Protrec2：組織特異的ネットワークベースの欠損タンパク質回復法

Despite technological advances, missing proteins remain a challenge in proteomics, obscuring proteins that are biologically or clinically important. We present Protrec2, a probabilistic framework that integrates tissue-specific protein complex annotations with Bayesian inference to recover unreported but biologically present proteins. We benchmarked Protrec2 on HeLa and A549-derived proteomes under "upper-bound" and "lower-bound" scenarios, reflecting distinct but complementary real-world use cases. In upper-bound evaluations, Protrec2 consistently outperformed state-of-the-art methods such as PROTein RECovery, Functional Class Scoring, Hypergeometric Enrichment, and Gene Set Enrichment Analysis, achieving the highest recovery rates: up to 98.4% in A549 and 96.5% in HeLa and validating 650 and 453 proteins, respectively. In lower-bound evaluations, Protrec2 maintained superior precision, validating over 90% of its predicted proteins in the A549 dataset and 74.6% in HeLa, while other methods exhibited significant performance drops. We applied Protrec2 to six matched lung tumor-normal pairs and validated predictions against CPTAC. Over 85% of predicted proteins were supported, with cancer-specific proteins mostly upregulated and normal-exclusive ones downregulated. Frequently recovered proteins (e.g. P4HA3, SNX1, HIP1R, NOS2) are known to play key roles in lung cancer, highlighting the biological and clinical relevance of Protrec2. These findings establish Protrec2 as a robust, biologically grounded tool for missing protein recovery, with broad applicability in discovery proteomics and translational research.