ProtLoc-Mex1: Interpretable Analysis of Amino Acids Sequence Chemical Feature and GO Annotations for Predicting Protein Subcellular Localization.

Machine learning algorithms have revolutionized the study of protein subcellular localization; however, their black-box nature limits their interpretability. To address this, we built upon ProtLoc-Mex1, an automated pipeline incorporating interpretation techniques, by integrating chemical and GO annotation features to create a transparent random forest predictor. When applied to membrane protein type distinction and subcellular localization prediction, ProtLoc-Mex1 identified important features, explored the feature interaction effect and explored the functional feature semantic representation in language models, deepening our understanding of protein targeting mechanisms. We also created modules to facilitate their use for various prediction understanding in machine learning systems and provide a valuable resource for the scientific community. The code is available at (https://github.com/yujuan-zhang/ProtLoc-mexl). 1. ProtLoc-Mex1 extracts key features from protein sequences and GO annotations, enabling filtering, interaction analysis, and semantic interpretation for protein localization. 2. It includes two prediction models: one classifies proteins as Single-pass or Multi-pass membrane types, while the other integrates sequence and GO data to predict various subcellular localizations. 3. This study pioneers the semantic analysis of GO representation vectors, enhancing model interpretability and uncovering key features for membrane structure and localization. [ABSTRACT FROM AUTHOR]