Construction and experimental validation of a novel ferroptosis-related gene signature for myelodysplastic syndromes

BACKGROUND

Myelodysplastic syndromes (MDS) are clonal hematopoietic disorders characterized by morphological abnormalities and peripheral blood cytopenias, carrying a risk of progression to acute myeloid leukemia. Although ferroptosis is a promising target for MDS treatment, the specific roles of ferroptosis-related genes (FRGs) in MDS diagnosis have not been elucidated.

METHODS

MDS-related microarray data were obtained from the Gene Expression Omnibus database. A comprehensive analysis of FRG expression levels in patients with MDS and controls was conducted, followed by the use of multiple machine learning methods to establish prediction models. The predictive ability of the optimal model was evaluated using nomogram analysis and an external data set. Functional analysis was applied to explore the underlying mechanisms. The mRNA levels of the model genes were verified in MDS clinical samples by quantitative real-time polymerase chain reaction (qRT-PCR).

RESULTS

The extreme gradient boosting model demonstrated the best performance, leading to the identification of a panel of six signature genes: SREBF1, PTPN6, PARP9, MAP3K11, MDM4, and EZH2. Receiver operating characteristic curves indicated that the model exhibited high accuracy in predicting MDS diagnosis, with area under the curve values of 0.989 and 0.962 for the training and validation cohorts, respectively. Functional analysis revealed significant associations between these genes and the infiltrating immune cells. The expression levels of these genes were successfully verified in MDS clinical samples.

CONCLUSION

Our study is the first to identify a novel model using FRGs to predict the risk of developing MDS. FRGs may be implicated in MDS pathogenesis through immune-related pathways. These findings highlight the intricate correlation between ferroptosis and MDS, offering insights that may aid in identifying potential therapeutic targets for this debilitating disorder.

Correlation between intraosseous thermal change and drilling impulse data during osteotomy within autonomous dental implant robotic system: An in vitro study

OBJECTIVES

This study aims at examining the correlation of intraosseous temperature change with drilling impulse data during osteotomy and establishing real-time temperature prediction models.

MATERIALS AND METHODS

A combination of in vitro bovine rib model and Autonomous Dental Implant Robotic System (ADIR) was set up, in which intraosseous temperature and drilling impulse data were measured using an infrared camera and a six-axis force/torque sensor respectively. A total of 800 drills with different parameters (e.g., drill diameter, drill wear, drilling speed, and thickness of cortical bone) were experimented, along with an independent test set of 200 drills. Pearson correlation analysis was done for linear relationship. Four machining learning (ML) algorithms (e.g., support vector regression [SVR], ridge regression [RR], extreme gradient boosting [XGboost], and artificial neural network [ANN]) were run for building prediction models.

RESULTS

By incorporating different parameters, it was found that lower drilling speed, smaller drill diameter, more severe wear, and thicker cortical bone were associated with higher intraosseous temperature changes and longer time exposure and were accompanied with alterations in drilling impulse data. Pearson correlation analysis further identified highly linear correlation between drilling impulse data and thermal changes. Finally, four ML prediction models were established, among which XGboost model showed the best performance with the minimum error measurements in test set.

CONCLUSION

The proof-of-concept study highlighted close correlation of drilling impulse data with intraosseous temperature change during osteotomy. The ML prediction models may inspire future improvement on prevention of thermal bone injury and intelligent design of robot-assisted implant surgery.

Prediction of submitochondrial proteins localization based on Gene Ontology

Mitochondria, which are double-membrane bound organelles commonly found in eukaryotic cells, play a fundamental role as sites for cellular energy production. Within the mitochondria, there exist substructures called submitochondria, and specific proteins associated with submitochondria have been implicated in various human diseases. Therefore, comprehending the precise localization of these submitochondrial proteins is of utmost importance. Such knowledge not only aids in unraveling their role in the pathogenesis of diseases but also facilitates the development of therapeutic drugs and diagnostic methods. In this study, we proposed a novel method based on Gene Ontology (GO) to predict the localization of the submitochondrial proteins, called GO-Submito. More specifically, the GO-Submito fine-tuned pre-training Bidirectional Encoder Representations from Transformers models to encode GO annotations into vectors. Subsequently, the Multi-head Attention Mechanism was employed to fuse these encoded vectors of GO annotations, enabling precise localization prediction. Through comprehensive evaluation, our results demonstrated that GO-Submito outperforms existing methods, offering a reliable and efficient tool for precisely localizing submitochondrial proteins.

Prediction of the interaction between Calloselasma rhodostoma venom-derived peptides and cancer-associated hub proteins: A computational study

The use of peptide drugs to treat cancer is gaining popularity because of their efficacy, fewer side effects, and several advantages over other properties. Identifying the peptides that interact with cancer proteins is crucial in drug discovery. Several approaches related to predicting peptide-protein interactions have been conducted. However, problems arise due to the high costs of resources and time and the smaller number of studies. This study predicts peptide-protein interactions using Random Forest, XGBoost, and SAE-DNN. Feature extraction is also performed on proteins and peptides using intrinsic disorder, amino acid sequences, physicochemical properties, position-specific assessment matrices, amino acid composition, and dipeptide composition. Results show that all algorithms perform equally well in predicting interactions between peptides derived from venoms and target proteins associated with cancer. However, XGBoost produces the best results with accuracy, precision, and area under the receiver operating characteristic curve of 0.859, 0.663, and 0.697, respectively. The enrichment analysis revealed that peptides from the Calloselasma rhodostoma venom targeted several proteins (ESR1, GOPC, and BRD4) related to cancer.

Machine learning identification and immune infiltration of disulfidptosis-related Alzheimer's disease molecular subtypes

BACKGROUND

Alzheimer's disease (AD) is a common neurodegenerative disorder. Disulfidptosis is a newly discovered form of programmed cell death that holds promise as a therapeutic strategy for various disorders. However, the functional roles of disulfidptosis-related genes (DRGs) in AD remain unknown.

METHODS

Microarray data and clinical information from patients with AD and healthy controls were downloaded from the Gene Expression Omnibus database. A thorough examination of DRG expression and immune characteristics in both groups was performed. Based on the identified DRGs, we performed an unsupervised clustering analysis to categorize the AD samples into various disulfidptosis-related molecular clusters. Weighted gene co-expression network analysis was performed to select hub genes specific to disulfidptosis-related AD clusters. The performances of various machine learning models were compared to determine the optimal predictive model. The predictive ability of the optimal model was assessed using nomogram analysis and five external datasets.

RESULTS

Eight DRGs showed differential expression between the AD and control samples. Two different molecular clusters were identified. The immune cell infiltration analysis revealed distinct differences in the immune microenvironment of the two clusters. The support vector machine model showed the highest performance, and a panel of five signature genes was identified, which showed excellent performance on the external validation datasets. The nomogram analysis also showed high accuracy in predicting AD.

CONCLUSION

We identified disulfidptosis-related molecular clusters in AD and established a novel risk model to assess the likelihood of developing AD. These findings revealed a complex association between disulfidptosis and AD, which may aid in identifying potential therapeutic targets for this debilitating disorder.

Identification of plant vacuole proteins by using graph neural network and contact maps

Plant vacuoles are essential organelles in the growth and development of plants, and accurate identification of their proteins is crucial for understanding their biological properties. In this study, we developed a novel model called GraphIdn for the identification of plant vacuole proteins. The model uses SeqVec, a deep representation learning model, to initialize the amino acid sequence. We utilized the AlphaFold2 algorithm to obtain the structural information of corresponding plant vacuole proteins, and then fed the calculated contact maps into a graph convolutional neural network. GraphIdn achieved accuracy values of 88.51% and 89.93% in independent testing and fivefold cross-validation, respectively, outperforming previous state-of-the-art predictors. As far as we know, this is the first model to use predicted protein topology structure graphs to identify plant vacuole proteins. Furthermore, we assessed the effectiveness and generalization capability of our GraphIdn model by applying it to identify and locate peroxisomal proteins, which yielded promising outcomes. The source code and datasets can be accessed at https://github.com/SJNNNN/GraphIdn .

BiGRUD-SA: Protein S-sulfenylation sites prediction based on BiGRU and self-attention

S-sulfenylation is a vital post-translational modification (PTM) of proteins, which is an intermediate in other redox reactions and has implications for signal transduction and protein function regulation. However, there are many restrictions on the experimental identification of S-sulfenylation sites. Therefore, predicting S-sulfoylation sites by computational methods is fundamental to studying protein function and related biological mechanisms. In this paper, we propose a method named BiGRUD-SA based on bi-directional gated recurrent unit (BiGRU) and self-attention mechanism to predict protein S-sulfenylation sites. We first use AAC, BLOSUM62, AAindex, EAAC and GAAC to extract features, and do feature fusion to obtain original feature space. Next, we use SMOTE-Tomek method to handle data imbalance. Then, we input the processed data to the BiGRU and use self-attention mechanism to do further feature extraction. Finally, we input the data obtained to the deep neural networks (DNN) to identify S-sulfenylation sites. The accuracies of training set and independent test set are 96.66% and 95.91% respectively, which indicates that our method is conducive to identifying S-sulfenylation sites. Furthermore, we use a data set of S-sulfenylation sites in Arabidopsis thaliana to effectively verify the generalization ability of BiGRUD-SA method, and obtain better prediction results.

XGBoost-SHAP-based interpretable diagnostic framework for alzheimer's disease

BACKGROUND

Due to the class imbalance issue faced when Alzheimer's disease (AD) develops from normal cognition (NC) to mild cognitive impairment (MCI), present clinical practice is met with challenges regarding the auxiliary diagnosis of AD using machine learning (ML). This leads to low diagnosis performance. We aimed to construct an interpretable framework, extreme gradient boosting-Shapley additive explanations (XGBoost-SHAP), to handle the imbalance among different AD progression statuses at the algorithmic level. We also sought to achieve multiclassification of NC, MCI, and AD.

METHODS

We obtained patient data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including clinical information, neuropsychological test results, neuroimaging-derived biomarkers, and APOE-ε4 gene statuses. First, three feature selection algorithms were applied, and they were then included in the XGBoost algorithm. Due to the imbalance among the three classes, we changed the sample weight distribution to achieve multiclassification of NC, MCI, and AD. Then, the SHAP method was linked to XGBoost to form an interpretable framework. This framework utilized attribution ideas that quantified the impacts of model predictions into numerical values and analysed them based on their directions and sizes. Subsequently, the top 10 features (optimal subset) were used to simplify the clinical decision-making process, and their performance was compared with that of a random forest (RF), Bagging, AdaBoost, and a naive Bayes (NB) classifier. Finally, the National Alzheimer's Coordinating Center (NACC) dataset was employed to assess the impact path consistency of the features within the optimal subset.

RESULTS

Compared to the RF, Bagging, AdaBoost, NB and XGBoost (unweighted), the interpretable framework had higher classification performance with accuracy improvements of 0.74%, 0.74%, 1.46%, 13.18%, and 0.83%, respectively. The framework achieved high sensitivity (81.21%/74.85%), specificity (92.18%/89.86%), accuracy (87.57%/80.52%), area under the receiver operating characteristic curve (AUC) (0.91/0.88), positive clinical utility index (0.71/0.56), and negative clinical utility index (0.75/0.68) on the ADNI and NACC datasets, respectively. In the ADNI dataset, the top 10 features were found to have varying associations with the risk of AD onset based on their SHAP values. Specifically, the higher SHAP values of CDRSB, ADAS13, ADAS11, ventricle volume, ADASQ4, and FAQ were associated with higher risks of AD onset. Conversely, the higher SHAP values of LDELTOTAL, mPACCdigit, RAVLT_immediate, and MMSE were associated with lower risks of AD onset. Similar results were found for the NACC dataset.

CONCLUSIONS

The proposed interpretable framework contributes to achieving excellent performance in imbalanced AD multiclassification tasks and provides scientific guidance (optimal subset) for clinical decision-making, thereby facilitating disease management and offering new research ideas for optimizing AD prevention and treatment programs.

Early identification of bloodstream infection in hemodialysis patients by machine learning

Background

Bloodstream infection (BSI) is a prevalent cause of admission in hemodialysis (HD) patients and is associated with increased morbidity and mortality. This study aimed to establish a diagnostic, predictive model for the early identification of BSI in HD patients.

Methods

HD patients who underwent blood culture testing between August 2018 and March 2022 were enrolled in this study. Machine learning algorithms, including stepwise logistic regression (SLR), Lasso logistic regression (LLR), support vector machine (SVM), decision tree, random forest (RF), and gradient boosting machine (XGboost), were used to predict the risk of developing BSI from the patient's clinical data. The accuracy (ACC) and area under the subject working curve (AUC) were used to evaluate the performance of such models. The Shapley Additive Explanation (SHAP) values were used to explain each feature's predictive value on the models' output. Finally, a simplified nomogram for predicting BSI was devised.

Results

A total of 391 HD patients were enrolled in this study, of whom 74 (18.9%) were diagnosed with BSI. The XGboost model achieved the highest AUC (0.914, 95% confidence interval [CI]: 0.861-0.964) and ACC (86.3%) for BSI prediction. The four most significant co-variables in both the significance matrix plot of the XGboost model variables and the SHAP summary plot were body temperature, dialysis access via a non-arteriovenous fistula (non-AVF), the procalcitonin levels (PCT), and neutrophil-lymphocyte ratio (NLR).

Conclusions

This study created an effective machine-learning model for predicting BSI in HD patients. The model could be used to detect BSI at an early stage and hence guide antibiotic treatment in HD patients.

GraphCPIs: A novel graph-based computational model for potential compound-protein interactions

Identifying proteins that interact with drug compounds has been recognized as an important part in the process of drug discovery. Despite extensive efforts that have been invested in predicting compound-protein interactions (CPIs), existing traditional methods still face several challenges. The computer-aided methods can identify high-quality CPI candidates instantaneously. In this research, a novel model is named GraphCPIs, proposed to improve the CPI prediction accuracy. First, we establish the adjacent matrix of entities connected to both drugs and proteins from the collected dataset. Then, the feature representation of nodes could be obtained by using the graph convolutional network and Grarep embedding model. Finally, an extreme gradient boosting (XGBoost) classifier is exploited to identify potential CPIs based on the stacked two kinds of features. The results demonstrate that GraphCPIs achieves the best performance, whose average predictive accuracy rate reaches 90.09%, average area under the receiver operating characteristic curve is 0.9572, and the average area under the precision and recall curve is 0.9621. Moreover, comparative experiments reveal that our method surpasses the state-of-the-art approaches in the field of accuracy and other indicators with the same experimental environment. We believe that the GraphCPIs model will provide valuable insight to discover novel candidate drug-related proteins.

DBGRU-SE: predicting drug-drug interactions based on double BiGRU and squeeze-and-excitation attention mechanism

The prediction of drug-drug interactions (DDIs) is essential for the development and repositioning of new drugs. Meanwhile, they play a vital role in the fields of biopharmaceuticals, disease diagnosis and pharmacological treatment. This article proposes a new method called DBGRU-SE for predicting DDIs. Firstly, FP3 fingerprints, MACCS fingerprints, Pubchem fingerprints and 1D and 2D molecular descriptors are used to extract the feature information of the drugs. Secondly, Group Lasso is used to remove redundant features. Then, SMOTE-ENN is applied to balance the data to obtain the best feature vectors. Finally, the best feature vectors are fed into the classifier combining BiGRU and squeeze-and-excitation (SE) attention mechanisms to predict DDIs. After applying five-fold cross-validation, The ACC values of DBGRU-SE model on the two datasets are 97.51 and 94.98%, and the AUC are 99.60 and 98.85%, respectively. The results showed that DBGRU-SE had good predictive performance for drug-drug interactions.

DE-MHAIPs: Identification of SARS-CoV-2 phosphorylation sites based on differential evolution multi-feature learning and multi-head attention mechanism

The rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) around the world affects the normal lives of people all over the world. The computational methods can be used to accurately identify SARS-CoV-2 phosphorylation sites. In this paper, a new prediction model of SARS-CoV-2 phosphorylation sites, called DE-MHAIPs, is proposed. First, we use six feature extraction methods to extract protein sequence information from different perspectives. For the first time, we use a differential evolution (DE) algorithm to learn individual feature weights and fuse multi-information in a weighted combination. Next, Group LASSO is used to select a subset of good features. Then, the important protein information is given higher weight through multi-head attention. After that, the processed data is fed into long short-term memory network (LSTM) to further enhance model's ability to learn features. Finally, the data from LSTM are input into fully connected neural network (FCN) to predict SARS-CoV-2 phosphorylation sites. The AUC values of the S/T and Y datasets under 5-fold cross-validation reach 91.98% and 98.32%, respectively. The AUC values of the two datasets on the independent test set reach 91.72% and 97.78%, respectively. The experimental results show that the DE-MHAIPs method exhibits excellent predictive ability compared with other methods.

Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction

Interactions between DNA and transcription factors (TFs) play an essential role in understanding transcriptional regulation mechanisms and gene expression. Due to the large accumulation of training data and low expense, deep learning methods have shown huge potential in determining the specificity of TFs-DNA interactions. Convolutional network-based and self-attention network-based methods have been proposed for transcription factor binding sites (TFBSs) prediction. Convolutional operations are efficient to extract local features but easy to ignore global information, while self-attention mechanisms are expert in capturing long-distance dependencies but difficult to pay attention to local feature details. To discover comprehensive features for a given sequence as far as possible, we propose a Dual-branch model combining Self-Attention and Convolution, dubbed as DSAC, which fuses local features and global representations in an interactive way. In terms of features, convolution and self-attention contribute to feature extraction collaboratively, enhancing the representation learning. In terms of structure, a lightweight but efficient architecture of network is designed for the prediction, in particular, the dual-branch structure makes the convolution and the self-attention mechanism can be fully utilized to improve the predictive ability of our model. The experiment results on 165 ChIP-seq datasets show that DSAC obviously outperforms other five deep learning based methods and demonstrate that our model can effectively predict TFBSs based on sequence feature alone. The source code of DSAC is available at https://github.com/YuBinLab-QUST/DSAC/.

PScL-2LSAESM: bioimage-based prediction of protein subcellular localization by integrating heterogeneous features with the two-level SAE-SM and mean ensemble method

MOTIVATION

Over the past decades, a variety of in silico methods have been developed to predict protein subcellular localization within cells. However, a common and major challenge in the design and development of such methods is how to effectively utilize the heterogeneous feature sets extracted from bioimages. In this regards, limited efforts have been undertaken.

RESULTS

We propose a new two-level stacked autoencoder network (termed 2L-SAE-SM) to improve its performance by integrating the heterogeneous feature sets. In particular, in the first level of 2L-SAE-SM, each optimal heterogeneous feature set is fed to train our designed stacked autoencoder network (SAE-SM). All the trained SAE-SMs in the first level can output the decision sets based on their respective optimal heterogeneous feature sets, known as 'intermediate decision' sets. Such intermediate decision sets are then ensembled using the mean ensemble method to generate the 'intermediate feature' set for the second-level SAE-SM. Using the proposed framework, we further develop a novel predictor, referred to as PScL-2LSAESM, to characterize image-based protein subcellular localization. Extensive benchmarking experiments on the latest benchmark training and independent test datasets collected from the human protein atlas databank demonstrate the effectiveness of the proposed 2L-SAE-SM framework for the integration of heterogeneous feature sets. Moreover, performance comparison of the proposed PScL-2LSAESM with current state-of-the-art methods further illustrates that PScL-2LSAESM clearly outperforms the existing state-of-the-art methods for the task of protein subcellular localization.

AVAILABILITY AND IMPLEMENTATION

https://github.com/csbio-njust-edu/PScL-2LSAESM.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Discovery of new potent lysine specific histone demythelase-1 inhibitors (LSD-1) using structure based and ligand based molecular modelling and machine learning

Lysine-specific histone demethylase 1 (LSD-1) is an epigenetic enzyme that oxidatively cleaves methyl groups from monomethyl and dimethyl Lys4 of histone H3 and is highly overexpressed in different types of cancer. Therefore, it has been widely recognized as a promising therapeutic target for cancer therapy. Towards this end, we employed various Computer Aided Drug Design (CADD) approaches including pharmacophore modelling and machine learning. Pharmacophores generated by structure-based (SB) (either crystallographic-based or docking-based) and ligand-based (LB) (either supervised or unsupervised) modelling methods were allowed to compete within the context of genetic algorithm/machine learning and were assessed by Shapley additive explanation values (SHAP) to end up with three successful pharmacophores that were used to screen the National Cancer Institute (NCI) database. Seventy-five NCI hits were tested for their LSD-1 inhibitory properties against neuroblastoma SH-SY5Y cells, pancreatic carcinoma Panc-1 cells, glioblastoma U-87 MG cells and in vitro enzymatic assay, culminating in 3 nanomolar LSD-1 inhibitors of novel chemotypes.

Accurate Prediction of Anti-hypertensive Peptides Based on Convolutional Neural Network and Gated Recurrent unit

Hypertension (HT) is a general disease, and also one of the most ordinary and major causes of cardiovascular disease. Some diseases are caused by high blood pressure, including impairment of heart and kidney function, cerebral hemorrhage and myocardial infarction. Due to the limitations of laboratory methods, bioactive peptides for the treatment of HT need a long time to be identified. Therefore, it is of great immediate significance for the identification of anti-hypertensive peptides (AHTPs). With the prevalence of machine learning, it is suggested to use it as a supplementary method for AHTPs classification. Therefore, we develop a new model to identify AHTPs based on multiple features and deep learning. And the deep model is constructed by combining a convolutional neural network (CNN) and a gated recurrent unit (GRU). The unique convolution structure is used to reduce the feature dimension and running time. The data processed by CNN is input into the recurrent structure GRU, and important information is filtered out through the reset gate and update gate. Finally, the output layer adopts Sigmoid activation function. Firstly, we use Kmer, the deviation between the dipeptide frequency and the expected mean (DDE), encoding based on grouped weight (EBGW), enhanced grouped amino acid composition (EGAAC) and dipeptide binary profile and frequency (DBPF) to extract features. For Kmer, DDE, EBGW and EGAAC, it is widely used in the field of protein research. DBPF is a new feature representation method designed by us. It corresponds dipeptides to binary numbers, and finally obtains a binary coding file and a frequency file. Then these features are spliced together and input into our proposed model for prediction and analysis. After a tenfold cross-validation test, this model has a better competitive advantage than the previous methods, and the accuracy is 96.23% and 99.10%, respectively. From the results, compared with the previous methods, it has been greatly improved. It shows that the combination of convolution calculation and recurrent structure has a positive impact on the classification of AHTPs. The results show that this method is a feasible, efficient and competitive sequence analysis tool for AHTPs. Meanwhile, we design a friendly online prediction tool and it is freely accessible at http://ahtps.zhanglab.site/ .

Predicting suitable habitats of Melia azedarach L. in China using data mining

Melia azedarach L. is an important economic tree widely distributed in tropical and subtropical regions of China and some other countries. However, it is unclear how the species’ suitable habitat will respond to future climate changes. We aimed to select the most accurate one among seven data mining models to predict the current and future suitable habitats for M. azedarach in China. These models include: maximum entropy (MaxEnt), support vector machine (SVM), generalized linear model (GLM), random forest (RF), naive bayesian model (NBM), extreme gradient boosting (XGBoost), and gradient boosting machine (GBM). A total of 906 M. azedarach locations were identified, and sixteen climate predictors were used for model building. The models’ validity was assessed using three measures (Area Under the Curves (AUC), kappa, and overall accuracy (OA)). We found that the RF provided the most outstanding performance in prediction power and generalization capacity. The top climate factors affecting the species’ suitable habitats were mean coldest month temperature (MCMT), followed by the number of frost-free days (NFFD), degree-days above 18 °C (DD > 18), temperature difference between MWMT and MCMT, or continentality (TD), mean annual precipitation (MAP), and degree-days below 18 °C (DD < 18). We projected that future suitable habitat of this species would increase under both the RCP4.5 and RCP8.5 scenarios for the 2011–2040 (2020s), 2041–2070 (2050s), and 2071–2100 (2080s). Our findings are expected to assist in better understanding the impact of climate change on the species and provide scientific basis for its planting and conservation.

PrUb-EL: A hybrid framework based on deep learning for identifying ubiquitination sites in Arabidopsis thaliana using ensemble learning strategy

Identification of ubiquitination sites is central to many biological experiments. Ubiquitination is a kind of post-translational protein modification (PTM). It is a key mechanism for increasing protein diversity and plays a vital role in regulating cell function. In recent years, many models have been developed to predict ubiquitination sites in humans, mice and yeast. However, few studies have predicted ubiquitination sites in Arabidopsis thaliana. In view of this, a deep network model named PrUb-EL is proposed to predict ubiquitination sites in Arabidopsis thaliana. Firstly, six features based on the protein sequence are extracted with amino acid index database (AAindex), dipeptide deviates from the expected mean (DDE), dipeptide composition (DPC), blocks substitution matrix (BLOSUM62), enhanced amino acid composition (EAAC) and binary encoding. Secondly, the synthetic minority over-sampling technique (SMOTE) is utilized to process the imbalanced data set. Then a new classifier named DG is presented, which includes Dense block, Residual block and Gated recurrent unit (GRU) block. Finally, each of six feature extraction methods is integrated into the DG model, and the ensemble learning strategy is used to gain the final prediction result. Experimental results show that PrUb-EL has good predictive ability with the accuracy (ACC) and area under the ROC curve (auROC) values of 91.00% and 97.70% using 5-fold cross-validation, respectively. Note that the values of ACC and auROC are 88.58% and 96.09% in the independent test, respectively. Compared with previous studies, our model has significantly improved performance thus it is an excellent method for identifying ubiquitination sites in Arabidopsis thaliana. The datasets and code used for the article are available at https://github.com/Tom-Wangy/PreUb-EL.git.

Predicting Age-related Macular Degeneration Progression with Longitudinal Fundus Images Using Deep Learning

Accurately predicting a patient's risk of progressing to late age-related macular degeneration (AMD) is difficult but crucial for personalized medicine. While existing risk prediction models for progression to late AMD are useful for triaging patients, none utilizes longitudinal color fundus photographs (CFPs) in a patient's history to estimate the risk of late AMD in a given subsequent time interval. In this work, we seek to evaluate how deep neural networks capture the sequential information in longitudinal CFPs and improve the prediction of 2-year and 5-year risk of progression to late AMD. Specifically, we proposed two deep learning models, CNN-LSTM and CNN-Transformer, which use a Long-Short Term Memory (LSTM) and a Transformer, respectively with convolutional neural networks (CNN), to capture the sequential information in longitudinal CFPs. We evaluated our models in comparison to baselines on the Age-Related Eye Disease Study, one of the largest longitudinal AMD cohorts with CFPs. The proposed models outperformed the baseline models that utilized only single-visit CFPs to predict the risk of late AMD (0.879 vs 0.868 in AUC for 2-year prediction, and 0.879 vs 0.862 for 5-year prediction). Further experiments showed that utilizing longitudinal CFPs over a longer time period was helpful for deep learning models to predict the risk of late AMD. We made the source code available at https://github.com/bionlplab/AMD_prognosis_mlmi2022 to catalyze future works that seek to develop deep learning models for late AMD prediction.

Opening the black box: interpretable machine learning for predictor finding of metabolic syndrome

OBJECTIVE

The internal workings ofmachine learning algorithms are complex and considered as low-interpretation "black box" models, making it difficult for domain experts to understand and trust these complex models. The study uses metabolic syndrome (MetS) as the entry point to analyze and evaluate the application value of model interpretability methods in dealing with difficult interpretation of predictive models.

METHODS

The study collects data from a chain of health examination institution in Urumqi from 2017 ~ 2019, and performs 39,134 remaining data after preprocessing such as deletion and filling. RFE is used for feature selection to reduce redundancy; MetS risk prediction models (logistic, random forest, XGBoost) are built based on a feature subset, and accuracy, sensitivity, specificity, Youden index, and AUROC value are used to evaluate the model classification performance; post-hoc model-agnostic interpretation methods (variable importance, LIME) are used to interpret the results of the predictive model.

RESULTS

Eighteen physical examination indicators are screened out by RFE, which can effectively solve the problem of physical examination data redundancy. Random forest and XGBoost models have higher accuracy, sensitivity, specificity, Youden index, and AUROC values compared with logistic regression. XGBoost models have higher sensitivity, Youden index, and AUROC values compared with random forest. The study uses variable importance, LIME and PDP for global and local interpretation of the optimal MetS risk prediction model (XGBoost), and different interpretation methods have different insights into the interpretation of model results, which are more flexible in model selection and can visualize the process and reasons for the model to make decisions. The interpretable risk prediction model in this study can help to identify risk factors associated with MetS, and the results showed that in addition to the traditional risk factors such as overweight and obesity, hyperglycemia, hypertension, and dyslipidemia, MetS was also associated with other factors, including age, creatinine, uric acid, and alkaline phosphatase.

CONCLUSION

The model interpretability methods are applied to the black box model, which can not only realize the flexibility of model application, but also make up for the uninterpretable defects of the model. Model interpretability methods can be used as a novel means of identifying variables that are more likely to be good predictors.

PScL-DDCFPred: an ensemble deep learning-based approach for characterizing multiclass subcellular localization of human proteins from bioimage data

MOTIVATION

Characterization of protein subcellular localization has become an important and long-standing task in bioinformatics and computational biology, which provides valuable information for elucidating various cellular functions of proteins and guiding drug design.

RESULTS

Here, we develop a novel bioimage-based computational approach, termed PScL-DDCFPred, to accurately predict protein subcellular localizations in human tissues. PScL-DDCFPred first extracts multiview image features, including global and local features, as base or pure features; next, it applies a new integrative feature selection method based on stepwise discriminant analysis and generalized discriminant analysis to identify the optimal feature sets from the extracted pure features; Finally, a classifier based on deep neural network (DNN) and deep-cascade forest (DCF) is established. Stringent 10-fold cross-validation tests on the new protein subcellular localization training dataset, constructed from the human protein atlas databank, illustrates that PScL-DDCFPred achieves a better performance than several existing state-of-the-art methods. Moreover, the independent test set further illustrates the generalization capability and superiority of PScL-DDCFPred over existing predictors. In-depth analysis shows that the excellent performance of PScL-DDCFPred can be attributed to three critical factors, namely the effective combination of the DNN and DCF models, complementarity of global and local features, and use of the optimal feature sets selected by the integrative feature selection algorithm.

AVAILABILITY AND IMPLEMENTATION

https://github.com/csbio-njust-edu/PScL-DDCFPred.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

R5hmCFDV: computational identification of RNA 5-hydroxymethylcytosine based on deep feature fusion and deep voting

RNA 5-hydroxymethylcytosine (5hmC) is a kind of RNA modification, which is related to the life activities of many organisms. Studying its distribution is very important to reveal its biological function. Previously, high-throughput sequencing was used to identify 5hmC, but it is expensive and inefficient. Therefore, machine learning is used to identify 5hmC sites. Here, we design a model called R5hmCFDV, which is mainly divided into feature representation, feature fusion and classification. (i) Pseudo dinucleotide composition, dinucleotide binary profile and frequency, natural vector and physicochemical property are used to extract features from four aspects: nucleotide composition, coding, natural language and physical and chemical properties. (ii) To strengthen the relevance of features, we construct a novel feature fusion method. Firstly, the attention mechanism is employed to process four single features, stitch them together and feed them to the convolution layer. After that, the output data are processed by BiGRU and BiLSTM, respectively. Finally, the features of these two parts are fused by the multiply function. (iii) We design the deep voting algorithm for classification by imitating the soft voting mechanism in the Python package. The base classifiers contain deep neural network (DNN), convolutional neural network (CNN) and improved gated recurrent unit (GRU). And then using the principle of soft voting, the corresponding weights are assigned to the predicted probabilities of the three classifiers. The predicted probability values are multiplied by the corresponding weights and then summed to obtain the final prediction results. We use 10-fold cross-validation to evaluate the model, and the evaluation indicators are significantly improved. The prediction accuracy of the two datasets is as high as 95.41% and 93.50%, respectively. It demonstrates the stronger competitiveness and generalization performance of our model. In addition, all datasets and source codes can be found at https://github.com/HongyanShi026/R5hmCFDV.

Supervised Pretraining through Contrastive Categorical Positive Samplings to Improve COVID-19 Mortality Prediction

Clinical EHR data is naturally heterogeneous, where it contains abundant sub-phenotype. Such diversity creates challenges for outcome prediction using a machine learning model since it leads to high intra-class variance. To address this issue, we propose a supervised pre-training model with a unique embedded k-nearest-neighbor positive sampling strategy. We demonstrate the enhanced performance value of this framework theoretically and show that it yields highly competitive experimental results in predicting patient mortality in real-world COVID-19 EHR data with a total of over 7,000 patients admitted to a large, urban health system. Our method achieves a better AUROC prediction score of 0.872, which outperforms the alternative pre-training models and traditional machine learning methods. Additionally, our method performs much better when the training data size is small (345 training instances).

eXtreme Gradient Boosting-based method to classify patients with COVID-19

Different demographic, clinical and laboratory variables have been related to the severity and mortality following SARS-CoV-2 infection. Most studies applied traditional statistical methods and in some cases combined with a machine learning (ML) method. This is the first study to date to comparatively analyze five ML methods to select the one that most closely predicts mortality in patients admitted with COVID-19. The aim of this single-center observational study is to classify, based on different types of variables, adult patients with COVID-19 at increased risk of mortality. SARS-CoV-2 infection was defined by a positive reverse transcriptase PCR. A total of 203 patients were admitted between March 15 and June 15, 2020 to a tertiary hospital. Data were extracted from the electronic medical record. Four supervised ML algorithms (k-nearest neighbors (KNN), decision tree (DT), Gaussian naïve Bayes (GNB) and support vector machine (SVM)) were compared with the eXtreme Gradient Boosting (XGB) method proposed to have excellent scalability and high running speed, among other qualities. The results indicate that the XGB method has the best prediction accuracy (92%), high precision (>0.92) and high recall (>0.92). The KNN, SVM and DT approaches present moderate prediction accuracy (>80%), moderate recall (>0.80) and moderate precision (>0.80). The GNB algorithm shows relatively low classification performance. The variables with the greatest weight in predicting mortality were C reactive protein, procalcitonin, glutamyl oxaloacetic transaminase, glutamyl pyruvic transaminase, neutrophils, D-dimer, creatinine, lactic acid, ferritin, days of non-invasive ventilation, septic shock and age. Based on these results, XGB is a solid candidate for correct classification of patients with COVID-19.

A versatile active learning workflow for optimization of genetic and metabolic networks

Optimization of biological networks is often limited by wet lab labor and cost, and the lack of convenient computational tools. Here, we describe METIS, a versatile active machine learning workflow with a simple online interface for the data-driven optimization of biological targets with minimal experiments. We demonstrate our workflow for various applications, including cell-free transcription and translation, genetic circuits, and a 27-variable synthetic CO₂-fixation cycle (CETCH cycle), improving these systems between one and two orders of magnitude. For the CETCH cycle, we explore 10²⁵ conditions with only 1,000 experiments to yield the most efficient CO₂-fixation cascade described to date. Beyond optimization, our workflow also quantifies the relative importance of individual factors to the performance of a system identifying unknown interactions and bottlenecks. Overall, our workflow opens the way for convenient optimization and prototyping of genetic and metabolic networks with customizable adjustments according to user experience, experimental setup, and laboratory facilities.

Optimization of biological networks is often limited by wet lab labor and cost, and the lack of convenient computational tools. Here, aimed at democratization and standardization, the authors describe METIS, a modular and versatile active machine learning workflow with a simple online interface for the optimization of biological target functions with minimal experimental datasets.

CRCF: A Method of Identifying Secretory Proteins of Malaria Parasites

Malaria is a mosquito-borne disease that results in millions of cases and deaths annually. The development of a fast computational method that identifies secretory proteins of the malaria parasite is important for research on antimalarial drugs and vaccines. Thus, a method was developed to identify the secretory proteins of malaria parasites. In this method, a reduced alphabet was selected to recode the original protein sequence. A feature synthesis method was used to synthesise three different types of feature information. Finally, the random forest method was used as a classifier to identify the secretory proteins. In addition, a web server was developed to share the proposed algorithm. Experiments using the benchmark dataset demonstrated that the overall accuracy achieved by the proposed method was greater than 97.8 percent using the 10-fold cross-validation method. Furthermore, the reduced schemes and characteristic performance analyses are discussed.

SuccSPred2.0: A Two-Step Model to Predict Succinylation Sites Based on Multifeature Fusion and Selection Algorithm

Protein succinylation is a novel type of post-translational modification in recent decade years. It played an important role in biological structure and functions verified by experiments. However, it is time consuming and laborious for the wet experimental identification of succinylation sites. Traditional technology cannot adapt to the rapid growth of the biological sequence data sets. In this study, a new computational method named SuccSPred2.0 was proposed to identify succinylation sites in the protein sequences based on multifeature fusion and maximal information coefficient (MIC) method. SuccSPred2.0 was implemented based on a two-step strategy. At first, high-dimension features were reduced by linear discriminant analysis to prevent overfitting. Subsequently, MIC method was employed to select the important features binding classifiers to predict succinylation sites. From the compared experiments on 10-fold cross-validation and independent test data sets, SuccSPred2.0 obtained promising improvements. Comparative experiments showed that SuccSPred2.0 was superior to previous tools in identifying succinylation sites in the given proteins.

PON-All: Amino Acid Substitution Tolerance Predictor for All Organisms

Genetic variations are investigated in human and many other organisms for many purposes (e.g., to aid in clinical diagnosis). Interpretation of the identified variations can be challenging. Although some dedicated prediction methods have been developed and some tools for human variants can also be used for other organisms, the performance and species range have been limited. We developed a novel variant pathogenicity/tolerance predictor for amino acid substitutions in any organism. The method, PON-All, is a machine learning tool trained on human, animal, and plant variants. Two versions are provided, one with Gene Ontology (GO) annotations and another without these details. GO annotations are not available or are partial for many organisms of interest. The methods provide predictions for three classes: pathogenic, benign, and variants of unknown significance. On the blind test, when using GO annotations, accuracy was 0.913 and MCC 0.827. When GO features were not used, accuracy was 0.856 and MCC 0.712. The performance is the best for human and plant variants and somewhat lower for animal variants because the number of known disease-causing variants in animals is rather small. The method was compared to several other tools and was found to have superior performance. PON-All is freely available at http://structure.bmc.lu.se/PON-All and http://8.133.174.28:8999/.

DIRECT-NET: An efficient method to discover cis-regulatory elements and construct regulatory networks from single-cell multiomics data

The emergence of single-cell multiomics data provides unprecedented opportunities to scrutinize the transcriptional regulatory mechanisms controlling cell identity. However, how to use those datasets to dissect the cis-regulatory element (CRE)–to–gene relationships at a single-cell level remains a major challenge. Here, we present DIRECT-NET, a machine-learning method based on gradient boosting, to identify genome-wide CREs and their relationship to target genes, either from parallel single-cell gene expression and chromatin accessibility data or from single-cell chromatin accessibility data alone. By extensively evaluating and characterizing DIRECT-NET’s predicted CREs using independent functional genomics data, we find that DIRECT-NET substantially improves the accuracy of inferring CRE-to-gene relationships in comparison to existing methods. DIRECT-NET is also capable of revealing cell subpopulation–specific and dynamic regulatory linkages. Overall, DIRECT-NET provides an efficient tool for predicting transcriptional regulation codes from single-cell multiomics data.

Construction of Prediction Model of Renal Damage in Children with Henoch-Schönlein Purpura Based on Machine Learning

Objective

The children with Henoch-Schönlein purpura (HSP) may suffer from renal insufficiency, which seriously affects the life and health of the children. This study aims to construct a prediction model of Henoch-Schönlein purpura nephritis (HSPN).

Methods

A total of 240 children with HSP treated in dermatology and pediatrics in our hospital were selected. The general information, patients' clinical symptoms, and laboratory examination indicators were collected for feature selection, and the XGBoost algorithm prediction model was built.

Results

According to the input feature indexes, the top ten crucial feature indicators output by the XGBoost model were urine N-acetyl-β-D-aminoglucosidase, urinary retinol-binding protein, IgA, age, recurrence of purpura, purpura area, abdominal pain, 24-h urinary protein quantification, percentage of neutrophils, and serum albumin. The areas under the curves of the training set (0.895, 95% CI: 0.827-0.963) and test set (0.870, 95% CI: 0.799-0.941) models were similar.

Conclusion

The prediction model based on XGBoost is used to predict HSP renal damage based on clinical data of children, which can reduce the harm caused by invasive examination for patients.

Recent Advances in the Prediction of Subcellular Localization of Proteins and Related Topics

Prediction of subcellular localization of proteins from their amino acid sequences has a long history in bioinformatics and is still actively developing, incorporating the latest advances in machine learning and proteomics. Notably, deep learning-based methods for natural language processing have made great contributions. Here, we review recent advances in the field as well as its related fields, such as subcellular proteomics and the prediction/recognition of subcellular localization from image data.

SCSilicon: a tool for synthetic single-cell DNA sequencing data generation

Background

Single-cell DNA sequencing is getting indispensable in the study of cell-specific cancer genomics. The performance of computational tools that tackle single-cell genome aberrations may be nevertheless undervalued or overvalued, owing to the insufficient size of benchmarking data. In silicon simulation is a cost-effective approach to generate as many single-cell genomes as possible in a controlled manner to make reliable and valid benchmarking.

Results

This study proposes a new tool, SCSilicon, which efficiently generates single-cell in silicon DNA reads with minimum manual intervention. SCSilicon automatically creates a set of genomic aberrations, including SNP, SNV, Indel, and CNV. Besides, SCSilicon yields the ground truth of CNV segmentation breakpoints and subclone cell labels. We have manually inspected a series of synthetic variations. We conducted a sanity check of the start-of-the-art single-cell CNV callers and found SCYN was the most robust one.

Conclusions

SCSilicon is a user-friendly software package for users to develop and benchmark single-cell CNV callers. Source code of SCSilicon is available at https://github.com/xikanfeng2/SCSilicon.

Supplementary Information

The online version contains supplementary material available at (10.1186/s12864-022-08566-w).

Biological activities of drug inactive ingredients

In a drug formulation (DFM), the major components by mass are not Active Pharmaceutical Ingredient (API) but rather Drug Inactive Ingredients (DIGs). DIGs can reach much higher concentrations than that achieved by API, which raises great concerns about their clinical toxicities. Therefore, the biological activities of DIG on physiologically relevant target are widely demanded by both clinical investigation and pharmaceutical industry. However, such activity data are not available in any existing pharmaceutical knowledge base, and their potentials in predicting the DIG-target interaction have not been evaluated yet. In this study, the comprehensive assessment and analysis on the biological activities of DIGs were therefore conducted. First, the largest number of DIGs and DFMs were systematically curated and confirmed based on all drugs approved by US Food and Drug Administration. Second, comprehensive activities for both DIGs and DFMs were provided for the first time to pharmaceutical community. Third, the biological targets of each DIG and formulation were fully referenced to available databases that described their pharmaceutical/biological characteristics. Finally, a variety of popular artificial intelligence techniques were used to assess the predictive potential of DIGs' activity data, which was the first evaluation on the possibility to predict DIG's activity. As the activities of DIGs are critical for current pharmaceutical studies, this work is expected to have significant implications for the future practice of drug discovery and precision medicine.

XGB-DrugPred: computational prediction of druggable proteins using eXtreme gradient boosting and optimized features set

Accurate identification of drug-targets in human body has great significance for designing novel drugs. Compared with traditional experimental methods, prediction of drug-targets via machine learning algorithms has enhanced the attention of many researchers due to fast and accurate prediction. In this study, we propose a machine learning-based method, namely XGB-DrugPred for accurate prediction of druggable proteins. The features from primary protein sequences are extracted by group dipeptide composition, reduced amino acid alphabet, and novel encoder pseudo amino acid composition segmentation. To select the best feature set, eXtreme Gradient Boosting-recursive feature elimination is implemented. The best feature set is provided to eXtreme Gradient Boosting (XGB), Random Forest, and Extremely Randomized Tree classifiers for model training and prediction. The performance of these classifiers is evaluated by tenfold cross-validation. The empirical results show that XGB-based predictor achieves the best results compared with other classifiers and existing methods in the literature.

A sequence-based two-layer predictor for identifying enhancers and their strength through enhanced feature extraction

Enhancers are short regulatory DNA fragments that are bound with proteins called activators. They are free-bound and distant elements, which play a vital role in controlling gene expression. It is challenging to identify enhancers and their strength due to their dynamic nature. Although some machine learning methods exist to accelerate identification process, their prediction accuracy and efficiency will need more improvement. In this regard, we propose a two-layer prediction model with enhanced feature extraction strategy which does feature combination from improved position-specific amino acid propensity (PSTKNC) method along with Enhanced Nucleic Acid Composition (ENAC) and Composition of k-spaced Nucleic Acid Pairs (CKSNAP). The feature sets from all three feature extraction approaches were concatenated and then sent through a simple artificial neural network (ANN) to accurately identify enhancers in the first layer and their strength in the second layer. Experiments are conducted on benchmark chromatin nine cell lines dataset. A 10-fold cross validation method is employed to evaluate model's performance. The results show that the proposed model gives an outstanding performance with 94.50%, 0.8903 of accuracy and Matthew's correlation coefficient (MCC) in predicting enhancers and fairly does well with independent test also when compared with all other existing methods.

Unifying Diagnosis Identification and Prediction Method Embedding the Disease Ontology Structure From Electronic Medical Records

OBJECTIVE

The reasonable classification of a large number of distinct diagnosis codes can clarify patient diagnostic information and help clinicians to improve their ability to assign and target treatment for primary diseases. Our objective is to identify and predict a unifying diagnosis (UD) from electronic medical records (EMRs).

METHODS

We screened 4,418 sepsis patients from a public MIMIC-III database and extracted their diagnostic information for UD identification, their demographic information, laboratory examination information, chief complaint, and history of present illness information for UD prediction. We proposed a data-driven UD identification and prediction method (UDIPM) embedding the disease ontology structure. First, we designed a set similarity measure method embedding the disease ontology structure to generate a patient similarity matrix. Second, we applied affinity propagation clustering to divide patients into different clusters, and extracted a typical diagnosis code co-occurrence pattern from each cluster. Furthermore, we identified a UD by fusing visual analysis and a conditional co-occurrence matrix. Finally, we trained five classifiers in combination with feature fusion and feature selection method to unify the diagnosis prediction.

RESULTS

The experimental results on a public electronic medical record dataset showed that the UDIPM could extracted a typical diagnosis code co-occurrence pattern effectively, identified and predicted a UD based on patients' diagnostic and admission information, and outperformed other fusion methods overall.

CONCLUSIONS

The accurate identification and prediction of the UD from a large number of distinct diagnosis codes and multi-source heterogeneous patient admission information in EMRs can provide a data-driven approach to assist better coding integration of diagnosis.

A Novel Framework Based on Deep Learning and ANOVA Feature Selection Method for Diagnosis of COVID-19 Cases from Chest X-Ray Images

Background and Objective. The new coronavirus disease (known as COVID-19) was first identified in Wuhan and quickly spread worldwide, wreaking havoc on the economy and people's everyday lives. As the number of COVID-19 cases is rapidly increasing, a reliable detection technique is needed to identify affected individuals and care for them in the early stages of COVID-19 and reduce the virus's transmission. The most accessible method for COVID-19 identification is Reverse Transcriptase-Polymerase Chain Reaction (RT-PCR); however, it is time-consuming and has false-negative results. These limitations encouraged us to propose a novel framework based on deep learning that can aid radiologists in diagnosing COVID-19 cases from chest X-ray images. Methods. In this paper, a pretrained network, DenseNet169, was employed to extract features from X-ray images. Features were chosen by a feature selection method, i.e., analysis of variance (ANOVA), to reduce computations and time complexity while overcoming the curse of dimensionality to improve accuracy. Finally, selected features were classified by the eXtreme Gradient Boosting (XGBoost). The ChestX-ray8 dataset was employed to train and evaluate the proposed method. Results and Conclusion. The proposed method reached 98.72% accuracy for two-class classification (COVID-19, No-findings) and 92% accuracy for multiclass classification (COVID-19, No-findings, and Pneumonia). The proposed method's precision, recall, and specificity rates on two-class classification were 99.21%, 93.33%, and 100%, respectively. Also, the proposed method achieved 94.07% precision, 88.46% recall, and 100% specificity for multiclass classification. The experimental results show that the proposed framework outperforms other methods and can be helpful for radiologists in the diagnosis of COVID-19 cases.

Multiple statistical models reveal specific volatile organic compounds affect sex hormones in American adult male: NHANES 2013-2016

BACKGROUND

Some VOCs are identified as endocrine-disrupting chemicals (EDCs), interfering with the effect of sex hormones. However, no studies focused on the common spectrum of environmental VOCs exposure affecting sex hormones in the average male population.

OBJECTIVES

We aimed to explore the association between VOCs and sex hormones in American adult males using multiple statistical models.

METHODS

The generalized linear (GLM), eXtreme Gradient Boosting (XGBoost), weighted quantile sum (WQS), Bayesian kernel machine regression (BKMR) and stratified models were used to evaluate the associations between Specific Volatile Organic Compounds and sex hormones in American adult male from NHANES 2013-2016.

RESULTS

Pearson correlation model revealed the potential co-exposure pattern among VOCs. XGBoost algorithm models and the WQS model suggested the relative importance of VOCs. BKMR models reveal that co-exposure to the VOCs was associated with increased Testosterone (TT), Estradiol (E₂), SHBG and decreased TT/E₂. GLM models revealed specific VOC exposure as an independent risk factor causing male sex hormones disorders. Stratified analysis identified the high-risk group on the VOCs exposures. We found Blood 2,5-Dimethylfuran in VOCs was the most significant effect on sex hormones in male. Testosterone increased by 213.594 (ng/dL) (124.552, 302.636) and estradiol increased by 7.229 (pg/mL) for each additional unit of blood 2,5-Dimethylfuran (ng/mL).

CONCLUSION

This study is an academic illustration of the association between VOCs exposure and sex hormones, suggesting that exposure to VOCs might be associated with sex hormone metabolic disorder in American adult males.

VirVACPRED: A Web Server for Prediction of Protective Viral Antigens

Viral antigens are key in the development of vaccines that prevent or eradicate infections caused by these pathogens. Bioinformatics tools are modern alternatives that facilitate the discovery of viral antigens, reducing the costs of experimental assays. We developed a bioinformatics tool called VirVACPRED, which is highly efficient in predicting viral antigens. In this study, we obtained a model based on the gradient boosting classifier, which showed high performance during the training, leave-one-out cross-validation (accuracy = 0.7402, sensitivity = 0.7319, precision = 0.7503, F1 = 0.7251, kappa = 0.4774, Matthews correlation coefficient = 0.4981) and testing (accuracy = 0.8889, sensitivity = 1.0, precision = 0.8276, F1 = 0.9057, kappa = 0.7734, Matthews correlation coefficient = 0.7941). VirVACPRED is a robust tool that can be of great help in the search and proposal of new viral antigens, which can be considered in the development of future vaccines against infections caused by viruses.

Gene-Based Testing of Interactions Using XGBoost in Genome-Wide Association Studies

Among the myriad of statistical methods that identify gene–gene interactions in the realm of qualitative genome-wide association studies, gene-based interactions are not only powerful statistically, but also they are interpretable biologically. However, they have limited statistical detection by making assumptions on the association between traits and single nucleotide polymorphisms. Thus, a gene-based method (GGInt-XGBoost) originated from XGBoost is proposed in this article. Assuming that log odds ratio of disease traits satisfies the additive relationship if the pair of genes had no interactions, the difference in error between the XGBoost model with and without additive constraint could indicate gene–gene interaction; we then used a permutation-based statistical test to assess this difference and to provide a statistical p-value to represent the significance of the interaction. Experimental results on both simulation and real data showed that our approach had superior performance than previous experiments to detect gene–gene interactions.

Predicting the multi-label protein subcellular localization through multi-information fusion and MLSI dimensionality reduction based on MLFE classifier

MOTIVATION

Multi-label (ML) protein subcellular localization (SCL) is an indispensable way to study protein function. It can locate a certain protein (such as the human transmembrane protein that promotes the invasion of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)) or expression product at a specific location in a cell, which can provide a reference for clinical treatment of diseases such as coronavirus disease 2019 (COVID-19).

RESULTS

The article proposes a novel method named ML-locMLFE. First of all, six feature extraction methods are adopted to obtain protein effective information. These methods include pseudo amino acid composition, encoding based on grouped weight, gene ontology, multi-scale continuous and discontinuous, residue probing transformation and evolutionary distance transformation. In the next part, we utilize the ML information latent semantic index method to avoid the interference of redundant information. In the end, ML learning with feature-induced labeling information enrichment is adopted to predict the ML protein SCL. The Gram-positive bacteria dataset is chosen as a training set, while the Gram-negative bacteria dataset, virus dataset, newPlant dataset and SARS-CoV-2 dataset as the test sets. The overall actual accuracy of the first four datasets are 99.23%, 93.82%, 93.24% and 96.72% by the leave-one-out cross validation. It is worth mentioning that the overall actual accuracy prediction result of our predictor on the SARS-CoV-2 dataset is 72.73%. The results indicate that the ML-locMLFE method has obvious advantages in predicting the SCL of ML protein, which provides new ideas for further research on the SCL of ML protein.

AVAILABILITY AND IMPLEMENTATION

The source codes and datasets are publicly available at https://github.com/QUST-AIBBDRC/ML-locMLFE/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

iRice-MS: An integrated XGBoost model for detecting multitype post-translational modification sites in rice

Post-translational modification (PTM) refers to the covalent and enzymatic modification of proteins after protein biosynthesis, which orchestrates a variety of biological processes. Detecting PTM sites in proteome scale is one of the key steps to in-depth understanding their regulation mechanisms. In this study, we presented an integrated method based on eXtreme Gradient Boosting (XGBoost), called iRice-MS, to identify 2-hydroxyisobutyrylation, crotonylation, malonylation, ubiquitination, succinylation and acetylation in rice. For each PTM-specific model, we adopted eight feature encoding schemes, including sequence-based features, physicochemical property-based features and spatial mapping information-based features. The optimal feature set was identified from each encoding, and their respective models were established. Extensive experimental results show that iRice-MS always display excellent performance on 5-fold cross-validation and independent dataset test. In addition, our novel approach provides the superiority to other existing tools in terms of AUC value. Based on the proposed model, a web server named iRice-MS was established and is freely accessible at http://lin-group.cn/server/iRice-MS.

SCYN: single cell CNV profiling method using dynamic programming

BACKGROUND

Copy number variation is crucial in deciphering the mechanism and cure of complex disorders and cancers. The recent advancement of scDNA sequencing technology sheds light upon addressing intratumor heterogeneity, detecting rare subclones, and reconstructing tumor evolution lineages at single-cell resolution. Nevertheless, the current circular binary segmentation based approach proves to fail to efficiently and effectively identify copy number shifts on some exceptional trails.

RESULTS

Here, we propose SCYN, a CNV segmentation method powered with dynamic programming. SCYN resolves the precise segmentation on in silico dataset. Then we verified SCYN manifested accurate copy number inferring on triple negative breast cancer scDNA data, with array comparative genomic hybridization results of purified bulk samples as ground truth validation. We tested SCYN on two datasets of the newly emerged 10x Genomics CNV solution. SCYN successfully recognizes gastric cancer cells from 1% and 10% spike-ins 10x datasets. Moreover, SCYN is about 150 times faster than state of the art tool when dealing with the datasets of approximately 2000 cells.

CONCLUSIONS

SCYN robustly and efficiently detects segmentations and infers copy number profiles on single cell DNA sequencing data. It serves to reveal the tumor intra-heterogeneity. The source code of SCYN can be accessed in https://github.com/xikanfeng2/SCYN .

DeepStack-DTIs: Predicting Drug-Target Interactions Using LightGBM Feature Selection and Deep-Stacked Ensemble Classifier

Accurate prediction of drug-target interactions (DTIs), which is often used in the fields of drug discovery and drug repositioning, is regarded a key challenge in the study of drug science. In this paper, a new method called DeepStack-DTIs is proposed to predict DTIs. First, for the target protein, pseudo-position specific score matrix, pseudo amino acid composition and SPIDER3 are used to extract the different feature information of the target protein. Meanwhile, the path-based fingerprint features of each drug are extracted. Then, the synthetic minority oversampling technique (SMOTE) and light gradient boosting machine (LightGBM) are used for data balancing and feature selection, respectively. Finally, the processed features are input to the deep-stacked ensemble classifier composed of gated recurrent unit (GRU), deep neural network (DNN), support vector machine (SVM), eXtreme gradient boosting (XGBoost) and logistic regression (LR) to predict DTIs. Under the five-fold cross-validation and compared with existing methods, the proposed method achieves higher prediction accuracy on the gold standard dataset. To evaluate the predictive power of DeepStack-DTIs, we validate the method on another dataset and predict the drug-target interaction network. The results indicate that DeepStack-DTIs has excellent predictive ability than the other methods, and provides novel insights for the prediction of DTIs. A novel method DeepStack-DTIs for drug-target interactions prediction. PsePSSM, PseAAC, SPIDER3 and FP2 are fused to convert protein sequence and drug molecule information into digital information, respectively. The SMOTE algorithm is used to balance the dataset and LightGBM feature selection algorithm is employed to remove redundant and irrelevant features to select the optimal feature subset. This optimal feature subset is inputted into the deep-stacked ensemble classifier to predict drug-target interactions. The experimental results show DeepStack-DTIs method can significantly improve the prediction accuracy of drug-target interactions.

Computational methods for protein localization prediction

The accurate annotation of protein localization is crucial in understanding protein function in tandem with a broad range of applications such as pathological analysis and drug design. Since most proteins do not have experimentally-determined localization information, the computational prediction of protein localization has been an active research area for more than two decades. In particular, recent machine-learning advancements have fueled the development of new methods in protein localization prediction. In this review paper, we first categorize the main features and algorithms used for protein localization prediction. Then, we summarize a list of protein localization prediction tools in terms of their coverage, characteristics, and accessibility to help users find suitable tools based on their needs. Next, we evaluate some of these tools on a benchmark dataset. Finally, we provide an outlook on the future exploration of protein localization methods.