The prognostic value of SUMO1/Sentrin specific peptidase 1 (SENP1) in prostate cancer is limited to ERG-fusion positive tumors lacking PTEN deletion

Background: Posttranscriptional protein modification by SUMOylation plays an important role in tumor development and progression. In the current study we analyzed prevalence and prognostic impact of the de SUMOylation enzyme SENP1 in prostate cancer. Methods: SENP1 expression was analyzed by immunohistochemistry on a tissue microarray containing more than 12,400 prostate cancer specimens. Results were compared to tumor phenotype, ERG status, genomic deletions of 3p, 5q, 6q and PTEN, and biochemical recurrence. Results: SENP1 immunostaining was detectable in 34.5 % of 9,516 interpretable cancers and considered strong in 7.3 %, moderate in 14.9 % and weak in 12.3 % of cases. Strong SENP1 expression was linked to advanced pT stage (p < 0.0001), high Gleason grade (p < 0.0001), positive lymph node status (p = 0.0019), high pre-operative PSA levels (p = 0.0037), and PSA recurrence (p < 0.0001). SENP1 expression was strongly associated with positive ERG fusion status as determined by both in situ hybridization (FISH) and immunohistochemistry as well as with PTEN deletions. Detectable SENP1 immunostaining was found in 41 % of ERG positive and in 47 % of PTEN deleted cancers but in only 30 % of ERG negative and 30 % of PTEN non-deleted cancers (p < 0.0001 each). Deletions of 3p, 5q, and 6q were unrelated to SENP1 expression. Subset analyses revealed that the prognostic impact of SENP1 expression was solely driven by the subgroup of ERG positive, PTEN undeleted cancers. In this subgroup, the prognostic role of SENP1 expression was independent of the preoperative PSA level, tumor stage, Gleason grade, and the status of the resection margin. Conclusions: SENP1 expression has strong prognostic impact in a molecularly defined subset of cancers. This is per se not surprising as the biologic impact of each individual molecular event is likely to be dependent on its cellular environment. However, such findings challenge the concept of finding clinically relevant molecular signatures that are equally applicable to all prostate cancers.