--- title: "ShortStop: Prioritizing Microproteins with Machine Learning" description: ShortStop uses machine learning to classify smORFs by similarity to known microproteins, helping prioritise candidates for follow-up and validation image: https://blog.varsome.com/hubfs/ShortStop%20feat%202.png --- [Skip to content](https://blog.varsome.com/annotated/shortstop-prioritizing-microproteins-with-machine-learning#main-content) ![VarSome logo white txts](https://blog.varsome.com/hs-fs/hubfs/VarSome%20logo%20white%20txts.png?width=160&height=40&name=VarSome%20logo%20white%20txts.png)Homepage - Editions - [VarSome.com](https://landing.varsome.com/varsome) - [VarSome Clinical](https://landing.varsome.com/varsome-clinical) - [VarSome Premium](https://landing.varsome.com/varsome-premium) - [VarSome API](https://landing.varsome.com/varsome-api) - [VarSome Insights](https://landing.varsome.com/varsome-insights) - About - [The Company](https://saphetor.com/) - [Contact Us](https://landing.varsome.com/contact) - [Distributors](https://landing.varsome.com/distributors) - [Become a Partner](https://landing.varsome.com/become-varsome-partner) - [Community](https://varsome.com/community-contributions/) - [Cite VarSome!](https://landing.varsome.com/citations) - Resources - [Datasources](https://varsome.com/datasources/) - [Germline Classification](https://varsome.com/about/resources/germline-implementation/) - [Somatic Classification](https://varsome.com/about/resources/somatic-implementation/) - [CNV Classification](https://varsome.com/about/resources/sv-implementation/) - [Help Center](https://docs.varsome.com/) - [Library](https://landing.varsome.com/whitepapers) - [IVDR](https://landing.varsome.com/ivdr-whitepaper) - [Legal & Compliance](https://docs.varsome.com/en/legal-compliance) - Blog - [Platform Updates](https://updates.varsome.com/en) - [Company News](https://news.varsome.com/en) - [VarSome Annotated](https://blog.varsome.com/annotated) - Editions - [VarSome.com](https://landing.varsome.com/varsome) - [VarSome Clinical](https://landing.varsome.com/varsome-clinical) - [VarSome Premium](https://landing.varsome.com/varsome-premium) - [VarSome API](https://landing.varsome.com/varsome-api) - [VarSome Insights](https://landing.varsome.com/varsome-insights) - About - [The Company](https://saphetor.com/) - [Contact Us](https://landing.varsome.com/contact) - [Distributors](https://landing.varsome.com/distributors) - [Become a Partner](https://landing.varsome.com/become-varsome-partner) - [Community](https://varsome.com/community-contributions/) - [Cite VarSome!](https://landing.varsome.com/citations) - Resources - [Datasources](https://varsome.com/datasources/) - [Germline Classification](https://varsome.com/about/resources/germline-implementation/) - [Somatic Classification](https://varsome.com/about/resources/somatic-implementation/) - [CNV Classification](https://varsome.com/about/resources/sv-implementation/) - [Help Center](https://docs.varsome.com/) - [Library](https://landing.varsome.com/whitepapers) - [IVDR](https://landing.varsome.com/ivdr-whitepaper) - [Legal & Compliance](https://docs.varsome.com/en/legal-compliance) - Blog - [Platform Updates](https://updates.varsome.com/en) - [Company News](https://news.varsome.com/en) - [VarSome Annotated](https://blog.varsome.com/annotated) ![](https://blog.varsome.com/hs-fs/hubfs/ShortStop%20feat%202.png?width=1000&height=523&name=ShortStop%20feat%202.png) Technology VarSome.com Research Brief # ShortStop: Prioritizing Microproteins with Machine Learning ![Jason Armstrong](https://blog.varsome.com/hs-fs/hubfs/Jason%20HHS.jpeg?width=48&height=48&name=Jason%20HHS.jpeg) Jason Armstrong August 11, 2025 In a new paper, Miller *et al.* (2025)1 present *ShortStop*, a machine learning framework to distinguish potentially functional microproteins in non-coding regions from the noise. It’s a problem with clear relevance in clinical genomics, where data volume continues to outpace interpretation capacity.  *ShortStop* is designed to triage thousands of small open reading frames (smORFs) now known to be translated in the human genome. Most don’t resemble canonical proteins and may only have a regulatory role, if any function at all. The authors propose a method to classify smORFs based on their biochemical similarity to known, experimentally validated proteins.  # A Two-class System The *ShortStops* approach introduces two reference groups:  - SAMs (Swiss-Prot Analog Microproteins): short, validated, evolutionarily conserved proteins in the Swiss-Prot database. - PRISMs (Physiochemically Resembling *In Silico* Microproteins): synthetic smORFs that mimic the composition of real ones but lack evolutionary or functional structure. By defining two reference classes and training a model on physicochemical features (e.g., hydrophobicity, amino acid motifs, charge), the authors built a classifier that achieved high precision and recall. Extreme Gradient Boosting (XGBoost) outperformed other models with an AUC of 0.97. When applied to 7264 smORFs from Mudge *et al.* (2022)2, *ShortStop* classified only 8% as SAMS, suggesting most translated smORFs resemble non-canonical or likely non-functional sequences.  # Why This Matters As in variant interpretation, the challenge isn’t finding candidates but narrowing them down. The value of a method like *ShortStop* lies in prioritization. By flagging those smORFs that share biochemical properties with known proteins, researchers can focus follow-up efforts where they are most likely to yield meaningful results, reducing time spent on low-likelihood candidates and streamlining decision-making.  These goals are becoming increasingly important as data volumes grow and analysis becomes more complex. The infrastructure now exists to support more automation in research and clinical settings. What is still limited is time and expert capacity. Manual review remains essential, especially for edge cases or unexpected results, but it needs to be used more efficiently. Tools like *ShortStop* can help by guiding attention to the most promising signals and away from low-likelihood noise.  # Case Example: StARump A previously overlooked smORF in the *StAR* gene is used as an example by the authors. Later named *StARump,* this microprotein had not been identified by standard ribosome profiling or by TIS transformers, likely due to its location in a region of overlapping coding sequence with poor mappability. However, *ShortStop* classified it as a SAM, which was confirmed by mass spectrometry (MS). *StARump* was found to be highly expressed in the testis, ovary, and CSF, despite low transcript levels of the canonical *StAR* ORF in those tissues.  *StARump’s* detection demonstrates how combining prediction tools with complementary inputs, such as *ShortStop’s* classifier and MS data, respectively, can reveal overlooked biology. # Clinical Relevance: Lung Cancer To show translational relevance, the authors applied *ShortStop* to RNA-seq and immunopeptidome data from non-smoking lung cancer patients. Several SAMs were differentially expressed between tumor and normal tissues. 210 SAM-derived peptides were detected on MHC-I, including one from an alternative *COL1A1* transcript that was strongly upregulated. This supports the theory that some of these overlooked microproteins may play biological roles, or even become clinically relevant.  # Final Thoughts *ShortStop* fills a specific gap in current discovery tools by classifying smORFs according to their similarity to known microproteins. It cannot detect translation, but helps prioritize which translated smORFs are worth further study. This kind of triage supports the same goals as many diagnostic workflows: reducing manual review, improving consistency, and focusing attention on the most informative candidates.  There is a growing push to integrate multimodal data into clinical workflows. Combining genomics, transcriptomics, proteomics, and immunopeptidomics can reveal patterns invisible to any single data type. Machine learning tools that complement or incorporate this kind of information will become more important in diagnostic pipelines. As automation becomes more embedded, the aim is not to replace human expertise but to support it, so interpretation efforts can focus where they are most likely to be impactful. The *ShortStop* framework is freely available on GitHub: [https://github.com/brendan-miller-salk/ShortStop](https://github.com/brendan-miller-salk/ShortStop) # References 1. [Miller B, De Souza EV, Pai VJ, et al. ShortStop: a machine learning framework for microprotein discovery. BMC Methods. 2025;2(1):16. doi:10.1186/s44330-025-00037-4](https://bmcmethods.biomedcentral.com/articles/10.1186/s44330-025-00037-4) 2. [Mudge JM, Ruiz-Orera J, Prensner JR, et al. Standardized annotation of translated open reading frames. Nat Biotechnol. 2022;40(7):994-999. doi:10.1038/s41587-022-01369-0](https://pubmed.ncbi.nlm.nih.gov/35831657/) ## Share this post [mailto:https%3A%2F%2Fblog.varsome.com%2Fannotated%2Fshortstop-prioritizing-microproteins-with-machine-learning](mailto:https%3A%2F%2Fblog.varsome.com%2Fannotated%2Fshortstop-prioritizing-microproteins-with-machine-learning) ## Keep reading ### [![](https://blog.varsome.com/hs-fs/hubfs/Monogenic%20Diabetes.png?width=1000&height=523&name=Monogenic%20Diabetes.png) VarSome Annotated Minor Spliceosome Defects Drive Monogenic Autoimmune Diabetes](https://blog.varsome.com/annotated/minor-spliceosome-defects-drive-monogenic-autoimmune-diabetes) ### [![](https://blog.varsome.com/hs-fs/hubfs/Sickle%20Cell.png?width=1000&height=523&name=Sickle%20Cell.png) VarSome Annotated Promoter Editing and Fetal Hemoglobin Reactivation in Sickle Cell Disease](https://blog.varsome.com/annotated/promoter-editing-and-fetal-hemoglobin-reactivation-in-sickle-cell-disease) --- Privacy Policy · Legal · © 2025. All rights reserved. ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Jason Armstrong", "url" : "https://blog.varsome.com/annotated/author/jason-armstrong" }, "dateModified" : "2025-08-12T07:14:07.178Z", "datePublished" : "2025-08-11T08:14:42.000Z", "headline" : "ShortStop: Prioritizing Microproteins with Machine Learning", "image" : [ "https://blog.varsome.com/hubfs/ShortStop%20feat%202.png" ], "mainEntityOfPage" : { "@id" : "https://blog.varsome.com/annotated/shortstop-prioritizing-microproteins-with-machine-learning", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://blog.varsome.com/hubfs/varsome-new.png" }, "name" : "Saphetor SA" } } ```