Prediction of the Values of CRP, eGFR, and Hemoglobin in the Follow-Up of Renal Cell Carcinoma Patients after (Cryo)Surgery Using Machine Learning Algorithms.

BACKGROUND: Artificial intelligence can support clinical decisions by predictive modeling. Using patient-specific characteristics, models may predict the course of clinical parameters, thus guiding monitoring approaches for the individual patient. Here, we present prediction models for inflammation and for the course of renal function and hemoglobin (Hb) in renal cell carcinoma patients after (cryo)surgery. METHODS: Using random forest machine learning in a longitudinal value-based healthcare data set (n = 86) of renal cell carcinoma patients, prediction models were established and optimized using random and grid searches. Data were split into a training and test set in a 70:30 ratio. Inflammation was predicted for a single timepoint, whereas for renal function estimated glomerular filtration rate (eGFR) and Hb time course prediction was performed. RESULTS: Whereas the last Hb and eGFR values before (cryo)surgery were the main basis for the course of Hb and renal function, age and several time frame features also contributed significantly. For eGFR, the type of (cryo)surgery was also a main predicting feature, and for Hb, tumor location, and body mass index were important predictors. With regard to prediction of inflammation no feature was markedly prominent. Inflammation prediction was based on a combination of patient characteristics, physiological parameters, and time frame features. CONCLUSIONS: This study provided interesting insights into factors influencing complications and recovery in individual renal cell carcinoma patients. The established prediction models provide the basis for development of clinical decision support tools for selection and timing of laboratory analyses after (cryo)surgery, thus contributing to quality and efficiency of care.

Real-time observation of tetrapyrrole binding to an engineered bacterial phytochrome.

Near-infrared fluorescent proteins (NIR FPs) engineered from bacterial phytochromes are widely used for structural and functional deep-tissue imaging in vivo. To fluoresce, NIR FPs covalently bind a chromophore, such as biliverdin IXa tetrapyrrole. The efficiency of biliverdin binding directly affects the fluorescence properties, rendering understanding of its molecular mechanism of major importance. miRFP proteins constitute a family of bright monomeric NIR FPs that comprise a Per-ARNT-Sim (PAS) and cGMP-specific phosphodiesterases - Adenylyl cyclases - FhlA (GAF) domain. Here, we structurally analyze biliverdin binding to miRFPs in real time using time-resolved stimulated Raman spectroscopy and quantum mechanics/molecular mechanics (QM/MM) calculations. Biliverdin undergoes isomerization, localization to its binding pocket, and pyrrolenine nitrogen protonation in <1 min, followed by hydrogen bond rearrangement in ~2 min. The covalent attachment to a cysteine in the GAF domain was detected in 4.3 min and 19 min in miRFP670 and its C20A mutant, respectively. In miRFP670, a second C-S covalent bond formation to a cysteine in the PAS domain occurred in 14 min, providing a rigid tetrapyrrole structure with high brightness. Our findings provide insights for the rational design of NIR FPs and a novel method to assess cofactor binding to light-sensitive proteins.

Real-time observation of tetrapyrrole binding to an engineered bacterial phytochrome.

Near-infrared fluorescent proteins (NIR FPs) engineered from bacterial phytochromes are widely used for structural and functional deep-tissue imaging in vivo. To fluoresce, NIR FPs covalently bind a chromophore, such as biliverdin IXa tetrapyrrole. The efficiency of biliverdin binding directly affects the fluorescence properties, rendering understanding of its molecular mechanism of major importance. miRFP proteins constitute a family of bright monomeric NIR FPs that comprise a Per-ARNT-Sim (PAS) and cGMP-specific phosphodiesterases - Adenylyl cyclases - FhlA (GAF) domain. Here, we structurally analyze biliverdin binding to miRFPs in real time using time-resolved stimulated Raman spectroscopy and quantum mechanics/molecular mechanics (QM/MM) calculations. Biliverdin undergoes isomerization, localization to its binding pocket, and pyrrolenine nitrogen protonation in <1 min, followed by hydrogen bond rearrangement in ~2 min. The covalent attachment to a cysteine in the GAF domain was detected in 4.3 min and 19 min in miRFP670 and its C20A mutant, respectively. In miRFP670, a second C-S covalent bond formation to a cysteine in the PAS domain occurred in 14 min, providing a rigid tetrapyrrole structure with high brightness. Our findings provide insights for the rational design of NIR FPs and a novel method to assess cofactor binding to light-sensitive proteins.