Development and external validation of a machine learning model for prediction of survival in undifferentiated pleomorphic sarcoma.

PURPOSE: Machine learning (ML) algorithms to predict cancer survival have recently been reported for a number of sarcoma subtypes, but none have investigated undifferentiated pleomorphic sarcoma (UPS). ML is a powerful tool that has the potential to better prognosticate UPS. METHODS: The Surveillance, Epidemiology, and End Results (SEER) database was queried for cases of histologically confirmed undifferentiated pleomorphic sarcoma (UPS) (n = 665). Patient, tumor, and treatment characteristics were recorded, and ML models were developed to predict 1-, 3-, and 5-year survival. The best performing ML model was externally validated using an institutional cohort of UPS patients (n = 151). RESULTS: All ML models performed best at the 1-year time point and worst at the 5-year time point. On internal validation within the SEER cohort, the best models had c-statistics of 0.67-0.69 at the 5-year time point. The Multi-Layer Perceptron Neural Network (MLP) model was the best performing model and used for external validation. Similarly, the MLP model performed best at 1-year and worst at 5-year on external validation with c-statistics of 0.85 and 0.81, respectively. The MLP model was well calibrated on external validation. The MLP model has been made publicly available at https://rachar.shinyapps.io/ups_app/ . CONCLUSION: Machine learning models perform well for survival prediction in UPS, though this sarcoma subtype may be more difficult to prognosticate than other subtypes. Future studies are needed to further validate the machine learning approach for UPS prognostication.

A physical and transcript map of the MCOLN1 gene region on human chromosome 19p13.3-p13.2.

Mutations in MCOLN1 have been found to cause mucolipidosis type IV (MLIV; MIM 252650), a rare autosomal recessive lysosomal storage disorder found primarily in the Ashkenazi Jewish population. As a part of the successful cloning of MCOLN1, we constructed a 1.4-Mb physical map containing 14 BACs and 4 cosmids that encompasses the region surrounding MCOLN1 on human chromosome 19p13.3-p13.2-a region to which linkage or association has been reported for multiple diseases. Here we detail the precise physical mapping of 28 expressed sequence tags that represent unique UniGene clusters, of which 15 are known genes. We present a detailed transcript map of the MCOLN1 gene region that includes the genes KIAA0521, neuropathy target esterase (NTE), a novel zinc finger gene, and two novel transcripts in addition to MCOLN1. We also report the identification of eight new polymorphic markers between D19S406 and D19S912, which allowed us to pinpoint the location of MCOLN1 by haplotype analysis and which will facilitate future fine-mapping in this region. Additionally, we briefly describe the correlation between the observed haplotypes and the mutations found in MCOLN1. The complete 14-marker haplotypes of non-Jewish disease chromosomes, which are crucial for the genetic diagnosis of MLIV in the non-Jewish population, are presented here for the first time.