Lin Zhu

Lin Zhu

Auto-generated profile, based on publicly available information

Lin Zhu

Institute of Machine Learning and Systems Biology, School of Electronics and Information Engineering, Tongji University, Caoan Road 4800, Shanghai 201804, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 March 2018 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
QZQinhu Zhang
Qinhu Zhang
LZLin Zhu
Lin Zhu
DHDe-Shuang Huang
De-Shuang Huang
Although Deep learning algorithms have outperformed conventional methods in predicting the sequence specificities of DNA-protein binding, they lack to consider the dependencies among nucleotides and the diverse binding lengths for different transcription factors (TFs). To address the above two limitations simultaneously, in this paper, we propose a high-order convolutional neural network architecture (HOCNN), which employs a high-order encoding method to build high-order dependencies among nucleotides, and a multi-scale convolutional layer to capture the motif features of different lengths. The experimental results on real ChIP-seq datasets show that the proposed method outperforms the state-of-the-art deep learning method (DeepBind) in the motif discovery task. In addition, we provide further insights about the importance of introducing additional convolutional kernels and the degeneration problem of importing high-order in the motif discovery task.

7 August 2018 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
QZQinhu Zhang
Qinhu Zhang
LZLin Zhu
Lin Zhu
WBWenzheng Bao
Wenzheng Bao
DHDe-Shuang Huang
De-Shuang Huang
Although convolutional neural networks (CNN) have outperformed conventional methods in predicting the sequence specificities of protein-DNA binding in recent years, they do not take full advantage of the intrinsic weakly-supervised information of DNA sequences that a bound sequence may contain multiple TFBS(s). Here, we propose a weakly-supervised convolutional neural network architecture (WSCNN), combining multiple-instance learning (MIL) with CNN, to further boost the performance of predicting protein-DNA binding. WSCNN first divides each DNA sequence into multiple overlapping subsequences (instances) with a sliding window, and then separately models each instance using CNN, and finally fuses the predicted scores of all instances in the same bag using four fusion methods, including Max, Average, Linear Regression, and Top-Bottom Instances. The experimental results on in vivo and in vitro datasets illustrate the performance of the proposed approach. Moreover, models built on in vitro data using WSCNN can predict in vivo protein-DNA binding with good accuracy. In addition, we give a quantitative analysis of the importance of the reverse-complement mode in predicting in vivo protein-DNA binding, and explain why not directly use advanced pooling layers to combine MIL with CNN, through a series of experiments.

26 February 2015 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
LZLin Zhu
Lin Zhu
SDSu-Ping Deng
Su-Ping Deng
ZYZhu-Hong You
Zhu-Hong You
DHDe-Shuang Huang
De-Shuang Huang
In recent years, a remarkable amount of protein-protein interaction (PPI) data are being available owing to the advance made in experimental high-throughput technologies. However, the experimentally detected PPI data usually contain a large amount of spurious links, which could contaminate the analysis of the biological significance of protein links and lead to incorrect biological discoveries, thereby posing new challenges to both computational and biological scientists. In this paper, we develop a new embedding algorithm called local similarity preserving embedding (LSPE) to rank the interaction possibility of protein links. By going beyond limitations of current geometric embedding methods for network denoising and emphasizing the local information of PPI networks, LSPE can avoid the unstableness of previous methods. We demonstrate experimental results on benchmark PPI networks and show that LSPE was the overall leader, outperforming the state-of-the-art methods in topological false links elimination problems.

21 September 2017 in Plant Signaling & Behavior
Verified
Journal Article
Open access
CZCheng Zhou
Cheng Zhou
FLFeiyue Li
Feiyue Li
YXYue Xie
Yue Xie
LZLin Zhu
Lin Zhu
XXXin Xiao
Xin Xiao
JWJianfei Wang
Jianfei Wang
Soil salinity-alkalinity is one of abiotic stresses that lead to plant growth inhibition and yield loss. It has recently been indicated that plant growth promoting rhizobacteria (PGPR) can enhance the capacity of plants to counteract negative effects caused by adverse environments. However, whether PGPR confers increased saline-alkaline resistance of plants and the underlying mechanisms remain unclear. We thus investigated the effects of Bacillus licheniformis (strain SA03) on Chrysanthemum plants grown under saline-alkaline conditions. Soil inoculation with SA03 significantly mitigated saline-alkaline stress in plants with augmented photosynthesis, biomass and survival rates. Moreover, the inoculated plants accumulated more Fe and less Na+ content than the non-inoculated plants under the stress. However, the inoculation with SA03 failed to trigger a series of saline-alkaline stress responses in abscisic acid (ABA)- and nitric oxide (NO)-deficient plants. Furthermore, NO acted as a secondary messenger of ABA to regulate the stress responses and tolerance in Chrysanthemum plants. Therefore, these findings indicated that B. licheniformis SA03 could be employed to improve saline-alkaline tolerance of plants by mediating cellular ABA levels.

7 January 2019 in IEEE Transactions on Nanobioscience
Verified
Journal Article
Closed access
WXWenxuan Xu
Wenxuan Xu
LZLin Zhu
Lin Zhu
DHDe-Shuang Huang
De-Shuang Huang
Efficient human promoter feature extraction is still a major challenge in genome analysis as it can better understand human gene regulation and will be useful for experimental guidance. Although many machine learning algorithms have been developed for eukaryotic gene recognition, performance on promoters is unsatisfactory due to the diverse nature. To extract discriminative features from human promoters, an efficient deep convolutional divergence encoding method (DCDE) is proposed based on statistical divergence (SD) and convolutional neural network (CNN). SD can help optimize kmer feature extraction for human promoters. CNN can also be used to automatically extract features in gene analysis. In DCDE, we first perform informative kmers settlement to encode original gene sequences. A series of SD methods can optimize the most discriminative kmers distributions while maintaining important positional information. Then CNN is utilized to extract lower dimensional deep features by secondary encoding. Finally, we construct a hybrid recognition architecture with multiple support vector machines and a bilayer decision method. It is flexible to add new features or new models and can be extended to identify other genomic functional elements. Extensive experiments demonstrate that DCDE is effective in promoter encoding and can significantly improve the performance of promoter recognition.

3 May 2016 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
HZHongbo Zhang
Hongbo Zhang
LZLin Zhu
Lin Zhu
DHDe-Shuang Huang
De-Shuang Huang
The transcription factors (TFs) can activate or suppress gene expression by binding to specific sites, hence are crucial regulatory elements for transcription. Recently, series of discriminative motif finders have been tailored to offering promising strategy for harnessing the power of large quantities of accumulated high-throughput experimental data. However, in order to achieve high speed, these algorithms have to sacrifice accuracy by employing simplified statistical models during the searching process. In this paper, we propose a novel approach named Discriminative Motif Learning via AUC (DiscMLA) to discover motifs on high-throughput datasets. Unlike previous approaches, DiscMLA tries to optimize with a more comprehensive criterion (AUC) during motifs searching. In addition, based on an experimental observation of motif identification on large-scale datasets, some novel procedures are designed to accelerate DiscMLA. The experimental results on 52 real-world datasets demonstrate that our approach substantially outperforms previous methods on discriminative motif learning problems. DiscMLA' stability, discriminability, and validity will help to exploit high-throughput datasets and answer many fundamental biological questions.