Ten-fold Cross Validation Test Research Articles

A hybrid residue based sequential encoding mechanism with XGBoost improved ensemble model for identifying 5-hydroxymethylcytosine modifications

RNA modifications play an important role in actively controlling recently created formation in cellular regulation mechanisms, which link them to gene expression and protein. The RNA modifications have numerous alterations, presenting broad glimpses of RNA’s operations and character. The modification process by the TET enzyme oxidation is the crucial change associated with cytosine hydroxymethylation. The effect of CR is an alteration in specific biochemical ways of the organism, such as gene expression and epigenetic alterations. Traditional laboratory systems that identify 5-hydroxymethylcytosine (5hmC) samples are expensive and time-consuming compared to other methods. To address this challenge, the paper proposed XGB5hmC, a machine learning algorithm based on a robust gradient boosting algorithm (XGBoost), with different residue based formulation methods to identify 5hmC samples. Their results were amalgamated, and six different frequency residue based encoding features were fused to form a hybrid vector in order to enhance model discrimination capabilities. In addition, the proposed model incorporates SHAP (Shapley Additive Explanations) based feature selection to demonstrate model interpretability by highlighting the high contributory features. Among the applied machine learning algorithms, the XGBoost ensemble model using the tenfold cross-validation test achieved improved results than existing state-of-the-art models. Our model reported an accuracy of 89.97%, sensitivity of 87.78%, specificity of 94.45%, F1-score of 0.8934%, and MCC of 0.8764%. This study highlights the potential to provide valuable insights for enhancing medical assessment and treatment protocols, representing a significant advancement in RNA modification analysis.

A novel deep learning identifier for promoters and their strength using heterogeneous features

Promoters, which are short (50–1500 base-pair) in DNA regions, have emerged to play a critical role in the regulation of gene transcription. Numerous dangerous diseases, likewise cancer, cardiovascular, and inflammatory bowel diseases, are caused by genetic variations in promoters. Consequently, the correct identification and characterization of promoters are significant for the discovery of drugs. However, experimental approaches to recognizing promoters and their strengths are challenging in terms of cost, time, and resources. Therefore, computational techniques are highly desirable for the correct characterization of promoters from unannotated genomic data. Here, we designed a powerful bi-layer deep-learning based predictor named “PROCABLES“, which discriminates DNA samples as promoters in the first-phase and strong or weak promoters in the second-phase respectively. The proposed method utilizes five distinct features, such as word2vec, k-spaced nucleotide pairs, trinucleotide propensity-based features, trinucleotide composition, and electron–ion interaction pseudopotentials, to extract the hidden patterns from the DNA sequence. Afterwards, a stacked framework is formed by integrating a convolutional neural network (CNN) with bidirectional long-short-term memory (LSTM) using multi-view attributes to train the proposed model. The PROCABLES model achieved an accuracy of 0.971 and 0.920 and the MCC 0.940 and 0.840 for the first and second-layer using the ten-fold cross-validation test, respectively. The predicted results anticipate that the proposed PROCABLES protocol outperformed the advanced computational predictors targeting promoters and their types. In summary, this research will provide useful hints for the recognition of large-scale promoters in particular and other DNA problems in general.

Machine-learning-assisted high-throughput identification of potent and stable neutralizing antibodies against all four dengue virus serotypes

Several computational methods have been developed to identify neutralizing antibodies (NAbs) covering four dengue virus serotypes (DENV-1 to DENV-4); however, limitations of the dataset and the resulting performance remain. Here, we developed a new computational framework to predict potent and stable NAbs against DENV-1 to DENV-4 using only antibody (CDR-H3) and epitope sequences as input. Specifically, our proposed computational framework employed sequence-based ML and molecular dynamic simulation (MD) methods to achieve more accurate identification. First, we built a novel dataset (n = 1108) by compiling the interactions of CDR-H3 and epitope sequences with the half maximum inhibitory concentration (IC50) values, which represent neutralizing activities. Second, we achieved an accurately predictive ML model that showed high AUC values of 0.879 and 0.885 by tenfold cross-validation and independent tests, respectively. Finally, our computational framework could be applied to filter approximately 2.5 million unseen antibodies into two final candidates that showed strong and stable binding to all four serotypes. In addition, the most potent and stable candidate (1B3B9_V21) was evaluated for its development potential as a therapeutic agent by molecular docking and MD simulations. This study provides an antibody computational approach to facilitate the high-throughput identification of NAbs and accelerate the development of therapeutic antibodies.

Deriving general structure–activity/selectivity relationship patterns for different subfamilies of cyclin-dependent kinase inhibitors using machine learning methods

Cyclin-dependent kinases (CDKs) play essential roles in regulating the cell cycle and are among the most critical targets for cancer therapy and drug discovery. The primary objective of this research is to derive general structure–activity relationship (SAR) patterns for modeling the selectivity and activity levels of CDK inhibitors using machine learning methods. To accomplish this, 8592 small molecules with different binding affinities to CDK1, CDK2, CDK4, CDK5, and CDK9 were collected from Binding DB, and a diverse set of descriptors was calculated for each molecule. The supervised Kohonen networks (SKN) and counter propagation artificial neural networks (CPANN) models were trained to predict the activity levels and therapeutic targets of the molecules. The validity of models was confirmed through tenfold cross-validation and external test sets. Using selected sets of molecular descriptors (e.g. hydrophilicity and total polar surface area) we derived activity and selectivity maps to elucidate local regions in chemical space for active and selective CDK inhibitors. The SKN models exhibited prediction accuracies ranging from 0.75 to 0.94 for the external test sets. The developed multivariate classifiers were used for ligand-based virtual screening of 2 million random molecules of the PubChem database, yielding areas under the receiver operating characteristic curves ranging from 0.72 to 1.00 for the SKN model. Considering the persistent challenge of achieving CDK selectivity, this research significantly contributes to addressing the issue and underscores the paramount importance of developing drugs with minimized side effects.

DP-site: A dual deep learning-based method for protein-peptide interaction site prediction

BackgroundProtein-peptide interaction prediction is an important topic for several applications including various biological processes, understanding drug discovery, protein function abnormal cellular behaviors, and treating diseases. Over the years, studies have shown that experimental methods have improved the identification of this bio-molecular interaction. However, predicting protein-peptide interactions using these methods is laborious, time-consuming, dependent on third-party tools, and costly. MethodTo address these previous drawbacks, this study introduces a computational framework called DP-Site. The proposed framework concentrates on using a compound of a dual pipeline along with a combination predictor. A deep convolutional neural network for feature extraction and classification is embedded in pipeline 1. In addition, pipeline 2 includes a deep long-short-term memory-based and a random forest classifier for feature extraction and classification. In this investigation, the evolutionary, structure-based, sequence-based, and physicochemical information of proteins is utilized for identifying protein-peptide interaction at the residue level. ResultsThe proposed method is evaluated on both the ten-fold cross-validation and independent test sets. The robust and consistent results between cross-validation and independent test sets confirm the ability of the proposed method to predict peptide binding residues in proteins. Moreover, experimental findings demonstrate that DP-Site has significantly outperformed other state-of-the-art sequence-based and structure-based methods. The proposed method achieves a remarkable balance between a specificity of 0.799 and a sensitivity of 0.770, along with the best f-measure of 0.661 and the highest precision of 0.580 using an independent test set. ConclusionsThe outcome of various experiments confirms the proficiency of the proposed method and outperforms state-of-the-art sequence-based and structure-based methods in terms of the mentioned criteria. DP-Site can be accessed at https://github.com/shafiee 95/shima.shafiee.DP-Site.

UniproLcad: Accurate Identification of Antimicrobial Peptide by Fusing Multiple Pre-Trained Protein Language Models

Antimicrobial peptides (AMPs) are vital components of innate immunotherapy. Existing approaches mainly rely on either deep learning for the automatic extraction of sequence features or traditional manual amino acid features combined with machine learning. The peptide sequence contains symmetrical sequence motifs or repetitive amino acid patterns, which may be related to the function and structure of the peptide. Recently, the advent of large language models has significantly boosted the representational power of sequence pattern features. In light of this, we present a novel AMP predictor called UniproLcad, which integrates three prominent protein language models—ESM-2, ProtBert, and UniRep—to obtain a more comprehensive representation of protein features. UniproLcad utilizes deep learning networks, encompassing the bidirectional long and short memory network (Bi-LSTM) and one-dimensional convolutional neural networks (1D-CNN), while also integrating an attention mechanism to enhance its capabilities. These deep learning frameworks, coupled with pre-trained language models, efficiently extract multi-view features from antimicrobial peptide sequences and assign attention weights to them. Through ten-fold cross-validation and independent testing, UniproLcad demonstrates competitive performance in the field of antimicrobial peptide identification. This integration of diverse language models and deep learning architectures enhances the accuracy and reliability of predicting antimicrobial peptides, contributing to the advancement of computational methods in this field.

DNI-MDCAP: improvement of causal MiRNA-disease association prediction based on deep network imputation

BackgroundMiRNAs are involved in the occurrence and development of many diseases. Extensive literature studies have demonstrated that miRNA-disease associations are stratified and encompass ~ 20% causal associations. Computational models that predict causal miRNA-disease associations provide effective guidance in identifying novel interpretations of disease mechanisms and potential therapeutic targets. Although several predictive models for miRNA-disease associations exist, it is still challenging to discriminate causal miRNA-disease associations from non-causal ones. Hence, there is a pressing need to develop an efficient prediction model for causal miRNA-disease association prediction.ResultsWe developed DNI-MDCAP, an improved computational model that incorporated additional miRNA similarity metrics, deep graph embedding learning-based network imputation and semi-supervised learning framework. Through extensive predictive performance evaluation, including tenfold cross-validation and independent test, DNI-MDCAP showed excellent performance in identifying causal miRNA-disease associations, achieving an area under the receiver operating characteristic curve (AUROC) of 0.896 and 0.889, respectively. Regarding the challenge of discriminating causal miRNA-disease associations from non-causal ones, DNI-MDCAP exhibited superior predictive performance compared to existing models MDCAP and LE-MDCAP, reaching an AUROC of 0.870. Wilcoxon test also indicated significantly higher prediction scores for causal associations than for non-causal ones. Finally, the potential causal miRNA-disease associations predicted by DNI-MDCAP, exemplified by diabetic nephropathies and hsa-miR-193a, have been validated by recently published literature, further supporting the reliability of the prediction model.ConclusionsDNI-MDCAP is a dedicated tool to specifically distinguish causal miRNA-disease associations with substantially improved accuracy. DNI-MDCAP is freely accessible at http://www.rnanut.net/DNIMDCAP/.

Improvement of Translation Accuracy for the Word Sense Disambiguation System using Novel Classifier Approach

Machine Translation (MT) is a crucial application of Natural language Processing (NLP). This MT technique automatic and based on computers. One of the most modern techniques adopted in MT is Machine Learning (ML). Over the past few years, ML has grown in popularity during MT process among researchers. Ambiguity is a major challenge in MT. Word Sense Disambiguation (WSD) is a common technique for solving the ambiguity problem. ML approaches are commonly used for the WSD techniques and are used for training and testing purposes. The outcome prediction of the test data gives encouraging results. Text classification is one of the most significant techniques for resolving the WSD. In this paper, we have analyzed some common supervised ML text classification algorithms and also proposed a “hybrid model” called “AmbiF.” We have compared the results of all analyzed algorithms with the proposed model “AmbiF. The analyzed supervised algorithms are Decision Tree (DT), Bayesian network, Support Vector Machines (SVMs), K-Nearest Neighbor (KNN), Random Forest (RF), and Logistic Regression (LR). The range of accuracy for all the algorithms that were examined is between sixty-eight and eighty-four percent. To improve the accuracy of the AmbiF model, we have merged the DT, SVM, and Naïve Bayes (NB)-classifier approach. For testing the model, we have used the ten-fold cross-validation test method. The AmbiF model’s accuracy has been reported eighty-five percent. Comparing the AmbiF model to all other analyzed supervised ML classification algorithms, it has also demonstrated great precision, recall, and F-score. Waikato Environment for Knowledge Analysis (WEKA)’s ML-tool is used to analyze the algorithms and the AmbiF model.

An ensemble-based deep learning model for detection of mutation causing cutaneous melanoma

When the mutation affects the melanocytes of the body, a condition called melanoma results which is one of the deadliest skin cancers. Early detection of cutaneous melanoma is vital for raising the chances of survival. Melanoma can be due to inherited defective genes or due to environmental factors such as excessive sun exposure. The accuracy of the state-of-the-art computer-aided diagnosis systems is unsatisfactory. Moreover, the major drawback of medical imaging is the shortage of labeled data. Generalized classifiers are required to diagnose melanoma to avoid overfitting the dataset. To address these issues, blending ensemble-based deep learning (BEDLM-CMS) model is proposed to detect mutation of cutaneous melanoma by integrating long short-term memory (LSTM), Bi-directional LSTM (BLSTM) and gated recurrent unit (GRU) architectures. The dataset used in the proposed study contains 2608 human samples and 6778 mutations in total along with 75 types of genes. The most prominent genes that function as biomarkers for early diagnosis and prognosis are utilized. Multiple extraction techniques are used in this study to extract the most-prominent features. Afterwards, we applied different DL models optimized through grid search technique to diagnose melanoma. The validity of the results is confirmed using several techniques, including tenfold cross validation (10-FCVT), independent set (IST), and self-consistency (SCT). For validation of the results multiple metrics are used which include accuracy, specificity, sensitivity, and Matthews’s correlation coefficient. BEDLM gives the highest accuracy of 97% in the independent set test whereas in self-consistency test and tenfold cross validation test it gives 94% and 93% accuracy, respectively. Accuracy of in self-consistency test, independent set test, and tenfold cross validation test is LSTM (96%, 94%, 92%), GRU (93%, 94%, 91%), and BLSTM (99%, 98%, 93%), respectively. The findings demonstrate that the proposed BEDLM-CMS can be used effectively applied for early diagnosis and treatment efficacy evaluation of cutaneous melanoma.

Optimization of Rituximab Therapy in Adult Patients With PLA2R1-Associated Membranous Nephropathy With Artificial Intelligence

IntroductionRituximab is a first-line treatment for membranous nephropathy. Nephrotic syndrome limits rituximab exposure due to urinary drug loss. Rituximab underdosing (serum level< 2 μg/mL at month-3) is a risk factor for treatment failure. We developed a machine learning algorithm to predict the risk of underdosing based on patients’ characteristics at rituximab infusion. We investigated the relationship between the predicted risk of underdosing and the cumulative dose of rituximab required to achieve remission. MethodsRituximab concentrations were measured at month-3 in 92 sera from adult patients with primary membranous nephropathy, split into a training (75%) and a testing set (25%). A forward-backward machine-learning procedure determined the best combination of variables to predict rituximab underdosing in the training dataset, which was tested in the test set. The performances were evaluated for accuracy, sensitivity and specificity in ten-fold cross-validation training and test sets. ResultsThe best variables combination to predict rituximab underdosing included: age, sex, body surface area, anti-PLA2R1 antibody titer at day-0, serum albumin at day-0 and day-15 and serum creatinine at day-0 and day-15. The accuracy, sensitivity and specificity were respectively 79.4%, 78.7% and 81.0% (training dataset), and 79.2%, 84.6% and 72.7% (testing dataset). In both sets, the algorithm performed significantly better than chance (p<0.05). Patients with an initial high probability of underdosing experienced a longer time to remission with higher rituximab cumulative doses required to achieved remission. ConclusionThis algorithm could allow for early intensification of rituximab regimen in patients at high estimated risk of underdosing to increase the likelihood of remission.

EMNGly: predicting N-linked glycosylation sites using the language models for feature extraction.

N-linked glycosylation is a frequently occurring post-translational protein modification that serves critical functions in protein folding, stability, trafficking, and recognition. Its involvement spans across multiple biological processes and alterations to this process can result in various diseases. Therefore, identifying N-linked glycosylation sites is imperative for comprehending the mechanisms and systems underlying glycosylation. Due to the inherent experimental complexities, machine learning and deep learning have become indispensable tools for predicting these sites. In this context, a new approach called EMNGly has been proposed. The EMNGly approach utilizes pretrained protein language model (Evolutionary Scale Modeling) and pretrained protein structure model (Inverse Folding Model) for features extraction and support vector machine for classification. Ten-fold cross-validation and independent tests show that this approach has outperformed existing techniques. And it achieves Matthews Correlation Coefficient, sensitivity, specificity, and accuracy of 0.8282, 0.9343, 0.8934, and 0.9143, respectively on a benchmark independent test set.

PAMPred: A hierarchical evolutionary ensemble framework for identifying plant antimicrobial peptides

Antimicrobial peptides (AMPs) play a crucial role in plant immune regulation, growth and development stages, which have attracted significant attentions in recent years. As the wet-lab experiments are laborious and cost-prohibitive, it is indispensable to develop computational methods to discover novel plant AMPs accurately. In this study, we presented a hierarchical evolutionary ensemble framework, named PAMPred, which consisted of a multi-level heterogeneous architecture to identify plant AMPs. Specifically, to address the existing class imbalance problem, a cluster-based resampling method was adopted to build multiple balanced subsets. Then, several peptide features including sequence information-based and physicochemical properties-based features were fed into the different types of basic learners to increase the ensemble diversity. For boosting the predictive capability of PAMPred, the improved particle swarm optimization (PSO) algorithm and dynamic ensemble pruning strategy were used to optimize the weights at different levels adaptively. Furthermore, extensive ten-fold cross-validation and independent testing experimental results demonstrated that PAMPred achieved excellent prediction performance and generalization ability, and outperformed the state-of-the-art methods. It also indicated that the proposed method could serve as an effective auxiliary tool to identify plant AMPs, which would be conducive to explore the immune regulatory mechanism of plants.

TIPred: a novel stacked ensemble approach for the accelerated discovery of tyrosinase inhibitory peptides

BackgroundTyrosinase is an enzyme involved in melanin production in the skin. Several hyperpigmentation disorders involve the overproduction of melanin and instability of tyrosinase activity resulting in darker, discolored patches on the skin. Therefore, discovering tyrosinase inhibitory peptides (TIPs) is of great significance for basic research and clinical treatments. However, the identification of TIPs using experimental methods is generally cost-ineffective and time-consuming.ResultsHerein, a stacked ensemble learning approach, called TIPred, is proposed for the accurate and quick identification of TIPs by using sequence information. TIPred explored a comprehensive set of various baseline models derived from well-known machine learning (ML) algorithms and heterogeneous feature encoding schemes from multiple perspectives, such as chemical structure properties, physicochemical properties, and composition information. Subsequently, 130 baseline models were trained and optimized to create new probabilistic features. Finally, the feature selection approach was utilized to determine the optimal feature vector for developing TIPred. Both tenfold cross-validation and independent test methods were employed to assess the predictive capability of TIPred by using the stacking strategy. Experimental results showed that TIPred significantly outperformed the state-of-the-art method in terms of the independent test, with an accuracy of 0.923, MCC of 0.757 and an AUC of 0.977.ConclusionsThe proposed TIPred approach could be a valuable tool for rapidly discovering novel TIPs and effectively identifying potential TIP candidates for follow-up experimental validation. Moreover, an online webserver of TIPred is publicly available at http://pmlabstack.pythonanywhere.com/TIPred.

Identifying Genetic Signatures Associated with Oncogene-Induced Replication Stress in Osteosarcoma and Screening for Potential Targeted Drugs.

Osteosarcoma is the most common type of primary malignant bone tumor. Due to the lack of selectivity and sensitivity of chemotherapy drugs to tumor cells, coupled with the use of large doses, chemotherapy drugs often have systemic toxicity. The use of modern sequencing technology to screen tumor markers in a large number of tumor samples is a common method for screening highly specific and selective anti-tumor drugs. This study aims to identify potential biomarkers using the latest reported gene expression signatures of oncogene-induced replication stress (ORS) in aggressive cancers, and potential anti-osteosarcoma drugs were screened in different drug databases. In this study, we obtained 89 osteosarcoma-related samples in the TARGET database, all of which included survival information. According to the median expression of each of six reported ORS gene markers (NAT10/DDX27/ZNF48/C8ORF33/MOCS3/MPP6), we divided 89 osteosarcoma gene expression datasets into a high expression group and a low expression group and then performed a differentially expressed gene (DEG) analysis. The coexisting genes of 6 groups of DEGs were used as replication stress-related genes (RSGs) of osteosarcoma. Then, key RSGs were screened using LASSO regression, a Cox risk proportional regression prognostic model and a tenfold cross-validation test. GSE21257 datasets collected from the Gene Expression Omnibus (GEO) database were used to verify the prognostic model. The final key RSGs selected were used in the L1000PWD and DGIdb databases to mine potential drugs. After further validation by the prognostic model, we identified seven genes associated with ORS in osteosarcoma as key RSGs, including transcription factor 7 like 2 (TCF7L2), solute carrier family 27 member 4 (SLC27A4), proprotein convertase subtilisin/kexin type 5 (PCSK5), nucleolar protein 6 (NOL6), coiled-coil-coil-coil-coil-helix domain containing 4 (CHCHD4), eukaryotic translation initiation factor 3 subunit B (EIF3B), and synthesis of cytochrome C oxidase 1 (SCO1). Then, we screened the seven key RSGs in two drug databases and found six potential anti-osteosarcoma drugs (D GIdb database: repaglinide, tacrolimus, sirolimus, cyclosporine, and hydrochlorothiazide; L1000PWD database: the small molecule VU-0365117-1). Seven RSGs (TCF7L2, SLC27A4, PCSK5, NOL6, CHCHD4, EIF3B, and SCO1) may be associated with the ORS gene signatures in osteosarcoma. Repaglinide, tacrolimus, sirolimus, cyclosporine, hydrochlorothiazide and the small molecule VU-0365117-1 are potential therapeutic drugs for osteosarcoma.

Development and validation of machine learning models for the prediction of SH-2 containing protein tyrosine phosphatase 2 inhibitors.

Discovery and development of a new drug to the market is a highly challenging and resource consuming process. Although, modern drug discovery technologies have enabled the rapid identification of lead compounds, translation of the lead compounds into successful clinical candidates remains a big challenge. In recent years, the availability of massive structural and biological data of diverse small molecules and macromolecules has helped the researchers to deep mine the multidimensional data with the help of artificial intelligence-based predictive tools to draw useful insights on the structural features of biological or therapeutic significance. The aim of this study was to utilize the available data on small molecule (SH2)-containing protein tyrosine phosphatase 2 (SHP2) inhibitors to build and develop machine learning (ML) models that can predict the SHP2 inhibitory potential of new compounds. The dataset contained 2739 unique small molecule SHP2 inhibitors obtained from the BindingDB, ChEMBL and recent literature. After curation of the data, the predictive models such as XGBoost, K nearest neighbours, neural networks were developed and validated through a tenfold cross-validation testing procedure. Out of the seven models developed, the XGBoost model showed an excellent performance with ROC AUC score of 0.96 and accuracy of 0.97 on the test data. Moreover, the Shapley Additive Explanations method was applied to assess a more in-depth understanding of the influence of variables on the model's predictions. In summary, the XGBoost model developed in this study can be useful in the identification of novel SHP2 inhibitors and therefore, can accelerate the discovery of novel therapeutics for cancer therapy.

SPPPred: Sequence-Based Protein-Peptide Binding Residue Prediction Using Genetic Programming and Ensemble Learning.

Peptide-binding proteins play significant roles in various applications such as gene expression, metabolism, signal transmission, DNA (Deoxyribose Nucleic Acid) repair, and replication. Investigating the binding residues in protein-peptide complexes, especially from their sequence only, is challenging experimentally and computationally. Although several computational approaches have been introduced to determine and predict these binding residues, there is still ample room to improve the prediction performance. In this work, we introduce a novel ensemble machine learning-based approach called SPPPred (Sequence-based Protein-Peptide binding residue Prediction) to predict protein-peptide binding residues. First, we extract relevant sequential information and employ genetic programming algorithm for feature construction to find more distinctive features. We then, in the next step, build an ensemble-based machine learning classifier to predict binding residues. The proposed method shows consistent and comparable performance on both ten-fold cross-validation and independent test set. Furthermore, SPPPred yields F-Measure (F-M), Accuracy(ACC), and Matthews' Correlation Coefficient (MCC) of 0.310, 0.949, and 0.230 on the independent test set, respectively, which outperforms other competing methods by approximately up to 9% on the independent test set. SPPPred is publicly available https://github.com/GTaherzadeh/SPPPred.git.

EdeepSADPr: an extensive deep-learning architecture for prediction of the in situ crosstalks of serine phosphorylation and ADP-ribosylation.

The in situ post-translational modification (PTM) crosstalk refers to the interactions between different types of PTMs that occur on the same residue site of a protein. The crosstalk sites generally have different characteristics from those with the single PTM type. Studies targeting the latter's features have been widely conducted, while studies on the former's characteristics are rare. For example, the characteristics of serine phosphorylation (pS) and serine ADP-ribosylation (SADPr) have been investigated, whereas those of their in situ crosstalks (pSADPr) are unknown. In this study, we collected 3,250 human pSADPr, 7,520 SADPr, 151,227pS and 80,096 unmodified serine sites and explored the features of the pSADPr sites. We found that the characteristics of pSADPr sites are more similar to those of SADPr compared to pS or unmodified serine sites. Moreover, the crosstalk sites are likely to be phosphorylated by some kinase families (e.g., AGC, CAMK, STE and TKL) rather than others (e.g., CK1 and CMGC). Additionally, we constructed three classifiers to predict pSADPr sites from the pS dataset, the SADPr dataset and the protein sequences separately. We built and evaluated five deep-learning classifiers in ten-fold cross-validation and independent test datasets. We also used the classifiers as base classifiers to develop a few stacking-based ensemble classifiers to improve performance. The best classifiers had the AUC values of 0.700, 0.914 and 0.954 for recognizing pSADPr sites from the SADPr, pS and unmodified serine sites, respectively. The lowest prediction accuracy was achieved by separating pSADPr and SADPr sites, which is consistent with the observation that pSADPr's characteristics are more similar to those of SADPr than the rest. Finally, we developed an online tool for extensively predicting human pSADPr sites based on the CNNOH classifier, dubbed EdeepSADPr. It is freely available through http://edeepsadpr.bioinfogo.org/. We expect our investigation will promote a comprehensive understanding of crosstalks.

MSINGB: A Novel Computational Method Based on NGBoost for Identifying Microsatellite Instability Status from Tumor Mutation Annotation Data.

Microsatellite instability (MSI), a vital mutator phenotype caused by DNA mismatch repair deficiency, is frequently observed in several tumors. MSI is recognized as a critical molecular biomarker for diagnosis, prognosis, and therapeutic selection in several cancers. Identifying MSI status for current gold standard methods based on experimental analysis is laborious, time-consuming, and costly. Although several computational methods based on machine learning have been proposed to identify MSI status, we need to further understand which machine learning model would favor identification for MSI and which feature subset is strongly related to MSI. On this basis, more effective machine learning-based methods can be developed to improve the performance of MSI status identification. In this work, we present MSINGB, an NGBoost-based method for identifying MSI status from tumor somatic mutation annotation data. MSINGB first evaluates the prediction performance of 11 popular machine learning algorithms and 9 deep learning models to identify MSI. Among 20 models, NGBoost, a novel natural gradient boosting method, achieves the overall best performance. MSINGB then introduces two feature selection strategies to find the compact feature subset, which is strongly related to MSI, and employs the SHAP approach to interpreting how selected features impact the model prediction. MSINGB achieves a better prediction performance on both the tenfold cross-validation test and independent test compared with state-of-the-art methods.

Revision and Extension of a Generally Applicable Group Additivity Method for the Calculation of the Refractivity and Polarizability of Organic Molecules at 298.15 K

In a continuation and extension of an earlier publication, the calculation of the refractivity and polarizability of organic molecules at standard conditions is presented, applying a commonly applicable computer algorithm based on an atom group additivity method, where the molecules are broken down into their constituting atoms, these again being further characterized by their immediate neighbor atoms. The calculation of their group contributions, carried out by means of a fast Gauss–Seidel fitting calculus, used the experimental data of 5988 molecules from literature. An immediate subsequent ten-fold cross-validation test confirmed the extraordinary accuracy of the prediction of the molar refractivity, indicated by a correlation coefficient R2 and a cross-validated analog Q2 of 0.9997, a standard deviation σ of 0.38, a cross-validated analog S of 0.41, and a mean absolute deviation of 0.76%. The high reliability of the predictions was exemplified with three classes of molecules: ionic liquids and silicon- and boron-containing compounds. The corresponding molecular polarizabilities were calculated indirectly from the refractivity using the inverse Lorentz–Lorenz relation. In addition, it could be shown that there is a close relationship between the “true” volume and the refractivity of a molecule, revealing an excellent correlation coefficient R2 of 0.9645 and a mean absolute deviation of 7.53%.

StackPR is a new computational approach for large-scale identification of progesterone receptor antagonists using the stacking strategy

Progesterone receptors (PRs) are implicated in various cancers since their presence/absence can determine clinical outcomes. The overstimulation of progesterone can facilitate oncogenesis and thus, its modulation through PR inhibition is urgently needed. To address this issue, a novel stacked ensemble learning approach (termed StackPR) is presented for fast, accurate, and large-scale identification of PR antagonists using only SMILES notation without the need for 3D structural information. We employed six popular machine learning (ML) algorithms (i.e., logistic regression, partial least squares, k-nearest neighbor, support vector machine, extremely randomized trees, and random forest) coupled with twelve conventional molecular descriptors to create 72 baseline models. Then, a genetic algorithm in conjunction with the self-assessment-report approach was utilized to determine m out of the 72 baseline models as means of developing the final meta-predictor using the stacking strategy and tenfold cross-validation test. Experimental results on the independent test dataset show that StackPR achieved impressive predictive performance with an accuracy of 0.966 and Matthew’s coefficient correlation of 0.925. In addition, analysis based on the SHapley Additive exPlanation algorithm and molecular docking indicates that aliphatic hydrocarbons and nitrogen-containing substructures were the most important features for having PR antagonist activity. Finally, we implemented an online webserver using StackPR, which is freely accessible at http://pmlabstack.pythonanywhere.com/StackPR. StackPR is anticipated to be a powerful computational tool for the large-scale identification of unknown PR antagonist candidates for follow-up experimental validation.