Robust and accurate prediction of self-interacting proteins from protein sequence information by exploiting weighted sparse representation based classifier.

BACKGROUND: Self-interacting proteins (SIPs), two or more copies of the protein that can interact with each other expressed by one gene, play a central role in the regulation of most living cells and cellular functions. Although numerous SIPs data can be provided by using high-throughput experimental techniques, there are still several shortcomings such as in time-consuming, costly, inefficient, and inherently high in false-positive rates, for the experimental identification of SIPs even nowadays. Therefore, it is more and more significant how to develop efficient and accurate automatic approaches as a supplement of experimental methods for assisting and accelerating the study of predicting SIPs from protein sequence information. RESULTS: In this paper, we present a novel framework, termed GLCM-WSRC (gray level co-occurrence matrix-weighted sparse representation based classification), for predicting SIPs automatically based on protein evolutionary information from protein primary sequences. More specifically, we firstly convert the protein sequence into Position Specific Scoring Matrix (PSSM) containing protein sequence evolutionary information, exploiting the Position Specific Iterated BLAST (PSI-BLAST) tool. Secondly, using an efficient feature extraction approach, i.e., GLCM, we extract abstract salient and invariant feature vectors from the PSSM, and then perform a pre-processing operation, the adaptive synthetic (ADASYN) technique, to balance the SIPs dataset to generate new feature vectors for classification. Finally, we employ an efficient and reliable WSRC model to identify SIPs according to the known information of self-interacting and non-interacting proteins. CONCLUSIONS: Extensive experimental results show that the proposed approach exhibits high prediction performance with 98.10% accuracy on the yeast dataset, and 91.51% accuracy on the human dataset, which further reveals that the proposed model could be a useful tool for large-scale self-interacting protein prediction and other bioinformatics tasks detection in the future.

Effect of Dual Trigger In Vitro Fertilization and Intracytoplasmic Sperm Injection During the Gonadotropin-releasing Hormone-Antagonist Cycle on Final Oocyte Maturation and Cumulative Live Birth Rate in Women with Diminished Ovarian Reserve.

OBJECTIVE: It is well known that a dual trigger treatment can improve clinical outcomes of in vitro fertilization (IVF) in high or normal ovarian responders. However, it is not clear whether dual triggering also benefits patients with diminished ovarian reserve (DOR). The aim of this study was to investigate whether a dual trigger treatment of gonadotropin-releasing hormone (GnRH) agonist combined with human chorionic gonadotropin (hCG) for final follicular maturation improves the cumulative live birth rate (CLBR) during the GnRH-antagonist cycle in patients with DOR. METHODS: This retrospective study included patients with DOR who received a GnRH-antagonist protocol during IVF and intracytoplasmic sperm injection (IVF-ICSI) cycles at Peking University People's Hospital from January 1, 2017 through December 31, 2017. Oocyte maturation was triggered by GnRH combined with hCG (n=110) or hCG alone (n=71). Embryos were transferred on the third day after oocyte retrieval or during a subsequent freeze-thaw cycle. Patients were followed up for 3 years. RESULTS: The dual trigger treatment did not affect CLBR, which is an overall determinant of the success rate of assisted reproductive technology (ART). Women in the dual trigger group had significantly higher rates of fertilization than those in the hCG group (90.1% vs. 83.9%, P=0.040). CONCLUSION: Dual trigger with GnRH agonist and hCG did not improve CLBR in patients with DOR, but did slightly improve fertilization rate, oocyte count, and embryo quality.

Logistic Regression Analysis of the Mechanism of Blunt Brain Injury Inference Based on CT Images.

OBJECTIVES: To study the correlation between CT imaging features of acceleration and deceleration brain injury and injury degree. METHODS: A total of 299 cases with acceleration and deceleration brain injury were collected and divided into acceleration brain injury group and deceleration brain injury group according to the injury mechanism. Subarachnoid hemorrhage (SAH) and Glasgow coma scale (GCS), combined with skull fracture, epidural hematoma (EDH), subdural hematoma (SDH) and brain contusion on the same and opposite sides of the stress point were selected as the screening indexes. χ2 test was used for primary screening, and binary logistic regression analysis was used for secondary screening. The indexes with the strongest correlation in acceleration and deceleration injury mechanism were selected. RESULTS: χ2 test showed that skull fracture and EDH on the same side of the stress point; EDH, SDH and brain contusion on the opposite of the stress point; SAH, GCS were correlated with acceleration and deceleration injury (P<0.05). According to binary logistic regression analysis, the odds ratio (OR) of EDH on the same side of the stress point was 2.697, the OR of brain contusion on the opposite of the stress point was 0.043 and the OR of GCS was 0.238, suggesting there was statistically significant (P<0.05). CONCLUSIONS: EDH on the same side of the stress point, brain contusion on the opposite of the stress point and GCS can be used as key indicators to distinguish acceleration and deceleration injury mechanism. In addition, skull fracture on the same side of the stress point, EDH and SDH on the opposite of the stress point and SAH were relatively weak indicators in distinguishing acceleration and deceleration injury mechanism.

Automatic Identification of Brain Injury Mechanism Based on Deep Learning.

OBJECTIVES: To apply the convolutional neural network (CNN) Inception_v3 model in automatic identification of acceleration and deceleration injury based on CT images of brain, and to explore the application prospect of deep learning technology in forensic brain injury mechanism inference. METHODS: CT images from 190 cases with acceleration and deceleration brain injury were selected as the experimental group, and CT images from 130 normal brain cases were used as the control group. The above-mentioned 320 imaging data were divided into training validation dataset and testing dataset according to random sampling method. The model classification performance was evaluated by the accuracy rate, precision rate, recall rate, F1-value and AUC value. RESULTS: In the training process and validation process, the accuracy rate of the model to classify acceleration injury, deceleration injury and normal brain was 99.00% and 87.21%, which met the requirements. The optimized model was used to test the data of the testing dataset, the result showed that the accuracy rate of the model in the test set was 87.18%, and the precision rate, recall rate, F1-score and AUC of the model to recognize acceleration injury were 84.38%, 90.00%, 87.10% and 0.98, respectively, to recognize deceleration injury were 86.67%, 72.22%, 78.79% and 0.92, respectively, to recognize normal brain were 88.57%, 89.86%, 89.21% and 0.93, respectively. CONCLUSIONS: Inception_v3 model has potential application value in distinguishing acceleration and deceleration injury based on brain CT images, and is expected to become an auxiliary tool to infer the mechanism of head injury.

Digital single-operator cholangioscopy for biliary stricture after cadaveric liver transplantation.

BACKGROUND: Biliary strictures after liver transplantation (LT) remain clinically arduous and challenging situations, and endoscopic retrograde cholangiopancreatography (ERCP) has been considered as the gold standard for the management of biliary strictures after LT. Nevertheless, in the treatment of biliary strictures after LT with ERCP, many studies show that there is a large variation in diagnostic accuracy and therapeutic success rate. Digital single-operator peroral cholangioscopy (DSOC) is considered a valuable diagnostic modality for indeterminate biliary strictures. AIM: To evaluate DSOC in addition to ERCP for management of biliary strictures after LT. METHODS: Nineteen patients with duct-to-duct biliary reconstruction who underwent ERCP for suspected biliary complications between March 2019 and March 2020 at Beijing Chaoyang Hospital, Capital Medical University, were consecutively enrolled in this observational study. After evaluating bile ducts using fluoroscopy, cholangioscopy using a modern digital single-operator cholangioscopy system (SpyGlass DS™) was performed during the same procedure with patients under conscious sedation. All patients received peri-interventional antibiotic prophylaxis. Biliary strictures after LT were classified according to the manifestations of choledochoscopic strictures and the manifestations of transplanted hepatobiliary ducts. RESULTS: Twenty-one biliary strictures were found in a total of 19 patients, among which anastomotic strictures were evident in 18 (94.7%) patients, while non-anastomotic strictures in 2 (10.5%), and space-occupying lesions in 1 (5.3%). Stones were found in 11 (57.9%) and loose sutures in 8 (42.1%). A benefit of cholangioscopy was seen in 15 (78.9%) patients. Cholangioscopy was crucial for selective guidewire placement prior to planned intervention in 4 patients. It was instrumental in identifying biliary stone and/or loose sutures in 9 patients in whom ERCP failed. It also provided a direct vision for laser lithotripsy. A space-occupying lesion in the bile duct was diagnosed by cholangioscopy in one patient. Patients with biliary stricture after LT displayed four types: (A) mild inflammatory change (n = 9); (B) acute inflammatory change edema, ulceration, and sloughing (n = 3); (C) chronic inflammatory change; and (D) acute suppurative change. Complications were seen in three patients with post-interventional cholangitis and another three with hyperamylasemia. CONCLUSION: DSOC can provide important diagnostic information, helping plan and perform interventional procedures in LT-related biliary strictures.

Bacteriocyte development is sexually differentiated in Bemesia tabaci.

Some symbiotic microbes are restricted to specialized host cells called bacteriocytes. However, the molecular and cellular mechanisms underlying the development of bacteriocytes are largely obscure. We find that maternally inherited bacteriocytes proliferate in adult females but degenerate in adult males of the whitefly Bemisia tabaci. Single-cell transcriptomics and immunohistochemistry reveal that cell division only occurs in the bacteriocytes of adult females, whereas autophagy and apoptosis are induced in the bacteriocytes of adult males. A transcription factor, Adf-1, enriched in bacteriocytes, is highly expressed in female bacteriocytes relative to male bacteriocytes. Silencing Adf-1 reduces the bacteriocyte number and Portiera titer and activates autophagy and apoptosis in females. The differential dynamics of both cell division and death in bacteriocytes and distinct expression of Adf-1 in bacteriocytes between whitefly sexes underlie the sexual differentiation of bacteriocyte development. Our study reveals that insect sex affects the development of bacteriocytes by cellular and molecular remodeling.

A learning-based method to predict LncRNA-disease associations by combining CNN and ELM.

BACKGROUND: lncRNAs play a critical role in numerous biological processes and life activities, especially diseases. Considering that traditional wet experiments for identifying uncovered lncRNA-disease associations is limited in terms of time consumption and labor cost. It is imperative to construct reliable and efficient computational models as addition for practice. Deep learning technologies have been proved to make impressive contributions in many areas, but the feasibility of it in bioinformatics has not been adequately verified. RESULTS: In this paper, a machine learning-based model called LDACE was proposed to predict potential lncRNA-disease associations by combining Extreme Learning Machine (ELM) and Convolutional Neural Network (CNN). Specifically, the representation vectors are constructed by integrating multiple types of biology information including functional similarity and semantic similarity. Then, CNN is applied to mine both local and global features. Finally, ELM is chosen to carry out the prediction task to detect the potential lncRNA-disease associations. The proposed method achieved remarkable Area Under Receiver Operating Characteristic Curve of 0.9086 in Leave-one-out cross-validation and 0.8994 in fivefold cross-validation, respectively. In addition, 2 kinds of case studies based on lung cancer and endometrial cancer indicate the robustness and efficiency of LDACE even in a real environment. CONCLUSIONS: Substantial results demonstrated that the proposed model is expected to be an auxiliary tool to guide and assist biomedical research, and the close integration of deep learning and biology big data will provide life sciences with novel insights.

A Retrospective Study of the Safety and Efficacy of Endoscopic Radiofrequency Therapy Under Direct Vision in 59 Patients with Gastroesophageal Reflux Disease from 2 Centers in Beijing, China Using the Gastroesophageal Reflux Disease Questionnaire.

BACKGROUND This retrospective study from 2 centers in Beijing, China aimed to assess the safety and efficacy of endoscopic radiofrequency therapy under direct vision in 59 patients with gastroesophageal reflux disease (GERD) using the gastroesophageal reflux disease questionnaire (GerdQ). MATERIAL AND METHODS Fifty-nine GERD patients who underwent endoscopic radiofrequency treatment were included. Patients were divided into 2 groups: the endoscopic radiofrequency therapy under direct vision group and the non-direct vision radiofrequency therapy group. Indicators such as GerdQ score, lower esophageal sphincter (LES) pressure, DeMeester score, acid exposure time, and proton pump inhibitors (PPIs) use were collected before and after radiofrequency treatment. Postoperative complications were also recorded. The efficacy and safety of endoscopic radiofrequency therapy under direct vision were evaluated by comparing the indicators of patients in the 2 groups. RESULTS At 3 months after radiofrequency treatment, patients in the endoscopic radiofrequency therapy under direct vision group improved significantly in GerdQ score, decreased from 11.0 (10.0, 12.0) to 6.0 (6.0, 8.0), better than patients in the non-direct vision radiofrequency therapy group, and the better improvements remained at 12 months after the procedure (P<0.05). At 6 months after treatment, patients in the endoscopic radiofrequency therapy under direct vision group had significant improvements in LES pressure, which increased from 8.15 (3.18, 12.88) mmHg to 15.20 (10.25, 27.03) mmHg (P<0.05). There were no severe complications in our trial. CONCLUSIONS When compared with non-visualized endoscopic radiofrequency therapy, treatment under direct vision was safer and improved the GerdQ score and LES pressure at up to 12 months.

Autophagy Regulates Whitefly-Symbiont Metabolic Interactions.

Nutritional symbionts are restricted to specialized host cells called bacteriocytes in various insect orders. These symbionts can provide essential nutrients to the host. However, the cellular mechanisms underlying the regulation of these insect-symbiont metabolic associations remain largely unclear. The whitefly Bemisia tabaci MEAM1 hosts "Candidatus Portiera aleyrodidarum" (here, "Ca. Portiera") and "Candidatus Hamiltonella defensa" (here, "Ca. Hamiltonella") bacteria in the same bacteriocyte. In this study, the induction of autophagy by chemical treatment and gene silencing decreased symbiont titers and essential amino acid (EAA) and B vitamin contents. In contrast, the repression of autophagy in bacteriocytes via Atg8 silencing increased symbiont titers, and amino acid and B vitamin contents. Furthermore, dietary supplementation with non-EAAs or B vitamins alleviated autophagy in whitefly bacteriocytes, elevated TOR (target of rapamycin) expression, and increased symbiont titers. TOR silencing restored symbiont titers in whiteflies after dietary supplementation with B vitamins. These data suggest that "Ca. Portiera" and "Ca. Hamiltonella" evade autophagy of the whitefly bacteriocytes by activating the TOR pathway via providing essential nutrients. Taken together, we demonstrate that autophagy plays a critical role in regulating the metabolic interactions between the whitefly and two intracellular symbionts. Therefore, this study reveals that autophagy is an important cellular basis for bacteriocyte evolution and symbiosis persistence in whiteflies. The whitefly symbiosis unravels the interactions between cellular and metabolic functions of bacteriocytes. IMPORTANCE Nutritional symbionts, which are restricted to specialized host cells called bacteriocytes, can provide essential nutrients for many hosts. However, the cellular mechanisms of regulation of animal-symbiont metabolic associations have been largely unexplored. Here, using the whitefly-"Ca. Portiera"/"Ca. Hamiltonella" endosymbiosis, we demonstrate autophagy regulates the symbiont titers and thereby alters the essential amino acid and B vitamin contents. For persistence in the whitefly bacteriocytes, "Ca. Portiera" and "Ca. Hamiltonella" alleviate autophagy by activating the TOR (target of rapamycin) pathway through providing essential nutrients. Therefore, we demonstrate that autophagy plays a critical role in regulating the metabolic interactions between the whitefly and two intracellular symbionts. This study also provides insight into the cellular basis of bacteriocyte evolution and symbiosis persistence in the whitefly. The mechanisms underlying the role of autophagy in whitefly symbiosis could be widespread in many insect nutritional symbioses. These findings provide a new avenue for whitefly control via regulating autophagy in the future.

Lysine provisioning by horizontally acquired genes promotes mutual dependence between whitefly and two intracellular symbionts.

Horizontal gene transfer is widespread in insects bearing intracellular symbionts. Horizontally transferred genes (HTGs) are presumably involved in amino acid synthesis in sternorrhynchan insects. However, their role in insect-symbiont interactions remains largely unknown. We found symbionts Portiera, Hamiltonella and Rickettsia possess most genes involved in lysine synthesis in the whitefly Bemisia tabaci MEAM1 although their genomes are reduced. Hamiltonella maintains a nearly complete lysine synthesis pathway. In contrast, Portiera and Rickettsia require the complementation of whitefly HTGs for lysine synthesis and have lysE, encoding a lysine exporter. Furthermore, each horizontally transferred lysine gene of ten B. tabaci cryptic species shares an evolutionary origin. We demonstrated that Hamiltonella did not alter the titers of Portiera and Rickettsia or lysine gene expression of Portiera, Rickettsia and whiteflies. Hamiltonella also did not impact on lysine levels or protein localization in bacteriocytes harboring Portiera and ovaries infected with Rickettsia. Complementation with whitefly lysine synthesis HTGs rescued E. coli lysine gene knockout mutants. Silencing whitefly lysA in whiteflies harboring Hamiltonella reduced lysine levels, adult fecundity and titers of Portiera and Rickettsia without influencing the expression of Hamiltonella lysA. Furthermore, silencing whitefly lysA in whiteflies lacking Hamiltonella reduced lysine levels, adult fecundity and titers of Portiera and Rickettsia in ovarioles. Therefore, we, for the first time, demonstrated an essential amino acid lysine synthesized through HTGs is important for whitefly reproduction and fitness of both obligate and facultative symbionts, and it illustrates the mutual dependence between whitefly and its two symbionts. Collectively, this study reveals that acquisition of horizontally transferred lysine genes contributes to coadaptation and coevolution between B. tabaci and its symbionts.

Robust and accurate prediction of protein-protein interactions by exploiting evolutionary information.

Various biochemical functions of organisms are performed by protein-protein interactions (PPIs). Therefore, recognition of protein-protein interactions is very important for understanding most life activities, such as DNA replication and transcription, protein synthesis and secretion, signal transduction and metabolism. Although high-throughput technology makes it possible to generate large-scale PPIs data, it requires expensive cost of both time and labor, and leave a risk of high false positive rate. In order to formulate a more ingenious solution, biology community is looking for computational methods to quickly and efficiently discover massive protein interaction data. In this paper, we propose a computational method for predicting PPIs based on a fresh idea of combining orthogonal locality preserving projections (OLPP) and rotation forest (RoF) models, using protein sequence information. Specifically, the protein sequence is first converted into position-specific scoring matrices (PSSMs) containing protein evolutionary information by using the Position-Specific Iterated Basic Local Alignment Search Tool (PSI-BLAST). Then we characterize a protein as a fixed length feature vector by applying OLPP to PSSMs. Finally, we train an RoF classifier for the purpose of identifying non-interacting and interacting protein pairs. The proposed method yielded a significantly better results than existing methods, with 90.07% and 96.09% prediction accuracy on Yeast and Human datasets. Our experiment show the proposed method can serve as a useful tool to accelerate the process of solving key problems in proteomics.

Lewis Acid Enables Ketone Phosphorylation to Form a C-P Bond and a C-C Bond: Synthesis of 9-Phosphoryl Fluorene Derivatives.

An efficient method for the Lewis acid promotion of the synthesis 9-phosphoryl fluorenes has been reported. This method focuses on ketone phosphonylation to form a C-P bond and a C-C bond between diphenylmethanone and H-phosphinate esters, H-phosphites, and H-phosphine oxides via phospha-aldol elimination, in which a series of 9-phosphoryl fluorene derivatives were selectively obtained in moderate to excellent yields.

Nanoscale Pore Structure Characteristics of Deep Coalbed Methane Reservoirs and Its Influence on CH4 Adsorption in the Linxing Area, Eastern Ordos Basin, China.

The high gas content of deep coal seams is a driving force for the exploration and development of deep coalbed methane (CBM). The nanoscale pores, which are the main spaces for adsorption and storage of CBM, are closely related to the burial depth. Based on integrated approaches of vitrinite reflectance (Ro), maceral composition, scanning electron microscope (SEM), proximate analysis, fluid inclusion test, low-temperature N2 adsorption-desorption, and CH4 isothermal adsorption, the nanoscale pore structure of coals recovered at depths from 650 to 2078 m was determined, and its influence on the CH4 adsorption capacity was discussed. The results show that the coal rank has a good linear relationship with the current burial depth of the coal seams; that is, the influences of the burial depth on the coals can be reflected by the influences of the coal rank on the coals. With the increase in the coal rank, the moisture and volatile content decrease, and the fixed carbon content increases. The variation in the pore volume and specific surface area with the increase in the coal rank can be divided into two stages: the rapid decline stage (when 0.75% 1.0%, the FD of the micropores is close to 2. This indicates that with the increase in the degree of coalification, the surface of the micropores is simpler. The above results show that the gas adsorption capacity of coal first slightly decreases (when 0.75% < Ro < 1.0%) and then increases (when 1.0% < Ro < 1.35%), and the coincident results are shown in the Langmuir volume (VL) test results.

MeSHHeading2vec: a new method for representing MeSH headings as vectors based on graph embedding algorithm.

Effectively representing Medical Subject Headings (MeSH) headings (terms) such as disease and drug as discriminative vectors could greatly improve the performance of downstream computational prediction models. However, these terms are often abstract and difficult to quantify. In this paper, we converted the MeSH tree structure into a relationship network and applied several graph embedding algorithms on it to represent these terms. Specifically, the relationship network consisting of nodes (MeSH headings) and edges (relationships), which can be constructed by the tree num. Then, five graph embedding algorithms including DeepWalk, LINE, SDNE, LAP and HOPE were implemented on the relationship network to represent MeSH headings as vectors. In order to evaluate the performance of the proposed methods, we carried out the node classification and relationship prediction tasks. The results show that the MeSH headings characterized by graph embedding algorithms can not only be treated as an independent carrier for representation, but also can be utilized as additional information to enhance the representation ability of vectors. Thus, it can serve as an input and continue to play a significant role in any computational models related to disease, drug, microbe, etc. Besides, our method holds great hope to inspire relevant researchers to study the representation of terms in this network perspective.

Intracellular symbionts drive sex ratio in the whitefly by facilitating fertilization and provisioning of B vitamins.

Symbionts can regulate animal reproduction in multiple ways, but the underlying physiological and biochemical mechanisms remain largely unknown. The presence of multiple lineages of maternally inherited, intracellular symbionts (the primary and secondary symbionts) in terrestrial arthropods is widespread in nature. However, the biological, metabolic, and evolutionary role of co-resident secondary symbionts for hosts is poorly understood. The bacterial symbionts Hamiltonella and Arsenophonus have very high prevalence in two globally important pests, the whiteflies Bemisia tabaci and Trialeurodes vaporariorum, respectively. Both symbionts coexist with the primary symbiont Portiera in the same host cell (bacteriocyte) and are maternally transmitted. We found that elimination of both Hamiltonella and Arsenophonous by antibiotic treatment reduced the percentage of female offspring in whiteflies. Microsatellite genotyping and cytogenetic analysis revealed that symbiont deficiency inhibited fertilization in whiteflies, leading to more haploid males with one maternal allele, which is consistent with distorted sex ratio in whiteflies. Quantification of essential amino acids and B vitamins in whiteflies indicated that symbiont deficiency reduced B vitamin levels, and dietary B vitamin supplementation rescued fitness of whiteflies. This study, for the first time, conclusively demonstrates that these two intracellular symbionts affect sex ratios in their whitefly hosts by regulating fertilization and supplying B vitamins. Our results reveal that both symbionts have the convergent function of regulating reproduction in phylogenetically-distant whitefly species. The 100% frequency, the inability of whiteflies to develop normally without their symbiont, and rescue with B vitamins suggests that both symbionts may be better considered co-primary symbionts.

Bioentity2vec: Attribute- and behavior-driven representation for predicting multi-type relationships between bioentities.

BACKGROUND: The explosive growth of genomic, chemical, and pathological data provides new opportunities and challenges for humans to thoroughly understand life activities in cells. However, there exist few computational models that aggregate various bioentities to comprehensively reveal the physical and functional landscape of biological systems. RESULTS: We constructed a molecular association network, which contains 18 edges (relationships) between 8 nodes (bioentities). Based on this, we propose Bioentity2vec, a new method for representing bioentities, which integrates information about the attributes and behaviors of a bioentity. Applying the random forest classifier, we achieved promising performance on 18 relationships, with an area under the curve of 0.9608 and an area under the precision-recall curve of 0.9572. CONCLUSIONS: Our study shows that constructing a network with rich topological and biological information is important for systematic understanding of the biological landscape at the molecular level. Our results show that Bioentity2vec can effectively represent biological entities and provides easily distinguishable information about classification tasks. Our method is also able to simultaneously predict relationships between single types and multiple types, which will accelerate progress in biological experimental research and industrial product development.

Prediction of Drug-Target Interactions From Multi-Molecular Network Based on Deep Walk Embedding Model.

Predicting drug-target interactions (DTIs) is crucial in innovative drug discovery, drug repositioning and other fields. However, there are many shortcomings for predicting DTIs using traditional biological experimental methods, such as the high-cost, time-consumption, low efficiency, and so on, which make these methods difficult to widely apply. As a supplement, the in silico method can provide helpful information for predictions of DTIs in a timely manner. In this work, a deep walk embedding method is developed for predicting DTIs from a multi-molecular network. More specifically, a multi-molecular network, also called molecular associations network, is constructed by integrating the associations among drug, protein, disease, lncRNA, and miRNA. Then, each node can be represented as a behavior feature vector by using a deep walk embedding method. Finally, we compared behavior features with traditional attribute features on an integrated dataset by using various classifiers. The experimental results revealed that the behavior feature could be performed better on different classifiers, especially on the random forest classifier. It is also demonstrated that the use of behavior information is very helpful for addressing the problem of sequences containing both self-interacting and non-interacting pairs of proteins. This work is not only extremely suitable for predicting DTIs, but also provides a new perspective for the prediction of other biomolecules' associations.

Pattern of liver injury in adult patients with COVID-19: a retrospective analysis of 105 patients.

BACKGROUND: Recent studies reported that patients with coronavirus disease-2019 (COVID-19) might have liver injury. However, few data on the combined analysis and change patterns of alanine aminotransferase (ALT), aspartate aminotransferase (AST) and total bilirubin (TBil) have been shown. METHODS: This is a single-center retrospective study. A total of 105 adult patients hospitalized for confirmed COVID-19 in Beijing Ditan Hospital between January 12, and March 17, 2020 were included, and divided into mild group (n = 79) and severe group(n = 26). We compared liver functional test results between the two groups. Category of ALT change during the disease course was also examined. RESULTS: 56.2% (59/105) of the patients had unnormal ALT, AST, or total TBil throughout the course of the disease, but in 91.4% (96/105) cases the level of ALT, AST or TBil ≤3 fold of the upper limit of normal reference range (ULN). The overall distribution of ALT, AST, and TBil were all significantly difference between mild and severe group (P <  0.05). The percentage of the patients with elevated both ALT and AST was 12.7% (10/79) in mild cases vs. 46.2% (12/26) in severe cases (P = 0.001). 34.6% (9/26) severe group patients started to have abnormal ALT after admission, and 73.3% (77/105) of all patients had normal ALT before discharge. CONCLUSIONS: Elevated liver function index is very common in patients with COVID-19 infection, and the level were less than 3 × ULN, but most are reversible. The abnormality of 2 or more indexes is low in the patients with COVID-19, but it is more likely to occur in the severe group.

A learning based framework for diverse biomolecule relationship prediction in molecular association network.

Abundant life activities are maintained by various biomolecule relationships in human cells. However, many previous computational models only focus on isolated objects, without considering that cell is a complete entity with ample functions. Inspired by holism, we constructed a Molecular Associations Network (MAN) including 9 kinds of relationships among 5 types of biomolecules, and a prediction model called MAN-GF. More specifically, biomolecules can be represented as vectors by the algorithm called biomarker2vec which combines 2 kinds of information involved the attribute learned by k-mer, etc and the behavior learned by Graph Factorization (GF). Then, Random Forest classifier is applied for training, validation and test. MAN-GF obtained a substantial performance with AUC of 0.9647 and AUPR of 0.9521 under 5-fold Cross-validation. The results imply that MAN-GF with an overall perspective can act as ancillary for practice. Besides, it holds great hope to provide a new insight to elucidate the regulatory mechanisms.