Background Limited successes of gene finding for major depressive disorder (MDD) may be partly due to phenotypic heterogeneity. We tested whether the genetic load for MDD, bipolar disorder, and schizophrenia (SCZ) is increased in phenotypically more homogenous MDD patients identified by specific clinical characteristics. Methods Patients (n = 1539) with a DSM-IV MDD diagnosis and control subjects (n = 1792) were from two large cohort studies (Netherlands Study of Depression and Anxiety and Netherlands Twin Register). Genomic profile risk scores (GPRSs) for MDD, bipolar disorder, and SCZ were based on meta-analysis results of the Psychiatric Genomics Consortium. Regression analyses (adjusted for year of birth, sex, three principal components) examined the association between GPRSs with characteristics and GPRSs with MDD subgroups stratified according to the most relevant characteristics. The proportion of liability variance explained by GPRSs for each MDD subgroup was estimated. Results GPRS-MDD explained 1.0% (p = 4.19e−09) of MDD variance, and 1.5% (p = 4.23e−09) for MDD endorsing nine DSM symptoms. GPRS–bipolar disorder explained 0.6% (p = 2.97e−05) of MDD variance and 1.1% (p = 1.30e−05) for MDD with age at onset <18 years. GPRS-SCZ explained 2.0% (p = 6.15e−16) of MDD variance, 2.6% (p = 2.88e−10) for MDD with higher symptom severity, and 2.3% (p = 2.26e−13) for MDD endorsing nine DSM symptoms. An independent sample replicated the same pattern of stronger associations between cases with more DSM symptoms, as compared to overall MDD, and GPRS-SCZ. Conclusions MDD patients with early age at onset and higher symptom severity have an increased genetic risk for three major psychiatric disorders, suggesting that it is useful to create phenotypically more homogenous groups when searching for genes associated with MDD.