No abstract

Identification of phosphorylation sites is an important step in the function study and drug design of proteins. In recent years, there have been increasing applications of the computational method in the identification of phosphorylation sites because of its low cost and high speed. Most of the currently available methods focus on using local information around potential phosphorylation sites for prediction and do not take the global information of the protein sequence into consideration. Here, we demonstrated that the global information of protein sequences may be also critical for phosphorylation site prediction. In this paper, a new deep neural network model, called DeepPSP, was proposed for the prediction of protein phosphorylation sites. In the DeepPSP model, two parallel modules were introduced to extract both local and global features from protein sequences. Two squeeze-and-excitation blocks and one bidirectional long shortterm memory block were introduced into each module to capture effective representations of the sequences. Comparative studies were carried out to evaluate the performance of DeepPSP, and four other prediction methods using public data sets The F1-score, area under receiver operating characteristic curves (AUROC), and area under precision−recall curves (AUPRC) of DeepPSP were found to be 0.4819, 0.82, and 0.50, respectively, for S/T general site prediction and 0.4206, 0.73, and 0.39, respectively, for Y general site prediction. Compared with the MusiteDeep method, the F1-score, AUROC, and AUPRC of DeepPSP were found to increase by 8.6, 2.5, and 8.7%, respectively, for S/T general site prediction and by 20.6, 5.8, and 18.2%, respectively, for Y general site prediction. Among the tested methods, the developed DeepPSP method was also found to produce best results for different kinase-specific site predictions including CDK, mitogen-activated protein kinase, CAMK, AGC, and CMGC. Taken together, the developed DeepPSP method may offer a more accurate phosphorylation site prediction by including global information. It may serve as an alternative model with better performance and interpretability for protein phosphorylation site prediction.

BackgroundAltered gut microbiome (GM) composition has been established in Parkinson’s disease (PD). However, few studies have longitudinally investigated the GM in PD, or the impact of device-assisted therapies.ObjectivesTo investigate the temporal stability of GM profiles from PD patients on standard therapies and those initiating device-assisted therapies (DAT) and define multivariate models of disease and progression.MethodsWe evaluated validated clinical questionnaires and stool samples from 74 PD patients and 74 household controls (HCs) at 0, 6, and 12 months. Faster or slower disease progression was defined from levodopa equivalence dose and motor severity measures. 19 PD patients initiating Deep Brain Stimulation or Levodopa-Carbidopa Intestinal Gel were separately evaluated at 0, 6, and 12 months post-therapy initiation.ResultsPersistent underrepresentation of short-chain fatty-acid-producing bacteria, Butyricicoccus, Fusicatenibacter, Lachnospiraceae ND3007 group, and Erysipelotrichaceae UCG-003, were apparent in PD patients relative to controls. A sustained effect of DAT initiation on GM associations with PD was not observed. PD progression analysis indicated that the genus Barnesiella was underrepresented in faster progressing PD patients at t = 0 and t = 12 months. Two-stage predictive modeling, integrating microbiota abundances and nutritional profiles, improved predictive capacity (change in Area Under the Curve from 0.58 to 0.64) when assessed at Amplicon Sequence Variant taxonomic resolution.ConclusionWe present longitudinal GM studies in PD patients, showing persistently altered GM profiles suggestive of a reduced butyrogenic production potential. DATs exerted variable GM influences across the short and longer-term. We found that specific GM profiles combined with dietary factors improved prediction of disease progression in PD patients.

PurposeTo investigate the prognostic value of intratumoral invariant natural killer T (iNKT) cells and interferon-gamma (IFN-γ) in hepatocellular carcinoma (HCC) after curative resection.Experimental DesignExpression of TRAV10, encoding the Vα24 domain of iNKT cells, and IFN-γ mRNA were assessed by quantitative real-time polymerase chain reaction in tumor from 224 HCC patients undergoing curative resection. The prognostic value of these two and other clinicopathologic factors was evaluated.ResultsEither intratumoral iNKT cells and IFN-γ alone or their combination was an independent prognostic factor for OS (P = 0.001) and RFS (P = 0.001) by multivariate Cox proportional hazards analysis. Patients with concurrent low levels of iNKT cells and IFN-γ had a hazard ratio (HR) of 2.784 for OS and 2.673 for RFS. The areas under the curve of iNKT cells, IFN-γand their combination were 0.618 vs 0.608 vs 0.654 for death and 0.591 vs 0.604 vs 0.633 for recurrence respectively by receiver operating characteristic curve analysis. The prognosis was the worst for HCC patients with concurrent low levels of iNKT cells and IFN-γ, which might be related with more advanced pTNM stage and more vascular invasion.ConclusionsCombination of intratumoral iNKT cells and IFN-γ is a promising independent predictor for recurrence and survival in HCC, which has a better power to predict HCC patients’ outcome compared with intratumoral iNKT cells or IFN-γ alone.