dat spect imaging features, and hybrid machine learning systems","volume":"13","author":"Hosseinzadeh","year":"2023","journal-title":"Diagnostics"},{"key":"10.7717\/peerj-cs.3639\/ref-18","first-page":"291","article-title":"MetaAD: metabolism-aware anomaly detection for Parkinson\u2019s disease in 3D 18F-FDG PET","author":"Huang","year":"2024"},{"key":"10.7717\/peerj-cs.3639\/ref-19","article-title":"kaiser-meyer-olkin-measure-identity-correlation-matrix","author":"IBM","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-20","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.bbe.2019.05.005","article-title":"Parkinson disease prediction using intrinsic mode function based features from speech signal","volume":"40","author":"Karan","year":"2020","journal-title":"Biocybernetics and Biomedical Engineering"},{"issue":"10","key":"10.7717\/peerj-cs.3639\/ref-21","doi-asserted-by":"publisher","first-page":"101216","DOI":"10.1016\/j.csl.2021.101216","article-title":"Non-negative matrix factorization-based time-frequency feature extraction of voice signal for parkinson\u2019s disease prediction","volume":"69","author":"Karan","year":"2021","journal-title":"Computer Speech & Language"},{"key":"10.7717\/peerj-cs.3639\/ref-22","doi-asserted-by":"publisher","first-page":"181","DOI":"10.65278\/ijtaci.2025.21","article-title":"Feature selection methods in big medical databases: a comprehensive survey","volume":"2025","author":"Karimi","year":"2025","journal-title":"International Journal of Theoretical & Applied Computational Intelligence"},{"key":"10.7717\/peerj-cs.3639\/ref-23","article-title":"The sequential model","author":"Keras","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.3639\/ref-24","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1007\/s00362-017-0960-2","article-title":"Correlated endpoints: simulation, modeling, and extreme correlations","volume":"61","author":"Leonov","year":"2020","journal-title":"Statistical Papers"},{"key":"10.7717\/peerj-cs.3639\/ref-25","article-title":"AMP-Parkinsons disease progression prediction","author":"Leslie","year":"2023"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-26","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/s12539-024-00665-4","article-title":"DeepPD: a deep learning method for predicting peptide detectability based on multi-feature representation and information bottleneck","volume":"17","author":"Li","year":"2025","journal-title":"Interdisciplinary Sciences: Computational Life Sciences"},{"issue":"1\u20132","key":"10.7717\/peerj-cs.3639\/ref-27","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.jns.2015.02.029","article-title":"Heterogeneity among patients with Parkinson\u2019s disease: cluster analysis and genetic association","volume":"351","author":"Ma","year":"2015","journal-title":"Journal of the Neurological Sciences"},{"key":"10.7717\/peerj-cs.3639\/ref-28","doi-asserted-by":"publisher","first-page":"98","DOI":"10.3389\/fnagi.2023.1047017","article-title":"A progression analysis of motor features in Parkinson\u2019s disease based on the mapper algorithm","volume":"15","author":"Ma","year":"2023","journal-title":"Frontiers in Aging Neuroscience"},{"key":"10.7717\/peerj-cs.3639\/ref-29","doi-asserted-by":"publisher","first-page":"627199","DOI":"10.3389\/fnagi.2020.627199","article-title":"Motor progression in early-stage parkinson\u2019s disease: a clinical prediction model and the role of cerebrospinal fluid biomarkers","volume":"12","author":"Ma","year":"2021","journal-title":"Frontiers in Aging Neuroscience"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-30","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1080\/03091902.2022.2097326","article-title":"Machine learning algorithms for the diagnosis of Alzheimer and Parkinson disease","volume":"47","author":"Nancy Noella","year":"2023","journal-title":"Journal of Medical Engineering & Technology"},{"issue":"7","key":"10.7717\/peerj-cs.3639\/ref-31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42979-025-04327-0","article-title":"Cascade convolutional neural network-autoencoder method for Parkinson\u2019s disease detection using multilingual voice signal","volume":"6","author":"Pandey","year":"2025a","journal-title":"SN Computer Science"},{"issue":"8S","key":"10.7717\/peerj-cs.3639\/ref-32","doi-asserted-by":"publisher","first-page":"1142642","DOI":"10.1016\/j.jvoice.2025.06.036","article-title":"Parkinson\u2019s disease detection using hybrid siamese neural network and support vector machine in multilingual voice signal","volume":"211","author":"Pandey","year":"2025b","journal-title":"Journal of Voice"},{"issue":"3","key":"10.7717\/peerj-cs.3639\/ref-33","doi-asserted-by":"publisher","first-page":"e460","DOI":"10.1212\/wnl.0000000000011155","article-title":"Parkinson disease propagation using mri biomarkers and partial least squares path modeling","volume":"96","author":"Pyatigorskaya","year":"2021","journal-title":"Neurology"},{"issue":"2","key":"10.7717\/peerj-cs.3639\/ref-34","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1002\/ana.25962","article-title":"A prodromal brain-clinical pattern of cognition in synucleinopathies","volume":"89","author":"Rahayel","year":"2021","journal-title":"Annals of Neurology"},{"issue":"13","key":"10.7717\/peerj-cs.3639\/ref-35","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.3390\/electronics12132856","article-title":"Parkinsons disease detection using hybrid LSTM-GRU deep learning model","volume":"12","author":"Rehman","year":"2023","journal-title":"Electronics"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-36","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1038\/s41531-022-00412-w","article-title":"Genetically-informed prediction of short-term Parkinson\u2019s disease progression","volume":"8","author":"Sadaei","year":"2022","journal-title":"NPJ Parkinson\u2019s Disease"},{"issue":"9","key":"10.7717\/peerj-cs.3639\/ref-37","doi-asserted-by":"publisher","first-page":"e555","DOI":"10.1016\/s2589-7500(21)00101-1","article-title":"Discovery of Parkinson\u2019s disease states and disease progression modelling: a longitudinal data study using machine learning","volume":"3","author":"Severson","year":"2021","journal-title":"The Lancet Digital Health"},{"issue":"8","key":"10.7717\/peerj-cs.3639\/ref-38","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1057\/jors.2014.103","article-title":"A better measure of relative prediction accuracy for model selection and model estimation","volume":"66","author":"Tofallis","year":"2015","journal-title":"Journal of the Operational Research Society"},{"key":"10.7717\/peerj-cs.3639\/ref-39","first-page":"267","article-title":"Ince-PD model for Parkinson\u2019s disease prediction using MDS-UPDRS i & ii and PDQ-8 score","author":"Tsolakis","year":"2023"},{"key":"10.7717\/peerj-cs.3639\/ref-40","article-title":"Parkinson disease","author":"WHO","year":"2023"},{"issue":"2","key":"10.7717\/peerj-cs.3639\/ref-41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s44174-023-00068-x","article-title":"Artificial intelligence model for Parkinson disease detection using machine learning algorithms","volume":"1","author":"Yadav","year":"2023","journal-title":"Biomedical Materials & Devices"},{"issue":"1","key":"10.7717\/peerj-cs.3639\/ref-42","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s13677-024-00641-9","article-title":"Predicting updrs in Parkinson\u2019s disease using ensembles of self-organizing map and neuro-fuzzy","volume":"13","author":"Zhao","year":"2024","journal-title":"Journal of Cloud Computing"},{"issue":"5","key":"10.7717\/peerj-cs.3639\/ref-43","doi-asserted-by":"publisher","first-page":"5457","DOI":"10.1007\/s10489-021-02524-x","article-title":"Feature selection based on mutual information with correlation coefficient","volume":"52","author":"Zhou","year":"2022","journal-title":"Applied Intelligence"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3639.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3639.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3639.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3639.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T08:18:28Z","timestamp":1772698708000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":43,"alternative-id":["10.7717\/peerj-cs.3639"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3639","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]},"article-number":"e3639"}}