Discovering Biomarker Proteins and Peptides for Parkinson's Disease Prognosis Prediction with Machine Learning and Interpretability Methods
Park, H.-m.; Kabanga, E.; Moon, D.-i.; Chung, M.; Im, J.; Kim, Y.; Van Messem, A.; De Neve, W.
Show abstract
Parkinsons disease is a neurodegenerative disorder that affects millions of people worldwide, posing significant challenges for diagnosis and treatment. This study presents a machine learning pipeline for identifying candidate biomarker proteins and peptides from cerebrospinal fluid mass spectrometry (CSF-MS) tests in Parkinsons disease patients. Our pipeline comprises two main stages: (1) model training using mutual information-based feature selection and five different machine learning regressors and (2) identification of candidate biomarkers by combining three types of interpretability methods. Our regression models demonstrated promising effectiveness in predicting the Movement Disorder Society-Unified Parkinsons Disease Rating Scale (MDS-UPDRS) scores, with UPDRS-1 receiving the best predictions, followed by UPDRS-3 and UPDRS-2. Furthermore, our pipeline identified 11 proteins and peptides as potential biomarkers for Parkinsons disease, excluding Levodopa usage which trivially has the most significant impact on the prognosis prediction. Comparisons with four additional pipelines confirmed the effectiveness of our approach in terms of both model performance and biomarker identification. In conclusion, our study presents a comprehensive machine learning pipeline that demonstrates effectiveness in predicting the severity of Parkinsons disease using CSF-MS tests. Our approach also identifies potential biomarkers, which could aid in the development of new diagnostic tools and treatments for patients with Parkinsons disease.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ToxinPred 3.0: An improved method for predicting the toxicity of peptides 93%
- AE-LGBM: Sequence-Based Novel Approach To Detect Interacting Protein Pairs via Ensemble of Autoencoder and LightGBM. 92%
- Discriminating the Single-cell Gene Regulatory Networks of Human Pancreatic Islets: A Novel Deep Learning Application 91%
Similar papers in this journal
- Benchmarking feature selection and feature extraction methods to improve the performances of machine-learning algorithms for patient classification using metabolomics biomedical data. 93%
- DeepNeuropePred: a robust and universal tool to predict cleavage sites from neuropeptide precursors by protein language model 93%
- Quality control of variant peptides identified through proteogenomics- catching the (un)usual suspects 92%
Similar papers in this journal
- AITeQ: A machine learning framework for Alzheimer's prediction using a distinctive 5-gene signature 93%
- scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery 92%
- AI-Guided Discovery and Optimization of Antimicrobial Peptides Through Species-Aware Language Model 92%
Similar papers in this journal
- Interpretable dimensionality reduction and classification of mass spectrometry imaging data in a visceral pain model via non-negative matrix factorization 92%
- ICAN: interpretable cross-attention network for identifying drug and target protein interactions 92%
- Improving prediction of drug-target interactions based on fusing multiple features with data balancing and feature selection techniques 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.