Search

Molecular property prediction is an important task in drug discovery, and with help of self-supervised learning methods, the performance of molecular property prediction could be improved by utilizing large-scale unlabeled dataset. In this paper, we propose a triple generative self-supervised learning method for molecular property prediction, called TGSS. Three encoders including a bi-directional long short-term memory recurrent neural network (BiLSTM), a Transformer, and a graph attention network (GAT) are used in pre-training the model using molecular sequence and graph structure data to extract molecular features. The variational auto encoder (VAE) is used for reconstructing features from the three models. In the downstream task, in order to balance the information between different molecular features, a feature fusion module is added to assign different weights to each feature. In addition, to improve the interpretability of the model, atomic similarity heat maps were introduced to demonstrate the effectiveness and rationality of molecular feature extraction. We demonstrate the accuracy of the proposed method on chemical and biological benchmark datasets by comparative experiments. [ABSTRACT FROM AUTHOR]

Drug–target interactions underlie the actions of chemical substances in medicine. Moreover, drug repurposing can expand use profiles while reducing costs and development time by exploiting potential multi-functional pharmacological properties based upon additional target interactions. Nonetheless, drug repurposing relies on the accurate identification and validation of drug–target interactions (DTIs). In this study, a novel drug–target interaction prediction model was developed. The model, based on an interactive inference network, contains embedding, encoding, interaction, feature extraction, and output layers. In addition, this study used Morgan and PubChem molecular fingerprints as additional information for drug encoding. The interaction layer in our model simulates the drug–target interaction process, which assists in understanding the interaction by representing the interaction space. Our method achieves high levels of predictive performance, as well as interpretability of drug–target interactions. Additionally, we predicted and validated 22 Alzheimer's disease-related targets, suggesting our model is robust and effective and thus may be beneficial for drug repurposing. [ABSTRACT FROM AUTHOR]

MicroRNA(miRNA)-mRNA interactions are important for understanding many biological processes, including development, differentiation and disease progression, but their identification is highly context-dependent. When computationally derived from sequence information alone, the identification should be verified by integrated analyses of mRNA and miRNA expression. The drawback of this strategy is the vast number of identified interactions, which prevents an experimental or detailed investigation of each pair. In this paper, we overcome this difficulty by the recently proposed principal component analysis (PCA)-based unsupervised feature extraction (FE), which reduces the number of identified miRNA-mRNA interactions that properly discriminate between patients and healthy controls without losing biological feasibility. The approach is applied to six cancers: hepatocellular carcinoma, non-small cell lung cancer, esophageal squamous cell carcinoma, prostate cancer, colorectal/colon cancer and breast cancer. In PCA-based unsupervised FE, the significance does not depend on the number of samples (as in the standard case) but on the number of features, which approximates the number of miRNAs/mRNAs. To our knowledge, we have newly identified miRNA-mRNA interactions in multiple cancers based on a single common (universal) criterion. Moreover, the number of identified interactions was sufficiently small to be sequentially curated by literature searches. [ABSTRACT FROM AUTHOR]

Drug–target interactions (DTIs) are considered a crucial component of drug design and drug discovery. To date, many computational methods were developed for drug–target interactions, but they are insufficiently informative for accurately predicting DTIs due to the lack of experimentally verified negative datasets, inaccurate molecular feature representation, and ineffective DTI classifiers. Therefore, we address the limitations of randomly selecting negative DTI data from unknown drug–target pairs by establishing two experimentally validated datasets and propose a capsule network-based framework called CapBM-DTI to capture hierarchical relationships of drugs and targets, which adopts pre-trained bidirectional encoder representations from transformers (BERT) for contextual sequence feature extraction from target proteins through transfer learning and the message-passing neural network (MPNN) for the 2-D graph feature extraction of compounds to accurately and robustly identify drug–target interactions. We compared the performance of CapBM-DTI with state-of-the-art methods using four experimentally validated DTI datasets of different sizes, including human (Homo sapiens) and worm (Caenorhabditis elegans) species datasets, as well as three subsets (new compounds, new proteins, and new pairs). Our results demonstrate that the proposed model achieved robust performance and powerful generalization ability in all experiments. The case study on treating COVID-19 demonstrates the applicability of the model in virtual screening. [ABSTRACT FROM AUTHOR]

Identification of protein-protein interactions (PPIs) is a difficult and important problem in biology. Since experimental methods for predicting PPIs are both expensive and time-consuming, many computational methods have been developed to predict PPIs and interaction networks, which can be used to complement experimental approaches. However, these methods have limitations to overcome. They need a large number of homology proteins or literature to be applied in their method. In this paper, we propose a novel matrix-based protein sequence representation approach to predict PPIs, using an ensemble learning method for classification. We construct the matrix of Amino Acid Contact (AAC), based on the statistical analysis of residue-pairing frequencies in a database of 6323 protein-protein complexes. We first represent the protein sequence as a Substitution Matrix Representation (SMR) matrix. Then, the feature vector is extracted by applying algorithms of Histogram of Oriented Gradient (HOG) and Singular Value Decomposition (SVD) on the SMR matrix. Finally, we feed the feature vector into a Random Forest (RF) for judging interaction pairs and non-interaction pairs. Our method is applied to several PPI datasets to evaluate its performance. On the S. cerevisiae dataset, our method achieves 94.83% accuracy and 92.40% sensitivity. Compared with existing methods, and the accuracy of our method is increased by 0.11 percentage points. On the H. pylori dataset, our method achieves 89.06% accuracy and 88.15% sensitivity, the accuracy of our method is increased by 0.76%. On the Human PPI dataset, our method achieves 97.60% accuracy and 96.37% sensitivity, and the accuracy of our method is increased by 1.30%. In addition, we test our method on a very important PPI network, and it achieves 92.71% accuracy. In the Wnt-related network, the accuracy of our method is increased by 16.67%. The source code and all datasets are available at https://figshare.com/s/580c11dce13e63cb9a53. [ABSTRACT FROM AUTHOR]

Cancer is one of the leading diseases threatening human life and health worldwide. Peptide-based therapies have attracted much attention in recent years. Therefore, the precise prediction of anticancer peptides (ACPs) is crucial for discovering and designing novel cancer treatments. In this study, we proposed a novel machine learning framework (GRDF) that incorporates deep graphical representation and deep forest architecture for identifying ACPs. Specifically, GRDF extracts graphical features based on the physicochemical properties of peptides and integrates their evolutionary information along with binary profiles for constructing models. Moreover, we employ the deep forest algorithm, which adopts a layer-by-layer cascade architecture similar to deep neural networks, enabling excellent performance on small datasets but without complicated tuning of hyperparameters. The experiment shows GRDF exhibits state-of-the-art performance on two elaborate datasets (Set 1 and Set 2), achieving 77.12% accuracy and 77.54% F1-score on Set 1, as well as 94.10% accuracy and 94.15% F1-score on Set 2, exceeding existing ACP prediction methods. Our models exhibit greater robustness than the baseline algorithms commonly used for other sequence analysis tasks. In addition, GRDF is well-interpretable, enabling researchers to better understand the features of peptide sequences. The promising results demonstrate that GRDF is remarkably effective in identifying ACPs. Therefore, the framework presented in this study could assist researchers in facilitating the discovery of anticancer peptides and contribute to developing novel cancer treatments. [ABSTRACT FROM AUTHOR]

Epigenetics, referring to genetic modifications that change gene expression, but which are not encoded in DNA, has been shown to be related to oncology, with the potential to influence associated treatments. As such, epigenetic drugs comprise an important new field in cancer therapy; however, drug development is a high-cost and time-consuming procedure. Different epigenetic modifications, such as mutations in DNA methyltransferase and somatic mutations in core histone genes that lead to a global loss of the histone modifications, have innumerable relationships. In this article, we propose a graph neural network-based model for the extraction of molecular features, thus reducing the computational requirements. Through integration with a popular and efficient supervised learner, our model achieves higher prediction accuracy in both single- and multi-target tasks and can determine the pleiotropy associated with drugs, providing theoretical support for drug combination and discovery research. [ABSTRACT FROM AUTHOR]

Jellyfishes are considered a new potential resource in food, pharmaceutical and biomedical industries. In these latter cases, they are studied as source of active principles but are also exploited to produce marine collagen. In the present work, jellyfish skin polysaccharides (JSP) with glycosaminoglycan (GAG) features were extracted from Rhizostoma pulmo, a main blooming species of Mediterranean Sea, massively augmented by climate leaded "jellyfishication" of the sea. Two main fractions of R. pulmo JSP (RP-JSPs) were isolated and characterized, namely a neutral fraction (RP-JSP1) and a sulphate rich, negatively charged fraction (RP-JSP2). The two fractions have average molecular weights of 121 kDa and 590 kDa, respectively. Their sugar composition was evaluated through LC-MS analysis and the result confirmed the presence of typical GAG saccharides, such as glucose, galactose, glucosamine and galactosamine. Their use as promoters of wound healing was evaluated through in vitro scratch assay on murine fibroblast cell line (BALB/3T3 clone A31) and human keratinocytes (HaCaT). Both RP-JSPs demonstrated an effective confluency rate activity leading to 80% of scratch repair in two days, promoting both cell migration and proliferation. Additionally, RP-JSPs exerted a substantial protection from oxidative stress, resulting in improved viability of treated fibroblasts exposed to H2O2. The isolated GAG-like polysaccharides appear promising as functional component for biomedical skin treatments, as well as for future exploitation as pharmaceutical excipients. [ABSTRACT FROM AUTHOR]

DNA-binding proteins play an important role in cell metabolism. In biological laboratories, the detection methods of DNA-binding proteins includes yeast one-hybrid methods, bacterial singles and X-ray crystallography methods and others, but these methods involve a lot of labor, material and time. In recent years, many computation-based approachs have been proposed to detect DNA-binding proteins. In this paper, a machine learning-based method, which is called the Fuzzy Kernel Ridge Regression model based on Multi-View Sequence Features (FKRR-MVSF), is proposed to identifying DNA-binding proteins. First of all, multi-view sequence features are extracted from protein sequences. Next, a Multiple Kernel Learning (MKL) algorithm is employed to combine multiple features. Finally, a Fuzzy Kernel Ridge Regression (FKRR) model is built to detect DNA-binding proteins. Compared with other methods, our model achieves good results. Our method obtains an accuracy of 83.26% and 81.72% on two benchmark datasets (PDB1075 and compared with PDB186), respectively. [ABSTRACT FROM AUTHOR]

Identification of ionic liquids with low toxicity is paramount for applications in various domains. Traditional approaches used for determining the toxicity of ionic liquids are often expensive, and can be labor intensive and time consuming. In order to mitigate these limitations, researchers have resorted to using computational models. This work presents a probabilistic model built from deep kernel learning with the aim of predicting the toxicity of ionic liquids in the leukemia rat cell line (IPC-81). Only open source tools, namely, RDKit and Mol2vec, are required to generate predictors for this model; as such, its predictions are solely based on chemical structure of the ionic liquids and no manual extraction of features is needed. The model recorded an RMSE of 0.228 and R 2 of 0.943. These results indicate that the model is both reliable and accurate. Furthermore, this model provides an accompanying uncertainty level for every prediction it makes. This is important because discrepancies in experimental measurements that generated the dataset used herein are inevitable, and ought to be modeled. A user-friendly web server was developed as well, enabling researchers and practitioners ti make predictions using this model. [ABSTRACT FROM AUTHOR]

Dihydrouridine (D) is an abundant post-transcriptional modification present in transfer RNA from eukaryotes, bacteria, and archaea. D has contributed to treatments for cancerous diseases. Therefore, the precise detection of D modification sites can enable further understanding of its functional roles. Traditional experimental techniques to identify D are laborious and time-consuming. In addition, there are few computational tools for such analysis. In this study, we utilized eleven sequence-derived feature extraction methods and implemented five popular machine algorithms to identify an optimal model. During data preprocessing, data were partitioned for training and testing. Oversampling was also adopted to reduce the effect of the imbalance between positive and negative samples. The best-performing model was obtained through a combination of random forest and nucleotide chemical property modeling. The optimized model presented high sensitivity and specificity values of 0.9688 and 0.9706 in independent tests, respectively. Our proposed model surpassed published tools in independent tests. Furthermore, a series of validations across several aspects was conducted in order to demonstrate the robustness and reliability of our model. [ABSTRACT FROM AUTHOR]

Protein-protein interactions (PPIs) play a key role in many cellular processes. Unfortunately, the experimental methods currently used to identify PPIs are both time-consuming and expensive. These obstacles could be overcome by developing computational approaches to predict PPIs. Here, we report two methods of amino acids feature extraction: (i) distance frequency with PCA reducing the dimension (DFPCA) and (ii) amino acid index distribution (AAID) representing the protein sequences. In order to obtain the most robust and reliable results for PPI prediction, pairwise kernel function and support vector machines (SVM) were employed to avoid the concatenation order of two feature vectors generated with two proteins. The highest prediction accuracies of AAID and DFPCA were 94% and 93.96%, respectively, using the 10 CV test, and the results of pairwise radial basis kernel function are considerably improved over those based on radial basis kernel function. Overall, the PPI prediction tool, termed PPI-PKSVM, which is freely available at http://159.226.118.31/PPI/index.html, promises to become useful in such areas as bio-analysis and drug development. [ABSTRACT FROM AUTHOR]

Recently, anticancer peptides (ACPs) have emerged as unique and promising therapeutic agents for cancer treatment compared with antibody and small molecule drugs. In addition to experimental methods of ACPs discovery, it is also necessary to develop accurate machine learning models for ACP prediction. In this study, features were extracted from the three-dimensional (3D) structure of peptides to develop the model, compared to most of the previous computational models, which are based on sequence information. In order to develop ACPs with more potency, more selectivity and less toxicity, the model for predicting ACPs, hemolytic peptides and toxic peptides were established by peptides 3D structure separately. Multiple datasets were collected according to whether the peptide sequence was chemically modified. After feature extraction and screening, diverse algorithms were used to build the model. Twelve models with excellent performance (Acc > 90%) in the ACPs mixed datasets were used to form a hybrid model to predict the candidate ACPs, and then the optimal model of hemolytic peptides (Acc = 73.68%) and toxic peptides (Acc = 85.5%) was used for safety prediction. Novel ACPs were found by using those models, and five peptides were randomly selected to determine their anticancer activity and toxic side effects in vitro experiments. [ABSTRACT FROM AUTHOR]

The study of protein-protein interaction is of great biological significance, and the prediction of protein-protein interaction sites can promote the understanding of cell biological activity and will be helpful for drug development. However, uneven distribution between interaction and non-interaction sites is common because only a small number of protein interactions have been confirmed by experimental techniques, which greatly affects the predictive capability of computational methods. In this work, two imbalanced data processing strategies based on XGBoost algorithm were proposed to re-balance the original dataset from inherent relationship between positive and negative samples for the prediction of protein-protein interaction sites. Herein, a feature extraction method was applied to represent the protein interaction sites based on evolutionary conservatism of proteins, and the influence of overlapping regions of positive and negative samples was considered in prediction performance. Our method showed good prediction performance, such as prediction accuracy of 0.807 and MCC of 0.614, on an original dataset with 10,455 surface residues but only 2297 interface residues. Experimental results demonstrated the effectiveness of our XGBoost-based method. [ABSTRACT FROM AUTHOR]

Protein plays a critical role in the regulation of biological cell functions. Among them, whether proteins interact with each other has become a fundamental problem, because proteins usually perform their functions by interacting with other proteins. Although a large amount of protein–protein interactions (PPIs) data has been produced by high-throughput biotechnology, the disadvantage of biological experimental technique is time-consuming and costly. Thus, computational methods for predicting protein interactions have become a research hot spot. In this research, we propose an efficient computational method that combines Rotation Forest (RF) classifier with Local Binary Pattern (LBP) feature extraction method to predict PPIs from the perspective of Position-Specific Scoring Matrix (PSSM). The proposed method has achieved superior performance in predicting Yeast, Human, and H. pylori datasets with average accuracies of 92.12%, 96.21%, and 86.59%, respectively. In addition, we also evaluated the performance of the proposed method on the four independent datasets of C. elegans, H. pylori, H. sapiens, and M. musculus datasets. These obtained experimental results fully prove that our model has good feasibility and robustness in predicting PPIs. [ABSTRACT FROM AUTHOR]