Sequence-based Model Research Articles

Sequence-based modeling of deep learning with LSTM and GRU networks for structural damage detection of floating offshore wind turbine blades

This paper proposes and tests a sequence-based modeling of deep learning (DL) for structural damage detection of floating offshore wind turbine (FOWT) blades using Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks. The complete framework was developed with four different designs of deep networks using unidirectional or bidirectional layers of LSTM and GRU networks. These neural networks, specifically developed to learn long-term and short-term dependencies within sequential information such as time-series data, are successfully trained with the sensor signals of damaged FOWT. The sensor data were simulated due to the limited availability of field data from damaged FOWTs using multiple computational methods previously validated with experimental tests. The simulations accounted for the damage scenarios with various intensities, locations, and damage shapes, totaling 1320 damage scenarios. Both the presence of damage and its location were detected up to an accuracy of 94.8% using the best performing model of the selected network when tested for independent signals. The K-fold cross-validation accuracy of the selected network is estimated to be 91.7%. The presence of damage itself was detected with an accuracy of 99.9% based on the cross-validation regardless of the damage location. Structural damage detection using deep learning is not restricted by the assumptions of the systems or the environmental conditions as the networks learn the system directly from the data. The framework can be applied to various types of civil and offshore structures. Furthermore, the sequence-based modeling enables engineers to harness the vast amounts of digital information to improve the safety of structures.

Multi-PLI: interpretable multi\u2010task deep learning model for unifying protein\u2013ligand interaction datasets

The assessment of protein–ligand interactions is critical at early stage of drug discovery. Computational approaches for efficiently predicting such interactions facilitate drug development. Recently, methods based on deep learning, including structure- and sequence-based models, have achieved impressive performance on several different datasets. However, their application still suffers from a generalizability issue because of insufficient data, especially for structure based models, as well as a heterogeneity problem because of different label measurements and varying proteins across datasets. Here, we present an interpretable multi-task model to evaluate protein–ligand interaction (Multi-PLI). The model can run classification (binding or not) and regression (binding affinity) tasks concurrently by unifying different datasets. The model outperforms traditional docking and machine learning on both binary classification and regression tasks and achieves competitive results compared with some structure-based deep learning methods, even with the same training set size. Furthermore, combined with the proposed occlusion algorithm, the model can predict the important amino acids of proteins that are crucial for binding, thus providing a biological interpretation.

Impact of Structural Observables From Simulations to Predict the Effect of Single-Point Mutations in MHC Class II Peptide Binders

The prediction of peptide binders to Major Histocompatibility Complex (MHC) class II receptors is of great interest to study autoimmune diseases and for vaccine development. Most approaches predict the affinities using sequence-based models trained on experimental data and multiple alignments from known peptide substrates. However, detecting activity differences caused by single-point mutations is a challenging task. In this work, we used interactions calculated from simulations to build scoring matrices for quickly estimating binding differences by single-point mutations. We modelled a set of 837 peptides bound to an MHC class II allele, and optimized the sampling of the conformations using the Rosetta backrub method by comparing the results to molecular dynamics simulations. From the dynamic trajectories of each complex, we averaged and compared structural observables for each amino acid at each position of the 9°mer peptide core region. With this information, we generated the scoring-matrices to predict the sign of the binding differences. We then compared the performance of the best scoring-matrix to different computational methodologies that range in computational costs. Overall, the prediction of the activity differences caused by single mutated peptides was lower than 60% for all the methods. However, the developed scoring-matrix in combination with existing methods reports an increase in the performance, up to 86% with a scoring method that uses molecular dynamics.

Orca: Sequence-based modeling of genome 3D architecture from kilobase to chromosome-scale (Part3)

Orca: Sequence-based modeling of genome 3D architecture from kilobase to chromosome-scale (Part3)

A Novel Position-Specific Encoding Algorithm (SeqPose) of Nucleotide Sequences and Its Application for Detecting Enhancers.

Enhancers are short genomic regions exerting tissue-specific regulatory roles, usually for remote coding regions. Enhancers are observed in both prokaryotic and eukaryotic genomes, and their detections facilitate a better understanding of the transcriptional regulation mechanism. The accurate detection and transcriptional regulation strength evaluation of the enhancers remain a major bioinformatics challenge. Most of the current studies utilized the statistical features of short fixed-length nucleotide sequences. This study introduces the location information of each k-mer (SeqPose) into the encoding strategy of a DNA sequence and employs the attention mechanism in the two-layer bi-directional long-short term memory (BD-LSTM) model (spEnhancer) for the enhancer detection problem. The first layer of the delivered classifier discriminates between enhancers and non-enhancers, and the second layer evaluates the transcriptional regulation strength of the detected enhancer. The SeqPose-encoded features are selected by the Chi-squared test, and 45 positions are removed from further analysis. The existing studies may focus on selecting the statistical DNA sequence descriptors with large contributions to the prediction models. This study does not utilize these statistical DNA sequence descriptors. Then the word vector of the SeqPose-encoded features is obtained by using the word embedding layer. This study hypothesizes that different word vector features may contribute differently to the enhancer detection model, and assigns different weights to these word vectors through the attention mechanism in the BD-LSTM model. The previous study generously provided the training and independent test datasets, and the proposed spEnhancer is compared with the three existing state-of-the-art studies using the same experimental procedure. The leave-one-out validation data on the training dataset shows that the proposed spEnhancer achieves similar detection performances as the three existing studies. While spEnhancer achieves the best overall performance metric MCC for both of the two binary classification problems on the independent test dataset. The experimental data shows that the strategy of removing redundant positions (SeqPose) may help improve the DNA sequence-based prediction models. spEnhancer may serve well as a complementary model to the existing studies, especially for the novel query enhancers that are not included in the training dataset.

Biomedical cross-sentence relation extraction via multihead attention and graph convolutional networks

Most biomedical information extraction efforts are focused on binary relations, there is a strong need to extract drug–gene–mutation n-ary relations among cross-sentences. In recent years, end-to-end biomedical relation extraction with sequence-based or dependency-based method has gained increasing attention. However, handling global dependencies and structural information remains challenges for sequence-based and dependency-based models. Joint exploitation of sequence and graph information may improve biomedical cross-sentence relation extraction. In this paper, we present a hybrid model for extracting biomedical relation in a cross-sentence which aims to address these problems. Our models rely on the self-attention mechanism that directly draws the global dependency relation of the sentence. Furthermore, to preserve the dependency structural information between the words that contain the syntactic dependency relations, we employ graph convolutional networks that encode the dependency structural information to guide the multihead attention to learn the dependency relation. Through extensive experiments on benchmark datasets, we demonstrated the effectiveness of our method.

A sequence-based deep learning approach to predict CTCF-mediated chromatin loop

Three-dimensional (3D) architecture of the chromosomes is of crucial importance for transcription regulation and DNA replication. Various high-throughput chromosome conformation capture-based methods have revealed that CTCF-mediated chromatin loops are a major component of 3D architecture. However, CTCF-mediated chromatin loops are cell type specific, and most chromatin interaction capture techniques are time-consuming and labor-intensive, which restricts their usage on a very large number of cell types. Genomic sequence-based computational models are sophisticated enough to capture important features of chromatin architecture and help to identify chromatin loops. In this work, we develop Deep-loop, a convolutional neural network model, to integrate k-tuple nucleotide frequency component, nucleotide pair spectrum encoding, position conservation, position scoring function and natural vector features for the prediction of chromatin loops. By a series of examination based on cross-validation, Deep-loop shows excellent performance in the identification of the chromatin loops from different cell types. The source code of Deep-loop is freely available at the repository https://github.com/linDing-group/Deep-loop.

A sequence-based and context modelling framework for recommendation

Since the last decade, data collection is becoming more pervasive, passive and easier to perform. This is resulting in the rise of data wherein a user performs some activities in a sequence, such as locations visited, physical activities performed, and modes of transport taken. In such cases, activities are often performed in a particular order, and each activity in turn may influence the subsequent activities to be performed. Moreover, such activities may be associated with multiple features or contexts, such as location, time, weather, etc. The order encoded in such data, along with the context, capture important information when it comes to modelling the preferences and personal habits of users. Traditional recommender systems, however, typically do not consider the order in which users perform activities and there is little work which considers both sequence and context simultaneously. In this work, a generic recommendation framework is proposed which leverages both sequences and context in user activity data for activity recommendation. To model user activities, a semantic view of the user’s past activities as a timeline of activity objects is presented. An essential step in the recommendation process is finding patterns in past activities performed which are closely aligned to the recent activities undertaken by the user. To calculate the distance between timelines, a novel two-level distance metric is presented which calculates distance with respect to the order of the activities as well as the context features associated with each activity occurrence. The efficacy of the proposed activity recommendation framework in various recommendation scenarios, is demonstrated using real-world datasets from multiple domains.

Motif-Raptor: a cell type-specific and transcription factor centric approach for post-GWAS prioritization of causal regulators.

Genome-wide association studies (GWASs) have identified thousands of common trait-associated genetic variants but interpretation of their function remains challenging. These genetic variants can overlap the binding sites of transcription factors (TFs) and therefore could alter gene expression. However, we currently lack a systematic understanding on how this mechanism contributes to phenotype. We present Motif-Raptor, a TF-centric computational tool that integrates sequence-based predictive models, chromatin accessibility, gene expression datasets and GWAS summary statistics to systematically investigate how TF function is affected by genetic variants. Given trait-associated non-coding variants, Motif-Raptor can recover relevant cell types and critical TFs to drive hypotheses regarding their mechanism of action. We tested Motif-Raptor on complex traits such as rheumatoid arthritis and red blood cell count and demonstrated its ability to prioritize relevant cell types, potential regulatory TFs and non-coding SNPs which have been previously characterized and validated. Motif-Raptor is freely available as a Python package at: https://github.com/pinellolab/MotifRaptor. Supplementary data are available at Bioinformatics online.

Sequence-Based Selection Hyper-Heuristic Model via MAP-Elites

Although the number of solutions in combinatorial optimization problems (COPs) is finite, some problems grow exponentially and render exact approaches unfeasible. So, approximate methods, such as heuristics, are customary. Each heuristic usually specializes in specific kinds of problems. Hence, other approaches seek to merge their strengths. One of them is selection hyper-heuristics. However, they usually provide scarce information about their sensitivity. Illumination algorithms may fix this issue since they focus on exploration rather than exploitation while preserving the best solutions under different criteria. Still, literature falls short when merging both approaches, representing a knowledge gap. This work tests the feasibility of using an illumination algorithm, MAP-Elites (ME), for tuning a sequence-based selection hyper-heuristic model for Balanced Partition problems. We choose ME since other researchers have successfully applied it to a different COP. So, we may achieve a hyper-heuristic that represents the best combination of heuristics while simultaneously gaining intel on the performance of diverse alternatives. Our approach operates by creating a multi-dimensional map, where each design variable represents the application of a heuristic. Afterward, ME generates mutated sequences and tests them to determine if they represent a better-performing solution. We consider 1500 instances that include easy and hard instances, analyzed under different scenarios to test our approach. We also include limit instances that are neither easy nor hard. Our resulting data support the proposed approach, as it performs toe-to-toe with a synthetic oracle and may even outperform it. This represents an outstanding result, since a brute-force approach is needed to achieve such an oracle. So, merging ME and hyper-heuristics is a path worth pursuing. We also present how each parameter affects the model performance and identify the critical and virtually irrelevant ones. This serves as the groundwork for future works that focus on exploiting the most relevant parameters.

Genome-wide analysis of DNA uptake across the outer membrane of naturally competent Haemophilus influenzae

SummaryThe genomes of naturally competent Pasteurellaceae and Neisseriaceae have many short uptake sequences (USS), which allow them to distinguish self-DNA from foreign DNA. To fully characterize this preference we developed genome-wide maps of DNA uptake using both a sequence-based computational model and genomic DNA that had been sequenced after uptake by and recovery from competent Haemophilus influenzae cells. When DNA fragments were shorter than the average USS spacing of ∼1,000 bp, sharp peaks of uptake were centered at USS and separated by valleys with 1000-fold lower uptake. Long DNA fragments (1.5–17 kb) gave much less variation, with 90% of positions having uptake within 2-fold of the mean. All detectable uptake biases arose from sequences that fit the USS uptake motif. Simulated competition predicted that, in its respiratory tract environment, H. influenzae will efficiently take up its own DNA even when human DNA is present in 100-fold excess.

Modeling the minus two base pair stutter ratio of the D1S1656 locus: A sequence-based mixture distribution model

In this study, we propose a stutter ratio for a minus two base pair stutter (-2bpSR) model of the D1S1656 locus in capillary electrophoresis (CE)-based short tandem repeat (STR) typing. DNA from a total of 108 Japanese individuals was analyzed via massively parallel sequencing to investigate the length of the longest uninterrupted stretch of two base repeat motif (2bpLUS value) within repetitive structures involving the flanking region. Additionally, -2bpSR data was collected using the GlobalFiler Kit on a 3500xL Genetic Analyzer. As a result of sequencing analysis, all alleles were classified into two types by their 2bpLUS values. The -2bpSR differed significantly between the types. Then, we modeled the -2bpSR with a mixture log-normal distribution using the classification of alleles based on the 2bpLUS values. Furthermore, probabilities of the sequence type within each repeat number in the mixture log-normal distribution model were estimated using logistic regression for each of the five major detected populations. This study is expected to enable interpretation of STR typing while considering minus two base pair stutter at the D1S1656 locus.

Effectiveness of multi-gated sequence model for the learning of kinematics and dynamics of an industrial robot

Purpose For efficient trajectory control of industrial robots, a cumbersome computation for inverse kinematics and inverse dynamics is needed, which is usually developed using spatial transformation using Denavit–Hartenberg principle and Lagrangian or Newton–Euler methods, respectively. The model is highly non-linear and needs to deal with uncertainties because of lack of accurate measurement of mechanical parameters, noise and non-inclusion of joint friction, which results in some inaccuracies in predicting accurate torque trajectories. To get a guaranteed closed form solution, the robot designers normally follow Pieper’s recommendation and compromise with the mechanical design. While this may be acceptable for the industrial robots where the aesthetic look is not that important, it is not for humanoid and social robots. To help solve this problem, this study aims to propose an alternative machine learning-based computational approach based on a multi-gated sequence model for finding appropriate mapping between Cartesian space to joint space and motion space to joint torque space. Design/methodology/approach First, the authors generate sufficient data required for the sequence model, using forward kinematics and forward dynamics by running N number of nested loops, where N is the number of joints of the robot. Subsequently, to develop a learning-based model based on sequence analysis, the authors propose to use long short-term memory (LSTM) and hence, train an LSTM model, the architecture details of which have been discussed in the paper. To make LSTM learning algorithms perform efficiently, the authors need to detect and eliminate redundant features from the data set, which the authors propose to do using an elegant statistical tool called Pearson coefficient. Findings To validate the proposed model, the authors have performed rigorous experiments using both hardware and simulation robots (Baxter/Anukul robot) available in their laboratory and KUKA simulation robot data set made available from Neural Learning for Robotics Laboratory. Through several characteristic plots, it has been shown that a sequence-based LSTM model of deep learning architecture with non-redundant features could help the robots to learn smooth and accurate trajectories more quickly compared to data sets having redundancy. Such data-driven modeling techniques can change the future course of direction of robotics research for solving the classical problems such as trajectory planning and motion planning for manipulating industrial as well as social humanoid robots. Originality/value The present investigation involves development of deep learning-based computation model, statistical analyses to eliminate redundant features, data creation from one hardware robot (Anukul) and one simulation robot model (KUKA), rigorously training and testing separately two computational models (specially configured two LSTM models) – one for learning inverse kinematics and one for learning inverse dynamics problem – and comparison of the inverse dynamics model with the state-of-the-art model. Hence, the authors strongly believe that the present paper is compact and complete to get published in a reputed journal so that dissemination of new ideas can benefit the researchers in the area of robotics.

Identification of L-asparaginases from Streptomyces strains with competitive activity and immunogenic profiles: a bioinformatic approach

The enzyme L-asparaginase from Escherichia coli is a therapeutic enzyme that has been a cornerstone in the clinical treatment of acute lymphoblastic leukemia for the last decades. However, treatment effectiveness is limited by the highly immunogenic nature of the protein and its cross-reactivity towards L-glutamine. In this work, a bioinformatic approach was used to identify, select and computationally characterize L-asparaginases from Streptomyces through sequence-based screening analyses, immunoinformatics, homology modeling, and molecular docking studies. Based on its predicted low immunogenicity and excellent enzymatic activity, we selected a previously uncharacterized L-asparaginase from Streptomyces scabrisporus. Furthermore, two putative asparaginase binding sites were identified and a 3D model is proposed. These promising features allow us to propose L-asparaginase from S. scabrisporus as an alternative for the treatment of acute lymphocytic leukemia.

Fungal assemblages in predictive stream bioassessment: A cross-taxon comparison along multiple stressor gradients

Degradation of freshwater ecosystems requires efficient tools for assessing the ecological status of freshwater biota and identifying potential cause(s) for their biological degradation. While diatoms and macroinvertebrates are widely used in stream bioassessment, the potential utility of microbial communities has not been fully harnessed. Using data from 113 Finnish streams, we assessed the performance of aquatic leaf-associated fungal decomposers, relative to benthic macroinvertebrates and diatoms, in modelling-based bioassessment. We built multi-taxon niche -type predictive models for fungal assemblages by using genus-based and sequence-based identification levels. We then compared the models’ precision and accuracy in the prediction of reference conditions (number of native taxa) to corresponding models for macroinvertebrates and diatoms. Genus-based fungal model nearly equalled the accuracy and precision of our best model (macroinvertebrates), whereas the sequence-based model was less accurate and tended to overestimate the number of taxa. However, when the models were applied to streams disturbed by anthropogenic stressors (nutrient enrichment, sedimentation and acidification), alone or in combination, the sequence-based fungal assemblages were more sensitive than other taxonomic groups, especially when multiple stressors were present. Microbial leaf decomposition rates were elevated in sediment-stressed streams whereas decomposition attributable to leaf-shredding macroinvertebrates was accelerated by nutrients and decelerated by sedimentation. Comparison of leaf decomposition results to model output suggested that leaf decomposition rates do not detect effectively the presence of multiple simultaneous disturbances. The rapid development of global microbial database may soon enable species-level identification of leaf-associated fungi, facilitating a more precise and accurate modelling of reference conditions in streams using fungal communities. This development, combined with the sensitivity of aquatic fungi in detecting the presence of multiple human disturbances, makes leaf-associated fungal assemblages an indispensable addition in a stream ecologist’s toolbox.

Ehrlichia chaffeensis and E. canis hypothetical protein immunoanalysis reveals small secreted immunodominant proteins and conformation-dependent antibody epitopes

Immunomolecular characterization of Ehrlichia chaffeensis (E. ch.) and E. canis (E. ca.) has defined protein orthologs, including tandem repeat proteins (TRPs) that have immunodominant linear antibody epitopes. In this study, we combined bioinformatic analysis and cell-free protein expression to identify undiscovered immunoreactive E. ch. and E. ca. hypothetical proteins. Antigenicity of the E. ch. and E. ca. ORFeomes (n = 1105 and n = 925, respectively) was analyzed by the sequence-based prediction model ANTIGENpro, and we identified ~250 ORFs in each respective ORFeome as highly antigenic. The hypothetical proteins (E. ch. n = 93 and E. ca. n = 98) present in the top 250 antigenic ORFs were further investigated in this study. By ELISA, 46 E. ch. and 30 E. ca. IVTT-expressed hypothetical proteins reacted with antibodies in sera from naturally E. ch.-infected patients or E. ca.-infected dogs. Moreover, 15 E. ch. and 16 E. ca. proteins consistently reacted with a panel of sera from patients or dogs, including many that revealed the immunoreactivity of “gold standard” TRPs. Antibody epitopes in most (>70%) of these proteins exhibited partial or complete conformation-dependence. The majority (23/31; 74%) of the major immunoreactive proteins identified were small (≤250 aa), and 20/31 (65%) were predicted to be secreted effectors. Unlike the strong linear antibody epitopes previously identified in TRP and OMP orthologs, there were contrasting differences in the E. ch. and E. ca. antigenic repertoires, epitopes and ortholog immunoreactivity. This study reveals numerous previously undefined immunodominant and subdominant antigens, and illustrates the breadth, complexity, and diversity of immunoreactive proteins/epitopes in Ehrlichia.

An evolution-based model for designing chorismate mutase enzymes.

The rational design of enzymes is an important goal for both fundamental and practical reasons. Here, we describe a process to learn the constraints for specifying proteins purely from evolutionary sequence data, design and build libraries of synthetic genes, and test them for activity in vivo using a quantitative complementation assay. For chorismate mutase, a key enzyme in the biosynthesis of aromatic amino acids, we demonstrate the design of natural-like catalytic function with substantial sequence diversity. Further optimization focuses the generative model toward function in a specific genomic context. The data show that sequence-based statistical models suffice to specify proteins and provide access to an enormous space of functional sequences. This result provides a foundation for a general process for evolution-based design of artificial proteins.

Flexible job shop scheduling problem with reconfigurable machine tools: An improved differential evolution algorithm

Developing reconfigurable machine tools (RMTs) has attracted increasing attention recently. An RMT can be utilized as a group of machines, which can obtain different configurations to satisfy manufacturing requirements. This paper deals with a production scheduling problem in a shop-floor with RMTs as an extension of a flexible job shop scheduling problem (FJSSP). To begin with, two mixed-integer linear programming models with the position- and sequence-based decision variables are formulated to minimize the maximum completion time (i.e., makespan). The CPLEX solver is used to solve the small- and medium-sized instances. The computational experiments show that the sequence-based model significantly outperforms the other one. Since even the sequence-based model cannot optimally solve most of the medium-sized problems, a self-adaptive differential evolution (DE) algorithm is proposed to efficiently solve the given problem. Moreover, the effectiveness of the proposed algorithm is enhanced by introducing a new mutation strategy based on a searching approach hired from a Nelder–Mead method. The performance of the proposed method and three other well-known variants of the DE algorithm are first validated by comparing their results with the results of the sequence-based model. Additional experiments on another data set including large-sized problems also confirm that the proposed algorithm is extremely efficient and effective.

TransformerCPI: improving compound-protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments.

Identifying compound-protein interaction (CPI) is a crucial task in drug discovery and chemogenomics studies, and proteins without three-dimensional structure account for a large part of potential biological targets, which requires developing methods using only protein sequence information to predict CPI. However, sequence-based CPI models may face some specific pitfalls, including using inappropriate datasets, hidden ligand bias and splitting datasets inappropriately, resulting in overestimation of their prediction performance. To address these issues, we here constructed new datasets specific for CPI prediction, proposed a novel transformer neural network named TransformerCPI, and introduced a more rigorous label reversal experiment to test whether a model learns true interaction features. TransformerCPI achieved much improved performance on the new experiments, and it can be deconvolved to highlight important interacting regions of protein sequences and compound atoms, which may contribute chemical biology studies with useful guidance for further ligand structural optimization. https://github.com/lifanchen-simm/transformerCPI.

Multi-task learning sparse group lasso: a method for quantifying antigenicity of influenza A(H1N1) virus using mutations and variations in glycosylation of Hemagglutinin

BackgroundIn addition to causing the pandemic influenza outbreaks of 1918 and 2009, subtype H1N1 influenza A viruses (IAVs) have caused seasonal epidemics since 1977. Antigenic property of influenza viruses are determined by both protein sequence and N-linked glycosylation of influenza glycoproteins, especially hemagglutinin (HA). The currently available computational methods are only considered features in protein sequence but not N-linked glycosylation.ResultsA multi-task learning sparse group least absolute shrinkage and selection operator (LASSO) (MTL-SGL) regression method was developed and applied to derive two types of predominant features including protein sequence and N-linked glycosylation in hemagglutinin (HA) affecting variations in serologic data for human and swine H1N1 IAVs. Results suggested that mutations and changes in N-linked glycosylation sites are associated with the rise of antigenic variants of H1N1 IAVs. Furthermore, the implicated mutations are predominantly located at five reported antibody-binding sites, and within or close to the HA receptor binding site. All of the three N-linked glycosylation sites (i.e. sequons NCSV at HA 54, NHTV at HA 125, and NLSK at HA 160) identified by MTL-SGL to determine antigenic changes were experimentally validated in the H1N1 antigenic variants using mass spectrometry analyses. Compared with conventional sparse learning methods, MTL-SGL achieved a lower prediction error and higher accuracy, indicating that grouped features and MTL in the MTL-SGL method are not only able to handle serologic data generated from multiple reagents, supplies, and protocols, but also perform better in genetic sequence-based antigenic quantification.ConclusionsIn summary, the results of this study suggest that mutations and variations in N-glycosylation in HA caused antigenic variations in H1N1 IAVs and that the sequence-based antigenicity predictive model will be useful in understanding antigenic evolution of IAVs.