Qiaoliang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiaoliang Liu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yun Liu
College of Communication Engineering, Jilin University, Changchun, China
3 shared publications Fu Liu
College of Communication Engineering, Jilin University
2 shared publicationsJiaxue He
Genetic Diagnosis Center, First Hospital of Jilin University, Changchun, China
2 shared publicationsTao Hou
College of Communication Engineering, Jilin University
2 shared publicationsTian Dong
College of Communication Engineering, Jilin University, Changchun, China
2 shared publications- Yan Miao
School of Computer Science and Artificial Intelligence, Northeast Forestry University, Harbin , Heilongjiang Province 150040
2 shared publications
Latest Publications
- 22 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (1) , 763-774
Virsearcher: Identifying Bacteriophages from Metagenomes by Combining Convolutional Neural Network and Gene Information
Metagenome sequencing provides an unprecedented opportunity for the discovery of unknown microbes and viruses. A large number of phages and prokaryotes are mixed together in metagenomes. To study the influence of phages on human bodies and environments, it is of great significance to isolate phages from metagenomes. However, it is difficult to identify novel phages because of the diversity of their sequences and the frequent presence of short contigs in metagenomes. Here, virSearcher is developed to identify phages from metagenomes by combining the convolutional neural network (CNN) and the gene information of input sequences. Firstly, an input sequence is encoded in accordance with the different functions of its coding and the non-coding regions and then is converted into word embedding code through a word embedding layer before a convolutional layer. Meanwhile, the hit ratio of the virus genes is combined with the output of the CNN to further improve the performance of the network. The genes used by virSearcher consist of complete and incomplete genes. Experiments on several metagenomes have showed that, compared with others, virSearcher can significantly improve the performance for the identification of short sequences, while maintaining the performance for long ones. The source code of virSearcher is freely available from http://github.com/DrJackson18/virSearcher.
- 22 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (1) , 763-774
Virsearcher: Identifying Bacteriophages from Metagenomes by Combining Convolutional Neural Network and Gene Information
Metagenome sequencing provides an unprecedented opportunity for the discovery of unknown microbes and viruses. A large number of phages and prokaryotes are mixed together in metagenomes. To study the influence of phages on human bodies and environments, it is of great significance to isolate phages from metagenomes. However, it is difficult to identify novel phages because of the diversity of their sequences and the frequent presence of short contigs in metagenomes. Here, virSearcher is developed to identify phages from metagenomes by combining the convolutional neural network (CNN) and the gene information of input sequences. Firstly, an input sequence is encoded in accordance with the different functions of its coding and the non-coding regions and then is converted into word embedding code through a word embedding layer before a convolutional layer. Meanwhile, the hit ratio of the virus genes is combined with the output of the CNN to further improve the performance of the network. The genes used by virSearcher consist of complete and incomplete genes. Experiments on several metagenomes have showed that, compared with others, virSearcher can significantly improve the performance for the identification of short sequences, while maintaining the performance for long ones. The source code of virSearcher is freely available from http://github.com/DrJackson18/virSearcher.
- Open Access
DETIRE: A Hybrid Deep Learning Model for identifying Viral Sequences from Metagenomes
A metagenome contains all DNA sequences from an environmental sample, including viruses, bacteria, fungi, actinomycetes and so on. Since viruses are of huge abundance and have caused vast mortality and morbidity to human society in history as a kind of major pathogens, detecting viruses from metagenomes plays a crucial role in analysing the viral component of samples and is the very first step for clinical diagnosis. However, detecting viral fragments directly from the metagenomes is still a tough issue because of the existence of huge number of short sequences. In this paper, a hybrid Deep lEarning model for idenTifying vIral sequences fRom mEtagenomes (DETIRE), is proposed to solve the problem. Firstly, the graph-based nucleotide sequence embedding strategy is utilized to enrich the expression of DNA sequences by training an embedding matrix. Then the spatial and sequential features are extracted by trained CNN and BiLSTM networks respectively to improve the feature expression of short sequences. Finally, the two set of features are weighted combined for the final decision. Trained by 220,000 sequences of 500bp subsampled from the Virus and Host RefSeq genomes, DETIRE identifies more short viral sequences (<1,000bp) than three latest methods, DeepVirFinder, PPR-Meta and CHEER. DETIRE is freely available at https://github.com/crazyinter/DETIRE .
Open AccessDETIRE: A Hybrid Deep Learning Model for identifying Viral Sequences from Metagenomes
A metagenome contains all DNA sequences from an environmental sample, including viruses, bacteria, fungi, actinomycetes and so on. Since viruses are of huge abundance and have caused vast mortality and morbidity to human society in history as a kind of major pathogens, detecting viruses from metagenomes plays a crucial role in analysing the viral component of samples and is the very first step for clinical diagnosis. However, detecting viral fragments directly from the metagenomes is still a tough issue because of the existence of huge number of short sequences. In this paper, a hybrid Deep lEarning model for idenTifying vIral sequences fRom mEtagenomes (DETIRE), is proposed to solve the problem. Firstly, the graph-based nucleotide sequence embedding strategy is utilized to enrich the expression of DNA sequences by training an embedding matrix. Then the spatial and sequential features are extracted by trained CNN and BiLSTM networks respectively to improve the feature expression of short sequences. Finally, the two set of features are weighted combined for the final decision. Trained by 220,000 sequences of 500bp subsampled from the Virus and Host RefSeq genomes, DETIRE identifies more short viral sequences (<1,000bp) than three latest methods, DeepVirFinder, PPR-Meta and CHEER. DETIRE is freely available at https://github.com/crazyinter/DETIRE .
- Open Access
- 5 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177529-177538
VFM: Identification of Bacteriophages From Metagenomic Bins and Contigs Based on Features Related to Gene and Genome Composition
As the main regulator of microbial community composition, bacteriophages exist widely on Earth. However, since they are hidden in metagenomes, most of them are unknown. To identify phages from metagenomes more effectively, a new tool named VFM (Virus Finding & Mining) is presented in this paper. VFM has two versions, i.e., bin-VFM and unbin-VFM. Eighteen new features describing the codon usage bias, the proportion of hits of clusters of orthologous groups of proteins (COG), and 1-mer and 2-mer frequency are introduced to improve the performance of the classifiers. By using missing value interpolation, bin-VFM improves the classification performance for short sequence bins significantly. Compared with previous tools for virus mining, bin-VFM and unbin-VFM perform much better for simulated and real metagenomes with short and long sequences respectively. Thus, VFM may play a helpful role in studies of metagenome-related problems, such as horizontal gene transfer and antibiotic resistance. VFM is freely available at https://github.com/liuql2019/VFM.
- 5 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 177529-177538
Open AccessVFM: Identification of Bacteriophages From Metagenomic Bins and Contigs Based on Features Related to Gene and Genome Composition
As the main regulator of microbial community composition, bacteriophages exist widely on Earth. However, since they are hidden in metagenomes, most of them are unknown. To identify phages from metagenomes more effectively, a new tool named VFM (Virus Finding & Mining) is presented in this paper. VFM has two versions, i.e., bin-VFM and unbin-VFM. Eighteen new features describing the codon usage bias, the proportion of hits of clusters of orthologous groups of proteins (COG), and 1-mer and 2-mer frequency are introduced to improve the performance of the classifiers. By using missing value interpolation, bin-VFM improves the classification performance for short sequence bins significantly. Compared with previous tools for virus mining, bin-VFM and unbin-VFM perform much better for simulated and real metagenomes with short and long sequences respectively. Thus, VFM may play a helpful role in studies of metagenome-related problems, such as horizontal gene transfer and antibiotic resistance. VFM is freely available at https://github.com/liuql2019/VFM.