Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 2.0 (RF-Phos 2.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 2.0, which uses random forest with sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 2.0 compares favorably to other popular mammalian phosphosite prediction methods, such as PhosphoSVM, GPS2.1, and Musite.

Recent advancements in natural language processing have highlighted the effectiveness of global contextualized representations from protein language models (pLMs) in numerous downstream tasks. Nonetheless, strategies to encode the site-of-interest leveraging pLMs for per-residue prediction tasks, such as crotonylation (Kcr) prediction, remain largely uncharted. Herein, we adopt a range of approaches for utilizing pLMs by experimenting with different input sequence types (full-length protein sequence versus window sequence), assessing the implications of utilizing per-residue embedding of the site-of-interest as well as embeddings of window residues centered around it. Building upon these insights, we developed a novel residual ConvBiLSTM network designed to process window-level embeddings of the site-of-interest generated by the ProtT5-XL-UniRef50 pLM using full-length sequences as input. This model, termed T5ResConvBiLSTM, surpasses existing state-of-the-art Kcr predictors in performance across three diverse datasets. To validate our approach of utilizing full sequence-based window-level embeddings, we also delved into the interpretability of ProtT5-derived embedding tensors in two ways: firstly, by scrutinizing the attention weights obtained from the transformer’s encoder block; and secondly, by computing SHAP values for these tensors, providing a model-agnostic interpretation of the prediction results. Additionally, we enhance the latent representation of ProtT5 by incorporating two additional local representations, one derived from amino acid properties and the other from supervised embedding layer, through an intermediate fusion stacked generalization approach, using an n-mer window sequence (or, peptide/fragment). The resultant stacked model, dubbed LMCrot, exhibits a more pronounced improvement in predictive performance across the tested datasets. LMCrot is publicly available at https://github.com/KCLabMTU/LMCrot.

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

Protein hydroxylation is an emerging posttranslational modification involved in both normal cellular processes and a growing number of pathological states, including several cancers. Protein hydroxylation is mediated by members of the hydroxylase family of enzymes, which catalyze the conversion of an alkyne group at select lysine or proline residues on their target substrates to a hydroxyl. Traditionally, hydroxylation has been identified using expensive and time-consuming experimental methods, such as tandem mass spectrometry. Therefore, to facilitate identification of putative hydroxylation sites and to complement existing experimental approaches, computational methods designed to predict the hydroxylation sites in protein sequences have recently been developed. Building on these efforts, we have developed a new method, termed RF-hydroxysite, that uses random forest to identify putative hydroxylysine and hydroxyproline residues in proteins using only the primary amino acid sequence as input. RF-Hydroxysite integrates features previously shown to contribute to hydroxylation site prediction with several new features that we found to augment the performance remarkably. These include features that capture physicochemical, structural, sequence-order and evolutionary information from the protein sequences. The features used in the final model were selected based on their contribution to the prediction. Physicochemical information was found to contribute the most to the model. The present study also sheds light on the contribution of evolutionary, sequence order, and protein disordered region information to hydroxylation site prediction. The web server for RF-hydroxysite is available online at http://bcb.ncat.edu/RF_hydroxy/.

O-linked β-N-acetylglucosamine (O-GlcNAc) is a distinct monosaccharide modification of serine (S) or threonine (T) residues of nucleocytoplasmic and mitochondrial proteins. O-GlcNAc modification (i.e., O-GlcNAcylation) is involved in the regulation of diverse cellular processes, including transcription, epigenetic modifications, and cell signaling. Despite the great progress in experimentally mapping O-GlcNAc sites, there is an unmet need to develop robust prediction tools that can effectively locate the presence of O-GlcNAc sites in protein sequences of interest. In this work, we performed a comprehensive evaluation of a framework for prediction of protein O-GlcNAc sites using embeddings from pre-trained protein language models. In particular, we compared the performance of three protein sequence-based large protein language models (pLMs), Ankh, ESM-2, and ProtT5, for prediction of O-GlcNAc sites and also evaluated various ensemble strategies to integrate embeddings from these protein language models. Upon investigation, the decision-level fusion approach that integrates the decisions of the three embedding models, which we call LM-OGlcNAc-Site, outperformed the models trained on these individual language models as well as other fusion approaches and other existing predictors in almost all of the parameters evaluated. The precise prediction of O-GlcNAc sites will facilitate the probing of O-GlcNAc site-specific functions of proteins in physiology and diseases. Moreover, these findings also indicate the effectiveness of combined uses of multiple protein language models in post-translational modification prediction and open exciting avenues for further research and exploration in other protein downstream tasks. LM-OGlcNAc-Site’s web server and source code are publicly available to the community.