PredHSP: Sequence Based Proteome-Wide Heat Shock Protein Prediction and Classification Tool to Unlock the Stress Biology

A review of artificial intelligence-assisted omics techniques in plant defense: current trends and future directions

Plants intricately deploy defense systems to counter diverse biotic and abiotic stresses. Omics technologies, spanning genomics, transcriptomics, proteomics, and metabolomics, have revolutionized the exploration of plant defense mechanisms, unraveling molecular intricacies in response to various stressors. However, the complexity and scale of omics data necessitate sophisticated analytical tools for meaningful insights. This review delves into the application of artificial intelligence algorithms, particularly machine learning and deep learning, as promising approaches for deciphering complex omics data in plant defense research. The overview encompasses key omics techniques and addresses the challenges and limitations inherent in current AI-assisted omics approaches. Moreover, it contemplates potential future directions in this dynamic field. In summary, AI-assisted omics techniques present a robust toolkit, enabling a profound understanding of the molecular foundations of plant defense and paving the way for more effective crop protection strategies amidst climate change and emerging diseases.

MulCNN-HSP: A multi-scale convolutional neural networks-based deep learning method for classification of heat shock proteins

Heat shock proteins (HSPs) are crucial cellular stress proteins that react to environmental cues, ensuring the preservation of cellular functions. They also play pivotal roles in orchestrating the immune response and participating in processes associated with cancer. Consequently, the classification of HSPs holds immense significance in enhancing our understanding of their biological functions and in various diseases. However, the use of computational methods for identifying and classifying HSPs still faces challenges related to accuracy and interpretability. In this study, we introduced MulCNN-HSP, a novel deep learning model based on multi-scale convolutional neural networks, for identifying and classifying of HSPs. Comparative results showed that MulCNN-HSP outperforms or matches existing models in the identification and classification of HSPs. Furthermore, MulCNN-HSP can extract and analyze essential features for the prediction task, enhancing its interpretability. To facilitate its accessibility, we have made MulCNN-HSP available at http://cbcb.cdutcm.edu.cn/HSP/. We hope that MulCNN-HSP will contribute to advancing the study of HSPs and their roles in various biological processes and diseases.

Gene expression and functional analysis of Aha1a and Aha1b in stress response in zebrafish

Activator of heat shock protein 90 (hsp90) ATPase (Aha1) is a Hsp90 co-chaperone required for Hsp90 ATPase activation. Aha1 is essential for yeast survival and muscle development in C. elegans under elevated temperature and hsp90-deficeiency induced stress conditions. The roles of Aha1 in vertebrates are poorly understood. Here, we characterized the expression and function of Aha1 in zebrafish. We showed that zebrafish genome contains two aha1 genes, aha1a and aha1b, that show distinct patterns of expression during development. Under the normal physiological conditions, aha1a is primarily expressed in skeletal muscle cells of zebrafish embryos, while aha1b is strongly expressed in the head region. aha1a and aha1b expression increased dramatically in response to heat shock induced stress. In addition, Aha1a-GFP fusion protein exhibited a dynamic translocation in muscle cells in response to heat shock. Moreover, upregulation of aha1 expression was also observed in hsp90a1 knockdown embryos that showed a muscle defect. Genetic studies demonstrated that knockout of aha1a, aha1b or both had no detectable effect on embryonic development, survival, and growth in zebrafish. The aha1a and aha1b mutant embryos showed normal muscle development and stress response in response to heat shock. Single or double aha1a and aha1b mutants could grow into normal reproductive adults with normal skeletal muscle structure and morphology compared with wild type control. Together, data from these studies indicate that Aha1a and Aha1b are involved in stress response. However, they are dispensable in zebrafish embryonic development, growth, and survival.

Protein transfer learning improves identification of heat shock protein families

Heat shock proteins (HSPs) play a pivotal role as molecular chaperones against unfavorable conditions. Although HSPs are of great importance, their computational identification remains a significant challenge. Previous studies have two major limitations. First, they relied heavily on amino acid composition features, which inevitably limited their prediction performance. Second, their prediction performance was overestimated because of the independent two-stage evaluations and train-test data redundancy. To overcome these limitations, we introduce two novel deep learning algorithms: (1) time-efficient DeepHSP and (2) high-performance DeeperHSP. We propose a convolutional neural network (CNN)-based DeepHSP that classifies both non-HSPs and six HSP families simultaneously. It outperforms state-of-the-art algorithms, despite taking 14–15 times less time for both training and inference. We further improve the performance of DeepHSP by taking advantage of protein transfer learning. While DeepHSP is trained on raw protein sequences, DeeperHSP is trained on top of pre-trained protein representations. Therefore, DeeperHSP remarkably outperforms state-of-the-art algorithms increasing F1 scores in both cross-validation and independent test experiments by 20% and 10%, respectively. We envision that the proposed algorithms can provide a proteome-wide prediction of HSPs and help in various downstream analyses for pathology and clinical research.

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features

Heat shock proteins (HSPs) are ubiquitous in living organisms. HSPs are an essential component for cell growth and survival; the main function of HSPs is controlling the folding and unfolding process of proteins. According to molecular function and mass, HSPs are categorized into six different families: HSP20 (small HSPS), HSP40 (J-proteins), HSP60, HSP70, HSP90, and HSP100. In this paper, improved methods for HSP prediction are proposed—the split amino acid composition (SAAC), the dipeptide composition (DC), the conjoint triad feature (CTF), and the pseudoaverage chemical shift (PseACS) were selected to predict the HSPs with a support vector machine (SVM). In order to overcome the imbalance data classification problems, the syntactic minority oversampling technique (SMOTE) was used to balance the dataset. The overall accuracy was 99.72% with a balanced dataset in the jackknife test by using the optimized combination feature SAAC+DC+CTF+PseACS, which was 4.81% higher than the imbalanced dataset with the same combination feature. The Sn, Sp, Acc, and MCC of HSP families in our predictive model were higher than those in existing methods. This improved method may be helpful for protein function prediction.

Recent Advances in Machine Learning Methods for Predicting Heat Shock Proteins

Background:

As molecular chaperones, Heat Shock Proteins (HSPs) not only play key roles in protein folding and maintaining protein stabilities, but are also linked with multiple kinds of diseases. Therefore, HSPs have been regarded as the focus of drug design. Since HSPs from different families play distinct functions, accurately classifying the families of HSPs is the key step to clearly understand their biological functions. In contrast to laborintensive and cost-ineffective experimental methods, computational classification of HSP families has emerged to be an alternative approach.

Methods:

We reviewed the paper that described the existing datasets of HSPs and the representative computational approaches developed for the identification and classification of HSPs.

Results:

The two benchmark datasets of HSPs, namely HSPIR and sHSPdb were introduced, which provided invaluable resources for computationally identifying HSPs. The gold standard dataset and sequence encoding schemes for building computational methods of classifying HSPs were also introduced. The three representative web-servers for identifying HSPs and their families were described.

Conclusion:

The existing machine learning methods for identifying the different families of HSPs indeed yielded quite encouraging results and did play a role in promoting the research on HSPs. However, the number of HSPs with known structures is very limited. Therefore, determining the structure of the HSPs is also urgent, which will be helpful in revealing their functions.

Identification of AtHsp90.6 involved in early embryogenesis and its structure prediction by molecular dynamics simulations

Heat-shock protein of 90 kDa (Hsp90) is a key molecular chaperone involved in folding the synthesized protein and controlling protein quality. Conformational dynamics coupled to ATPase activity in N-terminal domain is essential for Hsp90's function. However, the relevant process is still largely unknown in plant Hsp90s, especially those required for plant embryogenesis which is inextricably tied up with human survival. Here, AtHsp90.6, a member of Hsp90 family in Arabidopsis, was firstly identified as a protein essential for embryogenesis. Thus we modelled AtHsp90.6 in its functionally closed 'lid-down' and open 'lid-up' states, exploring the nucleotide binding mechanism in these two states. Free energy landscape and electrostatic potential analysis revealed the switching mechanism between these two states. Collectively, this study quantitatively analysed the conformational changes of AtHsp90.6 bound to ATP or ADP. This result may help us understand the mechanism of action of AtHsp90.6 in future.

HRGPred: Prediction of herbicide resistant genes with k-mer nucleotide compositional features and support vector machine

Herbicide resistance (HR) is a major concern for the agricultural producers as well as environmentalists. Resistance to commonly used herbicides are conferred due to mutation(s) in the genes encoding herbicide target sites/proteins (GETS). Identification of these genes through wet-lab experiments is time consuming and expensive. Thus, a supervised learning-based computational model has been proposed in this study, which is first of its kind for the prediction of seven classes of GETS. The cDNA sequences of the genes were initially transformed into numeric features based on the k-mer compositions and then supplied as input to the support vector machine. In the proposed SVM-based model, the prediction occurs in two stages, where a binary classifier in the first stage discriminates the genes involved in conferring the resistance to herbicides from other genes, followed by a multi-class classifier in the second stage that categorizes the predicted herbicide resistant genes in the first stage into any one of the seven resistant classes. Overall classification accuracies were observed to be ~89% and >97% for binary and multi-class classifications respectively. The proposed model confirmed higher accuracy than the homology-based algorithms viz., BLAST and Hidden Markov Model. Besides, the developed computational model achieved ~87% accuracy, while tested with an independent dataset. An online prediction server HRGPred (http://cabgrid.res.in:8080/hrgpred) has also been established to facilitate the prediction of GETS by the scientific community.

ir-HSP: Improved Recognition of Heat Shock Proteins, Their Families and Sub-types Based On g-Spaced Di-peptide Features and Support Vector Machine

Heat shock proteins (HSPs) play a pivotal role in cell growth and variability. Since conventional approaches are expensive and voluminous protein sequence information is available in the post-genomic era, development of an automated and accurate computational tool is highly desirable for prediction of HSPs, their families and sub-types. Thus, we propose a computational approach for reliable prediction of all these components in a single framework and with higher accuracy as well. The proposed approach achieved an overall accuracy of ~84% in predicting HSPs, ~97% in predicting six different families of HSPs, and ~94% in predicting four types of DnaJ proteins, with bench mark datasets. The developed approach also achieved higher accuracy as compared to most of the existing approaches. For easy prediction of HSPs by experimental scientists, a user friendly web server ir-HSP is made freely accessible at http://cabgrid.res.in:8080/ir-hsp. The ir-HSP was further evaluated for proteome-wide identification of HSPs by using proteome datasets of eight different species, and ~50% of the predicted HSPs in each species were found to be annotated with InterPro HSP families/domains. Thus, the developed computational method is expected to supplement the currently available approaches for prediction of HSPs, to the extent of their families and sub-types.

Prediction of endoplasmic reticulum resident proteins using fragmented amino acid composition and support vector machine

Background

The endoplasmic reticulum plays an important role in many cellular processes, which includes protein synthesis, folding and post-translational processing of newly synthesized proteins. It is also the site for quality control of misfolded proteins and entry point of extracellular proteins to the secretory pathway. Hence at any given point of time, endoplasmic reticulum contains two different cohorts of proteins, (i) proteins involved in endoplasmic reticulum-specific function, which reside in the lumen of the endoplasmic reticulum, called as endoplasmic reticulum resident proteins and (ii) proteins which are in process of moving to the extracellular space. Thus, endoplasmic reticulum resident proteins must somehow be distinguished from newly synthesized secretory proteins, which pass through the endoplasmic reticulum on their way out of the cell. Approximately only 50% of the proteins used in this study as training data had endoplasmic reticulum retention signal, which shows that these signals are not essentially present in all endoplasmic reticulum resident proteins. This also strongly indicates the role of additional factors in retention of endoplasmic reticulum-specific proteins inside the endoplasmic reticulum.

Methods

This is a support vector machine based method, where we had used different forms of protein features as inputs for support vector machine to develop the prediction models. During training leave-one-out approach of cross-validation was used. Maximum performance was obtained with a combination of amino acid compositions of different part of proteins.

Results

In this study, we have reported a novel support vector machine based method for predicting endoplasmic reticulum resident proteins, named as ERPred. During training we achieved a maximum accuracy of 81.42% with leave-one-out approach of cross-validation. When evaluated on independent dataset, ERPred did prediction with sensitivity of 72.31% and specificity of 83.69%. We have also annotated six different proteomes to predict the candidate endoplasmic reticulum resident proteins in them. A webserver, ERPred, was developed to make the method available to the scientific community, which can be accessed at http://proteininformatics.org/mkumar/erpred/index.html.

Discussion

We found that out of 124 proteins of the training dataset, only 66 proteins had endoplasmic reticulum retention signals, which shows that these signals are not an absolute necessity for endoplasmic reticulum resident proteins to remain inside the endoplasmic reticulum. This observation also strongly indicates the role of additional factors in retention of proteins inside the endoplasmic reticulum. Our proposed predictor, ERPred, is a signal independent tool. It is tuned for the prediction of endoplasmic reticulum resident proteins, even if the query protein does not contain specific ER-retention signal.

Heterologous expression of three Camellia sinensis small heat shock protein genes confers temperature stress tolerance in yeast and Arabidopsis thaliana

CsHSP17.7, CsHSP18.1, and CsHSP21.8 expressions are induced by heat and cold stresses, and CsHSP overexpression confers tolerance to heat and cold stresses in transgenic Pichia pastoris and Arabidopsis thaliana. Small heat shock proteins (sHSPs) are crucial for protecting plants against biotic and abiotic stresses, especially heat stress. However, knowledge concerning the functions of Camellia sinensis sHSP in heat and cold stresses remains poorly understood. In this study, three C. sinensis sHSP genes (i.e., CsHSP17.7, CsHSP18.1, and CsHSP21.8) were isolated and characterized using suppression subtractive hybridization (SSH) technology. The CsHSPs expression levels in C. sinensis leaves were significantly up-regulated by heat and cold stresses. Phylogenetic analyses revealed that CsHSP17.7, CsHSP18.1, and CsHSP21.8 belong to sHSP Classes I, II, and IV, respectively. Heterologous expression of the three CsHSP genes in Pichia pastoris cells enhanced heat and cold stress tolerance. When exposed to heat and cold treatments, transgenic Arabidopsis thaliana plants overexpressing CsHSP17.7, CsHSP18.1, and CsHSP21.8 had lower malondialdehyde contents, ion leakage, higher proline contents, and transcript levels of stress-related genes (e.g., AtPOD, AtAPX1, AtP5CS2, and AtProT1) compared with the control line. In addition, improved seed germination vigor was also observed in the CsHSP-overexpressing seeds under heat stress. Taken together, our results suggest that the three identified CsHSP genes play key roles in heat and cold tolerance.