Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics

Deep learning in preclinical antibody drug discovery and development

Antibody drugs have become a key part of biotherapeutics. Patients suffering from various diseases have benefited from antibody therapies. However, its development process is rather long, expensive and risky. To speed up the process, reduce cost and improve success rate, artificial intelligence, especially deep learning methods, have been widely used in all aspects of preclinical antibody drug development, from library generation to hit identification, developability screening, lead selection and optimization. In this review, we systematically summarize antibody encodings, deep learning architectures and models used in preclinical antibody drug discovery and development. We also critically discuss challenges and opportunities, problems and possible solutions, current applications and future directions of deep learning in antibody drug development.

Accelerating antibody discovery and design with artificial intelligence: Recent advances and prospects

Therapeutic antibodies are the largest class of biotherapeutics and have been successful in treating human diseases. However, the design and discovery of antibody drugs remains challenging and time-consuming. Recently, artificial intelligence technology has had an incredible impact on antibody design and discovery, resulting in significant advances in antibody discovery, optimization, and developability. This review summarizes major machine learning (ML) methods and their applications for computational predictors of antibody structure and antigen interface/interaction, as well as the evaluation of antibody developability. Additionally, this review addresses the current status of ML-based therapeutic antibodies under preclinical and clinical phases. While many challenges remain, ML may offer a new therapeutic option for the future direction of fully computational antibody design.

DeepBSRPred: deep learning-based binding site residue prediction for proteins

MOTIVATION

Proteins-protein interactions (PPIs) are important to govern several cellular activities. Amino acid residues, which are located at the interface are known as the binding sites and the information about binding sites helps to understand the binding affinities and functions of protein-protein complexes.

RESULTS

We have developed a deep neural network-based method, DeepBSRPred, for predicting the binding sites using protein sequence information and predicted structures from AlphaFold2. Specific sequence and structure-based features include position-specific scoring matrix (PSSM), solvent accessible surface area, conservation score and amino acid properties, and residue depth, respectively. Our method predicted the binding sites with an average F1 score of 0.73 in a dataset of 1236 proteins. Further, we compared the performance with other existing methods in the literature using four benchmark datasets and our method outperformed those methods.

AVAILABILITY AND IMPLEMENTATION

The DeepBSRPred web server can be found at https://web.iitm.ac.in/bioinfo2/deepbsrpred/index.html , along with all datasets used in this study. The trained models, the DeepBSRPred standalone source code, and the feature computation pipeline are freely available at https://web.iitm.ac.in/bioinfo2/deepbsrpred/download.html .

HNetGO: protein function prediction via heterogeneous network transformer

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

HNSPPI: a hybrid computational model combing network and sequence information for predicting protein-protein interaction

Most life activities in organisms are regulated through protein complexes, which are mainly controlled via Protein-Protein Interactions (PPIs). Discovering new interactions between proteins and revealing their biological functions are of great significance for understanding the molecular mechanisms of biological processes and identifying the potential targets in drug discovery. Current experimental methods only capture stable protein interactions, which lead to limited coverage. In addition, expensive cost and time consuming are also the obvious shortcomings. In recent years, various computational methods have been successfully developed for predicting PPIs based only on protein homology, primary sequences of protein or gene ontology information. Computational efficiency and data complexity are still the main bottlenecks for the algorithm generalization. In this study, we proposed a novel computational framework, HNSPPI, to predict PPIs. As a hybrid supervised learning model, HNSPPI comprehensively characterizes the intrinsic relationship between two proteins by integrating amino acid sequence information and connection properties of PPI network. The experimental results show that HNSPPI works very well on six benchmark datasets. Moreover, the comparison analysis proved that our model significantly outperforms other five existing algorithms. Finally, we used the HNSPPI model to explore the SARS-CoV-2-Human interaction system and found several potential regulations. In summary, HNSPPI is a promising model for predicting new protein interactions from known PPI data.

MFPred: prediction of ncRNA families based on multi-feature fusion

Non-coding RNA (ncRNA) plays a critical role in biology. ncRNAs from the same family usually have similar functions, as a result, it is essential to predict ncRNA families before identifying their functions. There are two primary methods for predicting ncRNA families, namely, traditional biological methods and computational methods. In traditional biological methods, a lot of manpower and resources are required to predict ncRNA families. Therefore, this paper proposed a new ncRNA family prediction method called MFPred based on computational methods. MFPred identified ncRNA families by extracting sequence features of ncRNAs, and it possessed three primary modules, including (1) four ncRNA sequences encoding and feature extraction module, which encoded ncRNA sequences and extracted four different features of ncRNA sequences, (2) dynamic Bi_GRU and feature fusion module, which extracted contextual information features of the ncRNA sequence and (3) ResNet_SE module that extracted local information features of the ncRNA sequence. In this study, MFPred was compared with the previously proposed ncRNA family prediction methods using two frequently used public ncRNA datasets, NCY and nRC. The results showed that MFPred outperformed other prediction methods in the two datasets.

Forecasting influenza hemagglutinin mutations through the lens of anomaly detection

The influenza virus hemagglutinin is an important part of the virus attachment to the host cells. The hemagglutinin proteins are one of the genetic regions of the virus with a high potential for mutations. Due to the importance of predicting mutations in producing effective and low-cost vaccines, solutions that attempt to approach this problem have recently gained significant attention. A historical record of mutations has been used to train predictive models in such solutions. However, the imbalance between mutations and preserved proteins is a big challenge for the development of such models that need to be addressed. Here, we propose to tackle this challenge through anomaly detection (AD). AD is a well-established field in Machine Learning (ML) that tries to distinguish unseen anomalies from normal patterns using only normal training samples. By considering mutations as anomalous behavior, we could benefit existing rich solutions in this field that have emerged recently. Such methods also fit the problem setup of extreme imbalance between the number of unmutated vs. mutated training samples. Motivated by this formulation, our method tries to find a compact representation for unmutated samples while forcing anomalies to be separated from the normal ones. This helps the model to learn a shared unique representation between normal training samples as much as possible, which improves the discernibility and detectability of mutated samples from the unmutated ones at the test time. We conduct a large number of experiments on four publicly available datasets, consisting of three different hemagglutinin protein datasets, and one SARS-CoV-2 dataset, and show the effectiveness of our method through different standard criteria.

Prediction of Protein-Protein Interactions Using Vision Transformer and Language Model

The knowledge of protein-protein interaction (PPI) helps us to understand proteins' functions, the causes and growth of several diseases, and can aid in designing new drugs. The majority of existing PPI research has relied mainly on sequence-based approaches. With the availability of multi-omics datasets (sequence, 3D structure) and advancements in deep learning techniques, it is feasible to develop a deep multi-modal framework that fuses the features learned from different sources of information to predict PPI. In this work, we propose a multi-modal approach utilizing protein sequence and 3D structure. To extract features from the 3D structure of proteins, we use a pre-trained vision transformer model that has been fine-tuned on the structural representation of proteins. The protein sequence is encoded into a feature vector using a pre-trained language model. The feature vectors extracted from the two modalities are fused and then fed to the neural network classifier to predict the protein interactions. To showcase the effectiveness of the proposed methodology, we conduct experiments on two popular PPI datasets, namely, the human dataset and the S. cerevisiae dataset. Our approach outperforms the existing methodologies to predict PPI, including multi-modal approaches. We also evaluate the contributions of each modality by designing uni-modal baselines. We perform experiments with three modalities as well, having gene ontology as the third modality.

Prot2GO: Predicting GO Annotations From Protein Sequences and Interactions

Protein is the main material basis of living organisms and plays crucial role in life activities. Understanding the function of protein is of great significance for new drug discovery, disease treatment and vaccine development. In recent years, with the widespread application of deep learning in bioinformatics, researchers have proposed many deep learning models to predict protein functions. However, the existing deep learning methods usually only consider protein sequences, and thus cannot effectively integrate multi-source data to annotate protein functions. In this article, we propose the Prot2GO model, which can integrate protein sequence and PPI network data to predict protein functions. We utilize an improved biased random walk algorithm to extract the features of PPI network. For sequence data, we use a convolutional neural network to obtain the local features of the sequence and a recurrent neural network to capture the long-range associations between amino acid residues in protein sequence. Moreover, Prot2GO adopts the attention mechanism to identify protein motifs and structural domains. Experiments show that Prot2GO model achieves the state-of-the-art performance on multiple metrics.

Predicting the target landscape of kinase inhibitors using 3D convolutional neural networks

Many therapies in clinical trials are based on single drug-single target relationships. To further extend this concept to multi-target approaches using multi-targeted drugs, we developed a machine learning pipeline to unravel the target landscape of kinase inhibitors. This pipeline, which we call 3D-KINEssence, uses a new type of protein fingerprints (3D FP) based on the structure of kinases generated through a 3D convolutional neural network (3D-CNN). These 3D-CNN kinase fingerprints were matched to molecular Morgan fingerprints to predict the targets of each respective kinase inhibitor based on available bioactivity data. The performance of the pipeline was evaluated on two test sets: a sparse drug-target set where each drug is matched in most cases to a single target and also on a densely-covered drug-target set where each drug is matched to most if not all targets. This latter set is more challenging to train, given its non-exclusive character. Our model's root-mean-square error (RMSE) based on the two datasets was 0.68 and 0.8, respectively. These results indicate that 3D FP can predict the target landscape of kinase inhibitors at around 0.8 log units of bioactivity. Our strategy can be utilized in proteochemometric or chemogenomic workflows by consolidating the target landscape of kinase inhibitors.

A survey of drug-target interaction and affinity prediction methods via graph neural networks

The tasks of drug-target interaction (DTI) and drug-target affinity (DTA) prediction play important roles in the field of drug discovery. However, biological experiment-based methods are time-consuming and expensive. Recently, computational-based approaches have accelerated the process of drug-target relationship prediction. Drug and target features are represented in structure-based, sequence-based, and graph-based ways. Although some achievements have been made regarding structure-based representations and sequence-based representations, the acquired feature information is not sufficiently rich. Molecular graph-based representations are some of the more popular approaches, and they have also generated a great deal of interest. In this article, we provide an overview of the DTI prediction and DTA prediction tasks based on graph neural networks (GNNs). We briefly discuss the molecular graphs of drugs, the primary sequences of target proteins, and the graph reSLBpresentations of target proteins. Meanwhile, we conducted experiments on various fundamental datasets to substantiate the plausibility of DTI and DTA utilizing graph neural networks.

Domain-PFP: Protein Function Prediction Using Function-Aware Domain Embedding Representations

Domains are functional and structural units of proteins that govern various biological functions performed by the proteins. Therefore, the characterization of domains in a protein can serve as a proper functional representation of proteins. Here, we employ a self-supervised protocol to derive functionally consistent representations for domains by learning domain-Gene Ontology (GO) co-occurrences and associations. The domain embeddings we constructed turned out to be effective in performing actual function prediction tasks. Extensive evaluations showed that protein representations using the domain embeddings are superior to those of large-scale protein language models in GO prediction tasks. Moreover, the new function prediction method built on the domain embeddings, named Domain-PFP, significantly outperformed the state-of-the-art function predictors. Additionally, Domain-PFP demonstrated competitive performance in the CAFA3 evaluation, achieving overall the best performance among the top teams that participated in the assessment.

Theoretical and Data-Driven Approaches for Biomolecular Condensates

Biomolecular condensation processes are increasingly recognized as a fundamental mechanism that living cells use to organize biomolecules in time and space. These processes can lead to the formation of membraneless organelles that enable cells to perform distinct biochemical processes in controlled local environments, thereby supplying them with an additional degree of spatial control relative to that achieved by membrane-bound organelles. This fundamental importance of biomolecular condensation has motivated a quest to discover and understand the molecular mechanisms and determinants that drive and control this process. Within this molecular viewpoint, computational methods can provide a unique angle to studying biomolecular condensation processes by contributing the resolution and scale that are challenging to reach with experimental techniques alone. In this Review, we focus on three types of dry-lab approaches: theoretical methods, physics-driven simulations and data-driven machine learning methods. We review recent progress in using these tools for probing biomolecular condensation across all three fields and outline the key advantages and limitations of each of the approaches. We further discuss some of the key outstanding challenges that we foresee the community addressing next in order to develop a more complete picture of the molecular driving forces behind biomolecular condensation processes and their biological roles in health and disease.

HydRA: Deep-learning models for predicting RNA-binding capacity from protein interaction association context and protein sequence

RNA-binding proteins (RBPs) control RNA metabolism to orchestrate gene expression and, when dysfunctional, underlie human diseases. Proteome-wide discovery efforts predict thousands of RBP candidates, many of which lack canonical RNA-binding domains (RBDs). Here, we present a hybrid ensemble RBP classifier (HydRA), which leverages information from both intermolecular protein interactions and internal protein sequence patterns to predict RNA-binding capacity with unparalleled specificity and sensitivity using support vector machines (SVMs), convolutional neural networks (CNNs), and Transformer-based protein language models. Occlusion mapping by HydRA robustly detects known RBDs and predicts hundreds of uncharacterized RNA-binding associated domains. Enhanced CLIP (eCLIP) for HydRA-predicted RBP candidates reveals transcriptome-wide RNA targets and confirms RNA-binding activity for HydRA-predicted RNA-binding associated domains. HydRA accelerates construction of a comprehensive RBP catalog and expands the diversity of RNA-binding associated domains.

Prediction of Antigenic Distance in Influenza A Using Attribute Network Embedding

Owing to the rapid changes in the antigenicity of influenza viruses, it is difficult for humans to obtain lasting immunity through antiviral therapy. Hence, tracking the dynamic changes in the antigenicity of influenza viruses can provide a basis for vaccines and drug treatments to cope with the spread of influenza viruses. In this paper, we developed a novel quantitative prediction method to predict the antigenic distance between virus strains using attribute network embedding techniques. An antigenic network is built to model and combine the genetic and antigenic characteristics of the influenza A virus H3N2, using the continuous distributed representation of the virus strain protein sequence (ProtVec) as a node attribute and the antigenic distance between virus strains as an edge weight. The results show a strong positive correlation between supplementing genetic features and antigenic distance prediction accuracy. Further analysis indicates that our prediction model can comprehensively and accurately track the differences in antigenic distances between vaccines and influenza virus strains, and it outperforms existing methods in predicting antigenic distances between strains.

Using machine learning to detect coronaviruses potentially infectious to humans

Establishing the host range for novel viruses remains a challenge. Here, we address the challenge of identifying non-human animal coronaviruses that may infect humans by creating an artificial neural network model that learns from spike protein sequences of alpha and beta coronaviruses and their binding annotation to their host receptor. The proposed method produces a human-Binding Potential (h-BiP) score that distinguishes, with high accuracy, the binding potential among coronaviruses. Three viruses, previously unknown to bind human receptors, were identified: Bat coronavirus BtCoV/133/2005 and Pipistrellus abramus bat coronavirus HKU5-related (both MERS related viruses), and Rhinolophus affinis coronavirus isolate LYRa3 (a SARS related virus). We further analyze the binding properties of BtCoV/133/2005 and LYRa3 using molecular dynamics. To test whether this model can be used for surveillance of novel coronaviruses, we re-trained the model on a set that excludes SARS-CoV-2 and all viral sequences released after the SARS-CoV-2 was published. The results predict the binding of SARS-CoV-2 with a human receptor, indicating that machine learning methods are an excellent tool for the prediction of host expansion events.

A convolutional network and attention mechanism-based approach to predict protein-RNA binding residues

Protein-RNA interactions play a key role in various biological cellular processes, and many experimental and computational studies have been initiated to analyze their interactions. However, experimental determination is quite complex and expensive. Therefore, researchers have worked to develop efficient computational tools to detect protein-RNA binding residues. The accuracy of existing methods is limited by the features of the target and the performance of the computational models; there remains room for improvement. To solve the problem of the accurate detection of protein-RNA binding residues, we propose a convolutional network model named PBRPre based on improved MobileNet. First, by extracting the position information of the target complex and the 3-mer amino acid feature data, the position-specific scoring matrix (PSSM) is improved by using spatial neighbor smoothing processing and discrete wavelet transform to fully exploit the spatial structure information of the target and enrich the feature dataset. Second, the deep learning model MobileNet is used to integrate and optimize the potential features in the target complexes; then, by introducing the Vision Transformer (ViT) network classification layer, the deep-level information of the target is mined to enhance the processing ability of the model for global information and to improve the detection accuracy of the classifiers. The results show that the AUC value of the model can reach 0.866 in the independent testing dataset, which shows that PBRPre can effectively realize the detection of protein-RNA binding residues. All datasets and resource codes of PBRPre are available at https://github.com/linglewu/PBRPre for academic use.

DiMo: discovery of microRNA motifs using deep learning and motif embedding

MicroRNAs are small regulatory RNAs that decrease gene expression after transcription in various biological disciplines. In bioinformatics, identifying microRNAs and predicting their functionalities is critical. Finding motifs is one of the most well-known and important methods for identifying the functionalities of microRNAs. Several motif discovery techniques have been proposed, some of which rely on artificial intelligence-based techniques. However, in the case of few or no training data, their accuracy is low. In this research, we propose a new computational approach, called DiMo, for identifying motifs in microRNAs and generally macromolecules of small length. We employ word embedding techniques and deep learning models to improve the accuracy of motif discovery results. Also, we rely on transfer learning models to pre-train a model and use it in cases of a lack of (enough) training data. We compare our approach with five state-of-the-art works using three real-world datasets. DiMo outperforms the selected related works in terms of precision, recall, accuracy and f1-score.

CPPVec: an accurate coding potential predictor based on a distributed representation of protein sequence

Long non-coding RNAs (lncRNAs) play a crucial role in numbers of biological processes and have received wide attention during the past years. Since the rapid development of high-throughput transcriptome sequencing technologies (RNA-seq) lead to a large amount of RNA data, it is urgent to develop a fast and accurate coding potential predictor. Many computational methods have been proposed to address this issue, they usually exploit information on open reading frame (ORF), protein sequence, k-mer, evolutionary signatures, or homology. Despite the effectiveness of these approaches, there is still much room to improve. Indeed, none of these methods exploit the contextual information of RNA sequence, for example, k-mer features that counts the occurrence frequencies of continuous nucleotides (k-mer) in the whole RNA sequence cannot reflect local contextual information of each k-mer. In view of this shortcoming, here, we present a novel alignment-free method, CPPVec, which exploits the contextual information of RNA sequence for coding potential prediction for the first time, it can be easily implemented by distributed representation (e.g., doc2vec) of protein sequence translated from the longest ORF. The experimental findings demonstrate that CPPVec is an accurate coding potential predictor and significantly outperforms existing state-of-the-art methods.

Large language models improve annotation of viral proteins

Viral sequences are poorly annotated in environmental samples, a major roadblock to understanding how viruses influence microbial community structure. Current annotation approaches rely on alignment-based sequence ho-mology methods, which are limited by available viral sequences and sequence divergence in viral proteins. Here, we show that protein language model representations capture viral protein function beyond the limits of remote sequence homology by targeting two axes of viral sequence annotation: systematic labeling of protein families and function identification for biologic discovery. Protein language model representations capture protein functional properties specific to viruses and expand the annotated fraction of ocean virome viral protein sequences by 37%. Among unannotated viral protein families, we identify a novel DNA editing protein family that defines a new mobile element in marine picocyanobacteria. Protein language models thus significantly enhance remote homology detection of viral proteins and can be utilized to enable new biological discovery across diverse functional categories.

BERT2OME: Prediction of 2'-O-Methylation Modifications From RNA Sequence by Transformer Architecture Based on BERT

Recent work on language models has resulted in state-of-the-art performance on various language tasks. Among these, Bidirectional Encoder Representations from Transformers (BERT) has focused on contextualizing word embeddings to extract context and semantics of the words. On the other hand, post-transcriptional 2'-O-methylation (Nm) RNA modification is important in various cellular tasks and related to a number of diseases. The existing high-throughput experimental techniques take longer time to detect these modifications, and costly in exploring these functional processes. Here, to deeply understand the associated biological processes faster, we come up with an efficient method Bert2Ome to infer 2'-O-methylation RNA modification sites from RNA sequences. Bert2Ome combines BERT-based model with convolutional neural networks (CNN) to infer the relationship between the modification sites and RNA sequence content. Unlike the methods proposed so far, Bert2Ome assumes each given RNA sequence as a text and focuses on improving the modification prediction performance by integrating the pretrained deep learning-based language model BERT. Additionally, our transformer-based approach could infer modification sites across multiple species. According to 5-fold cross-validation, human and mouse accuracies were 99.15% and 94.35% respectively. Similarly, ROC AUC scores were 0.99, 0.94 for the same species. Detailed results show that Bert2Ome reduces the time consumed in biological experiments and outperforms the existing approaches across different datasets and species over multiple metrics. Additionally, deep learning approaches such as 2D CNNs are more promising in learning BERT attributes than more conventional machine learning methods.

Improving the generalizability of protein-ligand binding predictions with AI-Bind

Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery.

Align-gram: Rethinking the Skip-gram Model for Protein Sequence Analysis

The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data. Protein sequences, being quoted as the 'language of life', has been analyzed for a multitude of applications and inferences. Owing to the rapid development of deep learning, in recent years there have been a number of breakthroughs in the domain of Natural Language Processing. Since these methods are capable of performing different tasks when trained with a sufficient amount of data, off-the-shelf models are used to perform various biological applications. In this study, we investigated the applicability of the popular Skip-gram model for protein sequence analysis and made an attempt to incorporate some biological insights into it. We propose a novel k-mer embedding scheme, Align-gram, which is capable of mapping the similar k-mers close to each other in a vector space. Furthermore, we experiment with other sequence-based protein representations and observe that the embeddings derived from Align-gram aids modeling and training deep learning models better. Our experiments with a simple baseline LSTM model and a much complex CNN model of DeepGoPlus shows the potential of Align-gram in performing different types of deep learning applications for protein sequence analysis.

Super High-Throughput Screening of Enzyme Variants by Spectral Graph Convolutional Neural Networks

Finding new enzyme variants with the desired substrate scope requires screening through a large number of potential variants. In a typical in silico enzyme engineering workflow, it is possible to scan a few thousands of variants, and gather several candidates for further screening or experimental verification. In this work, we show that a Graph Convolutional Neural Network (GCN) can be trained to predict the binding energy of combinatorial libraries of enzyme complexes using only sequence information. The GCN model uses a stack of message-passing and graph pooling layers to extract information from the protein input graph and yield a prediction. The GCN model is agnostic to the identity of the ligand, which is kept constant within the mutant libraries. Using a miniscule subset of the total combinatorial space (20⁴-20⁸ mutants) as training data, the proposed GCN model achieves a high accuracy in predicting the binding energy of unseen variants. The network's accuracy was further improved by injecting feature embeddings obtained from a language module pretrained on 10 million protein sequences. Since no structural information is needed to evaluate new variants, the deep learning algorithm is capable of scoring an enzyme variant in under 1 ms, allowing the search of billions of candidates on a single GPU.

ELMo4m6A: A Contextual Language Embedding-Based Predictor for Detecting RNA N6-Methyladenosine Sites

N6-methyladenosine (m6A) is a universal post-transcriptional modification of RNAs, and it is widely involved in various biological processes. Identifying m6A modification sites accurately is indispensable to further investigate m6A-mediated biological functions. How to better represent RNA sequences is crucial for building effective computational methods for detecting m6A modification sites. However, traditional encoding methods require complex biological prior knowledge and are time-consuming. Furthermore, most of the existing m6A sites prediction methods are limited to single species, and few methods are able to predict m6A sites across different species and tissues. Thus, it is necessary to design a more efficient computational method to predict m6A sites across multiple species and tissues. In this paper, we proposed ELMo4m6A, a contextual language embedding-based method for predicting m6A sites from RNA sequences without any prior knowledge. ELMo4m6A first learns embeddings of RNA sequences using a language model ELMo, then uses a hybrid convolutional neural network (CNN) and long short-term memory (LSTM) to identify m6A sites. The results of 5-fold cross-validation and independent testing demonstrate that ELMo4m6A is superior to state-of-the-art methods. Moreover, we applied integrated gradients to find potential sequence patterns contributing to m6A sites.

Effectively Identifying Compound-Protein Interaction Using Graph Neural Representation

Effectively identifying compound-protein interactions (CPIs) is crucial for new drug design, which is an important step in silico drug discovery. Current machine learning methods for CPI prediction mainly use one-demensional (1D) compound/protein strings and/or the specific descriptors. However, they often ignore the fact that molecules are essentially modeled by the molecular graph. We observe that in real-world scenarios, the topological structure information of the molecular graph usually provides an overview of how the atoms are connected, and the local chemical context reveals the functionality of the protein sequence in CPI. These two types of information are complementary to each other and they are both significant for modeling compound-protein pairs. Motivated by this, we propose an end-to-end deep learning framework named GraphCPI, which captures the structural information of compounds and leverages the chemical context of protein sequences for solving the CPI prediction task. Our framework can integrate any popular graph neural networks for learning compounds, and it combines with a convolutional neural network for embedding sequences. To compare our method with classic and state-of-the-art deep learning methods, we conduct extensive experiments based on several widely-used CPI datasets. The experimental results show the feasibility and competitiveness of our proposed method.

Prediction of Enhancers in DNA Sequence Data using a Hybrid CNN-DLSTM Model

Enhancer, a distal cis-regulatory element controls gene expression. Experimental prediction of enhancer elements is time-consuming and expensive. Consequently, various inexpensive deep learning-based fast methods have been developed for predicting the enhancers and determining their strength. In this paper, we have proposed a two-stage deep learning-based framework leveraging DNA structural features, natural language processing, convolutional neural network, and long short-term memory to predict the enhancer elements accurately in the genomics data. In the first stage, we extracted the features from DNA sequence data by using three feature representation techniques viz., k-mer based feature extraction along with word2vector based interpretation of underlined patterns, one-hot encoding, and the DNAshape technique. In the second stage, strength of enhancers is predicted from the extracted features using a hybrid deep learning model. The method is capable of adapting itself to varying sizes of datasets. Also, as proposed model can capture long-range sequencing patterns, the robustness of the method remains unaffected against minor variations in the genomics sequence. The method outperforms the other state-of-the-art methods at both stages in terms of performance metrics of prediction accuracy, specificity, Mathew's correlation coefficient, and area under the ROC curve. In summary, the proposed method is a reliable method for enhancer prediction.

SENSDeep: An Ensemble Deep Learning Method for Protein-Protein Interaction Sites Prediction

PURPOSE

The determination of which amino acid in a protein interacts with other proteins is important in understanding the functional mechanism of that protein. Although there are experimental methods to detect protein-protein interaction sites (PPISs), these are costly, time-consuming, and require expertise. Therefore, many computational methods have been proposed to accelerate this type of research, but they are generally insufficient to predict PPISs accurately. There is a need for development in this field.

METHODS

In this study, we introduce a new PPISs prediction method. This method is a sequence-based Stacking ENSemble Deep (SENSDeep) learning method that has an ensemble learning model including the models of RNN, CNN, GRU sequence to sequence (GRUs2s), GRU sequence to sequence with an attention layer (GRUs2satt) and a multilayer perceptron. Two embedded features, secondary structure, and protein sequence information are added to the training data set in addition to twelve existing features to improve the prediction performance of the method.

RESULTS

SENSDeep trained on the training data set without two extra features obtains a better performance on some of the independent testing data sets than that of the other methods in the literature, especially on scoring metrics of sensitivity, F1, MCC, and AUPRC, having increments up to 63.5%, 19.3%, 18.5%, 11.4%, respectively. It is shown that the added extra features improve the performance of the method by having almost the same performance with less data as the method trained on the data set without these added features. On the other hand, different sizes of the sliding window are tried on the data sets and an optimal sliding window size for SENSDeep is found. Moreover, SENSDeep has also been compared to structure-based methods. Some of these methods have been found to perform better. Using SENSDeep obtained by training with both training data sets, PPISs prediction examples of various proteins that are not in these training data sets are also presented. Furthermore, execution times for SENSDeep and its submodels are shown.

AVAILABILITY AND IMPLEMENTATION

https://github.com/enginaybey/SENSDeep.

Machine learning approaches to predict drug efficacy and toxicity in oncology

In recent years, there has been a surge of interest in using machine learning algorithms (MLAs) in oncology, particularly for biomedical applications such as drug discovery, drug repurposing, diagnostics, clinical trial design, and pharmaceutical production. MLAs have the potential to provide valuable insights and predictions in these areas by representing both the disease state and the therapeutic agents used to treat it. To fully utilize the capabilities of MLAs in oncology, it is important to understand the fundamental concepts underlying these algorithms and how they can be applied to assess the efficacy and toxicity of therapeutics. In this perspective, we lay out approaches to represent both the disease state and the therapeutic agents used by MLAs to derive novel insights and make relevant predictions.

How to approach machine learning-based prediction of drug/compound-target interactions

The identification of drug/compound-target interactions (DTIs) constitutes the basis of drug discovery, for which computational predictive approaches have been developed. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as a pair at the input level and processes them via statistical/machine learning. The representation of input samples (i.e., proteins and their ligands) in the form of quantitative feature vectors is crucial for the extraction of interaction-related properties during the artificial learning and subsequent prediction of DTIs. Lately, the representation learning approach, in which input samples are automatically featurized via training and applying a machine/deep learning model, has been utilized in biomedical sciences. In this study, we performed a comprehensive investigation of different computational approaches/techniques for protein featurization (including both conventional approaches and the novel learned embeddings), data preparation and exploration, machine learning-based modeling, and performance evaluation with the aim of achieving better data representations and more successful learning in DTI prediction. For this, we first constructed realistic and challenging benchmark datasets on small, medium, and large scales to be used as reliable gold standards for specific DTI modeling tasks. We developed and applied a network analysis-based splitting strategy to divide datasets into structurally different training and test folds. Using these datasets together with various featurization methods, we trained and tested DTI prediction models and evaluated their performance from different angles. Our main findings can be summarized under 3 items: (i) random splitting of datasets into train and test folds leads to near-complete data memorization and produce highly over-optimistic results, as a result, should be avoided, (ii) learned protein sequence embeddings work well in DTI prediction and offer high potential, despite interaction-related properties (e.g., structures) of proteins are unused during their self-supervised model training, and (iii) during the learning process, PCM models tend to rely heavily on compound features while partially ignoring protein features, primarily due to the inherent bias in DTI data, indicating the requirement for new and unbiased datasets. We hope this study will aid researchers in designing robust and high-performing data-driven DTI prediction systems that have real-world translational value in drug discovery.

The RESP AI model accelerates the identification of tight-binding antibodies

High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the K_D of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development.

Prediction of protein solubility based on sequence physicochemical patterns and distributed representation information with DeepSoluE

BACKGROUND

Protein solubility is a precondition for efficient heterologous protein expression at the basis of most industrial applications and for functional interpretation in basic research. However, recurrent formation of inclusion bodies is still an inevitable roadblock in protein science and industry, where only nearly a quarter of proteins can be successfully expressed in soluble form. Despite numerous solubility prediction models having been developed over time, their performance remains unsatisfactory in the context of the current strong increase in available protein sequences. Hence, it is imperative to develop novel and highly accurate predictors that enable the prioritization of highly soluble proteins to reduce the cost of actual experimental work.

RESULTS

In this study, we developed a novel tool, DeepSoluE, which predicts protein solubility using a long-short-term memory (LSTM) network with hybrid features composed of physicochemical patterns and distributed representation of amino acids. Comparison results showed that the proposed model achieved more accurate and balanced performance than existing tools. Furthermore, we explored specific features that have a dominant impact on the model performance as well as their interaction effects.

CONCLUSIONS

DeepSoluE is suitable for the prediction of protein solubility in E. coli; it serves as a bioinformatics tool for prescreening of potentially soluble targets to reduce the cost of wet-experimental studies. The publicly available webserver is freely accessible at http://lab.malab.cn/~wangchao/softs/DeepSoluE/ .

Data-driven enzyme engineering to identify function-enhancing enzymes

Identifying function-enhancing enzyme variants is a 'holy grail' challenge in protein science because it will allow researchers to expand the biocatalytic toolbox for late-stage functionalization of drug-like molecules, environmental degradation of plastics and other pollutants, and medical treatment of food allergies. Data-driven strategies, including statistical modeling, machine learning, and deep learning, have largely advanced the understanding of the sequence-structure-function relationships for enzymes. They have also enhanced the capability of predicting and designing new enzymes and enzyme variants for catalyzing the transformation of new-to-nature reactions. Here, we reviewed the recent progresses of data-driven models that were applied in identifying efficiency-enhancing mutants for catalytic reactions. We also discussed existing challenges and obstacles faced by the community. Although the review is by no means comprehensive, we hope that the discussion can inform the readers about the state-of-the-art in data-driven enzyme engineering, inspiring more joint experimental-computational efforts to develop and apply data-driven modeling to innovate biocatalysts for synthetic and pharmaceutical applications.

Learning the protein language of proteome-wide protein-protein binding sites via explainable ensemble deep learning

Protein-protein interactions (PPIs) govern cellular pathways and processes, by significantly influencing the functional expression of proteins. Therefore, accurate identification of protein-protein interaction binding sites has become a key step in the functional analysis of proteins. However, since most computational methods are designed based on biological features, there are no available protein language models to directly encode amino acid sequences into distributed vector representations to model their characteristics for protein-protein binding events. Moreover, the number of experimentally detected protein interaction sites is much smaller than that of protein-protein interactions or protein sites in protein complexes, resulting in unbalanced data sets that leave room for improvement in their performance. To address these problems, we develop an ensemble deep learning model (EDLM)-based protein-protein interaction (PPI) site identification method (EDLMPPI). Evaluation results show that EDLMPPI outperforms state-of-the-art techniques including several PPI site prediction models on three widely-used benchmark datasets including Dset_448, Dset_72, and Dset_164, which demonstrated that EDLMPPI is superior to those PPI site prediction models by nearly 10% in terms of average precision. In addition, the biological and interpretable analyses provide new insights into protein binding site identification and characterization mechanisms from different perspectives. The EDLMPPI webserver is available at http://www.edlmppi.top:5002/ .

MolRoPE-BERT: An enhanced molecular representation with Rotary Position Embedding for molecular property prediction

Molecular property prediction is a significant task in drug discovery. Most deep learning-based computational methods either develop unique chemical representation or combine complex model. However, researchers are less concerned with the possible advantages of enormous quantities of unlabeled molecular data. Since the obvious limited amount of labeled data available, this task becomes more difficult. In some senses, SMILES of the drug molecule may be regarded of as a language for chemistry, taking inspiration from natural language processing research and current advances in pretrained models. In this paper, we incorporated Rotary Position Embedding(RoPE) efficiently encode the position information of SMILES sequences, ultimately enhancing the capability of the BERT pretrained model to extract potential molecular substructure information for molecular property prediction. We proposed the MolRoPE-BERT framework, an new end-to-end deep learning framework that integrates an efficient position coding approach for capturing sequence position information with a pretrained BERT model for molecular property prediction. To generate useful molecular substructure embeddings, we first exclusively train the MolRoPE-BERT on four million unlabeled drug SMILES(i.e., ZINC 15 and ChEMBL 27). Then, we conduct a series of experiments to evaluate the performance of our proposed MolRoPE-BERT on four well-studied datasets. Compared with conventional and state-of-the-art baselines, our experiment demonstrated comparable or superior performance.

Computational Methods and Deep Learning for Elucidating Protein Interaction Networks

Protein interactions play a critical role in all biological processes, but experimental identification of protein interactions is a time- and resource-intensive process. The advances in next-generation sequencing and multi-omics technologies have greatly benefited large-scale predictions of protein interactions using machine learning methods. A wide range of tools have been developed to predict protein-protein, protein-nucleic acid, and protein-drug interactions. Here, we discuss the applications, methods, and challenges faced when employing the various prediction methods. We also briefly describe ways to overcome the challenges and prospective future developments in the field of protein interaction biology.

Identification of Phase Separating Proteins With Distributed Reduced Alphabet Representations of Sequences

Phase separation of proteins play key roles in cellular physiology including bacterial division, tumorigenesis etc. Consequently, understanding the molecular forces that drive phase separation has gained considerable attention and several factors including hydrophobicity, protein dynamics, etc., have been implicated in phase separation. Data-driven identification of new phase separating proteins can enable in-depth understanding of cellular physiology and may pave way towards developing novel methods of tackling disease progression. In this work, we exploit the existing wealth of data on phase separating proteins to develop sequence-based machine learning method for prediction of phase separating proteins. We use reduced alphabet schemes based on hydrophobicity and conformational similarity along with distributed representation of protein sequences and biochemical properties as input features to Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms. We used both curated and balanced dataset for building the models. RF trained on balanced dataset with hydropathy, conformational similarity embeddings and biochemical properties achieved accuracy of 97%. Our work highlights the use of conformational similarity, a feature that reflects amino acid flexibility, and hydrophobicity for predicting phase separating proteins. Use of such "interpretable" features obtained from the ever-growing knowledgebase of phase separation is likely to improve prediction performances further.

Sequence Representations and Their Utility for Predicting Protein-Protein Interactions

Protein-Protein Interactions (PPIs) are a crucial mechanism underpinning the function of the cell. So far, a wide range of machine-learning based methods have been proposed for predicting these relationships. Their success is heavily dependent on the construction of the underlying feature vectors, with most using a set of physico-chemical properties derived from the sequence. Few work directly with the sequence itself. In this paper, we explore the utility of sequence embeddings for predicting protein-protein interactions. We construct a protein pair feature vector by concatenating the embeddings of their constituent sequence. These feature vectors are then used as input to a binary classifier to make predictions. To learn sequence embeddings, we use two established Word2Vec based methods - Seq2Vec and BioVec - and we also introduce a novel feature construction method called SuperVecNW. The embeddings generated through SuperVecNW capture some network information in addition to the contextual information present in the sequences. We test the efficacy of our proposed approach on human and yeast PPI datasets and on three well-known networks: CD9, the Ras-Raf-Mek-Erk-Elk-Srf pathway, and a Wnt-related network. We demonstrate that low dimensional sequence embeddings provide better results than most alternative representations based on physico-chemical properties while offering a far simple approach to feature vector construction.

TEMPO: A transformer-based mutation prediction framework for SARS-CoV-2 evolution

The widespread of SARS-CoV-2 presents a significant threat to human society, as well as public health and economic development. Extensive efforts have been undertaken to battle against the pandemic, whereas effective approaches such as vaccination would be weakened by the continuous mutations, leading to considerable attention being attracted to the mutation prediction. However, most previous studies lack attention to phylogenetics. In this paper, we propose a novel and effective model TEMPO for predicting the mutation of SARS-CoV-2 evolution. Specifically, we design a phylogenetic tree-based sampling method to generate sequence evolution data. Then, a transformer-based model is presented for the site mutation prediction after learning the high-level representation of these sequence data. We conduct experiments to verify the effectiveness of TEMPO, leveraging a large-scale SARS-CoV- 2 dataset. Experimental results show that TEMPO is effective for mutation prediction of SARS- CoV-2 evolution and outperforms several state-of-the-art baseline methods. We further perform mutation prediction experiments of other infectious viruses, to explore the feasibility and robustness of TEMPO, and experimental results verify its superiority. The codes and datasets are freely available at https://github.com/ZJUDataIntelligence/TEMPO.

Drug-target binding affinity prediction method based on a deep graph neural network

The development of new drugs is a long and costly process, Computer-aided drug design reduces development costs while computationally shortening the new drug development cycle, in which DTA (Drug-Target binding Affinity) prediction is a key step to screen out potential drugs. With the development of deep learning, various types of deep learning models have achieved notable performance in a wide range of fields. Most current related studies focus on extracting the sequence features of molecules while ignoring the valuable structural information; they employ sequence data that represent only the elemental composition of molecules without considering the molecular structure maps that contain structural information. In this paper, we use graph neural networks to predict DTA based on corresponding graph data of drugs and proteins, and we achieve competitive performance on two benchmark datasets, Davis and KIBA. In particular, an MSE of 0.227 and CI of 0.895 were obtained on Davis, and an MSE of 0.127 and CI of 0.903 were obtained on KIBA.

A novel hybrid CNN and BiGRU-Attention based deep learning model for protein function prediction

Proteins are the building blocks of all living things. Protein function must be ascertained if the molecular mechanism of life is to be understood. While CNN is good at capturing short-term relationships, GRU and LSTM can capture long-term dependencies. A hybrid approach that combines the complementary benefits of these deep-learning models motivates our work. Protein Language models, which use attention networks to gather meaningful data and build representations for proteins, have seen tremendous success in recent years processing the protein sequences. In this paper, we propose a hybrid CNN + BiGRU - Attention based model with protein language model embedding that effectively combines the output of CNN with the output of BiGRU-Attention for predicting protein functions. We evaluated the performance of our proposed hybrid model on human and yeast datasets. The proposed hybrid model improves the Fmax value over the state-of-the-art model SDN2GO for the cellular component prediction task by 1.9 %, for the molecular function prediction task by 3.8 % and for the biological process prediction task by 0.6 % for human dataset and for yeast dataset the cellular component prediction task by 2.4 %, for the molecular function prediction task by 5.2 % and for the biological process prediction task by 1.2 %.

Pathogenicity Prediction of Single Amino Acid Variants With Machine Learning Model Based on Protein Structural Energies

The most popular tools for predicting pathogenicity of single amino acid variants (SAVs) were developed based on sequence-based techniques. SAVs may change protein structure and function. In the context of van der Waals force and disulfide bridge calculations, no method directly predicts the impact of mutations on the energies of the protein structure. Here, we combined machine learning methods and energy scores of protein structures calculated by Rosetta Energy Function 2015 to predict SAV pathogenicity. The accuracy level of our model (0.76) is higher than that of six prediction tools. Further analyses revealed that the differential reference energies, attractive energies, and solvation of polar atoms between wildtype and mutant side-chains played essential roles in distinguishing benign from pathogenic variants. These features indicated the physicochemical properties of amino acids, which were observed in 3D structures instead of sequences. We added 16 features to Rhapsody (the prediction tool we used for our data set) and consequently improved its performance. The results indicated that these energy scores were more appropriate and more detailed representations of the pathogenicity of SAVs.

Genomic landscape of the SARS-CoV-2 pandemic in Brazil suggests an external P.1 variant origin

Brazil was the epicenter of worldwide pandemics at the peak of its second wave. The genomic/proteomic perspective of the COVID-19 pandemic in Brazil could provide insights to understand the global pandemics behavior. In this study, we track SARS-CoV-2 molecular information in Brazil using real-time bioinformatics and data science strategies to provide a comparative and evolutive panorama of the lineages in the country. SWeeP vectors represented the Brazilian and worldwide genomic/proteomic data from Global Initiative on Sharing Avian Influenza Data (GISAID) between February 2020 and August 2021. Clusters were analyzed and compared with PANGO lineages. Hierarchical clustering provided phylogenetic and evolutionary analyses of the lineages, and we tracked the P.1 (Gamma) variant origin. The genomic diversity based on Chao's estimation allowed us to compare richness and coverage among Brazilian states and other representative countries. We found that epidemics in Brazil occurred in two moments with different genetic profiles. The P.1 lineages emerged in the second wave, which was more aggressive. We could not trace the origin of P.1 from the variants present in Brazil. Instead, we found evidence pointing to its external source and a possible recombinant event that may relate P.1 to a B.1.1.28 variant subset. We discussed the potential application of the pipeline for emerging variants detection and the PANGO terminology stability over time. The diversity analysis showed that the low coverage and unbalanced sequencing among states in Brazil could have allowed the silent entry and dissemination of P.1 and other dangerous variants. This study may help to understand the development and consequences of variants of concern (VOC) entry.

COPPER: an ensemble deep-learning approach for identifying exclusive virus-derived small interfering RNAs in plants

Antiviral defenses are one of the significant roles of RNA interference (RNAi) in plants. It has been reported that the host RNAi mechanism machinery can target viral RNAs for destruction because virus-derived small interfering RNAs (vsiRNAs) are found in infected host cells. Therefore, the recognition of plant vsiRNAs is the key to understanding the functional mechanisms of vsiRNAs and developing antiviral plants. In this work, we introduce a deep learning-based stacking ensemble approach, named computational prediction of plant exclusive virus-derived small interfering RNAs (COPPER), for plant vsiRNA prediction. COPPER used word2vec and fastText to generate sequence features and a hybrid deep learning framework, including a convolutional neural network, multiscale residual network and bidirectional long short-term memory network with a self-attention mechanism to enable precise predictions of plant vsiRNAs. Extensive benchmarking experiments with different sequence homology thresholds and ablation studies illustrated the comparative predictive performance of COPPER. In addition, the performance comparison with PVsiRNAPred conducted on an independent test dataset showed that COPPER significantly improved the predictive performance for plant vsiRNAs compared with other state-of-the-art methods. The datasets and source codes are publicly available at https://github.com/yuanyuanbu/COPPER.

Learning to discover medicines

Discovering new medicines is the hallmark of the human endeavor to live a better and longer life. Yet the pace of discovery has slowed down as we need to venture into more wildly unexplored biomedical space to find one that matches today's high standard. Modern AI-enabled by powerful computing, large biomedical databases, and breakthroughs in deep learning offers a new hope to break this loop as AI is rapidly maturing, ready to make a huge impact in the area. In this paper, we review recent advances in AI methodologies that aim to crack this challenge. We organize the vast and rapidly growing literature on AI for drug discovery into three relatively stable sub-areas: (a) representation learning over molecular sequences and geometric graphs; (b) data-driven reasoning where we predict molecular properties and their binding, optimize existing compounds, generate de novo molecules, and plan the synthesis of target molecules; and (c) knowledge-based reasoning where we discuss the construction and reasoning over biomedical knowledge graphs. We will also identify open challenges and chart possible research directions for the years to come.

De novo prediction of RNA-protein interactions with graph neural networks

RNA-binding proteins (RBPs) are key co- and post-transcriptional regulators of gene expression, playing a crucial role in many biological processes. Experimental methods like CLIP-seq have enabled the identification of transcriptome-wide RNA-protein interactions for select proteins; however, the time- and resource-intensive nature of these technologies call for the development of computational methods to complement their predictions. Here, we leverage recent, large-scale CLIP-seq experiments to construct a de novo predictor of RNA-protein interactions based on graph neural networks (GNN). We show that the GNN method allows us not only to predict missing links in an RNA-protein network, but to predict the entire complement of targets of previously unassayed proteins, and even to reconstruct the entire network of RNA-protein interactions in different conditions based on minimal information. Our results demonstrate the potential of modern machine learning methods to extract useful information on post-transcriptional regulation from large data sets.

Accurate Prediction of Human Essential Proteins Using Ensemble Deep Learning

Essential proteins are considered the foundation of life as they are indispensable for the survival of living organisms. Computational methods for essential protein discovery provide a fast way to identify essential proteins. But most of them heavily rely on various biological information, especially protein-protein interaction networks, which limits their practical applications. With the rapid development of high-throughput sequencing technology, sequencing data has become the most accessible biological data. However, using only protein sequence information to predict essential proteins has limited accuracy. In this paper, we propose EP-EDL, an ensemble deep learning model using only protein sequence information to predict human essential proteins. EP-EDL integrates multiple classifiers to alleviate the class imbalance problem and to improve prediction accuracy and robustness. In each base classifier, we employ multi-scale text convolutional neural networks to extract useful features from protein sequence feature matrices with evolutionary information. Our computational results show that EP-EDL outperforms the state-of-the-art sequence-based methods. Furthermore, EP-EDL provides a more practical and flexible way for biologists to accurately predict essential proteins. The source code and datasets can be downloaded from https://github.com/CSUBioGroup/EP-EDL.

IAV-CNN: A 2D Convolutional Neural Network Model to Predict Antigenic Variants of Influenza A Virus

The rapid evolution of influenza viruses constantly leads to the emergence of novel influenza strains that are capable of escaping from population immunity. The timely determination of antigenic variants is critical to vaccine design. Empirical experimental methods like hemagglutination inhibition (HI) assays are time-consuming and labor-intensive, requiring live viruses. Recently, many computational models have been developed to predict the antigenic variants without considerations of explicitly modeling the interdependencies between the channels of feature maps. Moreover, the influenza sequences consisting of similar distribution of residues will have high degrees of similarity and will affect the prediction outcome. Consequently, it is challenging but vital to determine the importance of different residue sites and enhance the predictive performance of influenza antigenicity. We have proposed a 2D convolutional neural network (CNN) model to infer influenza antigenic variants (IAV-CNN). Specifically, we apply a new distributed representation of amino acids, named ProtVec that can be applied to a variety of downstream proteomic machine learning tasks. After splittings and embeddings of influenza strains, a 2D squeeze-and-excitation CNN architecture is constructed that enables networks to focus on informative residue features by fusing both spatial and channel-wise information with local receptive fields at each layer. Experimental results on three influenza datasets show IAV-CNN achieves state-of-the-art performance combining the new distributed representation with our proposed architecture. It outperforms both traditional machine algorithms with the same feature representations and the majority of existing models in the independent test data. Therefore we believe that our model can be served as a reliable and robust tool for the prediction of antigenic variants.

TripletProt: Deep Representation Learning of Proteins Based On Siamese Networks

Pretrained representations have recently gained attention in various machine learning applications. Nonetheless, the high computational costs associated with training these models have motivated alternative approaches for representation learning. Herein we introduce TripletProt, a new approach for protein representation learning based on the Siamese neural networks. Representation learning of biological entities which capture essential features can alleviate many of the challenges associated with supervised learning in bioinformatics. The most important distinction of our proposed method is relying on the protein-protein interaction (PPI) network. The computational cost of the generated representations for any potential application is significantly lower than comparable methods since the length of the representations is significantly smaller than that in other approaches. TripletProt offers great potentials for the protein informatics tasks and can be widely applied to similar tasks. We evaluate TripletProt comprehensively in protein functional annotation tasks including sub-cellular localization (14 categories) and gene ontology prediction (more than 2000 classes), which are both challenging multi-class, multi-label classification machine learning problems. We compare the performance of TripletProt with the state-of-the-art approaches including a recurrent language model-based approach (i.e., UniRep), as well as a protein-protein interaction (PPI) network and sequence-based method (i.e., DeepGO). Our TripletProt showed an overall improvement of F1 score in the above mentioned comprehensive functional annotation tasks, solely relying on the PPI network. Availability: The source code and datasets are available at https://github.com/EsmaeilNourani/TripletProt.