TSE-ARF: An adaptive prediction method of effectors across secretion system types

Bacterial effector proteins are secreted by a variety of protein secretion systems and play an important role in the interaction between the host and pathogenic bacteria. Therefore, it is important to find a fast and inexpensive method to discover bacterial effectors. In this study, we propose a multi-type secretion effector adaptive random forest (TSE-ARF) to adaptively identify secretion effectors across T1SE-T4SE and T6SE based only on protein sequences. First, we proposed two new feature descriptors by considering some characteristic protein information and fused them with some universal features to form a 290-dimensional feature vector with good versatility. Then, the TSE-ARF model was used to make classification predictions by parameter adaptation of different secretion effectors integrating Shuffled Frog Leaping Algorithm and random forest. The perfect performance in TSE-ARF under different data sets and settings shows its considerable generalization ability, with which more candidate effectors were screened in the whole genome. Source code is available at https://github.com/AIMOVE/TSE-ARF.

POOE: predicting oomycete effectors based on a pre-trained large protein language model

Oomycetes are fungus-like eukaryotic microorganisms which can cause catastrophic diseases in many plants. Successful infection of oomycetes depends highly on their effector proteins that are secreted into plant cells to subvert plant immunity. Thus, systematic identification of effectors from the oomycete proteomes remains an initial but crucial step in understanding plant-pathogen relationships. However, the number of experimentally identified oomycete effectors is still limited. Currently, only a few bioinformatics predictors exist to detect potential effectors, and their prediction performance needs to be improved. Here, we used the sequence embeddings from a pre-trained large protein language model (ProtTrans) as input and developed a support vector machine-based method called POOE for predicting oomycete effectors. POOE could achieve a highly accurate performance with an area under the precision-recall curve of 0.804 (area under the receiver operating characteristic curve = 0.893, accuracy = 0.874, precision = 0.777, recall = 0.684, and specificity = 0.936) in the fivefold cross-validation, considerably outperforming various combinations of popular machine learning algorithms and other commonly used sequence encoding schemes. A similar prediction performance was also observed in the independent test. Compared with the existing oomycete effector prediction methods, POOE provided very competitive and promising performance, suggesting that ProtTrans effectively captures rich protein semantic information and dramatically improves the prediction task. We anticipate that POOE can accelerate the identification of oomycete effectors and provide new hints to systematically understand the functional roles of effectors in plant-pathogen interactions. The web server of POOE is freely accessible at http://zzdlab.com/pooe/index.php. The corresponding source codes and data sets are also available at https://github.com/zzdlabzm/POOE.IMPORTANCEIn this work, we use the sequence representations from a pre-trained large protein language model (ProtTrans) as input and develop a Support Vector Machine-based method called POOE for predicting oomycete effectors. POOE could achieve a highly accurate performance in the independent test set, considerably outperforming existing oomycete effector prediction methods. We expect that this new bioinformatics tool will accelerate the identification of oomycete effectors and further guide the experimental efforts to interrogate the functional roles of effectors in plant-pathogen interaction.

Protein Sorting Prediction

Many computational methods are available for predicting protein sorting in bacteria. When comparing them, it is important to know that they can be grouped into three fundamentally different approaches: signal-based, global property-based, and homology-based prediction. In this chapter, the strengths and drawbacks of each of these approaches are described through many examples of methods that predict secretion, integration into membranes, or subcellular locations in general. The aim of this chapter is to provide a user-level introduction to the field with a minimum of computational theory.

Natural language processing approach to model the secretion signal of type III effectors

Type III effectors are proteins injected by Gram-negative bacteria into eukaryotic hosts. In many plant and animal pathogens, these effectors manipulate host cellular processes to the benefit of the bacteria. Type III effectors are secreted by a type III secretion system that must "classify" each bacterial protein into one of two categories, either the protein should be translocated or not. It was previously shown that type III effectors have a secretion signal within their N-terminus, however, despite numerous efforts, the exact biochemical identity of this secretion signal is generally unknown. Computational characterization of the secretion signal is important for the identification of novel effectors and for better understanding the molecular translocation mechanism. In this work we developed novel machine-learning algorithms for characterizing the secretion signal in both plant and animal pathogens. Specifically, we represented each protein as a vector in high-dimensional space using Facebook's protein language model. Classification algorithms were next used to separate effectors from non-effector proteins. We subsequently curated a benchmark dataset of hundreds of effectors and thousands of non-effector proteins. We showed that on this curated dataset, our novel approach yielded substantially better classification accuracy compared to previously developed methodologies. We have also tested the hypothesis that plant and animal pathogen effectors are characterized by different secretion signals. Finally, we integrated the novel approach in Effectidor, a web-server for predicting type III effector proteins, leading to a more accurate classification of effectors from non-effectors.

Microbial Effectors: Key Determinants in Plant Health and Disease

Effectors are small, secreted molecules that alter host cell structure and function, thereby facilitating infection or triggering a defense response. Effectoromics studies have focused on effectors in plant-pathogen interactions, where their contributions to virulence are determined in the plant host, i.e., whether the effector induces resistance or susceptibility to plant disease. Effector molecules from plant pathogenic microorganisms such as fungi, oomycetes and bacteria are major disease determinants. Interestingly, the effectors of non-pathogenic plant organisms such as endophytes display similar functions but have different outcomes for plant health. Endophyte effectors commonly aid in the establishment of mutualistic interactions with the plant and contribute to plant health through the induction of systemic resistance against pathogens, while pathogenic effectors mainly debilitate the plant's immune response, resulting in the establishment of disease. Effectors of plant pathogens as well as plant endophytes are tools to be considered in effectoromics for the development of novel strategies for disease management. This review aims to present effectors in their roles as promotors of health or disease for the plant host.

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit-explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring "the state of the art" in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI-PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI-PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI-PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the "state of the art" on research in the AI-PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

T1SEstacker: A Tri-Layer Stacking Model Effectively Predicts Bacterial Type 1 Secreted Proteins Based on C-Terminal Non-repeats-in-Toxin-Motif Sequence Features

Type 1 secretion systems play important roles in pathogenicity of Gram-negative bacteria. However, the substrate secretion mechanism remains largely unknown. In this research, we observed the sequence features of repeats-in-toxin (RTX) proteins, a major class of type 1 secreted effectors (T1SEs). We found striking non-RTX-motif amino acid composition patterns at the C termini, most typically exemplified by the enriched “[FLI][VAI]” at the most C-terminal two positions. Machine-learning models, including deep-learning ones, were trained using these sequence-based non-RTX-motif features and further combined into a tri-layer stacking model, T1SEstacker, which predicted the RTX proteins accurately, with a fivefold cross-validated sensitivity of ∼0.89 at the specificity of ∼0.94. Besides substrates with RTX motifs, T1SEstacker can also well distinguish non-RTX-motif T1SEs, further suggesting their potential existence of common secretion signals. T1SEstacker was applied to predict T1SEs from the genomes of representative Salmonella strains, and we found that both the number and composition of T1SEs varied among strains. The number of T1SEs is estimated to reach 100 or more in each strain, much larger than what we expected. In summary, we made comprehensive sequence analysis on the type 1 secreted RTX proteins, identified common sequence-based features at the C termini, and developed a stacking model that can predict type 1 secreted proteins accurately.

ProtPlat: an efficient pre-training platform for protein classification based on FastText

Background

For the past decades, benefitting from the rapid growth of protein sequence data in public databases, a lot of machine learning methods have been developed to predict physicochemical properties or functions of proteins using amino acid sequence features. However, the prediction performance often suffers from the lack of labeled data. In recent years, pre-training methods have been widely studied to address the small-sample issue in computer vision and natural language processing fields, while specific pre-training techniques for protein sequences are few.

Results

In this paper, we propose a pre-training platform for representing protein sequences, called ProtPlat, which uses the Pfam database to train a three-layer neural network, and then uses specific training data from downstream tasks to fine-tune the model. ProtPlat can learn good representations for amino acids, and at the same time achieve efficient classification. We conduct experiments on three protein classification tasks, including the identification of type III secreted effectors, the prediction of subcellular localization, and the recognition of signal peptides. The experimental results show that the pre-training can enhance model performance effectively and ProtPlat is competitive to the state-of-the-art predictors, especially for small datasets. We implement the ProtPlat platform as a web service (https://compbio.sjtu.edu.cn/protplat) that is accessible to the public.

Conclusions

To enhance the feature representation of protein amino acid sequences and improve the performance of sequence-based classification tasks, we develop ProtPlat, a general platform for the pre-training of protein sequences, which is featured by a large-scale supervised training based on Pfam database and an efficient learning model, FastText. The experimental results of three downstream classification tasks demonstrate the efficacy of ProtPlat.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04604-2.

Genomic and Functional Dissections of Dickeya zeae Shed Light on the Role of Type III Secretion System and Cell Wall-Degrading Enzymes to Host Range and Virulence

Dickeya zeae is a worldwide destructive pathogen that causes soft rot diseases on various hosts such as rice, maize, banana, and potato. The strain JZL7 we recently isolated from clivia represents the first monocot-specific D. zeae and also has reduced pathogenicity compared to that of other D. zeae strains (e.g., EC1 and MS2). To elucidate the molecular mechanisms underlying its more restricted host range and weakened pathogenicity, we sequenced the complete genome of JZL7 and performed comparative genomic and functional analyses of JZL7 and other D. zeae strains. We found that, while having the largest genome among D. zeae strains, JZL7 lost almost the entire type III secretion system (T3SS), which is a key component of the virulence suite of many bacterial pathogens. Importantly, the deletion of T3SS in MS2 substantially diminished the expression of most type III secreted effectors (T3SEs) and MS2's pathogenicity on both dicots and monocots. Moreover, although JZL7 and MS2 share almost the same repertoire of cell wall-degrading enzymes (CWDEs), we found broad reduction in the production of CWDEs and expression levels of CWDE genes in JZL7. The lower expression of CWDEs, pectin lyases in particular, would probably make it difficult for JZL7 to break down the cell wall of dicots, which is rich in pectin. Together, our results suggest that the loss of T3SS and reduced CWDE activity together might have contributed to the host specificity and virulence of JZL7. Our findings also shed light on the pathogenic mechanism of Dickeya and other soft rot Pectobacteriaceae species in general. IMPORTANCE Dickeya zeae is an important, aggressive bacterial phytopathogen that can cause severe diseases in many crops and ornamental plants, thus leading to substantial economic losses. Strains from different sources showed significant diversity in their natural hosts, suggesting complicated evolution history and pathogenic mechanisms. However, molecular mechanisms that cause the differences in the host range of D. zeae strains remain poorly understood. This study carried out genomic and functional dissections of JZL7, a D. zeae strain with restricted host range, and revealed type III secretion system (T3SS) and cell wall-degrading enzymes (CWDEs) as two major factors contributing to the host range and virulence of D. zeae, which will provide a valuable reference for the exploration of pathogenic mechanisms in other bacteria and present new insights for the control of bacterial soft rot diseases on crops.

DeepT3 2.0: improving type III secreted effector predictions by an integrative deep learning framework

Type III secretion systems (T3SSs) are bacterial membrane-embedded nanomachines that allow a number of humans, plant and animal pathogens to inject virulence factors directly into the cytoplasm of eukaryotic cells. Export of effectors through T3SSs is critical for motility and virulence of most Gram-negative pathogens. Current computational methods can predict type III secreted effectors (T3SEs) from amino acid sequences, but due to algorithmic constraints, reliable and large-scale prediction of T3SEs in Gram-negative bacteria remains a challenge. Here, we present DeepT3 2.0 (http://advintbioinforlab.com/deept3/), a novel web server that integrates different deep learning models for genome-wide predicting T3SEs from a bacterium of interest. DeepT3 2.0 combines various deep learning architectures including convolutional, recurrent, convolutional-recurrent and multilayer neural networks to learn N-terminal representations of proteins specifically for T3SE prediction. Outcomes from the different models are processed and integrated for discriminating T3SEs and non-T3SEs. Because it leverages diverse models and an integrative deep learning framework, DeepT3 2.0 outperforms existing methods in validation datasets. In addition, the features learned from networks are analyzed and visualized to explain how models make their predictions. We propose DeepT3 2.0 as an integrated and accurate tool for the discovery of T3SEs.

Accurate plant pathogen effector protein classification ab initio with deepredeff: an ensemble of convolutional neural networks

Background

Plant pathogens cause billions of dollars of crop loss every year and are a major threat to global food security. Effector proteins are the tools such pathogens use to infect the cell, predicting effectors de novo from sequence is difficult because of the heterogeneity of the sequences. We hypothesised that deep learning classifiers based on Convolutional Neural Networks would be able to identify effectors and deliver new insights.

Results

We created a training set of manually curated effector sequences from PHI-Base and used these to train a range of model architectures for classifying bacteria, fungal and oomycete sequences. The best performing classifiers had accuracies from 93 to 84%. The models were tested against popular effector detection software on our own test data and data provided with those models. We observed better performance from our models. Specifically our models showed greater accuracy and lower tendencies to call false positives on a secreted protein negative test set and a greater generalisability. We used GRAD-CAM activation map analysis to identify the sequences that activated our CNN-LSTM models and found short but distinct N-terminal regions in each taxon that was indicative of effector sequences. No motifs could be observed in these regions but an analysis of amino acid types indicated differing patterns of enrichment and depletion that varied between taxa.

Conclusions

Small training sets can be used effectively to train highly accurate and sensitive deep learning models without need for the operator to know anything other than sequence and without arbitrary decisions made about what sequence features or physico-chemical properties are important. Biological insight on subsequences important for classification can be achieved by examining the activations in the model

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04293-3.

Machine learning for phytopathology: from the molecular scale towards the network scale

With the increasing volume of high-throughput sequencing data from a variety of omics techniques in the field of plant-pathogen interactions, sorting, retrieving, processing and visualizing biological information have become a great challenge. Within the explosion of data, machine learning offers powerful tools to process these complex omics data by various algorithms, such as Bayesian reasoning, support vector machine and random forest. Here, we introduce the basic frameworks of machine learning in dissecting plant-pathogen interactions and discuss the applications and advances of machine learning in plant-pathogen interactions from molecular to network biology, including the prediction of pathogen effectors, plant disease resistance protein monitoring and the discovery of protein-protein networks. The aim of this review is to provide a summary of advances in plant defense and pathogen infection and to indicate the important developments of machine learning in phytopathology.

Computational prediction of secreted proteins in gram-negative bacteria

Gram-negative bacteria harness multiple protein secretion systems and secrete a large proportion of the proteome. Proteins can be exported to periplasmic space, integrated into membrane, transported into extracellular milieu, or translocated into cytoplasm of contacting cells. It is important for accurate, genome-wide annotation of the secreted proteins and their secretion pathways. In this review, we systematically classified the secreted proteins according to the types of secretion systems in Gram-negative bacteria, summarized the known features of these proteins, and reviewed the algorithms and tools for their prediction.

MRMD2.0: A Python Tool for Machine Learning with Feature Ranking and Reduction

Aims:

The study aims to find a way to reduce the dimensionality of the dataset.

Background:

Dimensionality reduction is the key issue of the machine learning process. It does not only improve the prediction performance but also could recommend the intrinsic features and help to explore the biological expression of the machine learning “black box”.

Objective:

A variety of feature selection algorithms are used to select data features to achieve dimensionality reduction.

Methods:

First, MRMD2.0 integrated 7 different popular feature ranking algorithms with PageRank strategy. Second, optimized dimensionality was detected with forward adding strategy.

Result:

We have achieved good results in our experiments.

Conclusion:

Several works have been tested with MRMD2.0. It showed well performance. Otherwise, it also can draw the performance curves according to the feature dimensionality. If users want to sacrifice accuracy for fewer features, they can select the dimensionality from the performance curves.

Other:

We developed friendly python tools together with the web server. The users could upload their csv, arff or libsvm format files. Then the webserver would help to rank features and find the optimized dimensionality.

DeepT3_4: A Hybrid Deep Neural Network Model for the Distinction Between Bacterial Type III and IV Secreted Effectors

Gram-negative bacteria can deliver secreted proteins (also known as secreted effectors) directly into host cells through type III secretion system (T3SS), type IV secretion system (T4SS), and type VI secretion system (T6SS) and cause various diseases. These secreted effectors are heavily involved in the interactions between bacteria and host cells, so their identification is crucial for the discovery and development of novel anti-bacterial drugs. It is currently challenging to accurately distinguish type III secreted effectors (T3SEs) and type IV secreted effectors (T4SEs) because neither T3SEs nor T4SEs contain N-terminal signal peptides, and some of these effectors have similar evolutionary conserved profiles and sequence motifs. To address this challenge, we develop a deep learning (DL) approach called DeepT3_4 to correctly classify T3SEs and T4SEs. We generate amino-acid character dictionary and sequence-based features extracted from effector proteins and subsequently implement these features into a hybrid model that integrates recurrent neural networks (RNNs) and deep neural networks (DNNs). After training the model, the hybrid neural network classifies secreted effectors into two different classes with an accuracy, F-value, and recall of over 80.0%. Our approach stands for the first DL approach for the classification of T3SEs and T4SEs, providing a promising supplementary tool for further secretome studies.

iT3SE-PX: Identification of Bacterial Type III Secreted Effectors Using PSSM Profiles and XGBoost Feature Selection

Identification of bacterial type III secreted effectors (T3SEs) has become a popular research topic in the field of bioinformatics due to its crucial role in understanding host-pathogen interaction and developing better therapeutic targets against the pathogens. However, the recognition of all effector proteins by using traditional experimental approaches is often time-consuming and laborious. Therefore, development of computational methods to accurately predict putative novel effectors is important in reducing the number of biological experiments for validation. In this study, we proposed a method, called iT3SE-PX, to identify T3SEs solely based on protein sequences. First, three kinds of features were extracted from the position-specific scoring matrix (PSSM) profiles to help train a machine learning (ML) model. Then, the extreme gradient boosting (XGBoost) algorithm was performed to rank these features based on their classification ability. Finally, the optimal features were selected as inputs to a support vector machine (SVM) classifier to predict T3SEs. Based on the two benchmark datasets, we conducted a 100-time randomized 5-fold cross validation (CV) and an independent test, respectively. The experimental results demonstrated that the proposed method achieved superior performance compared to most of the existing methods and could serve as a useful tool for identifying putative T3SEs, given only the sequence information.

SubLocEP: a novel ensemble predictor of subcellular localization of eukaryotic mRNA based on machine learning

MOTIVATION

mRNA location corresponds to the location of protein translation and contributes to precise spatial and temporal management of the protein function. However, current assignment of subcellular localization of eukaryotic mRNA reveals important limitations: (1) turning multiple classifications into multiple dichotomies makes the training process tedious; (2) the majority of the models trained by classical algorithm are based on the extraction of single sequence information; (3) the existing state-of-the-art models have not reached an ideal level in terms of prediction and generalization ability. To achieve better assignment of subcellular localization of eukaryotic mRNA, a better and more comprehensive model must be developed.

RESULTS

In this paper, SubLocEP is proposed as a two-layer integrated prediction model for accurate prediction of the location of sequence samples. Unlike the existing models based on limited features, SubLocEP comprehensively considers additional feature attributes and is combined with LightGBM to generated single feature classifiers. The initial integration model (single-layer model) is generated according to the categories of a feature. Subsequently, two single-layer integration models are weighted (sequence-based: physicochemical properties = 3:2) to produce the final two-layer model. The performance of SubLocEP on independent datasets is sufficient to indicate that SubLocEP is an accurate and stable prediction model with strong generalization ability. Additionally, an online tool has been developed that contains experimental data and can maximize the user convenience for estimation of subcellular localization of eukaryotic mRNA.

Computational Systems Biology of Alfalfa - Bacterial Blight Host-Pathogen Interactions: Uncovering the Complex Molecular Networks for Developing Durable Disease Resistant Crop

Medicago sativa (also known as alfalfa), a forage legume, is widely cultivated due to its high yield and high-value hay crop production. Infectious diseases are a major threat to the crops, owing to huge economic losses to the agriculture industry, worldwide. The protein-protein interactions (PPIs) between the pathogens and their hosts play a critical role in understanding the molecular basis of pathogenesis. Pseudomonas syringae pv. syringae ALF3 suppresses the plant's innate immune response by secreting type III effector proteins into the host cell, causing bacterial stem blight in alfalfa. The alfalfa-P. syringae system has little information available for PPIs. Thus, to understand the infection mechanism, we elucidated the genome-scale host-pathogen interactions (HPIs) between alfalfa and P. syringae using two computational approaches: interolog-based and domain-based method. A total of ∼14 M putative PPIs were predicted between 50,629 alfalfa proteins and 2,932 P. syringae proteins by combining these approaches. Additionally, ∼0.7 M consensus PPIs were also predicted. The functional analysis revealed that P. syringae proteins are highly involved in nucleotide binding activity (GO:0000166), intracellular organelle (GO:0043229), and translation (GO:0006412) while alfalfa proteins are involved in cellular response to chemical stimulus (GO:0070887), oxidoreductase activity (GO:0016614), and Golgi apparatus (GO:0005794). According to subcellular localization predictions, most of the pathogen proteins targeted host proteins within the cytoplasm and nucleus. In addition, we discovered a slew of new virulence effectors in the predicted HPIs. The current research describes an integrated approach for deciphering genome-scale host-pathogen PPIs between alfalfa and P. syringae, allowing the researchers to better understand the pathogen's infection mechanism and develop pathogen-resistant lines.

autoBioSeqpy: A Deep Learning Tool for the Classification of Biological Sequences

Deep learning has proven to be a powerful method with applications in various fields including image, language, and biomedical data. Thanks to the libraries and toolkits such as TensorFlow, PyTorch, and Keras, researchers can use different deep learning architectures and data sets for rapid modeling. However, the available implementations of neural networks using these toolkits are usually designed for a specific research and are difficult to transfer to other work. Here, we present autoBioSeqpy, a tool that uses deep learning for biological sequence classification. The advantage of this tool is its simplicity. Users only need to prepare the input data set and then use a command line interface. Then, autoBioSeqpy automatically executes a series of customizable steps including text reading, parameter initialization, sequence encoding, model loading, training, and evaluation. In addition, the tool provides various ready-to-apply and adapt model templates to improve the usability of these networks. We introduce the application of autoBioSeqpy on three biological sequence problems: the prediction of type III secreted proteins, protein subcellular localization, and CRISPR/Cas9 sgRNA activity. autoBioSeqpy is freely available with examples at https://github.com/jingry/autoBioSeqpy.

T3SEpp: an Integrated Prediction Pipeline for Bacterial Type III Secreted Effectors

Many Gram-negative bacteria infect hosts and cause diseases by translocating a variety of type III secreted effectors (T3SEs) into the host cell cytoplasm. However, despite a dramatic increase in the number of available whole-genome sequences, it remains challenging for accurate prediction of T3SEs. Traditional prediction models have focused on atypical sequence features buried in the N-terminal peptides of T3SEs, but unfortunately, these models have had high false-positive rates. In this research, we integrated promoter information along with characteristic protein features for signal regions, chaperone-binding domains, and effector domains for T3SE prediction. Machine learning algorithms, including deep learning, were adopted to predict the atypical features mainly buried in signal sequences of T3SEs, followed by development of a voting-based ensemble model integrating the individual prediction results. We assembled this into a unified T3SE prediction pipeline, T3SEpp, which integrated the results of individual modules, resulting in high accuracy (i.e., ∼0.94) and >1-fold reduction in the false-positive rate compared to that of state-of-the-art software tools. The T3SEpp pipeline and sequence features observed here will facilitate the accurate identification of new T3SEs, with numerous benefits for future studies on host-pathogen interactions.IMPORTANCE Type III secreted effector (T3SE) prediction remains a big computational challenge. In practical applications, current software tools often suffer problems of high false-positive rates. One of the causal factors could be the relatively unitary type of biological features used for the design and training of the models. In this research, we made a comprehensive survey on the sequence-based features of T3SEs, including signal sequences, chaperone-binding domains, effector domains, and transcription factor binding promoter sites, and assembled a unified prediction pipeline integrating multi-aspect biological features within homology-based and multiple machine learning models. To our knowledge, we have compiled the most comprehensive biological sequence feature analysis for T3SEs in this research. The T3SEpp pipeline integrating the variety of features and assembling different models showed high accuracy, which should facilitate more accurate identification of T3SEs in new and existing bacterial whole-genome sequences.

ACNNT3: Attention-CNN Framework for Prediction of Sequence-Based Bacterial Type III Secreted Effectors

The type III secretion system (T3SS) is a special protein delivery system in Gram-negative bacteria which delivers T3SS-secreted effectors (T3SEs) to host cells causing pathological changes. Numerous experiments have verified that T3SEs play important roles in many biological activities and in host-pathogen interactions. Accurate identification of T3SEs is therefore essential to help understand the pathogenic mechanism of bacteria; however, many existing biological experimental methods are time-consuming and expensive. New deep-learning methods have recently been successfully applied to T3SE recognition, but improving the recognition accuracy of T3SEs is still a challenge. In this study, we developed a new deep-learning framework, ACNNT3, based on the attention mechanism. We converted 100 residues of the N-terminal of the protein sequence into a fusion feature vector of protein primary structure information (one-hot encoding) and position-specific scoring matrix (PSSM) which are used as the feature input of the network model. We then embedded the attention layer into CNN to learn the characteristic preferences of type III effector proteins, which can accurately classify any protein directly as either T3SEs or non-T3SEs. We found that the introduction of new protein features can improve the recognition accuracy of the model. Our method combines the advantages of CNN and the attention mechanism and is superior in many indicators when compared to other popular methods. Using the common independent dataset, our method is more accurate than the previous method, showing an improvement of 4.1-20.0%.

EP3: an ensemble predictor that accurately identifies type III secreted effectors

Type III secretion systems (T3SS) can be found in many pathogenic bacteria, such as Dysentery bacillus, Salmonella typhimurium, Vibrio cholera and pathogenic Escherichia coli. The routes of infection of these bacteria include the T3SS transferring a large number of type III secreted effectors (T3SE) into host cells, thereby blocking or adjusting the communication channels of the host cells. Therefore, the accurate identification of T3SEs is the precondition for the further study of pathogenic bacteria. In this article, a new T3SEs ensemble predictor was developed, which can accurately distinguish T3SEs from any unknown protein. In the course of the experiment, methods and models are strictly trained and tested. Compared with other methods, EP3 demonstrates better performance, including the absence of overfitting, strong robustness and powerful predictive ability. EP3 (an ensemble predictor that accurately identifies T3SEs) is designed to simplify the user's (especially nonprofessional users) access to T3SEs for further investigation, which will have a significant impact on understanding the progression of pathogenic bacterial infections. Based on the integrated model that we proposed, a web server had been established to distinguish T3SEs from non-T3SEs, where have EP3_1 and EP3_2. The users can choose the model according to the species of the samples to be tested. Our related tools and data can be accessed through the link http://lab.malab.cn/∼lijing/EP3.html.

ChlamDB: a comparative genomics database of the phylum Chlamydiae and other members of the Planctomycetes-Verrucomicrobiae-Chlamydiae superphylum

ChlamDB is a comparative genomics database containing 277 genomes covering the entire Chlamydiae phylum as well as their closest relatives belonging to the Planctomycetes-Verrucomicrobiae-Chlamydiae (PVC) superphylum. Genomes can be compared, analyzed and retrieved using accessions numbers of the most widely used databases including COG, KEGG ortholog, KEGG pathway, KEGG module, Pfam and InterPro. Gene annotations from multiple databases including UniProt (curated and automated protein annotations), KEGG (annotation of pathways), COG (orthology), TCDB (transporters), STRING (protein-protein interactions) and InterPro (domains and signatures) can be accessed in a comprehensive overview page. Candidate effectors of the Type III secretion system (T3SS) were identified using four in silico methods. The identification of orthologs among all PVC genomes allows users to perform large-scale comparative analyses and to identify orthologs of any protein in all genomes integrated in the database. Phylogenetic relationships of PVC proteins and their closest homologs in RefSeq, comparison of transmembrane domains and Pfam domains, conservation of gene neighborhood and taxonomic profiles can be visualized using dynamically generated graphs, available for download. As a central resource for researchers working on chlamydia, chlamydia-related bacteria, verrucomicrobia and planctomyces, ChlamDB facilitates the access to comprehensive annotations, integrates multiple tools for comparative genomic analyses and is freely available at https://chlamdb.ch/. Database URL: https://chlamdb.ch/.

SDM6A: A Web-Based Integrative Machine-Learning Framework for Predicting 6mA Sites in the Rice Genome

DNA N6-adenine methylation (6mA) is an epigenetic modification in prokaryotes and eukaryotes. Identifying 6mA sites in rice genome is important in rice epigenetics and breeding, but non-random distribution and biological functions of these sites remain unclear. Several machine-learning tools can identify 6mA sites but show limited prediction accuracy, which limits their usability in epigenetic research. Here, we developed a novel computational predictor, called the Sequence-based DNA N6-methyladenine predictor (SDM6A), which is a two-layer ensemble approach for identifying 6mA sites in the rice genome. Unlike existing methods, which are based on single models with basic features, SDM6A explores various features, and five encoding methods were identified as appropriate for this problem. Subsequently, an optimal feature set was identified from encodings, and corresponding models were developed individually using support vector machine and extremely randomized tree. First, all five single models were integrated via ensemble approach to define the class for each classifier. Second, two classifiers were integrated to generate a final prediction. SDM6A achieved robust performance on cross-validation and independent evaluation, with average accuracy and Matthews correlation coefficient (MCC) of 88.2% and 0.764, respectively. Corresponding metrics were 4.7%-11.0% and 2.3%-5.5% higher than those of existing methods, respectively. A user-friendly, publicly accessible web server (http://thegleelab.org/SDM6A) was implemented to predict novel putative 6mA sites in rice genome.