Phen2Disease: a phenotype-driven model for disease and gene prioritization by bidirectional maximum matching semantic similarities.

Human Phenotype Ontology (HPO)-based approaches have gained popularity in recent times as a tool for genomic diagnostics of rare diseases. However, these approaches do not make full use of the available information on disease and patient phenotypes. We present a new method called Phen2Disease, which utilizes the bidirectional maximum matching semantic similarity between two phenotype sets of patients and diseases to prioritize diseases and genes. Our comprehensive experiments have been conducted on six real data cohorts with 2051 cases (Cohort 1, n = 384; Cohort 2, n = 281; Cohort 3, n = 185; Cohort 4, n = 784; Cohort 5, n = 208; and Cohort 6, n = 209) and two simulated data cohorts with 1000 cases. The results of the experiments showed that Phen2Disease outperforms the three state-of-the-art methods when only phenotype information and HPO knowledge base are used, particularly in cohorts with fewer average numbers of HPO terms. We also observed that patients with higher information content scores have more specific information, leading to more accurate predictions. Moreover, Phen2Disease provides high interpretability with ranked diseases and patient HPO terms presented. Our method provides a novel approach to utilizing phenotype data for genomic diagnostics of rare diseases, with potential for clinical impact. Phen2Disease is freely available on GitHub at https://github.com/ZhuLab-Fudan/Phen2Disease.

META-DDIE: predicting drug-drug interaction events with few-shot learning.

Drug-drug interactions (DDIs) are one of the major concerns in pharmaceutical research, and a number of computational methods have been developed to predict whether two drugs interact or not. Recently, more attention has been paid to events caused by the DDIs, which is more useful for investigating the mechanism hidden behind the combined drug usage or adverse reactions. However, some rare events may only have few examples, hindering them from being precisely predicted. To address the above issues, we present a few-shot computational method named META-DDIE, which consists of a representation module and a comparing module, to predict DDI events. We collect drug chemical structures and DDIs from DrugBank, and categorize DDI events into hundreds of types using a standard pipeline. META-DDIE uses the structures of drugs as input and learns the interpretable representations of DDIs through the representation module. Then, the model uses the comparing module to predict whether two representations are similar, and finally predicts DDI events with few labeled examples. In the computational experiments, META-DDIE outperforms several baseline methods and especially enhances the predictive capability for rare events. Moreover, META-DDIE helps to identify the key factors that may cause DDI events and reveal the relationship among different events.

DeepMHCI: an anchor position-aware deep interaction model for accurate MHC-I peptide binding affinity prediction.

MOTIVATION: Computationally predicting major histocompatibility complex class I (MHC-I) peptide binding affinity is an important problem in immunological bioinformatics, which is also crucial for the identification of neoantigens for personalized therapeutic cancer vaccines. Recent cutting-edge deep learning-based methods for this problem cannot achieve satisfactory performance, especially for non-9-mer peptides. This is because such methods generate the input by simply concatenating the two given sequences: a peptide and (the pseudo sequence of) an MHC class I molecule, which cannot precisely capture the anchor positions of the MHC binding motif for the peptides with variable lengths. We thus developed an anchor position-aware and high-performance deep model, DeepMHCI, with a position-wise gated layer and a residual binding interaction convolution layer. This allows the model to control the information flow in peptides to be aware of anchor positions and model the interactions between peptides and the MHC pseudo (binding) sequence directly with multiple convolutional kernels. RESULTS: The performance of DeepMHCI has been thoroughly validated by extensive experiments on four benchmark datasets under various settings, such as 5-fold cross-validation, validation with the independent testing set, external HPV vaccine identification, and external CD8+ epitope identification. Experimental results with visualization of binding motifs demonstrate that DeepMHCI outperformed all competing methods, especially on non-9-mer peptides binding prediction. AVAILABILITY AND IMPLEMENTATION: DeepMHCI is publicly available at https://github.com/ZhuLab-Fudan/DeepMHCI.

Sc2Mol: a scaffold-based two-step molecule generator with variational autoencoder and transformer.

MOTIVATION: Finding molecules with desired pharmaceutical properties is crucial in drug discovery. Generative models can be an efficient tool to find desired molecules through the distribution learned by the model to approximate given training data. Existing generative models (i) do not consider backbone structures (scaffolds), resulting in inefficiency or (ii) need prior patterns for scaffolds, causing bias. Scaffolds are reasonable to use, and it is imperative to design a generative model without any prior scaffold patterns. RESULTS: We propose a generative model-based molecule generator, Sc2Mol, without any prior scaffold patterns. Sc2Mol uses SMILES strings for molecules. It consists of two steps: scaffold generation and scaffold decoration, which are carried out by a variational autoencoder and a transformer, respectively. The two steps are powerful for implementing random molecule generation and scaffold optimization. Our empirical evaluation using drug-like molecule datasets confirmed the success of our model in distribution learning and molecule optimization. Also, our model could automatically learn the rules to transform coarse scaffolds into sophisticated drug candidates. These rules were consistent with those for current lead optimization. AVAILABILITY AND IMPLEMENTATION: The code is available at https://github.com/zhiruiliao/Sc2Mol. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

HPODNets: deep graph convolutional networks for predicting human protein-phenotype associations.

MOTIVATION: Deciphering the relationship between human genes/proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment against diseases. The Human Phenotype Ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human disorders. However, the current HPO annotations are still incomplete. Thus, it is necessary to computationally predict human protein-phenotype associations. In terms of current, cutting-edge computational methods for annotating proteins (such as functional annotation), three important features are (i) multiple network input, (ii) semi-supervised learning and (iii) deep graph convolutional network (GCN), whereas there are no methods with all these features for predicting HPO annotations of human protein. RESULTS: We develop HPODNets with all above three features for predicting human protein-phenotype associations. HPODNets adopts a deep GCN with eight layers which allows to capture high-order topological information from multiple interaction networks. Empirical results with both cross-validation and temporal validation demonstrate that HPODNets outperforms seven competing state-of-the-art methods for protein function prediction. HPODNets with the architecture of deep GCNs is confirmed to be effective for predicting HPO annotations of human protein and, more generally, node label ranking problem with multiple biomolecular networks input in bioinformatics. AVAILABILITY AND IMPLEMENTATION: https://github.com/liulizhi1996/HPODNets. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DeepMHCII: a novel binding core-aware deep interaction model for accurate MHC-II peptide binding affinity prediction.

MOTIVATION: Computationally predicting major histocompatibility complex (MHC)-peptide binding affinity is an important problem in immunological bioinformatics. Recent cutting-edge deep learning-based methods for this problem are unable to achieve satisfactory performance for MHC class II molecules. This is because such methods generate the input by simply concatenating the two given sequences: (the estimated binding core of) a peptide and (the pseudo sequence of) an MHC class II molecule, ignoring biological knowledge behind the interactions of the two molecules. We thus propose a binding core-aware deep learning-based model, DeepMHCII, with a binding interaction convolution layer, which allows to integrate all potential binding cores (in a given peptide) with the MHC pseudo (binding) sequence, through modeling the interaction with multiple convolutional kernels. RESULTS: Extensive empirical experiments with four large-scale datasets demonstrate that DeepMHCII significantly outperformed four state-of-the-art methods under numerous settings, such as 5-fold cross-validation, leave one molecule out, validation with independent testing sets and binding core prediction. All these results and visualization of the predicted binding cores indicate the effectiveness of our model, DeepMHCII, and the importance of properly modeling biological facts in deep learning for high predictive performance and efficient knowledge discovery. AVAILABILITY AND IMPLEMENTATION: DeepMHCII is publicly available at https://github.com/yourh/DeepMHCII. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

NetGO 2.0: improving large-scale protein function prediction with massive sequence, text, domain, family and network information.

With the explosive growth of protein sequences, large-scale automated protein function prediction (AFP) is becoming challenging. A protein is usually associated with dozens of gene ontology (GO) terms. Therefore, AFP is regarded as a problem of large-scale multi-label classification. Under the learning to rank (LTR) framework, our previous NetGO tool integrated massive networks and multi-type information about protein sequences to achieve good performance by dealing with all possible GO terms (>44 000). In this work, we propose the updated version as NetGO 2.0, which further improves the performance of large-scale AFP. NetGO 2.0 also incorporates literature information by logistic regression and deep sequence information by recurrent neural network (RNN) into the framework. We generate datasets following the critical assessment of functional annotation (CAFA) protocol. Experiment results show that NetGO 2.0 outperformed NetGO significantly in biological process ontology (BPO) and cellular component ontology (CCO). In particular, NetGO 2.0 achieved a 12.6% improvement over NetGO in terms of area under precision-recall curve (AUPR) in BPO and around 2.6% in terms of $\mathbf {F_{max}}$ in CCO. These results demonstrate the benefits of incorporating text and deep sequence information for the functional annotation of BPO and CCO. The NetGO 2.0 web server is freely available at http://issubmission.sjtu.edu.cn/ng2/.

Assessment of metagenomic assemblers based on hybrid reads of real and simulated metagenomic sequences.

In metagenomic studies of microbial communities, the short reads come from mixtures of genomes. Read assembly is usually an essential first step for the follow-up studies in metagenomic research. Understanding the power and limitations of various read assembly programs in practice is important for researchers to choose which programs to use in their investigations. Many studies evaluating different assembly programs used either simulated metagenomes or real metagenomes with unknown genome compositions. However, the simulated datasets may not reflect the real complexities of metagenomic samples and the estimated assembly accuracy could be misleading due to the unknown genomes in real metagenomes. Therefore, hybrid strategies are required to evaluate the various read assemblers for metagenomic studies. In this paper, we benchmark the metagenomic read assemblers by mixing reads from real metagenomic datasets with reads from known genomes and evaluating the integrity, contiguity and accuracy of the assembly using the reads from the known genomes. We selected four advanced metagenome assemblers, MEGAHIT, MetaSPAdes, IDBA-UD and Faucet, for evaluation. We showed the strengths and weaknesses of these assemblers in terms of integrity, contiguity and accuracy for different variables, including the genetic difference of the real genomes with the genome sequences in the real metagenomic datasets and the sequencing depth of the simulated datasets. Overall, MetaSPAdes performs best in terms of integrity and continuity at the species-level, followed by MEGAHIT. Faucet performs best in terms of accuracy at the cost of worst integrity and continuity, especially at low sequencing depth. MEGAHIT has the highest genome fractions at the strain-level and MetaSPAdes has the overall best performance at the strain-level. MEGAHIT is the most efficient in our experiments. Availability: The source code is available at https://github.com/ziyewang/MetaAssemblyEval.

DeepGraphGO: graph neural network for large-scale, multispecies protein function prediction.

MOTIVATION: Automated function prediction (AFP) of proteins is a large-scale multi-label classification problem. Two limitations of most network-based methods for AFP are (i) a single model must be trained for each species and (ii) protein sequence information is totally ignored. These limitations cause weaker performance than sequence-based methods. Thus, the challenge is how to develop a powerful network-based method for AFP to overcome these limitations. RESULTS: We propose DeepGraphGO, an end-to-end, multispecies graph neural network-based method for AFP, which makes the most of both protein sequence and high-order protein network information. Our multispecies strategy allows one single model to be trained for all species, indicating a larger number of training samples than existing methods. Extensive experiments with a large-scale dataset show that DeepGraphGO outperforms a number of competing state-of-the-art methods significantly, including DeepGOPlus and three representative network-based methods: GeneMANIA, deepNF and clusDCA. We further confirm the effectiveness of our multispecies strategy and the advantage of DeepGraphGO over so-called difficult proteins. Finally, we integrate DeepGraphGO into the state-of-the-art ensemble method, NetGO, as a component and achieve a further performance improvement. AVAILABILITY AND IMPLEMENTATION: https://github.com/yourh/DeepGraphGO. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

HPOFiller: identifying missing protein-phenotype associations by graph convolutional network.

MOTIVATION: Exploring the relationship between human proteins and abnormal phenotypes is of great importance in the prevention, diagnosis and treatment of diseases. The human phenotype ontology (HPO) is a standardized vocabulary that describes the phenotype abnormalities encountered in human diseases. However, the current HPO annotations of proteins are not complete. Thus, it is important to identify missing protein-phenotype associations. RESULTS: We propose HPOFiller, a graph convolutional network (GCN)-based approach, for predicting missing HPO annotations. HPOFiller has two key GCN components for capturing embeddings from complex network structures: (i) S-GCN for both protein-protein interaction network and HPO semantic similarity network to utilize network weights; (ii) Bi-GCN for the protein-phenotype bipartite graph to conduct message passing between proteins and phenotypes. The core idea of HPOFiller is to repeat run these two GCN modules consecutively over the three networks, to refine the embeddings. Empirical results of extremely stringent evaluation avoiding potential information leakage including cross-validation and temporal validation demonstrates that HPOFiller significantly outperforms all other state-of-the-art methods. In particular, the ablation study shows that batch normalization contributes the most to the performance. The further examination offers literature evidence for highly ranked predictions. Finally using known disease-HPO term associations, HPOFiller could suggest promising, unknown disease-gene associations, presenting possible genetic causes of human disorders. AVAILABILITYAND IMPLEMENTATION: https://github.com/liulizhi1996/HPOFiller. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BERTMeSH: deep contextual representation learning for large-scale high-performance MeSH indexing with full text.

MOTIVATION: With the rapid increase of biomedical articles, large-scale automatic Medical Subject Headings (MeSH) indexing has become increasingly important. FullMeSH, the only method for large-scale MeSH indexing with full text, suffers from three major drawbacks: FullMeSH (i) uses Learning To Rank, which is time-consuming, (ii) can capture some pre-defined sections only in full text and (iii) ignores the whole MEDLINE database. RESULTS: We propose a computationally lighter, full text and deep-learning-based MeSH indexing method, BERTMeSH, which is flexible for section organization in full text. BERTMeSH has two technologies: (i) the state-of-the-art pre-trained deep contextual representation, Bidirectional Encoder Representations from Transformers (BERT), which makes BERTMeSH capture deep semantics of full text. (ii) A transfer learning strategy for using both full text in PubMed Central (PMC) and title and abstract (only and no full text) in MEDLINE, to take advantages of both. In our experiments, BERTMeSH was pre-trained with 3 million MEDLINE citations and trained on ∼1.5 million full texts in PMC. BERTMeSH outperformed various cutting-edge baselines. For example, for 20 K test articles of PMC, BERTMeSH achieved a Micro F-measure of 69.2%, which was 6.3% higher than FullMeSH with the difference being statistically significant. Also prediction of 20 K test articles needed 5 min by BERTMeSH, while it took more than 10 h by FullMeSH, proving the computational efficiency of BERTMeSH. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

ICH-LR2S2: a new risk score for predicting stroke-associated pneumonia from spontaneous intracerebral hemorrhage.

PURPOSE: We develop a new risk score to predict patients with stroke-associated pneumonia (SAP) who have an acute intracranial hemorrhage (ICH). METHOD: We applied logistic regression to develop a new risk score called ICH-LR2S2. It was derived from examining a dataset of 70,540 ICH patients between 2015 and 2018 from the Chinese Stroke Center Alliance (CSCA). During the training of ICH-LR2S2, patients were randomly divided into two groups - 80% for the training set and 20% for model validation. A prospective test set was developed using 12,523 patients recruited in 2019. To further verify its effectiveness, we tested ICH-LR2S2 on an external dataset of 24,860 patients from the China National Stroke Registration Management System II (CNSR II). The performance of ICH-LR2S2 was measured by the area under the receiver operating characteristic curve (AUROC). RESULTS: The incidence of SAP in the dataset was 25.52%. A 24-point ICH-LR2S2 was developed from independent predictors, including age, modified Rankin Scale, fasting blood glucose, National Institutes of Health Stroke Scale admission score, Glasgow Coma Scale score, C-reactive protein, dysphagia, Chronic Obstructive Pulmonary Disease, and current smoking. The results showed that ICH-LR2S2 achieved an AUC = 0.749 [95% CI 0.739-0.759], which outperforms the best baseline ICH-APS (AUC = 0.704) [95% CI 0.694-0.714]. Compared with the previous ICH risk scores, ICH-LR2S2 incorporates fasting blood glucose and C-reactive protein, improving its discriminative ability. Machine learning methods such as XGboost (AUC = 0.772) [95% CI 0.762-0.782] can further improve our prediction performance. It also performed well when further validated by the external independent cohort of patients (n = 24,860), ICH-LR2S2 AUC = 0.784 [95% CI 0.774-0.794]. CONCLUSION: ICH-LR2S2 accurately distinguishes SAP patients based on easily available clinical features. It can help identify high-risk patients in the early stages of diseases.

Sparse logistic regression revealed the associations between HBV PreS quasispecies and hepatocellular carcinoma.

BACKGROUND: Chronic infection with hepatitis B virus (HBV) has been proved highly associated with the development of hepatocellular carcinoma (HCC). AIMS: The purpose of the study is to investigate the association between HBV preS region quasispecies and HCC development, as well as to develop HCC diagnosis model using HBV preS region quasispecies. METHODS: A total of 104 chronic hepatitis B (CHB) patients and 117 HBV-related HCC patients were enrolled. HBV preS region was sequenced using next generation sequencing (NGS) and the nucleotide entropy was calculated for quasispecies evaluation. Sparse logistic regression (SLR) was used to predict HCC development and prediction performances were evaluated using receiver operating characteristic curves. RESULTS: Entropy of HBV preS1, preS2 regions and several nucleotide points showed significant divergence between CHB and HCC patients. Using SLR, the classification of HCC/CHB groups achieved a mean area under the receiver operating characteristic curve (AUC) of 0.883 in the training data and 0.795 in the test data. The prediction model was also validated by a completely independent dataset from Hong Kong. The 10 selected nucleotide positions showed significantly different entropy between CHB and HCC patients. The HBV quasispecies also classified three clinical parameters, including HBeAg, HBVDNA, and Alkaline phosphatase (ALP) with the AUC value greater than 0.6 in the test data. CONCLUSIONS: Using NGS and SLR, the association between HBV preS region nucleotide entropy and HCC development was validated in our study and this could promote the understanding of HCC progression mechanism.

Using Quasispecies Patterns of Hepatitis B Virus to Predict Hepatocellular Carcinoma With Deep Sequencing and Machine Learning.

BACKGROUND: Hepatitis B virus (HBV) infection is one of the main leading causes of hepatocellular carcinoma (HCC) worldwide. However, it remains uncertain how the reverse-transcriptase (rt) gene contributes to HCC progression. METHODS: We enrolled a total of 307 patients with chronic hepatitis B (CHB) and 237 with HBV-related HCC from 13 medical centers. Sequence features comprised multidimensional attributes of rt nucleic acid and rt/s amino acid sequences. Machine-learning models were used to establish HCC predictive algorithms. Model performances were tested in the training and independent validation cohorts using receiver operating characteristic curves and calibration plots. RESULTS: A random forest (RF) model based on combined metrics (10 features) demonstrated the best predictive performances in both cross and independent validation (AUC, 0.96; accuracy, 0.90), irrespective of HBV genotypes and sequencing depth. Moreover, HCC risk scores for individuals obtained from the RF model (AUC, 0.966; 95% confidence interval, .922-.989) outperformed α-fetoprotein (0.713; .632-.784) in distinguishing between patients with HCC and those with CHB. CONCLUSIONS: Our study provides evidence for the first time that HBV rt sequences contain vital HBV quasispecies features in predicting HCC. Integrating deep sequencing with feature extraction and machine-learning models benefits the longitudinal surveillance of CHB and HCC risk assessment.

HPOLabeler: improving prediction of human protein-phenotype associations by learning to rank.

MOTIVATION: Annotating human proteins by abnormal phenotypes has become an important topic. Human Phenotype Ontology (HPO) is a standardized vocabulary of phenotypic abnormalities encountered in human diseases. As of November 2019, only <4000 proteins have been annotated with HPO. Thus, a computational approach for accurately predicting protein-HPO associations would be important, whereas no methods have outperformed a simple Naive approach in the second Critical Assessment of Functional Annotation, 2013-2014 (CAFA2). RESULTS: We present HPOLabeler, which is able to use a wide variety of evidence, such as protein-protein interaction (PPI) networks, Gene Ontology, InterPro, trigram frequency and HPO term frequency, in the framework of learning to rank (LTR). LTR has been proved to be powerful for solving large-scale, multi-label ranking problems in bioinformatics. Given an input protein, LTR outputs the ranked list of HPO terms from a series of input scores given to the candidate HPO terms by component learning models (logistic regression, nearest neighbor and a Naive method), which are trained from given multiple evidence. We empirically evaluate HPOLabeler extensively through mainly two experiments of cross validation and temporal validation, for which HPOLabeler significantly outperformed all component models and competing methods including the current state-of-the-art method. We further found that (i) PPI is most informative for prediction among diverse data sources and (ii) low prediction performance of temporal validation might be caused by incomplete annotation of new proteins. AVAILABILITY AND IMPLEMENTATION: http://issubmission.sjtu.edu.cn/hpolabeler/. CONTACT: zhusf@fudan.edu.cn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

FullMeSH: improving large-scale MeSH indexing with full text.

MOTIVATION: With the rapidly growing biomedical literature, automatically indexing biomedical articles by Medical Subject Heading (MeSH), namely MeSH indexing, has become increasingly important for facilitating hypothesis generation and knowledge discovery. Over the past years, many large-scale MeSH indexing approaches have been proposed, such as Medical Text Indexer, MeSHLabeler, DeepMeSH and MeSHProbeNet. However, the performance of these methods is hampered by using limited information, i.e. only the title and abstract of biomedical articles. RESULTS: We propose FullMeSH, a large-scale MeSH indexing method taking advantage of the recent increase in the availability of full text articles. Compared to DeepMeSH and other state-of-the-art methods, FullMeSH has three novelties: (i) Instead of using a full text as a whole, FullMeSH segments it into several sections with their normalized titles in order to distinguish their contributions to the overall performance. (ii) FullMeSH integrates the evidence from different sections in a 'learning to rank' framework by combining the sparse and deep semantic representations. (iii) FullMeSH trains an Attention-based Convolutional Neural Network for each section, which achieves better performance on infrequent MeSH headings. FullMeSH has been developed and empirically trained on the entire set of 1.4 million full-text articles in the PubMed Central Open Access subset. It achieved a Micro F-measure of 66.76% on a test set of 10 000 articles, which was 3.3% and 6.4% higher than DeepMeSH and MeSHLabeler, respectively. Furthermore, FullMeSH demonstrated an average improvement of 4.7% over DeepMeSH for indexing Check Tags, a set of most frequently indexed MeSH headings. AVAILABILITY AND IMPLEMENTATION: The software is available upon request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

NetGO: improving large-scale protein function prediction with massive network information.

Automated function prediction (AFP) of proteins is of great significance in biology. AFP can be regarded as a problem of the large-scale multi-label classification where a protein can be associated with multiple gene ontology terms as its labels. Based on our GOLabeler-a state-of-the-art method for the third critical assessment of functional annotation (CAFA3), in this paper we propose NetGO, a web server that is able to further improve the performance of the large-scale AFP by incorporating massive protein-protein network information. Specifically, the advantages of NetGO are threefold in using network information: (i) NetGO relies on a powerful learning to rank framework from machine learning to effectively integrate both sequence and network information of proteins; (ii) NetGO uses the massive network information of all species (>2000) in STRING (other than only some specific species) and (iii) NetGO still can use network information to annotate a protein by homology transfer, even if it is not contained in STRING. Separating training and testing data with the same time-delayed settings of CAFA, we comprehensively examined the performance of NetGO. Experimental results have clearly demonstrated that NetGO significantly outperforms GOLabeler and other competing methods. The NetGO web server is freely available at http://issubmission.sjtu.edu.cn/netgo/.

Deep sequencing of HBV pre-S region reveals high heterogeneity of HBV genotypes and associations of word pattern frequencies with HCC.

Hepatitis B virus (HBV) infection is a common problem in the world, especially in China. More than 60-80% of hepatocellular carcinoma (HCC) cases can be attributed to HBV infection in high HBV prevalent regions. Although traditional Sanger sequencing has been extensively used to investigate HBV sequences, NGS is becoming more commonly used. Further, it is unknown whether word pattern frequencies of HBV reads by Next Generation Sequencing (NGS) can be used to investigate HBV genotypes and predict HCC status. In this study, we used NGS to sequence the pre-S region of the HBV sequence of 94 HCC patients and 45 chronic HBV (CHB) infected individuals. Word pattern frequencies among the sequence data of all individuals were calculated and compared using the Manhattan distance. The individuals were grouped using principal coordinate analysis (PCoA) and hierarchical clustering. Word pattern frequencies were also used to build prediction models for HCC status using both K-nearest neighbors (KNN) and support vector machine (SVM). We showed the extremely high power of analyzing HBV sequences using word patterns. Our key findings include that the first principal coordinate of the PCoA analysis was highly associated with the fraction of genotype B (or C) sequences and the second principal coordinate was significantly associated with the probability of having HCC. Hierarchical clustering first groups the individuals according to their major genotypes followed by their HCC status. Using cross-validation, high area under the receiver operational characteristic curve (AUC) of around 0.88 for KNN and 0.92 for SVM were obtained. In the independent data set of 46 HCC patients and 31 CHB individuals, a good AUC score of 0.77 was obtained using SVM. It was further shown that 3000 reads for each individual can yield stable prediction results for SVM. Thus, another key finding is that word patterns can be used to predict HCC status with high accuracy. Therefore, our study shows clearly that word pattern frequencies of HBV sequences contain much information about the composition of different HBV genotypes and the HCC status of an individual.

SolidBin: improving metagenome binning with semi-supervised normalized cut.

MOTIVATION: Metagenomic contig binning is an important computational problem in metagenomic research, which aims to cluster contigs from the same genome into the same group. Unlike classical clustering problem, contig binning can utilize known relationships among some of the contigs or the taxonomic identity of some contigs. However, the current state-of-the-art contig binning methods do not make full use of the additional biological information except the coverage and sequence composition of the contigs. RESULTS: We developed a novel contig binning method, Semi-supervised Spectral Normalized Cut for Binning (SolidBin), based on semi-supervised spectral clustering. Using sequence feature similarity and/or additional biological information, such as the reliable taxonomy assignments of some contigs, SolidBin constructs two types of prior information: must-link and cannot-link constraints. Must-link constraints mean that the pair of contigs should be clustered into the same group, while cannot-link constraints mean that the pair of contigs should be clustered in different groups. These constraints are then integrated into a classical spectral clustering approach, normalized cut, for improved contig binning. The performance of SolidBin is compared with five state-of-the-art genome binners, CONCOCT, COCACOLA, MaxBin, MetaBAT and BMC3C on five next-generation sequencing benchmark datasets including simulated multi- and single-sample datasets and real multi-sample datasets. The experimental results show that, SolidBin has achieved the best performance in terms of F-score, Adjusted Rand Index and Normalized Mutual Information, especially while using the real datasets and the single-sample dataset. AVAILABILITY AND IMPLEMENTATION: https://github.com/sufforest/SolidBin. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

GOLabeler: improving sequence-based large-scale protein function prediction by learning to rank.

Motivation: Gene Ontology (GO) has been widely used to annotate functions of proteins and understand their biological roles. Currently only <1% of >70 million proteins in UniProtKB have experimental GO annotations, implying the strong necessity of automated function prediction (AFP) of proteins, where AFP is a hard multilabel classification problem due to one protein with a diverse number of GO terms. Most of these proteins have only sequences as input information, indicating the importance of sequence-based AFP (SAFP: sequences are the only input). Furthermore, homology-based SAFP tools are competitive in AFP competitions, while they do not necessarily work well for so-called difficult proteins, which have <60% sequence identity to proteins with annotations already. Thus, the vital and challenging problem now is how to develop a method for SAFP, particularly for difficult proteins. Methods: The key of this method is to extract not only homology information but also diverse, deep-rooted information/evidence from sequence inputs and integrate them into a predictor in a both effective and efficient manner. We propose GOLabeler, which integrates five component classifiers, trained from different features, including GO term frequency, sequence alignment, amino acid trigram, domains and motifs, and biophysical properties, etc., in the framework of learning to rank (LTR), a paradigm of machine learning, especially powerful for multilabel classification. Results: The empirical results obtained by examining GOLabeler extensively and thoroughly by using large-scale datasets revealed numerous favorable aspects of GOLabeler, including significant performance advantage over state-of-the-art AFP methods. Availability and implementation: http://datamining-iip.fudan.edu.cn/golabeler. Supplementary information: Supplementary data are available at Bioinformatics online.