Computational identification of vesicular transport proteins from sequences using deep gated recurrent units architecture

Synergism of vesicle trafficking and cytoskeleton during regulation of plant growth and development: A mechanistic outlook

The cytoskeleton is a fundamental component found in all eukaryotic organisms, serving as a critical factor in various essential cyto-biological mechanisms, particularly in the locomotion and morphological transformations of plant cells. The cytoskeleton is comprised of three main components: microtubules (MT), microfilaments (MF), and intermediate filaments (IF). The cytoskeleton plays a crucial role in the process of cell wall formation and remodeling throughout the growth and development of cells. It is a highly organized and regulated network composed of filamentous components. In the basic processes of intracellular transport, such as mitosis, cytokinesis, and cell polarity, the plant cytoskeleton plays a crucial role according to recent studies. The major flaws in the organization of the cytoskeletal framework are at the root of the aberrant organogenesis currently observed in plant mutants. The regulation of protein compartmentalization and abundance within cells is predominantly governed by the process of vesicle/membrane transport, which plays a crucial role in several signaling cascades.The regulation of membrane transport in eukaryotic cells is governed by a diverse array of proteins. Recent developments in genomics have provided new tools to study the evolutionary relationships between membrane proteins in different plant species. It is known that members of the GTPases, COP, SNAREs, Rabs, tethering factors, and PIN families play essential roles in vesicle transport between plant, animal, and microbial species. This Review presents the latest research on the plant cytoskeleton, focusing on recent developments related to the cytoskeleton and summarizing the role of various proteins in vesicle transport. In addition, the report predicts future research direction of plant cytoskeleton and vesicle trafficking, potential research priorities, and provides researchers with specific pointers to further investigate the significant link between cytoskeleton and vesicle trafficking.

Complement System Inhibitory Drugs in a Zebrafish (Danio rerio) Model: Computational Modeling

The dysregulation of complement system activation usually results in acute or chronic inflammation and can contribute to the development of various diseases. Although the activation of complement pathways is essential for innate defense, exacerbated activity of this system may be harmful to the host. Thus, drugs with the potential to inhibit the activation of the complement system may be important tools in therapy for diseases associated with complement system activation. The synthetic peptides Cp40 and PMX205 can be highlighted in this regard, given that they selectively inhibit the C3 and block the C5a receptor (C5aR1), respectively. The zebrafish (Danio rerio) is a robust model for studying the complement system. The aim of the present study was to use in silico computational modeling to investigate the hypothesis that these complement system inhibitor peptides interact with their target molecules in zebrafish, for subsequent in vivo validation. For this, we analyzed molecular docking interactions between peptides and target molecules. Our study demonstrated that Cp40 and the cyclic peptide PMX205 have positive interactions with their respective zebrafish targets, thus suggesting that zebrafish can be used as an animal model for therapeutic studies on these inhibitors.

Stack-VTP: prediction of vesicle transport proteins based on stacked ensemble classifier and evolutionary information

Vesicle transport proteins not only play an important role in the transmembrane transport of molecules, but also have a place in the field of biomedicine, so the identification of vesicle transport proteins is particularly important. We propose a method based on ensemble learning and evolutionary information to identify vesicle transport proteins. Firstly, we preprocess the imbalanced dataset by random undersampling. Secondly, we extract position-specific scoring matrix (PSSM) from protein sequences, and then further extract AADP-PSSM and RPSSM features from PSSM, and use the Max-Relevance-Max-Distance (MRMD) algorithm to select the optimal feature subset. Finally, the optimal feature subset is fed into the stacked classifier for vesicle transport proteins identification. The experimental results show that the of accuracy (ACC), sensitivity (SN) and specificity (SP) of our method on the independent testing set are 82.53%, 0.774 and 0.836, respectively. The SN, SP and ACC of our proposed method are 0.013, 0.007 and 0.76% higher than the current state-of-the-art methods.

A GHKNN model based on the physicochemical property extraction method to identify SNARE proteins

There is a great deal of importance to SNARE proteins, and their absence from function can lead to a variety of diseases. The SNARE protein is known as a membrane fusion protein, and it is crucial for mediating vesicle fusion. The identification of SNARE proteins must therefore be conducted with an accurate method. Through extensive experiments, we have developed a model based on graph-regularized k-local hyperplane distance nearest neighbor model (GHKNN) binary classification. In this, the model uses the physicochemical property extraction method to extract protein sequence features and the SMOTE method to upsample protein sequence features. The combination achieves the most accurate performance for identifying all protein sequences. Finally, we compare the model based on GHKNN binary classification with other classifiers and measure them using four different metrics: SN, SP, ACC, and MCC. In experiments, the model performs significantly better than other classifiers.

Identification of Vesicle Transport Proteins via Hypergraph Regularized K-Local Hyperplane Distance Nearest Neighbour Model

The prediction of protein function is a common topic in the field of bioinformatics. In recent years, advances in machine learning have inspired a growing number of algorithms for predicting protein function. A large number of parameters and fairly complex neural networks are often used to improve the prediction performance, an approach that is time-consuming and costly. In this study, we leveraged traditional features and machine learning classifiers to boost the performance of vesicle transport protein identification and make the prediction process faster. We adopt the pseudo position-specific scoring matrix (PsePSSM) feature and our proposed new classifier hypergraph regularized k-local hyperplane distance nearest neighbour (HG-HKNN) to classify vesicular transport proteins. We address dataset imbalances with random undersampling. The results show that our strategy has an area under the receiver operating characteristic curve (AUC) of 0.870 and a Matthews correlation coefficient (MCC) of 0.53 on the benchmark dataset, outperforming all state-of-the-art methods on the same dataset, and other metrics of our model are also comparable to existing methods.

Using biological information to analyze potential miRNA-mRNA regulatory networks in the plasma of patients with non-small cell lung cancer

Background

Lung cancer is the most common malignant tumor, and it has a high mortality rate. However, the study of miRNA-mRNA regulatory networks in the plasma of patients with non-small cell lung cancer (NSCLC) is insufficient. Therefore, this study explored the differential expression of mRNA and miRNA in the plasma of NSCLC patients.

Methods

The Gene Expression Omnibus (GEO) database was used to download microarray datasets, and the differentially expressed miRNAs (DEMs) were analyzed. We predicted transcription factors and target genes of the DEMs by using FunRich software and the TargetScanHuman database, respectively. The Database for Annotation, Visualization, and Integrated Discovery (DAVID) was used for GO annotation and KEGG enrichment analysis of downstream target genes. We constructed protein-protein interaction (PPI) and DEM-hub gene networks using the STRING database and Cytoscape software. The GSE20189 dataset was used to screen out the key hub gene. Using The Cancer Genome Atlas (TCGA) and UALCAN databases to analyze the expression and prognosis of the key hub gene and DEMs. Then, GSE17681 and GSE137140 datasets were used to validate DEMs expression. Finally, the receiver operating characteristic (ROC) curve was used to verify the ability of the DEMs to distinguish lung cancer patients from healthy patients.

Results

Four upregulated candidate DEMs (hsa-miR199a-5p, hsa-miR-186-5p, hsa-miR-328-3p, and hsa-let-7d-3p) were screened from 3 databases, and 6 upstream transcription factors and 2253 downstream target genes were predicted. These genes were mainly enriched in cancer pathways and PI3k-Akt pathways. Among the top 30 hub genes, the expression of KLHL3 was consistent with the GSE20189 dataset. Except for let-7d-3p, the expression of other DEMs and KLHL3 in tissues were consistent with those in plasma. LUSC patients with high let-7d-3p expression had poor overall survival rates (OS). External validation demonstrated that the expression of hsa-miR-199a-5p and hsa-miR-186-5p in peripheral blood of NSCLC patients was higher than the healthy controls. The ROC curve confirmed that the DEMs could better distinguish lung cancer patients from healthy people.

Conclusion

The results showed that miR-199a-5p and miR-186-5p may be noninvasive diagnostic biomarkers for NSCLC patients. MiR-199a-5p-KLHL3 may be involved in the occurrence and development of NSCLC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09281-1.

Autophagy-related prognostic signature for survival prediction of triple negative breast cancer

BACKGROUND

Triple-negative breast cancer (TNBC) is a highly aggressive type of cancer with few available treatment methods. The aim of the current study was to provide a prognostic autophagy-related gene (ARG) model to predict the outcomes for TNBC patients using bioinformatic analysis.

METHODS

mRNA expression data and its clinical information for TNBC samples obtained from The Cancer Genome Atlas (TCGA) and Metabric databases were extracted for bioinformatic analysis. Differentially expressed autophagy genes were identified using the Wilcoxon rank sum test in R software. ARGs were downloaded from the Human Autophagy Database. The Kaplan-Meier plotter was employed to determine the prognostic significance of the ARGs. The sample splitting method and Cox regression analysis were employed to establish the risk model and to demonstrate the association between the ARGs and the survival duration. The corresponding ARG-transcription factor interaction network was visualized using the Cytoscape software.

RESULTS

A signature-based risk score model was established for eight genes (ITGA3, HSPA8, CTSD, ATG12, CLN3, ATG7, MAP1LC3C, and WIPI1) using the TCGA data and the model was validated with the GSE38959 and Metabric datasets, respectively. Patients with high risk scores had worse survival outcomes than those with low risk scores. Of note, amplification of ATG12 and reduction of WIPI were confirmed to be significantly correlated with the clinical stage of TNBC.

CONCLUSION

An eight-gene autophagic signature model was developed in this study to predict the survival risk for TNBC. The genes identified in the study may favor the design of target agents for autophagy control in advanced TNBC.

A SNARE Protein Identification Method Based on iLearnPlus to Efficiently Solve the Data Imbalance Problem

Machine learning has been widely used to solve complex problems in engineering applications and scientific fields, and many machine learning-based methods have achieved good results in different fields. SNAREs are key elements of membrane fusion and required for the fusion process of stable intermediates. They are also associated with the formation of some psychiatric disorders. This study processes the original sequence data with the synthetic minority oversampling technique (SMOTE) to solve the problem of data imbalance and produces the most suitable machine learning model with the iLearnPlus platform for the identification of SNARE proteins. Ultimately, a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the cross-validation dataset, and a sensitivity of 66.67%, specificity of 93.63%, accuracy of 91.33%, and MCC of 0.528 were obtained in the independent dataset (the adaptive skip dipeptide composition descriptor was used for feature extraction, and LightGBM with proper parameters was used as the classifier). These results demonstrate that this combination can perform well in the classification of SNARE proteins and is superior to other methods.

VTP-Identifier: Vesicular Transport Proteins Identification Based on PSSM Profiles and XGBoost

Vesicular transport proteins are related to many human diseases, and they threaten human health when they undergo pathological changes. Protein function prediction has been one of the most in-depth topics in bioinformatics. In this work, we developed a useful tool to identify vesicular transport proteins. Our strategy is to extract transition probability composition, autocovariance transformation and other information from the position-specific scoring matrix as feature vectors. EditedNearesNeighbours (ENN) is used to address the imbalance of the data set, and the Max-Relevance-Max-Distance (MRMD) algorithm is adopted to reduce the dimension of the feature vector. We used 5-fold cross-validation and independent test sets to evaluate our model. On the test set, VTP-Identifier presented a higher performance compared with GRU. The accuracy, Matthew's correlation coefficient (MCC) and area under the ROC curve (AUC) were 83.6%, 0.531 and 0.873, respectively.

Using BioPAX-Parser (BiP) to enrich lists of genes or proteins with pathway data

BACKGROUND

Pathway enrichment analysis (PEA) is a well-established methodology for interpreting a list of genes and proteins of interest related to a condition under investigation. This paper aims to extend our previous work in which we introduced a preliminary comparative analysis of pathway enrichment analysis tools. We extended the earlier work by providing more case studies, comparing BiP enrichment performance with other well-known PEA software tools.

METHODS

PEA uses pathway information to discover connections between a list of genes and proteins as well as biological mechanisms, helping researchers to overcome the problem of explaining biological entity lists of interest disconnected from the biological context.

RESULTS

We compared the results of BiP with some existing pathway enrichment analysis tools comprising Centrality-based Pathway Enrichment, pathDIP, and Signaling Pathway Impact Analysis, considering three cancer types (colorectal, endometrial, and thyroid), for a total of six datasets (that is, two datasets per cancer type) obtained from the The Cancer Genome Atlas and Gene Expression Omnibus databases. We measured the similarities between the overlap of the enrichment results obtained using each couple of cancer datasets related to the same cancer.

CONCLUSION

As a result, BiP identified some well-known pathways related to the investigated cancer type, validated by the available literature. We also used the Jaccard and meet-min indices to evaluate the stability and the similarity between the enrichment results obtained from each couple of cancer datasets. The obtained results show that BiP provides more stable enrichment results than other tools.

Analysis and forecasts for trends of COVID-19 in Pakistan using Bayesian models

BACKGROUND

COVID-19 is currently on full flow in Pakistan. Given the health facilities in the country, there are serious threats in the upcoming months which could be very testing for all the stakeholders. Therefore, there is a need to analyze and forecast the trends of COVID-19 in Pakistan.

METHODS

We have analyzed and forecasted the patterns of this pandemic in the country, for next 30 days, using Bayesian structural time series models. The causal impacts of lifting lockdown have also been investigated using intervention analysis under Bayesian structural time series models. The forecasting accuracy of the proposed models has been compared with frequently used autoregressive integrated moving average models. The validity of the proposed model has been investigated using similar datasets from neighboring countries including Iran and India.

RESULTS

We observed the improved forecasting accuracy of Bayesian structural time series models as compared to frequently used autoregressive integrated moving average models. As far as the forecasts are concerned, on August 10, 2020, the country is expected to have 333,308 positive cases with 95% prediction interval [275,034-391,077]. Similarly, the number of deaths in the country is expected to reach 7,187 [5,978-8,390] and recoveries may grow to 279,602 [208,420-295,740]. The lifting of lockdown has caused an absolute increase of 98,768 confirmed cases with 95% interval [85,544-111,018], during the post-lockdown period. The positive aspect of the forecasts is that the number of active cases is expected to decrease to 63,706 [18,614-95,337], on August 10, 2020. This is the time for the concerned authorities to further restrict the active cases so that the recession of the outbreak continues in the next month.

Identification of potential gene signatures associated with osteosarcoma by integrated bioinformatics analysis

Background

Osteosarcoma (OS) is the most primary malignant bone cancer in children and adolescents with a high mortality rate. This work aims to screen novel potential gene signatures associated with OS by integrated microarray analysis of the Gene Expression Omnibus (GEO) database.

Material and Methods

The OS microarray datasets were searched and downloaded from GEO database to identify differentially expressed genes (DEGs) between OS and normal samples. Afterwards, the functional enrichment analysis, protein–protein interaction (PPI) network analysis and transcription factor (TF)-target gene regulatory network were applied to uncover the biological function of DEGs. Finally, two published OS datasets (GSE39262 and GSE126209) were obtained from GEO database for evaluating the expression level and diagnostic values of key genes.

Results

 In total 1,059 DEGs (569 up-regulated DEGs and 490 down-regulated DEGs) between OS and normal samples were screened. Functional analysis showed that these DEGs were markedly enriched in 214 GO terms and 54 KEGG pathways such as pathways in cancer. Five genes (CAMP, METTL7A, TCN1, LTF and CXCL12) acted as hub genes in PPI network. Besides, METTL7A, CYP4F3, TCN1, LTF and NETO2 were key genes in TF-gene network. Moreover, Pax-6 regulated four key genes (TCN1, CYP4F3, NETO2 and CXCL12). The expression levels of four genes (METTL7A, TCN1, CXCL12 and NETO2) in GSE39262 set were consistent with our integration analysis. The expression levels of two genes (CXCL12 and NETO2) in GSE126209 set were consistent with our integration analysis. ROC analysis of GSE39262 set revealed that CYP4F3, CXCL12, METTL7A, TCN1 and NETO2 had good diagnostic values for OS patients. ROC analysis of GSE126209 set revealed that CXCL12, METTL7A, TCN1 and NETO2 had good diagnostic values for OS patients.

Analysis of ceRNA networks and identification of potential drug targets for drug-resistant leukemia cell K562/ADR

Background

Drug resistance is the main obstacle in the treatment of leukemia. As a member of the competitive endogenous RNA (ceRNA) mechanism, underlying roles of lncRNA are rarely reported in drug-resistant leukemia cells.

Methods

The gene expression profiles of lncRNAs and mRNAs in doxorubicin-resistant K562/ADR and sensitive K562 cells were established by RNA sequencing (RNA-seq). Expression of differentially expressed lncRNAs (DElncRNAs) and DEmRNAs was validated by qRT-PCR. The potential biological functions of DElncRNAs targets were identified by GO and KEGG pathway enrichment analyses, and the lncRNA-miRNA-mRNA ceRNA network was further constructed. K562/ADR cells were transfected with CCDC26 and LINC01515 siRNAs to detect the mRNA levels of GLRX5 and DICER1, respectively. The cell survival rate after transfection was detected by CCK-8 assay.

Results

The ceRNA network was composed of 409 lncRNA-miRNA pairs and 306 miRNA-mRNA pairs based on 67 DElncRNAs, 58 DEmiRNAs and 192 DEmRNAs. Knockdown of CCDC26 and LINC01515 increased the sensitivity of K562/ADR cells to doxorubicin and significantly reduced the half-maximal inhibitory concentration (IC₅₀) of doxorubicin. Furthermore, knockdown of GLRX5 and DICER1 increased the sensitivity of K562/ADR cells to doxorubicin and significantly reduced the IC₅₀ of doxorubicin.

Conclusions

The ceRNA regulatory networks may play important roles in drug resistance of leukemia cells. CCDC26/miR-140-5p/GLRX5 and LINC01515/miR-425-5p/DICER1 may be potential targets for drug resistance in K562/ADR cells. This study provides a promising strategy to overcome drug resistance and deepens the understanding of the ceRNA regulatory mechanism related to drug resistance in CML cells.

MultiPredGO: Deep Multi-Modal Protein Function Prediction by Amalgamating Protein Structure, Sequence, and Interaction Information

Protein is an essential macro-nutrient for perceiving a wide range of biochemical activities and biological regulations in living cells. In this work, we have presented a novel multi-modal approach, named MultiPredGO, for predicting protein functions by utilizing two different kinds of information, namely protein sequence and the protein secondary structure. Here, our contributions are threefold; firstly, along with the protein sequence, we learn the feature representation from the protein structure. Secondly, we develop two different deep learning models after considering the characteristics of the underlying data patterns of the protein sequence and protein 3D structures. Finally, along with these two modalities, we have also utilized protein interaction information for expediting the efficiency of the proposed model in predicting the protein functions. For extracting features from different modalities, we have utilized various variations of the convolutional neural network. As the protein function classes are dependent on each other, we have used a neuro-symbolic hierarchical classification model, which resembles the structure of Gene Ontology (GO), for effectively predicting the dependent protein functions. Finally, to validate the goodness of our proposed method (MultiPredGO), we have compared our results with various uni-modal along with two well-known multi-modal protein function prediction approaches, namely, INGA and DeepGO. Results show that the overall performance of the proposed approach in terms of accuracy, F-measure, precision, and recall metrics are better than those by the state-of-the-art methods. MultiPredGO attains an average 13.05% and 30.87% improvements over the best existing comparing approach (DeepGO) for cellular component and molecular functions, respectively.

Low compositions of human toll-like receptor 7/8-stimulating RNA motifs in the MERS-CoV, SARS-CoV and SARS-CoV-2 genomes imply a substantial ability to evade human innate immunity

Background

The innate immune system especially Toll-like receptor (TLR) 7/8 and the interferon pathway, constitutes an important first line of defense against single-stranded RNA viruses. However, large-scale, systematic comparisons of the TLR 7/8-stimulating potential of genomic RNAs of single-stranded RNA viruses are rare. In this study, a computational method to evaluate the human TLR 7/8-stimulating ability of single-stranded RNA virus genomes based on their human TLR 7/8-stimulating trimer compositions was used to analyze 1,002 human coronavirus genomes.

Results

The human TLR 7/8-stimulating potential of coronavirus genomic (positive strand) RNAs followed the order of NL63-CoV > HKU1-CoV >229E-CoV ≅ OC63-CoV > SARS-CoV-2 > MERS-CoV > SARS-CoV. These results suggest that among these coronaviruses, MERS-CoV, SARS-CoV and SARS-CoV-2 may have a higher ability to evade the human TLR 7/8-mediated innate immune response. Analysis with a logistic regression equation derived from human coronavirus data revealed that most of the 1,762 coronavirus genomic (positive strand) RNAs isolated from bats, camels, cats, civets, dogs and birds exhibited weak human TLR 7/8-stimulating potential equivalent to that of the MERS-CoV, SARS-CoV and SARS-CoV-2 genomic RNAs.

Conclusions

Prediction of the human TLR 7/8-stimulating potential of viral genomic RNAs may be useful for surveillance of emerging coronaviruses from nonhuman mammalian hosts.

Identification of an immune prognostic 11-gene signature for lung adenocarcinoma

Background

The immunological tumour microenvironment (TME) has occupied a very important position in the beginning and progression of non-small cell lung cancer (NSCLC). Prognosis of lung adenocarcinoma (LUAD) remains poor for the local progression and widely metastases at the time of clinical diagnosis. Our objective is to identify a potential signature model to improve prognosis of LUAD.

Methods

With the aim to identify a novel immune prognostic signature associated with overall survival (OS), we analysed LUADs extracted from The Cancer Genome Atlas (TCGA). Immune scores and stromal scores of TCGA-LUAD were downloaded from Estimation of STromal and Immune cells in MAlignant Tumour tissues Expression using data (ESTIMATE). LASSO COX regression was applied to build the prediction model. Then, the prognostic gene signature was validated in the GSE68465 dataset.

Results

The data from TCGA datasets showed patients in stage I and stage II had higher stromal scores than patients in stage IV (P < 0.05), and for immune score patients in stage I were higher than patients in stage III and stage IV (P < 0.05). The improved overall survivals were observed in high stromal score and immune score groups. Patients in the high-risk group exhibited the inferior OS (P = 2.501e − 05). By validating the 397 LUAD patients from GSE68465, we observed a better OS in the low-risk group compared to the high-risk group, which is consistent with the results from the TCGA cohort. Nomogram results showed that practical and predicted survival coincided very well, especially for 3-year survival.

Conclusion

We obtained an 11 immune score related gene signature model as an independent element to effectively classify LUADs into different risk groups, which might provide a support for precision treatments. Moreover, immune score may play a potential valuable sole for estimating OS in LUADs.

Ego-Motion Estimation Using Recurrent Convolutional Neural Networks through Optical Flow Learning

Visual odometry (VO) refers to incremental estimation of the motion state of an agent (e.g., vehicle and robot) by using image information, and is a key component of modern localization and navigation systems. Addressing the monocular VO problem, this paper presents a novel end-to-end network for estimation of camera ego-motion. The network learns the latent subspace of optical flow (OF) and models sequential dynamics so that the motion estimation is constrained by the relations between sequential images. We compute the OF field of consecutive images and extract the latent OF representation in a self-encoding manner. A Recurrent Neural Network is then followed to examine the OF changes, i.e., to conduct sequential learning. The extracted sequential OF subspace is used to compute the regression of the 6-dimensional pose vector. We derive three models with different network structures and different training schemes: LS-CNN-VO, LS-AE-VO, and LS-RCNN-VO. Particularly, we separately train the encoder in an unsupervised manner. By this means, we avoid non-convergence during the training of the whole network and allow more generalized and effective feature representation. Substantial experiments have been conducted on KITTI and Malaga datasets, and the results demonstrate that our LS-RCNN-VO outperforms the existing learning-based VO approaches.

Transcriptome profiling reveals Silibinin dose-dependent response network in non-small lung cancer cells

Silibinin (SIL), a natural flavonolignan from the milk thistle (Silybum marianum), is known to exhibit remarkable hepatoprotective, antineoplastic and EMT inhibiting effects in different cancer cells by targeting multiple molecular targets and pathways. However, the predominant majority of previous studies investigated effects of this phytocompound in a one particular cell line. Here, we carry out a systematic analysis of dose-dependent viability response to SIL in five non-small cell lung cancer (NSCLC) lines that gradually differ with respect to their intrinsic EMT stage. By correlating gene expression profiles of NSCLC cell lines with the pattern of their SIL IC50 response, a group of cell cycle, survival and stress responsive genes, including some prominent targets of STAT3 (BIRC5, FOXM1, BRCA1), was identified. The relevancy of these computationally selected genes to SIL viability response of NSCLC cells was confirmed by the transient knockdown test. In contrast to other EMT-inhibiting compounds, no correlation between the SIL IC50 and the intrinsic EMT stage of NSCLC cells was observed. Our experimental results show that SIL viability response of differently constituted NSCLC cells is linked to a subnetwork of tightly interconnected genes whose transcriptomic pattern can be used as a benchmark for assessment of individual SIL sensitivity instead of the conventional EMT signature. Insights gained in this study pave the way for optimization of customized adjuvant therapy of malignancies using Silibinin.

Comprehensive pathway-related genes signature for prognosis and recurrence of ovarian cancer

Background

Ovarian cancer (OC) is a highly malignant disease with a poor prognosis and high recurrence rate. At present, there is no accurate strategy to predict the prognosis and recurrence of OC. The aim of this study was to identify gene-based signatures to predict OC prognosis and recurrence.

Methods

mRNA expression profiles and corresponding clinical information regarding OC were collected from The Cancer Genome Atlas (TCGA) database. Gene set enrichment analysis (GSEA) and LASSO analysis were performed, and Kaplan–Meier curves, time-dependent ROC curves, and nomograms were constructed using R software and GraphPad Prism7.

Results

We first identified several key signalling pathways that affected ovarian tumorigenesis by GSEA. We then established a nine-gene-based signature for overall survival (OS) and a five-gene-based-signature for relapse-free survival (RFS) using LASSO Cox regression analysis of the TCGA dataset and validated the prognostic value of these signatures in independent GEO datasets. We also confirmed that these signatures were independent risk factors for OS and RFS by multivariate Cox analysis. Time-dependent ROC analysis showed that the AUC values for OS and RFS were 0.640, 0.663, 0.758, and 0.891, and 0.638, 0.722, 0.813, and 0.972 at 1, 3, 5, and 10 years, respectively. The results of the nomogram analysis demonstrated that combining two signatures with the TNM staging system and tumour status yielded better predictive ability.

Conclusion

In conclusion, the two-gene-based signatures established in this study may serve as novel and independent prognostic indicators for OS and RFS.

A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification

Essential genes contain key information of genomes that could be the key to a comprehensive understanding of life and evolution. Because of their importance, studies of essential genes have been considered a crucial problem in computational biology. Computational methods for identifying essential genes have become increasingly popular to reduce the cost and time-consumption of traditional experiments. A few models have addressed this problem, but performance is still not satisfactory because of high dimensional features and the use of traditional machine learning algorithms. Thus, there is a need to create a novel model to improve the predictive performance of this problem from DNA sequence features. This study took advantage of a natural language processing (NLP) model in learning biological sequences by treating them as natural language words. To learn the NLP features, a supervised learning model was consequentially employed by an ensemble deep neural network. Our proposed method could identify essential genes with sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC), and area under the receiver operating characteristic curve (AUC) values of 60.2%, 84.6%, 76.3%, 0.449, and 0.814, respectively. The overall performance outperformed the single models without ensemble, as well as the state-of-the-art predictors on the same benchmark dataset. This indicated the effectiveness of the proposed method in determining essential genes, in particular, and other sequencing problems, in general.

Identification and prognostic value of DLGAP5 in endometrial cancer

Background

Endometrial cancer poses a serious threat to women’s health worldwide, and its pathogenesis, although actively explored, is not fully understood. DLGAP5 is a recently identified cell cycle-regulation gene not reported in endometrial cancer. This study was aiming to analyze the role of DLGAP5 in tumorigenesis and development and to investigate its prognostic significance of patients with endometrial cancer.

Methodology

Microarray datasets (GSE17025, GSE39099 and GSE63678) from the GEO database were used for comparative analysis, and their intersection was obtained by applying the Venn diagram, and DLGAP5 was selected as the target gene. Next, transcriptome data (n = 578) was downloaded from TCGA-UCEC to analyze the mRNA expression profile of DLGAP5. Then, immunohistochemical data provided by HPA were used to identify the different protein expression levels of DLGAP5 in tumor tissues and normal tissues. Subsequently, the prognostic meaning of DLGAP5 in patients with endometrial cancer was explored based on survival data from TCGA-UCEC (n = 541). Finally, the reliability of DLGAP5 expression was verified by RT-qPCR.

Results

Transcriptome data from TCGA-UCEC, immunohistochemical data from HPA, and RT-qPCR results from clinical samples were used for triple validation to confirm that the expression of DLGAP5 in endometrial cancer tissues was significantly higher than that in normal endometrial tissues. Kaplan–Meier survival analysis announced that the expression level of DLGAP5 was negatively correlated with the overall survival of patients with endometrial cancer.

Conclusions

DLGAP5 is a potential oncogene with cell cycle regulation, and its overexpression can predict the poor prognosis of patients with endometrial cancer. As a candidate target for the diagnosis and treatment of endometrial cancer, it is worthwhile to make further study to reveal the carcinogenicity of DLGAP5 and the mechanism of its resistance of organisms.

Comprehensive analysis and identification of key genes and signaling pathways in the occurrence and metastasis of cutaneous melanoma

Background

Melanoma is a malignant tumor of melanocytes, and the incidence has increased faster than any other cancer over the past half century. Most primary melanoma can be cured by local excision, but metastatic melanoma has a poor prognosis. Cutaneous melanoma (CM) is prone to metastasis, so the research on the mechanism of melanoma occurrence and metastasis will be beneficial to diagnose early, improve treatment, and prolong life survival. In this study, we compared the gene expression of normal skin (N), primary cutaneous melanoma (PM) and metastatic cutaneous melanoma (MM) in the Gene Expression Omnibus (GEO) database. Then we identified the key genes and molecular pathways that may be involved in the development and metastasis of cutaneous melanoma, thus to discover potential markers or therapeutic targets.

Methods

Three gene expression profiles (GSE7553, GSE15605 and GSE46517) were downloaded from the GEO database, which contained 225 tissue samples. R software identified the differentially expressed genes (DEGs) between pairs of N, PM and MM samples in the three sets of data. Subsequently, we analyzed the gene ontology (GO) function and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway of the DEGs, and constructed a protein-protein interaction (PPI) network. MCODE was used to seek the most important modules in PPI network, and then the GO function and KEGG pathway of them were analyzed. Finally, the hub genes were calculated by the cytoHubba in Cytoscape software. The Cancer Genome Atlas (TCGA) data were analyzed using UALCAN and GEPIA to validate the hub genes and analyze the prognosis of patients.

Results

A total of 134, 317 and 147 DEGs were identified between N, PM and MM in pair. GO functions and KEGG pathways analysis results showed that the upregulated DEGs mainly concentrated in cell division, spindle microtubule, protein kinase activity and the pathway of transcriptional misregulation in cancer. The downregulated DEGs occurred in epidermis development, extracellular exosome, structural molecule activity, metabolic pathways and p53 signaling pathway. The PPI network obtained the most important module, whose GO function and KEGG pathway were enriched in oxidoreductase activity, cell division, cell exosomes, protein binding, structural molecule activity, and metabolic pathways. 14, 18 and 18 DEGs were identified respectively as the hub genes between N, PM and MM, and TCGA data confirmed the expression differences of hub genes. In addition, the overall survival curve of hub genes showed that the differences in these genes may lead to a significant decrease in overall survival of melanoma patients.

Conclusions

In this study, several hub genes were found from normal skin, primary melanoma and metastatic melanoma samples. These hub genes may play an important role in the production, invasion, recurrence or death of CM, and may provide new ideas and potential targets for its diagnosis or treatment.

Author Identification Using Chaos Game Representation and Deep Learning

An author unconsciously encodes in the written text a certain style that is often difficult to recognize. Still, there are many computational means developed for this purpose that take into account various features, from lexical and character-based attributes to syntactic or semantic ones. We propose an approach that starts from the character level and uses chaos game representation to illustrate documents like images which are subsequently classified by a deep learning algorithm. The experiments are made on three data sets and the outputs are comparable to the results from the literature. The study also verifies the suitability of the method for small data sets and whether image augmentation can improve the classification efficiency.

Integrated network pharmacology and molecular docking approaches to reveal the synergistic mechanism of multiple components in Venenum Bufonis for ameliorating heart failure

Venenum Bufonis (VB), also called Chan Su in China, has been extensively used as a traditional Chinese medicine (TCM) for treating heart failure (HF) since ancient time. However, the active components and the potential anti-HF mechanism of VB remain unclear. In the current study, the major absorbed components and metabolites of VB after oral administration in rats were first collected from literatures. A total of 17 prototypes and 25 metabolites were gathered. Next, a feasible network-based pharmacological approach was developed and employed to explore the therapeutic mechanism of VB on HF based on the collected constituents. In total, 158 main targets were screened out and considered as effective players in ameliorating HF. Then, the VB components-main HF putative targets-main pathways network was established, clarifying the underlying biological process of VB on HF. More importantly, the main hubs were found to be highly enriched in adrenergic signalling in cardio-myocytes. After verified by molecular docking studies, four key targets (ATP1A1, GNAS, MAPK1 and PRKCA) and three potential active leading compounds (bufotalin, cinobufaginol and 19-oxo-bufalin) were identified, which may play critical roles in cardiac muscle contraction. This study demonstrated that the integrated strategy based on network pharmacology and molecular docking was helpful to uncover the synergistic mechanism of multiple constituents in TCM.

Fine-Grained Breast Cancer Classification With Bilinear Convolutional Neural Networks (BCNNs)

Classification of histopathological images of cancer is challenging even for well-trained professionals, due to the fine-grained variability of the disease. Deep Convolutional Neural Networks (CNNs) showed great potential for classification of a number of the highly variable fine-grained objects. In this study, we introduce a Bilinear Convolutional Neural Networks (BCNNs) based deep learning method for fine-grained classification of breast cancer histopathological images. We evaluated our model by comparison with several deep learning algorithms for fine-grained classification. We used bilinear pooling to aggregate a large number of orderless features without taking into consideration the disease location. The experimental results on BreaKHis, a publicly available breast cancer dataset, showed that our method is highly accurate with 99.24% and 95.95% accuracy in binary and in fine-grained classification, respectively.

A Method for Identifying Vesicle Transport Proteins Based on LibSVM and MRMD

With the development of computer technology, many machine learning algorithms have been applied to the field of biology, forming the discipline of bioinformatics. Protein function prediction is a classic research topic in this subject area. Though many scholars have made achievements in identifying protein by different algorithms, they often extract a large number of feature types and use very complex classification methods to obtain little improvement in the classification effect, and this process is very time-consuming. In this research, we attempt to utilize as few features as possible to classify vesicular transportation proteins and to simultaneously obtain a comparative satisfactory classification result. We adopt CTDC which is a submethod of the method of composition, transition, and distribution (CTD) to extract only 39 features from each sequence, and LibSVM is used as the classification method. We use the SMOTE method to deal with the problem of dataset imbalance. There are 11619 protein sequences in our dataset. We selected 4428 sequences to train our classification model and selected other 1832 sequences from our dataset to test the classification effect and finally achieved an accuracy of 71.77%. After dimension reduction by MRMD, the accuracy is 72.16%.

CKS2 and RMI2 are two prognostic biomarkers of lung adenocarcinoma

Background

Lung adenocarcinoma (ACA) is the most common subtype of non-small-cell lung cancer. About 70%–80% patients are diagnosed at an advanced stage; therefore, the survival rate is poor. It is urgent to discover accurate markers that can differentiate the late stages of lung ACA from the early stages. With the development of biochips, researchers are able to efficiently screen large amounts of biological analytes for multiple purposes.

Methods

Our team downloaded GSE75037 and GSE32863 from the Gene Expression Omnibus (GEO) database. Next, we utilized GEO’s online tool, GEO2R, to analyze the differentially expressed genes (DEGs) between stage I and stage II–IV lung ACA. The using the Cytoscape software was used to analyze the DEGs and the protein-protein interaction (PPI) network was further constructed. The function of the DEGs were further analyzed by cBioPortal and Gene Expression Profiling Interactive Analysis (GEPIA) online tools. We validated these results in 72 pairs human samples.

Results

We identified 109 co-DEGs, most of which were involved in either proliferation, S phase of mitotic cell cycle, regulation of exit from mitosis, DNA replication initiation, DNA replication, and chromosome segregation. Utilizing cBioPortal and University of California Santa Cruz databases, we further confirmed 35 hub genes. Two of these genes, encoding CDC28 protein kinase regulatory subunit 2 (CKS2) and RecQ-mediated genome instability 2 (RMI2), were upregulated in lung ACA compared with adjacent normal tissues. The Kaplan–Meier curves revealed upregulation of CKS2 and RMI2 are associated with worse survival. Using CMap analysis, we discovered 10 small molecular compounds that reversed the altered DEGs, the top five are phenoxybenzamine, adiphenine, resveratrol, and trifluoperazine. We also evaluated 72 pairs resected samples, results revealed that upregulation of CKS2 and RMI2 in lung ACA were associated with larger tumor size. Our results allow the deeper recognizing of the mechanisms of the progression of lung ACA, and may indicate potential therapeutic strategies for the therapy of lung ACA.

The relationship between protein domains and homopeptides in the Plasmodium falciparum proteome

The proteome of the malaria parasite Plasmodium falciparum is notable for the pervasive occurrence of homopeptides or low-complexity regions (i.e., regions that are made from a small subset of amino-acid residue types). The most prevalent of these are made from residues encoded by adenine/thymidine (AT)-rich codons, in particular asparagine. We examined homopeptide occurrences within protein domains in P. falciparum. Homopeptide enrichments occur for hydrophobic (e.g., valine), or small residues (alanine or glycine) in short spans (<5 residues), but these enrichments disappear for longer lengths. We observe that short asparagine homopeptides (<10 residues long) have a dramatic relative depletion inside protein domains, indicating some selective constraint to keep them from forming. We surmise that this is possibly linked to co-translational protein folding, although there are specific protein domains that are enriched in longer asparagine homopeptides (≥10 residues) indicating a functional linkage for specific poly-asparagine tracts. Top gene ontology functional category enrichments for homopeptides associated with diverse protein domains include “vesicle-mediated transport”, and “DNA-directed 5′-3′ RNA polymerase activity”, with various categories linked to “binding” evidencing significant homopeptide depletions. Also, in general homopeptides are substantially enriched in the parts of protein domains that are near/in IDRs. The implications of these findings are discussed.

Integrative Analysis of Membrane Proteome and MicroRNA Reveals Novel Lung Cancer Metastasis Biomarkers

Lung cancer is one of the most common human cancers both in incidence and mortality, with prognosis particularly poor in metastatic cases. Metastasis in lung cancer is a multifarious process driven by a complex regulatory landscape involving many mechanisms, genes, and proteins. Membrane proteins play a crucial role in the metastatic journey both inside tumor cells and the extra-cellular matrix and are a viable area of research focus with the potential to uncover biomarkers and drug targets. In this work we performed membrane proteome analysis of highly and poorly metastatic lung cells which integrated genomic, proteomic, and transcriptional data. A total of 1,762 membrane proteins were identified, and within this set, there were 163 proteins with significant changes between the two cell lines. We applied the Tied Diffusion through Interacting Events method to integrate the differentially expressed disease-related microRNAs and functionally dys-regulated membrane protein information to further explore the role of key membrane proteins and microRNAs in multi-omics context. Has-miR-137 was revealed as a key gene involved in the activity of membrane proteins by targeting MET and PXN, affecting membrane proteins through protein-protein interaction mechanism. Furthermore, we found that the membrane proteins CDH2, EGFR, ITGA3, ITGA5, ITGB1, and CALR may have significant effect on cancer prognosis and outcomes, which were further validated in vitro. Our study provides multi-omics-based network method of integrating microRNAs and membrane proteome information, and uncovers a differential molecular signatures of highly and poorly metastatic lung cancer cells; these molecules may serve as potential targets for giant-cell lung metastasis treatment and prognosis.

A Deep Learning Framework to Predict Tumor Tissue-of-Origin Based on Copy Number Alteration

Cancer of unknown primary site (CUPS) is a type of metastatic tumor for which the sites of tumor origin cannot be determined. Precise diagnosis of the tissue origin for metastatic CUPS is crucial for developing treatment schemes to improve patient prognosis. Recently, there have been many studies using various cancer biomarkers to predict the tissue-of-origin (TOO) of CUPS. However, only a very few of them use copy number alteration (CNA) to trance TOO. In this paper, a two-step computational framework called CNA_origin is introduced to predict the tissue-of-origin of a tumor from its gene CNA levels. CNA_origin set up an intellectual deep-learning network mainly composed of an autoencoder and a convolution neural network (CNN). Based on real datasets released from the public database, CNA_origin had an overall accuracy of 83.81% on 10-fold cross-validation and 79% on independent datasets for predicting tumor origin, which improved the accuracy by 7.75 and 9.72% compared with the method published in a previous paper. Our results suggested that the autoencoder model can extract key characteristics of CNA and that the CNN classifier model developed in this study can predict the origin of tumors robustly and effectively. CNA_origin was written in Python and can be downloaded from https://github.com/YingLianghnu/CNA_origin.