This paper introduces a Support Vector Machine (SVM) approach for predicting the subcellular localization of proteins based on their amino acid compositions. The authors developed a prediction system called SubLoc, which achieved a total prediction accuracy of 91.4% for three subcellular locations in prokaryotic organisms and 79.4% for four locations in eukaryotic organisms. The SVM method is robust to errors in the protein N-terminal sequences and outperforms existing algorithms based on amino acid composition. The system is available as a web server at http://www.bioinfo.tsinghua.edu.cn/SubLoc/. The study also discusses the SVM's ability to condense information and its robustness to parameter variations, suggesting potential improvements through combination with other methods and incorporation of additional features.This paper introduces a Support Vector Machine (SVM) approach for predicting the subcellular localization of proteins based on their amino acid compositions. The authors developed a prediction system called SubLoc, which achieved a total prediction accuracy of 91.4% for three subcellular locations in prokaryotic organisms and 79.4% for four locations in eukaryotic organisms. The SVM method is robust to errors in the protein N-terminal sequences and outperforms existing algorithms based on amino acid composition. The system is available as a web server at http://www.bioinfo.tsinghua.edu.cn/SubLoc/. The study also discusses the SVM's ability to condense information and its robustness to parameter variations, suggesting potential improvements through combination with other methods and incorporation of additional features.