Jiyang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jiyang Zhang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Yunping Zhu
School of Basic Medical Sciences Anhui Medical University Hefei China
3 shared publications - Fuchu He
State Key Laboratory of Medical Proteomics, National Center for Protein Sciences (Beijing), Research Unit of Proteomics Driven Cancer Precision Medicine (Chinese Academy of Medical Sciences), Beijing, China
2 shared publications - Jie Ma
State Key Laboratory of Medical Proteomics, Beijing Proteome Research Center, National Center for Protein Sciences (Beijing), Beijing Institute of Lifeomics, Beijing 102206, China
2 shared publications - Junyi Jessy Li
University of Texas at Austin, Austin, USA
2 shared publications - Milos Gligoric
University of Texas at Austin, Austin, USA
2 shared publications - Pengyu Nie
University of Waterloo, Waterloo, Canada
2 shared publications
Latest Publications
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1193-1197
A Tool for Generating Exceptional Behavior Tests With Large Language Models
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1193-1197
Open AccessA Tool for Generating Exceptional Behavior Tests With Large Language Models
- Open Access
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 695-707
Multilingual Code Co-evolution using Large Language Models
Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and without errors, to implementations in other programming languages. In the world of ever-changing software, using rule-based translation tools (i.e., transpilers) or machine learning models for translating code from one language to another provides limited value. Translating each time the entire codebase from one language to another is not the way developers work. In this paper, we target a novel task: translating code changes from one programming language to another using large language models (LLMs). We design and implement the first LLM, dubbed Codeditor, to tackle this task. Codeditor explicitly models code changes as edit sequences and learns to correlate changes across programming languages. To evaluate Codeditor, we collect a corpus of 6,613 aligned code changes from 8 pairs of open-source software projects implementing similar functionalities in two programming languages (Java and C#). Results show that Codeditor outperforms the state-of-the-art approaches by a large margin on all commonly used automatic metrics. Our work also reveals that Codeditor is complementary to the existing generation-based models, and their combination ensures even greater performance.
- 30 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 695-707
Open AccessMultilingual Code Co-evolution using Large Language Models
Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and without errors, to implementations in other programming languages. In the world of ever-changing software, using rule-based translation tools (i.e., transpilers) or machine learning models for translating code from one language to another provides limited value. Translating each time the entire codebase from one language to another is not the way developers work. In this paper, we target a novel task: translating code changes from one programming language to another using large language models (LLMs). We design and implement the first LLM, dubbed Codeditor, to tackle this task. Codeditor explicitly models code changes as edit sequences and learns to correlate changes across programming languages. To evaluate Codeditor, we collect a corpus of 6,613 aligned code changes from 8 pairs of open-source software projects implementing similar functionalities in two programming languages (Java and C#). Results show that Codeditor outperforms the state-of-the-art approaches by a large margin on all commonly used automatic metrics. Our work also reveals that Codeditor is complementary to the existing generation-based models, and their combination ensures even greater performance.
- Top Cited PapersOpen Access
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-12
CoditT5: Pretraining for Source Code and Natural Language Editing
Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel pretraining objective which explicitly models edits and use it to build CoditT5, a large language model for software-related editing tasks that is pretrained on large amounts of source code and natural language comments. We fine-tune it on various downstream editing tasks, including comment updating, bug fixing, and automated code review. By outperforming standard generation-based models, we demonstrate the generalizability of our approach and its suitability for editing tasks. We also show how a standard generation model and our edit-based model can complement one another through simple reranking strategies, with which we achieve state-of-the-art performance for the three downstream editing tasks.
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Top Cited PapersOpen AccessCoditT5: Pretraining for Source Code and Natural Language Editing
Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel pretraining objective which explicitly models edits and use it to build CoditT5, a large language model for software-related editing tasks that is pretrained on large amounts of source code and natural language comments. We fine-tune it on various downstream editing tasks, including comment updating, bug fixing, and automated code review. By outperforming standard generation-based models, we demonstrate the generalizability of our approach and its suitability for editing tasks. We also show how a standard generation model and our edit-based model can complement one another through simple reranking strategies, with which we achieve state-of-the-art performance for the three downstream editing tasks.
- Open Access
- 15 December 2013
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 30 (4) , 586-587
SILVER: an efficient tool for stable isotope labeling LC-MS data quantitative analysis with quality control methods
Summary: With the advance of experimental technologies, different stable isotope labeling methods have been widely applied to quantitative proteomics. Here, we present an efficient tool named SILVER for processing the stable isotope labeling mass spectrometry data. SILVER implements novel methods for quality control of quantification at spectrum, peptide and protein levels, respectively. Several new quantification confidence filters and indices are used to improve the accuracy of quantification results. The performance of SILVER was verified and compared with MaxQuant and Proteome Discoverer using a large-scale dataset and two standard datasets. The results suggest that SILVER shows high accuracy and robustness while consuming much less processing time. Additionally, SILVER provides user-friendly interfaces for parameter setting, result visualization, manual validation and some useful statistics analyses. Availability and implementation: SILVER and its source codes are freely available under the GNU General Public License v3.0 at http://bioinfo.hupo.org.cn/silver. Contact:zhuyunping@gmail.com, hefc@nic.bmi.ac.cn and xhwei65@163.com Supplementary information: Supplementary data are available at Bioinformatics online
- 15 December 2013
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 30 (4) , 586-587
Open AccessSILVER: an efficient tool for stable isotope labeling LC-MS data quantitative analysis with quality control methods
Summary: With the advance of experimental technologies, different stable isotope labeling methods have been widely applied to quantitative proteomics. Here, we present an efficient tool named SILVER for processing the stable isotope labeling mass spectrometry data. SILVER implements novel methods for quality control of quantification at spectrum, peptide and protein levels, respectively. Several new quantification confidence filters and indices are used to improve the accuracy of quantification results. The performance of SILVER was verified and compared with MaxQuant and Proteome Discoverer using a large-scale dataset and two standard datasets. The results suggest that SILVER shows high accuracy and robustness while consuming much less processing time. Additionally, SILVER provides user-friendly interfaces for parameter setting, result visualization, manual validation and some useful statistics analyses. Availability and implementation: SILVER and its source codes are freely available under the GNU General Public License v3.0 at http://bioinfo.hupo.org.cn/silver. Contact:zhuyunping@gmail.com, hefc@nic.bmi.ac.cn and xhwei65@163.com Supplementary information: Supplementary data are available at Bioinformatics online
- Open Access
- 1 January 2011
- Published by Elsevier in Procedia Environmental Sciences
- Vol. 8, 483-491
The Prediction of Peptide Charge States for Electrospray Ionization in Mass Spectrometry
- 1 January 2011
- Published by Elsevier in Procedia Environmental Sciences
- Vol. 8, 483-491
Open AccessThe Prediction of Peptide Charge States for Electrospray Ionization in Mass Spectrometry
- 30 September 2010
- Published by Wiley in Proteomics
- Vol. 10 (23) , 4293-4300
Improving the sensitivity of MASCOT search results validation by combining new features with Bayesian nonparametric model
The probability‐based search engine MASCOT has been widely used to identify peptides and proteins in shotgun proteomic research. Most subsequent quality control methods filter out ambiguous assignments according to the ion score and thresholds provided by MASCOT. On the basis of target‐decoy database search strategy, we evaluated the performance of several filter methods on MASCOT search results and demonstrated that using filter boundaries on two‐dimensional feature spaces, the MASCOT ion score and its relative score can improve the sensitivity of the filter process. Furthermore, using a linear combination of several characteristics of the assigned peptides, including the MASCOT scores, 15 previously employed features, and some newly introduced features, we applied a Bayesian nonparametric model to MASCOT search results and validated more correctly identified peptides in control and complex data sets than those could be validated by empirical score thresholds.
- 30 September 2010
- Published by Wiley in Proteomics
- Vol. 10 (23) , 4293-4300
Improving the sensitivity of MASCOT search results validation by combining new features with Bayesian nonparametric model
The probability‐based search engine MASCOT has been widely used to identify peptides and proteins in shotgun proteomic research. Most subsequent quality control methods filter out ambiguous assignments according to the ion score and thresholds provided by MASCOT. On the basis of target‐decoy database search strategy, we evaluated the performance of several filter methods on MASCOT search results and demonstrated that using filter boundaries on two‐dimensional feature spaces, the MASCOT ion score and its relative score can improve the sensitivity of the filter process. Furthermore, using a linear combination of several characteristics of the assigned peptides, including the MASCOT scores, 15 previously employed features, and some newly introduced features, we applied a Bayesian nonparametric model to MASCOT search results and validated more correctly identified peptides in control and complex data sets than those could be validated by empirical score thresholds.