Computational analysis can accurately detect drug-gene interactions (DGIs) cost-effectively. However, transductive learning models are the hotspot to reveal the promising performance for unknown DGIs (both drugs and genes are present in the training model), without special attention to the unseen DGIs (both drugs and genes are absent in the training model). In view of this, this study, for the first time, proposed an inductive learning-based model for the precise identification of unseen DGIs. In our study, by integrating disease nodes to avoid data sparsity, a multi-relational drug-disease-gene (DDG) graph was constructed to achieve effective fusion of data on DDG intro-relationships and inter-actions. Following the extraction of graph features by utilizing graph embedding algorithms, our next step was the retrieval of the attributes of individual gene and drug nodes. In this way, a hybrid feature characterization was represented by integrating graph features and node attributes. Machine learning (ML) models were built, enabling the fulfillment of transductive predictions of unknown DGIs. To realize inductive learning, this study generated an innovative idea of transforming known node vectors derived from the DDG graph into representations of unseen nodes using node similarities as weights, enabling inductive predictions for the unseen DGIs. Consequently, the final model was superior to existing models, with significant improvement in predicting both external unknown and unseen DGIs. The practical feasibility of our model was further confirmed through case study and molecular docking. In summary, this study establishes an efficient data-driven approach through the proposed modeling, suggesting its value as a promising tool for accelerating drug discovery and repurposing.

BACKGROUND:With the application and development of 3D printing technology in medicine,orthopedic internal fixation surgery has become precise and individualized.The equal-scale fracture model obtained by 3D printing technology was simulated and planned before surgery,realizing the leap from traditional 2D images to more vivid and detailed three-dimensional objects.It allows the surgeon to understand the fracture type in advance and rehearse the reduction sequence,so as to realize the individualized implementation of fracture surgery,optimize the surgical process,bring better postoperative recovery and less surgical complications. OBJECTIVE:To compare clinical efficacy of three 3D printed models combined with computerized virtual repositioning technology to assist incision reduction bone plate internal fixation and traditional incision reduction bone plate internal fixation in the treatment of Robinson II B2 clavicle fracture. METHODS:Eighty patients with Robinson II B2 clavicle fracture were randomly divided into trial group(n=40)and control group(n=40).In the trial group,three kinds of 3D printing models(affected clavicle fracture model,computer simulation clavicle fracture reduction model,clavicle mirror model of healthy side)combined with computer virtual reduction technology were used for preoperative in vitro surgery rehearsal.Finally,3D printing was used for clavicle mirror model of healthy side to advance bending and select bone plates for internal fixation.In the control group,open reduction plate internal fixation was applied.The time from admission to surgery,intraoperative blood loss,operation time,frequency of fluoroscopy,number of bends of the bone plate,fracture healing time,complications,and visual analog scale score and Constant score before and after surgery were compared between the two groups. RESULTS AND CONCLUSION:The time from admission to operation in the trial group was greater than that in the control group(P<0.05).Operation time,intraoperative fluoroscopy frequency and bending times of the bone plate in the trial group were lower than those in the control group(P<0.05).The trial group had faster fracture healing and fewer complications(P<0.05).There was no significant difference in intraoperative blood loss between the two groups(P>0.05).Constant score of the two groups had an increasing trend with time(F=613.50,P<0.001),but the difference between the groups was not statistically significant(F=0.08,P=0.78),and there was no interaction between the measurement times and the group assignment(F=0.27,P=0.66).The visual analog scale score decreased with time(F=1 149.55,P<0.001),but there was no significant difference between groups(F=0.02,P=0.88),and there was no interaction between the number of measurements and the group assignment(F=1.02,P=0.36).The results show that the use of 3D printed model combined with computer virtual reduction technology for preoperative rehearsal can shorten the operation time,reduce the number of intraoperative fluoroscopy frequency and the times of bone plate bending,and have the advantages of faster fracture healing,fewer complications,and similar functional recovery to the traditional incision reduction bone plate internal fixation.

Genome-wide physical protein-protein interaction(PPI)mapping remains a major chal-lenge for current technologies.Here,we reported a high-efficiency BiFC-seq method,yeast-enhanced green fluorescent protein-based bimolecular fluorescence complementation(yEGFP-BiFC)coupled with next-generation DNA sequencing,for interactome mapping.We first applied yEGFP-BiFC method to systematically investigate an intraviral network of the Ebola virus.Two-thirds(9/14)of known interactions of EBOV were recaptured,and five novel interactions were discovered.Next,we used the BiFC-seq method to map the interactome of the tumor protein p53.We identified 97 interactors of p53,more than three-quarters of which were novel.Furthermore,in a more complex background,we screened potential interactors by pooling two BiFC libraries together and revealed a network of 229 interactions among 205 proteins.These results show that BiFC-seq is a highly sensitive,rapid,and economical method for genome-wide interactome map-ping.

Objective To explore the current status of the stress and coping styles of emergency room nurses in Class Ⅲ Grade A hospitals, to discuss the correlation between stress and coping styles, and to provide a basis for formulating targeted training plans. Methods Totally 178 emergency room nurses from 9 Class ⅢGrade A hospitals in Hebei Province were randomly selected as the study subject from April to May 2016 and investigated with the General Information Questionnaire, Nurse's Working Stress Source Scale and Coping Style Questionnaire. Results The total average stress score of the nurses was (1.88±0.56); and the scores for each dimension of coping styles were: (0.84±0.12) for problem-solving, (0.71±0.20) for fantasy, (0.68±0.22) for rationalization, (0.67±0.24) for avoidance, (0.67±0.14) for asking for help, and (0.60±0.29) for self-accusation. Nursing and working stress was positively correlated with the coping styles such as fantasy and rationalization (P<0.05), and negatively correlated with self-accusation (P<0.05). Conclusions Emergency room nurses' stress generally remains at a medium and high level. Therefore, nursing managers should formulate proper nursing management measures and take necessary measures to alleviate nurses' stress.

Purpose To detect the expression of CD90 in invasive ductal breast carcinoma with different molecular subtypes and to explore its clinical significance.Methods The expression of CD90,ER,PR,Ki-67 and HER-2 were detected in 80 cases of invasive ductal breast carcinoma tissue and 20 cases of breast benign lesion with immunohistochemical method.The relationship between CD90 and clinicopathological parameters were analyzed.Results The positive expression rate of CD90 in invasive ductal breast carcinoma and breast benign lesion tissues were 62.5％ and 20.0％,respectively (P ＜0.001).The expression of CD90 in invasive ductal breast carcinoma was correlated with lymph node metastasis (P ＜ 0.05),but not with age,tumor size,TNM staging and histological grade (P ＞ 0.05).Among different molecular subtypes,CD90 expression level in Luminal A type was the lowest (40.0％),and the level in triple negative type was the highest (82.4％) (P ＜0.05).CD90 expression level was negatively correlated with ER (r=-0.342,P＜0.05) orPR (r=-0.374,P＜0.05) expression level,but not with Ki-67 (r =0.084,P ＞ 0.05).Condusion The over-expression of CD90 is related with molecular subtypes of breast carcinoma,and its high expression suggests a poor prognosis.