Likun Jiang

Likun Jiang

Auto-generated profile, based on publicly available information

Likun Jiang

Department of Computer Science, Xiamen University, Xiamen, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
25 March 2022 in Briefings in Bioinformatics
Verified
Journal Article
Closed access
PDF file
LJLikun Jiang
Likun Jiang
CJChangzhi Jiang
Changzhi Jiang
XYXinyu Yu
Xinyu Yu
RFRao Fu
Rao Fu
SJShuting Jin
Shuting Jin
XLXiangrong Liu
Xiangrong Liu
Identifying new lead molecules to treat cancer requires more than a decade of dedicated effort. Before selected drug candidates are used in the clinic, their anti-cancer activity is generally validated by in vitro cellular experiments. Therefore, accurate prediction of cancer drug response is a critical and challenging task for anti-cancer drugs design and precision medicine. With the development of pharmacogenomics, the combination of efficient drug feature extraction methods and omics data has made it possible to use computational models to assist in drug response prediction. In this study, we propose DeepTTA, a novel end-to-end deep learning model that utilizes transformer for drug representation learning and a multilayer neural network for transcriptomic data prediction of the anti-cancer drug responses. Specifically, DeepTTA uses transcriptomic gene expression data and chemical substructures of drugs for drug response prediction. Compared to existing methods, DeepTTA achieved higher performance in terms of root mean square error, Pearson correlation coefficient and Spearman’s rank correlation coefficient on multiple test sets. Moreover, we discovered that anti-cancer drugs bortezomib and dactinomycin provide a potential therapeutic option with multiple clinical indications. With its excellent performance, DeepTTA is expected to be an effective method in cancer drug design.

10 October 2023 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
LJLikun Jiang
Likun Jiang
NSNan Sun
Nan Sun
YZYue Zhang
Yue Zhang
XYXinyu Yu
Xinyu Yu
XLXiangrong Liu
Xiangrong Liu
Bioactive peptides are defined as peptide sequences within a protein that can regulate important bodily functions through their myriad activities. With the development of machine learning, more computational methods were proposed for bioactive peptides recognition so that this task does not only rely on tedious and time-consuming wet-experiment. But the training and testing process of existing models are limited to small datasets, which affects model performance. Inspired by the success of sequence classification in natural language processing with unlabeled data, we proposed a pre-training method for Bioactive peptides recognition. By pre-trained with large-scale of protein sequences, our method achieved the best performance in multiple functional peptides identification including anti-cancer, anti-diabetic, anti-hypertensive, anti-inflammatory and anti-microbial peptides. Compared with the advanced model, our model's precision, coverage, accuracy and absolute true are improved by 7.2%, 6.9%, 6.1% and 4.2% in the result of 5-fold cross-validation. In addition, the results indicate the model has superior prediction performance in single functional peptides recognition, especially for anti-cancer peptides and anti-microbial peptides which with longer sequences.

12 July 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
LJLikun Jiang
Likun Jiang
ZZZiyun Zou
Ziyun Zou
XRXinru Ruan
Xinru Ruan
XZXinyi Zhang
Xinyi Zhang
XYXinyu Yu
Xinyu Yu
XLXiangrong Liu
Xiangrong Liu
DNA molecules, as natural information carriers, have several benefits over conventional digital storage mediums, including high information density and long-term durability. It is expected to be a promising candidate for information storage. However, despite significant research in this field, the pace of development has been slow due to the lack of complete encoding-decoding platform and simulaton-evaluation system. And the mutation in DNA sequences during synthesis and sequencing requires multiple experiments, and wet experiments can be costly. Thus, a silicon-based simulation platform is urgently needed for promoting research. Therefore, we proposed DNA Storage Designer, the first online platform to simulate the whole process of DNA storage experiments. Our platform offers classical and novel technologies and experimental settings that simulate three key processes: encoding, error simulation, and decoding for DNA storage system. Fisrt, 8 mainstream encoding methods were embedded in the encoding process to convert files to DNA sequences. Secondly, to uncover potential mutations and sequence distribution changes in actual experiments we integrate the simulation setting for five typical experiment sub-processes (synthesis, decay, PCR, sampling, and sequencing) in the error simulation stage. Finally, the corresponding decoding process realizes the conversion of DNA sequence to binary sequence. All the above simulation processes correspond to an analysis report will provide guides for better experiment design for researchers’ convenience. In short, DNA Storage Designer is an easy-to-use and automatic web-server for simulating DNA storage experiments, which could advance the development of DNA storage-related research. And it is freely available for all users at: https://dmci.xmu.edu.cn/dna/ . Author summary: DNA storage technology is an emerging and promising storage technology. At the same time, DNA storage is an interdisciplinary technology that requires researchers to know both computer cryptography and biological experiments knowledge. However, DNA storage experiments are costly and lengthy, many studies have been prevented by the lack of a comprehensive design and evaluation platform to guide DNA storage experiments. Herein, we introduce DNA Storage Designer, the first integrated and practical web server for providing the simulation of the whole process of DNA storage application, from encoding, error simulation during preservation, to decoding. In the encoding process, we not only provided the coding DNA sequences but also analyzed the sequence stability. In the error simulation process, we simulated as many experimental situations as possible, such as different mutation probabilities of DNA sequences due to being stored in different bacteria hosts or different sequencing platforms. The platform provides high freedom in that users could not only encode their files and conduct the entire operation but also could upload FASTA files and only simulate the sustaining process of sequences and imitate the mutation errors together with distribution changes of sequences.