Measuring protein turnover is essential for understanding cellular biological processes and advancing drug discovery. The multiplex-DIA mass spectrometry (DIA-MS) approach, combined with dynamic SILAC labeling (pulse-SILAC, or pSILAC), has proven to be a reliable method for analyzing protein turnover and degradation kinetics. Previous multiplex-DIA-MS workflows have employed various strategies, including leveraging the highest isotopic labeling channels of peptides to enhance the detection of isotopic MS signal pairs or clusters. In this study, we introduce an improved workflow that integrates a novel machine learning strategy and channel-specific statistical filtering, enabling dynamic adaptation to systematic variations in channel ratios throughout pSILAC and SILAC experiments. These functions were evaluated to significantly improve both the comprehensiveness and accuracy of protein turnover profiling. In addition, we developed Our integrative workflow was benchmarked on both 2-channel and 3-channel standard DIA datasets and across two mass spectrometry platforms, demonstrating its broad applicability. Applying this workflow to an aneuploid cancer cell model before and after developing cisplatin resistance, we discovered a remarkable negative correlation between transcript regulation and protein degradation for major protein complex subunits elucidating the proteome buffering mechanism in genome aneuploidy.