Acquired somatic mutations are incorporated in the classification and prognosis of myelodysplastic syndromes/neoplasms (MDS). However, the predictive role of molecular features in MDS need to be elucidated, especially in the lower-risk subtypes (LR-MDS), where treatment has become more heterogenous, and specific predictive biomarkers are lacking. In this study we investigated genetic markers associated with erythropoiesis stimulating agent (ESA) response in LR-MDS. A European cohort of 535 LR-MDS patients was analyzed using targeted next-generation sequencing (t-NGS) to calculate molecular prognostic scores (IPSS-M) and explore the relationship between somatic mutations and ESA response. The integration of IPSS-M score among the 2 known variables sEPO and transfusion dependence, refined the capability to predict response (AUC 0.71 vs 0.63, p=0.0004). Based on these 3 variables, a molecular predictive score, that we named ESA-PSS-M (-0.05*[sEPO U/L]-4.5*[IPSS-M score]-5*[TD, yes =1, no =0]; specificity 76%, sensitivity 57%), was generated and validated in an external cohort of 223 LR-MDS cases. Despite the impact of IPSS-M score, no single mutated gene was linked to ESA response, however, when we stratified cases by sex at birth, we observed that mutations in the X-linked STAG2 gene were significantly associated with ESA resistance in LR-MDS males (OR 0.13, p=0.003). To our knowledge, this is the first study based on a large multicenter cohort of patients suggesting that the integration of IPSS-M score and sex-specific mutations can characterize erythropoiesis defects and guide first line therapeutic choices for anemic LR-MDS (i.e. ESAs vs Luspatercept).