Sequence-Based Prediction of Plant Allergenic Proteins: Machine Learning Classification Approach

This Article proposes a novel chemometric approach to understanding and exploring the allergenic nature of food proteins. Using machine learning methods (supervised and unsupervised), this work aims to predict the allergenicity of plant proteins. The strategy is based on scoring descriptors and testing their classification performance. Partitioning was based on support vector machines (SVM), and a k-nearest neighbor (KNN) classifier was applied. A fivefold cross-validation approach was used to validate the KNN classifier in the variable selection step as well as the final classifier. To overcome the problem of food allergies, a robust and efficient method for protein classification is needed.

S2L-PSIBLAST: a supervised two-layer search framework based on PSI-BLAST for protein remote homology detection

MOTIVATION

Protein remote homology detection is a challenging task for the studies of protein evolutionary relationships. PSI-BLAST is an important and fundamental search method for detecting homology proteins. Although many improved versions of PSI-BLAST have been proposed, their performance is limited by the search processes of PSI-BLAST.

RESULTS

For further improving the performance of PSI-BLAST for protein remote homology detection, a supervised two-layer search framework based on PSI-BLAST (S2L-PSIBLAST) is proposed. S2L-PSIBLAST consists of a two-level search: the first-level search provides high-quality search results by using SMI-BLAST framework and double-link strategy to filter the non-homology protein sequences, the second-level search detects more homology proteins by profile-link similarity, and more accurate ranking lists for those detected protein sequences are obtained by learning to rank strategy. Experimental results on the updated version of Structural Classification of Proteins-extended benchmark dataset show that S2L-PSIBLAST not only obviously improves the performance of PSI-BLAST, but also achieves better performance on two improved versions of PSI-BLAST: DELTA-BLAST and PSI-BLASTexB.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

SMI-BLAST: a novel supervised search framework based on PSI-BLAST for protein remote homology detection

MOTIVATION

As one of the most important and widely used mainstream iterative search tool for protein sequence search, an accurate Position-Specific Scoring Matrix (PSSM) is the key of PSI-BLAST. However, PSSMs containing non-homologous information obviously reduce the performance of PSI-BLAST for protein remote homology.

RESULTS

To further study this problem, we summarize three types of Incorrectly Selected Homology (ISH) errors in PSSMs. A new search tool Supervised-Manner-based Iterative BLAST (SMI-BLAST) is proposed based on PSI-BLAST for solving these errors. SMI-BLAST obviously outperforms PSI-BLAST on the Structural Classification of Proteins-extended (SCOPe) dataset. Compared with PSI-BLAST on the ISH error subsets of SCOPe dataset, SMI-BLAST detects 1.6-2.87 folds more remote homologous sequences, and outperforms PSI-BLAST by 35.66% in terms of ROC1 scores. Furthermore, this framework is applied to JackHMMER, DELTA-BLAST and PSI-BLASTexB, and their performance is further improved.

AVAILABILITY AND IMPLEMENTATION

User-friendly webservers for SMI-BLAST, JackHMMER, DELTA-BLAST and PSI-BLASTexB are established at http://bliulab.net/SMI-BLAST/, by which the users can easily get the results without the need to go through the mathematical details.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A Comparative Analysis of Novel Deep Learning and Ensemble Learning Models to Predict the Allergenicity of Food Proteins

Traditional food allergen identification mainly relies on in vivo and in vitro experiments, which often needs a long period and high cost. The artificial intelligence (AI)-driven rapid food allergen identification method has solved the above mentioned some drawbacks and is becoming an efficient auxiliary tool. Aiming to overcome the limitations of lower accuracy of traditional machine learning models in predicting the allergenicity of food proteins, this work proposed to introduce deep learning model-transformer with self-attention mechanism, ensemble learning models (representative as Light Gradient Boosting Machine (LightGBM) eXtreme Gradient Boosting (XGBoost)) to solve the problem. In order to highlight the superiority of the proposed novel method, the study also selected various commonly used machine learning models as the baseline classifiers. The results of 5-fold cross-validation showed that the area under the receiver operating characteristic curve (AUC) of the deep model was the highest (0.9578), which was better than the ensemble learning and baseline algorithms. But the deep model need to be pre-trained, and the training time is the longest. By comparing the characteristics of the transformer model and boosting models, it can be analyzed that, each model has its own advantage, which provides novel clues and inspiration for the rapid prediction of food allergens in the future.

Genome-wide survey of remote homologues for protein domain superfamilies of known structure reveals unequal distribution across structural classes

Domains are the basic building blocks of proteins which can combine to give rise to different domain architectures. Annotation of domains in a sequence is the first step towards understanding the biological function. Since there are a limited number of folds and evolutionarily related proteins have a similar structure, function can be inferred through remote homology. Computational sequence searches were performed for remote homologues on genomes of around ∼160 000 different organisms, starting from nearly 11 000 superfamily queries of known structure. Case studies revealed that most of the associated domains are involved in the same biological process. Using all the proteins predicted to have at least one structural domain, a coverage of 61% of Pfam families was achieved which is higher than the existing methods (43.36% by SIFTS). Taxonomic analysis of the proteins revealed 493 superfamilies in all the major kingdoms of life and a few lateral gene transfers between viruses and cellular organisms. The distribution of remote homologues across different classes, folds and superfamilies was studied and reveals that sequences are unequally distributed across structural classes. Finally, domain architectures were computed for the homologues and these data were compiled for each superfamily and organism.

Isolation of bacteriophages and their application to control Pseudomonas aeruginosa in planktonic and biofilm models

Pseudomonas aeruginosa is frequently identified as a cause of diverse infections and chronic diseases. It forms biofilms and has natural resistance to several antibiotics. Strains of this pathogen resistant to new-generation beta-lactams have emerged. Due to the difficulties associated with treating chronic P. aeruginosa infections, bacteriophages are amongst the alternative therapeutic options being actively researched. Two obligatorily lytic P. aeruginosa phages, vB_PaeM_MAG1 (MAG1) and vB_PaeP_MAG4 (MAG4), have been isolated and characterized. These phages belong to the PAK_P1likevirus genus of the Myoviridae family and the LIT1virus genus of the Podoviridae family, respectively. They adsorb quickly to their hosts (∼90% in 5 min), have a short latent period (15 min), and are stable during storage. Each individual phage propagated in approximately 50% of P. aeruginosa strains tested, which increased to 72.9% when phages were combined into a cocktail. While MAG4 reduced biofilm more effectively after a short time of treatment, MAG1 was more effective after a longer time and selected less for phage-resistant clones. A MAG1-encoded homolog of YefM antitoxin of the bacterial toxin-antitoxin system may contribute to the superiority of MAG1 over MAG4.

Revisiting amino acid substitution matrices for identifying distantly related proteins

Motivation: Although many amino acid substitution matrices have been developed, it has not been well understood which is the best for similarity searches, especially for remote homology detection. Therefore, we collected information related to existing matrices, condensed it and derived a novel matrix that can detect more remote homology than ever.

Results: Using principal component analysis with existing matrices and benchmarks, we developed a novel matrix, which we designate as MIQS. The detection performance of MIQS is validated and compared with that of existing general purpose matrices using SSEARCH with optimized gap penalties for each matrix. Results show that MIQS is able to detect more remote homology than the existing matrices on an independent dataset. In addition, the performance of our developed matrix was superior to that of CS-BLAST, which was a novel similarity search method with no amino acid matrix. We also evaluated the alignment quality of matrices and methods, which revealed that MIQS shows higher alignment sensitivity than that with the existing matrix series and CS-BLAST. Fundamentally, these results are expected to constitute good proof of the availability and/or importance of amino acid matrices in sequence analysis. Moreover, with our developed matrix, sophisticated similarity search methods such as sequence–profile and profile–profile comparison methods can be improved further.

Availability and implementation: Newly developed matrices and datasets used for this study are available at http://csas.cbrc.jp/Ssearch/.

Contact:k-tomii@aist.go.jp

Supplementary information:Supplementary data are available at Bioinformatics online

Improved performance of sequence search approaches in remote homology detection

The protein sequence space is vast and diverse, spanning across different families. Biologically meaningful relationships exist between proteins at superfamily level. However, it is highly challenging to establish convincing relationships at the superfamily level by means of simple sequence searches. It is necessary to design a rigorous sequence search strategy to establish remote homology relationships and achieve high coverage. We have used iterative profile-based methods, along with constraints of sequence motifs, to specify search directions. We address the importance of multiple start points (queries) to achieve high coverage at protein superfamily level. We have devised strategies to employ a structural regime to search sequence space with good specificity and sensitivity. We employ two well-known sequence search methods, PSI-BLAST and PHI-BLAST, with multiple queries and multiple patterns to enhance homologue identification at the structural superfamily level. The study suggests that multiple queries improve sensitivity, while a pattern-constrained iterative sequence search becomes stringent at the initial stages, thereby driving the search in a specific direction and also achieves high coverage. This data mining approach has been applied to the entire structural superfamily database.

Bioinformatic analysis of α/β-hydrolase fold enzymes reveals subfamily-specific positions responsible for discrimination of amidase and lipase activities

Superfamily of alpha-beta hydrolases is one of the largest groups of structurally related enzymes with diverse catalytic functions. Bioinformatic analysis was used to study how lipase and amidase catalytic activities are implemented into the same structural framework. Subfamily-specific positions--conserved within lipases and peptidases but different between them--that were supposed to be responsible for functional discrimination have been identified. Mutations at subfamily-specific positions were used to introduce amidase activity into Candida antarctica lipase B (CALB). Molecular modeling was implemented to evaluate influence of selected residues on binding and catalytic conversion of amide substrate by corresponding library of mutants. In silico screening was applied to select reactive enzyme-substrate complexes that satisfy knowledge-based criteria of amidase catalytic activity. Selected CALB variants with substitutions at subfamily-specific positions Gly39, Thr103, Trp104, and Leu278 were produced and showed significant improvement of experimentally measured amidase activity. Based on these results, we suggest that value of subfamily-specific positions should be further explored in order to develop a systematic tool to study structure-function relationship in enzymes and to use this information for rational enzyme engineering.

Protein sequence comparison and fold recognition: progress and good-practice benchmarking

Protein sequence comparison methods have grown increasingly sensitive during the last decade and can often identify distantly related proteins sharing a common ancestor some 3 billion years ago. Although cellular function is not conserved so long, molecular functions and structures of protein domains often are. In combination with a domain-centered approach to function and structure prediction, modern remote homology detection methods have a great and largely underexploited potential for elucidating protein functions and evolution. Advances during the last few years include nonlinear scoring functions combining various sequence features, the use of sequence context information, and powerful new software packages. Since progress depends on realistically assessing new and existing methods and published benchmarks are often hard to compare, we propose 10 rules of good-practice benchmarking.

A performance enhanced PSI-BLAST based on hybrid alignment

MOTIVATION

Sequence alignment is one of the most popular tools of modern biology. NCBI's PSI-BLAST utilizes iterative model building in order to better detect distant homologs with greater sensitivity than non-iterative BLAST. However, PSI-BLAST's performance is limited by the fact that it relies on deterministic alignments. Using a semi-probabilistic alignment scheme such as Hybrid alignment should allow for better informed model building and improved identification of homologous sequences, particularly remote homologs.

RESULTS

We have built a new version of the tool in which the Smith-Waterman alignment algorithm core is replaced by the hybrid alignment algorithm. The favorable statistical properties of the hybrid algorithm allow the introduction of position-specific gap penalties in Hybrid PSI-BLAST. This improves the position-specific modeling of protein families and results in an overall improvement of performance.

AVAILABILITY

Source code is freely available for download at http://bioserv.mps.ohio-state.edu/HybridPSI, implemented in C and supported on linux.

Homologous over-extension: a challenge for iterative similarity searches

We have characterized a novel type of PSI-BLAST error, homologous over-extension (HOE), using embedded PFAM domain queries on searches against a reference library containing Pfam-annotated UniProt sequences and random synthetic sequences. PSI-BLAST makes two types of errors: alignments to non-homologous regions and HOE alignments that begin in a homologous region, but extend beyond the homology into neighboring sequence regions. When the neighboring sequence region contains a non-homologous domain, PSI-BLAST can incorporate the unrelated sequence into its position specific scoring matrix, which then finds non-homologous proteins with significant expectation values. HOE accounts for the largest fraction of the initial false positive (FP) errors, and the largest fraction of FPs at iteration 5. In searches against complete protein sequences, 5-9% of alignments at iteration 5 are non-homologous. HOE frequently begins in a partial protein domain; when partial domains are removed from the library, HOE errors decrease from 16 to 3% of weighted coverage (hard queries; 35-5% for sampled queries) and no-error searches increase from 2 to 58% weighed coverage (hard; 16-78% sampled). When HOE is reduced by not extending previously found sequences, PSI-BLAST specificity improves 4-8-fold, with little loss in sensitivity.

SIB-BLAST: a web server for improved delineation of true and false positives in PSI-BLAST searches

A SIB-BLAST web server (http://sib-blast.osc.edu) has been established for investigators to use the SimpleIsBeautiful (SIB) algorithm for sequence-based homology detection. SIB was developed to overcome the model corruption frequently observed in the later iterations of PSI-BLAST searches. The algorithm compares resultant hits from the second iteration to the final iteration of a PSI-BLAST search, calculates the figure of merit for each 'overlapped' hit and re-ranks the hits according to their figure of merit. By validating hits generated from the last profile against hits from the first profile when the model is least corrupted, the true and false positives are better delineated, which in turn, improves the accuracy of iterative PSI-BLAST searches. Notably, this improvement to PSI-BLAST comes at minimal computational cost as SIB-BLAST utilizes existing results already produced in a PSI-BLAST search.

Computational biology methods and their application to the comparative genomics of endocellular symbiotic bacteria of insects

Comparative genomics has become a real tantalizing challenge in the postgenomic era. This fact has been mostly magnified by the plethora of new genomes becoming available in a daily bases. The overwhelming list of new genomes to compare has pushed the field of bioinformatics and computational biology forward toward the design and development of methods capable of identifying patterns in a sea of swamping data noise. Despite many advances made in such endeavor, the ever-lasting annoying exceptions to the general patterns remain to pose difficulties in generalizing methods for comparative genomics. In this review, we discuss the different tools devised to undertake the challenge of comparative genomics and some of the exceptions that compromise the generality of such methods. We focus on endosymbiotic bacteria of insects because of their genomic dynamics peculiarities when compared to free-living organisms.