A systematic review of state-of-the-art strategies for machine learning-based protein function prediction.

New drug discovery is inseparable from the discovery of drug targets, and the vast majority of the known targets are proteins. At the same time, proteins are essential structural and functional elements of living cells necessary for the maintenance of all forms of life. Therefore, protein functions have become the focus of many pharmacological and biological studies. Traditional experimental techniques are no longer adequate for rapidly growing annotation of protein sequences, and approaches to protein function prediction using computational methods have emerged and flourished. A significant trend has been to use machine learning to achieve this goal. In this review, approaches to protein function prediction based on the sequence, structure, protein-protein interaction (PPI) networks, and fusion of multi-information sources are discussed. The current status of research on protein function prediction using machine learning is considered, and existing challenges and prominent breakthroughs are discussed to provide ideas and methods for future studies.

A systematic review on the state-of-the-art strategies for protein representation.

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

A Rapid and Sensitive Method for the Simultaneous Determination of Multipolar Compounds in Plant Tea by Supercritical Fluid Chromatography Coupled to Ion Mobility Quadrupole Time-of-Flight Mass Spectrometry.

In this study, matrix solid phase dispersion (MSPD) microextraction combined with supercritical fluid chromatography-ion mobility quadrupole time-of-flight mass spectrometry (SFC/IM-QTOF-MS) was used to analyze the multipolar compounds in plant tea. The parameters of stationary phase, mobile phase, make-up solution, temperature, and back pressure were optimized. The target analytes were gradient eluted in 8 min by supercritical CO2 on a Zorbax RX-SIL column. Collisional Cross Section (CCS) values for single and multiple fields were measured. A series of validation studies were carried out under the optimal conditions, and the linear relationship and reproducibility were good. The limits of detection were 1.4 (Scoparone (1))~70 (Naringenin (4)) ng/mL, and the limits of quantification were 4.7 (Scoparone (1))~241 (Naringenin (4)) ng/mL. The recoveries of most compounds ranged from 60.7% to 127%. As a consequence, the proposed method was used for the separation and quantitative analysis of active ingredients in caulis dendrobii.

Phase â and phase â ¡ metabolic studies of Citrus flavonoids based on electrochemical simulation and in vitro methods by EC-Q-TOF/MS and HPLC-Q-TOF/MS.

The oxidation products and metabolic pathways of five Citrus flavonoids were studied by online electrochemical/quadrupole time-of-flight mass spectrometry (EC/Q-TOF/MS). The simulated oxidation metabolism of target compounds in phase I and phase Ⅱ was carried out at boron-doped diamond (BDD) working electrode. The results obtained by EC-MS were compared with the conventional metabolism of rats and humans reported in previous literatures. In addition, the method of incubating the target compounds with rat liver microsomes in vitro was established, the target compounds and their metabolites were analyzed by high performance liquid chromatography coupled mass spectrometry. The structures of the metabolites were determined by accurate mass measurements and previous in vivo metabolite results. The results showed that the electrochemical oxidation metabolites were consistent with the results of in vitro incubation of liver microsomes, and also with the results reported in other literatures. As a consequence, EC/Q-TOF/MS is a promising and effective tool for studying metabolic transformation of different complex food components.

Ion pair-based mobile phase additives to improve the separation of alkaloids in supercritical fluid chromatography.

In this study, a supercritical fluid chromatography (SFC) method based on ion pair reagents was used to separate alkaloids. The chromatographic parameters, including the stationary phase, additive type, additive concentration, outlet pressure, temperature and flow rate, were optimized. Baseline separation was completed in 20 min on an Agilent Pursuit 5 PFP column (4.6 × 150 mm) using carbon dioxide as the mobile phase and 7.5 mM sodium 1-pentanesulfonate as an additive with gradient elution at 140 bar, 60 °C, and a flow rate of 1.5 mL/min. The retention rate and resolution of the analytes were satisfactory. The limits of detection were 27.04-298.03 ng/mL, and the limits of quantification were 90.15-993.42 ng/mL. The recoveries of low and high concentrations were 77.46-111.86% and 83.84-111.00%, respectively. This ion pair additive greatly improved the separation efficiency of alkaloids. Consequently, this SFC method was successfully applied to the separation of alkaloids from Rhizoma corydalis.

Boron nitride nanosheet-assisted matrix solid-phase dispersion microextraction of alkaloids from lotus plumule by high-performance liquid chromatography coupled with ultraviolet detection and ion mobility quadrupole time-of-flight mass spectrometry.

A boron nitride nanosheet (BNNS)-assisted matrix solid-phase dispersion method was established to microextract alkaloids from medicinal plants. The target compounds were identified by high-performance liquid chromatography coupled with ultraviolet detection and ion mobility quadrupole time-of-flight mass spectrometry. During the experimental process, several important parameters, including the type of dispersant, the amount of dispersant, the grinding time, and the type of elution solvent, were optimized. Finally, the BNNSs were chosen as the best dispersant, and their microcosmic morphologies were identified by scanning electron microscopy and transmission electron microscopy. Because of the special property of BNNSs, the cost of this experiment was greatly reduced, especially in elution volume, sample amount (50 mg), and extraction time (2 min). Under the best conditions, 50 mg of sample powder was dispersed with 50 mg of BNNSs, the grinding time was 120 s, the mixed powder was eluted with 200 µL of methanol, and good linearity (r2  > 0.9993) and satisfactory recoveries (80-100%) were obtained. The inter- and intraday precisions were acceptable, with RSDs lower than 2.01 and 4.84%, respectively. The limits of detection ranged from 2.54 to 15.00 ng/mL, and the limits of quantitation were 8.47 to 50.00 ng/mL. The proposed method was successfully applied for the determination of liensinine, isoliensinine, and neferine in lotus plumule.