Parkinson's disease (PD) is characterized by complex clinical symptoms, including classic motor and nonmotor disturbances. Patients with PD vary in clinical manifestations and prognosis, which point to the existence of subtypes. This study aimed to find the fiber connectivity correlations with several crucial clinical symptoms and identify PD subtypes using unsupervised clustering analysis. One hundred and thirty‐four PD patients and 77 normal controls were enrolled. Canonical correlation analysis (CCA) was performed to define the clinically relevant connectivity features, which were then used in the hierarchical clustering analysis to identify the distinct subtypes of PD patients. Multimodal neuroimaging analyses were further used to explore the neurophysiological basis of these subtypes. The methodology was validated in an independent data set. CCA revealed two significant clinically relevant patterns (motor‐related pattern and depression‐related pattern; r = .94, p < .001 and r = .926, p = .001, respectively) among PD patients, and hierarchical clustering analysis identified three neurophysiological subtypes (“mild” subtype, “severe depression‐dominant” subtype and “severe motor‐dominant” subtype). Multimodal neuroimaging analyses suggested that the patients in the “severe depression‐dominant” subtype exhibited widespread disruptions both in function and structure, while the other two subtypes exhibited relatively mild abnormalities in brain function. In the independent validation, three similar subtypes were identified. In conclusion, we revealed heterogeneous subtypes of PD patients according to their distinct clinically relevant connectivity features. Importantly, depression symptoms have a considerable impact on brain damage in patients with PD.