Search

ABSTRACT Matrix-assisted laser desorption/ionization–time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for detection of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa, a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern β-lactam/β-lactamase inhibitor drugs, namely, ceftazidime/avibactam and ceftolozane/tazobactam. For these drugs, the model demonstrated area under the receiver operating characteristic curve (AUROC) of 0.869 and 0.856, specificity of 0.925 and 0.897, and sensitivity of 0.731 and 0.714, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional feature engineering approaches, the dynamic binning method yielded highest performance in 7 of 10 antimicrobials. Moreover, we showcased the efficacy of transfer learning in enhancing the AUROC performance for 8 of 11 antimicrobials. By assessing the contribution of features to the model's prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa.IMPORTANCEPseudomonas aeruginosa is a key bacterial pathogen that causes significant global morbidity and mortality. Antimicrobial resistance (AMR) emerges rapidly in P. aeruginosa and is driven by complex mechanisms. Drug-resistant P. aeruginosa is a major challenge in clinical settings due to limited treatment options. Early detection of AMR can guide antibiotic choices, improve patient outcomes, and avoid unnecessary antibiotic use. Matrix-assisted laser desorption/ionization–time of flight mass spectrometry (MALDI-TOF MS) is widely used for rapid species identification in clinical microbiology. In this study, we repurposed mass spectra generated by MALDI-TOF and used them as inputs for artificial intelligence approaches to successfully predict AMR in P. aeruginosa for multiple key antibiotic classes. This work represents an important advance toward using MALDI-TOF as a rapid AMR diagnostic for P. aeruginosa in clinical settings.

Abstract Gastric cancer is one of the deadliest cancers worldwide. An accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the multiplexed immunohistochemistry (mIHC) images as Cell-Graphs, we propose a graph neural network-based approach, termed C e l l−G r a p h S i g n a t u r e o r C G S i g n a t u r e , powered by artificial intelligence, for the digital staging of TME and precise prediction of patient survival in gastric cancer. In this study, patient survival prediction is formulated as either a binary (short-term and long-term) or ternary (short-term, medium-term, and long-term) classification task. Extensive benchmarking experiments demonstrate that the C G S i g n a t u r e achieves outstanding model performance, with Area Under the Receiver Operating Characteristic curve of 0.960 ± 0.01, and 0.771 ± 0.024 to 0.904 ± 0.012 for the binary- and ternary-classification, respectively. Moreover, Kaplan–Meier survival analysis indicates that the “digital grade” cancer staging produced by C G S i g n a t u r e provides a remarkable capability in discriminating both binary and ternary classes with statistical significance (P value

Proteases are enzymes that cleave and hydrolyse the peptide bonds between two specific amino acid residues of target substrate proteins. Protease-controlled proteolysis plays a key role in the degradation and recycling of proteins, which is essential for various physiological processes. Thus, solving the substrate identification problem will have important implications for the precise understanding of functions and physiological roles of proteases, as well as for therapeutic target identification and pharmaceutical applicability. Consequently, there is a great demand for bioinformatics methods that can predict novel substrate cleavage events with high accuracy by utilizing both sequence and structural information. In this study, we present Procleave, a novel bioinformatics approach for predicting protease-specific substrates and specific cleavage sites by taking into account both their sequence and 3D structural information. Structural features of known cleavage sites were represented by discrete values using a LOWESS data-smoothing optimization method, which turned out to be critical for the performance of Procleave. The optimal approximations of all structural parameter values were encoded in a conditional random field (CRF) computational framework, alongside sequence and chemical group-based features. Here, we demonstrate the outstanding performance of Procleave through extensive benchmarking and independent tests. Procleave is capable of correctly identifying most cleavage sites in the case study. Importantly, when applied to the human structural proteome encompassing 17,628 protein structures, Procleave suggests a number of potential novel target substrates and their corresponding cleavage sites of different proteases. Procleave is implemented as a webserver and is freely accessible at http://procleave.erc.monash.edu/.

Linear models in machine learning are extremely computational efficient but they have high representation bias due to non-linear nature of many real-world datasets. In this article, we show that this representation bias can be greatly reduced by discretization. Discretization is a common procedure in machine learning that is used to convert a quantitative attribute into a qualitative one. It is often motivated by the limitation of some learners to handle qualitative data. Since discretization looses information (as fewer distinctions among instances are possible using discretized data relative to undiscretized data) - where discretization is not essential, it might appear desirable to avoid it, and typically, it is avoided. However, in the past, it has been shown that discretization can leads to superior performance on generative linear models, e.g., naive Bayes. This motivates a systematic study of the effects of discretizing quantitative attributes for discriminative linear models, as well. In this article, we demonstrate that, contrary to prevalent belief, discretization of quantitative attributes, for discriminative linear models, is a beneficial pre-processing step, as it leads to far superior classification performance, especially on bigger datasets, and surprisingly, much better convergence, which leads to better training time. We substantiate our claims with an empirical study on 52 benchmark datasets, using three linear models optimizing different objective functions.

Abstract Background S-sulphenylation is a ubiquitous protein post-translational modification (PTM) where an S-hydroxyl (−SOH) bond is formed via the reversible oxidation on the Sulfhydryl group of cysteine (C). Recent experimental studies have revealed that S-sulphenylation plays critical roles in many biological functions, such as protein regulation and cell signaling. State-of-the-art bioinformatic advances have facilitated high-throughput in silico screening of protein S-sulphenylation sites, thereby significantly reducing the time and labour costs traditionally required for the experimental investigation of S-sulphenylation. Results In this study, we have proposed a novel hybrid computational framework, termed SIMLIN, for accurate prediction of protein S-sulphenylation sites using a multi-stage neural-network based ensemble-learning model integrating both protein sequence derived and protein structural features. Benchmarking experiments against the current state-of-the-art predictors for S-sulphenylation demonstrated that SIMLIN delivered competitive prediction performance. The empirical studies on the independent testing dataset demonstrated that SIMLIN achieved 88.0% prediction accuracy and an AUC score of 0.82, which outperforms currently existing methods. Conclusions In summary, SIMLIN predicts human S-sulphenylation sites with high accuracy thereby facilitating biological hypothesis generation and experimental validation. The web server, datasets, and online instructions are freely available at http://simlin.erc.monash.edu/ for academic purposes.

Abstract Background As an important type of post-translational modification (PTM), protein glycosylation plays a crucial role in protein stability and protein function. The abundance and ubiquity of protein glycosylation across three domains of life involving Eukarya, Bacteria and Archaea demonstrate its roles in regulating a variety of signalling and metabolic pathways. Mutations on and in the proximity of glycosylation sites are highly associated with human diseases. Accordingly, accurate prediction of glycosylation can complement laboratory-based methods and greatly benefit experimental efforts for characterization and understanding of functional roles of glycosylation. For this purpose, a number of supervised-learning approaches have been proposed to identify glycosylation sites, demonstrating a promising predictive performance. To train a conventional supervised-learning model, both reliable positive and negative samples are required. However, in practice, a large portion of negative samples (i.e. non-glycosylation sites) are mislabelled due to the limitation of current experimental technologies. Moreover, supervised algorithms often fail to take advantage of large volumes of unlabelled data, which can aid in model learning in conjunction with positive samples (i.e. experimentally verified glycosylation sites). Results In this study, we propose a positive unlabelled (PU) learning-based method, PA2DE (V2.0), based on the AlphaMax algorithm for protein glycosylation site prediction. The predictive performance of this proposed method was evaluated by a range of glycosylation data collected over a ten-year period based on an interval of three years. Experiments using both benchmarking and independent tests show that our method outperformed the representative supervised-learning algorithms (including support vector machines and random forests) and one-class learners, as well as currently available prediction methods in terms of F1 score, accuracy and AUC measures. In addition, we developed an online web server as an implementation of the optimized model (available at http://glycomine.erc.monash.edu/Lab/GlycoMine_PU/) to facilitate community-wide efforts for accurate prediction of protein glycosylation sites. Conclusion The proposed PU learning approach achieved a competitive predictive performance compared with currently available methods. This PU learning schema may also be effectively employed and applied to address the prediction problems of other important types of protein PTM site and functional sites.

Abstract Matrix Metalloproteases (MMPs) are an important family of proteases that play crucial roles in key cellular and disease processes. Therefore, MMPs constitute important targets for drug design, development and delivery. Advanced proteomic technologies have identified type-specific target substrates; however, the complete repertoire of MMP substrates remains uncharacterized. Indeed, computational prediction of substrate-cleavage sites associated with MMPs is a challenging problem. This holds especially true when considering MMPs with few experimentally verified cleavage sites, such as for MMP-2, -3, -7, and -8. To fill this gap, we propose a new knowledge-transfer computational framework which effectively utilizes the hidden shared knowledge from some MMP types to enhance predictions of other, distinct target substrate-cleavage sites. Our computational framework uses support vector machines combined with transfer machine learning and feature selection. To demonstrate the value of the model, we extracted a variety of substrate sequence-derived features and compared the performance of our method using both 5-fold cross-validation and independent tests. The results show that our transfer-learning-based method provides a robust performance, which is at least comparable to traditional feature-selection methods for prediction of MMP-2, -3, -7, -8, -9 and -12 substrate-cleavage sites on independent tests. The results also demonstrate that our proposed computational framework provides a useful alternative for the characterization of sequence-level determinants of MMP-substrate specificity.

Abstract Protein phosphorylation is a major form of post-translational modification (PTM) that regulates diverse cellular processes. In silico methods for phosphorylation site prediction can provide a useful and complementary strategy for complete phosphoproteome annotation. Here, we present a novel bioinformatics tool, PhosphoPredict, that combines protein sequence and functional features to predict kinase-specific substrates and their associated phosphorylation sites for 12 human kinases and kinase families, including ATM, CDKs, GSK-3, MAPKs, PKA, PKB, PKC, and SRC. To elucidate critical determinants, we identified feature subsets that were most informative and relevant for predicting substrate specificity for each individual kinase family. Extensive benchmarking experiments based on both five-fold cross-validation and independent tests indicated that the performance of PhosphoPredict is competitive with that of several other popular prediction tools, including KinasePhos, PPSP, GPS, and Musite. We found that combining protein functional and sequence features significantly improves phosphorylation site prediction performance across all kinases. Application of PhosphoPredict to the entire human proteome identified 150 to 800 potential phosphorylation substrates for each of the 12 kinases or kinase families. PhosphoPredict significantly extends the bioinformatics portfolio for kinase function analysis and will facilitate high-throughput identification of kinase-specific phosphorylation sites, thereby contributing to both basic and translational research programs.

Latest remote sensing sensors are capable of acquiring high spatial and spectral Satellite Image Time Series (SITS) of the world. These image series are a key component of classification systems that aim at obtaining up-to-date and accurate land cover maps of the Earth’s surfaces. More specifically, current SITS combine high temporal, spectral and spatial resolutions, which makes it possible to closely monitor vegetation dynamics. Although traditional classification algorithms, such as Random Forest (RF), have been successfully applied to create land cover maps from SITS, these algorithms do not make the most of the temporal domain. This paper proposes a comprehensive study of Temporal Convolutional Neural Networks (TempCNNs), a deep learning approach which applies convolutions in the temporal dimension in order to automatically learn temporal (and spectral) features. The goal of this paper is to quantitatively and qualitatively evaluate the contribution of TempCNNs for SITS classification, as compared to RF and Recurrent Neural Networks (RNNs) —a standard deep learning approach that is particularly suited to temporal data. We carry out experiments on Formosat-2 scene with 46 images and one million labelled time series. The experimental results show that TempCNNs are more accurate than the current state of the art for SITS classification. We provide some general guidelines on the network architecture, common regularization mechanisms, and hyper-parameter values such as batch size; we also draw out some differences with standard results in computer vision (e.g., about pooling layers). Finally, we assess the visual quality of the land cover maps produced by TempCNNs.