Large language models (LLMs) such as ChatGPT have shown remarkable capabilities in code generation. Despite significant achievements, they rely on enormous training data to acquire a broad spectrum of open-domain knowledge. Besides, their evaluation revolves around open-domain benchmarks like HumanEval, which primarily consist of programming contests. Therefore, it is hard to fully characterize the intricacies and challenges associated with particular domains (e.g., Web, game, and math). In this article, we conduct an in-depth study of the LLMs in domain-specific code generation. Our results demonstrate that LLMs exhibit sub-optimal performance in generating domain-specific code, due to their limited proficiency in utilizing domain-specific libraries. We further observe that incorporating API knowledge as prompts can empower LLMs to generate more professional code. Based on these findings, we further investigate how to effectively incorporate API knowledge into the code generation process. We experiment with three strategies for incorporating domain knowledge, namely, external knowledge inquirer, chain-of-thought prompting, and chain-of-thought fine-tuning. We refer to these strategies as a new code generation approach called DomCoder . Experimental results show that all strategies of DomCoder improve the effectiveness of domain-specific code generation under certain settings.

Variable names are of critical importance in code representation learning. However, due to diverse naming conventions, variables often receive arbitrary names, leading to long-tail, out-of-vocabulary (OOV), and other well-known problems. While the Byte-Pair Encoding (BPE) tokenizer has addressed the surface-level recognition of low-frequency tokens, it has not noticed the inadequate training of low-frequency identifiers by code representation models, resulting in an imbalanced distribution of rare and common identifiers. Consequently, code representation models struggle to effectively capture the semantics of low-frequency variable names. In this paper, we propose VarGAN, a novel method for variable name representations. VarGAN strengthens the training of low-frequency variables through adversarial training. Specifically, we regard the code representation model as a generator responsible for producing vectors from source code. Additionally, we employ a discriminator that detects whether the code input to the generator contains low-frequency variables. This adversarial setup regularizes the distribution of rare variables, making them overlap with their corresponding high-frequency counterparts in the vector space. Experimental results demonstrate that VarGAN empowers CodeBERT to generate code vectors that exhibit more uniform distribution for both low- and high-frequency identifiers. There is an improvement of 8% in similarity and relatedness scores compared to VarCLR in the IdBench benchmark. VarGAN is also validated in downstream tasks, where it exhibits enhanced capabilities in capturing token- and code-level semantics.

Liquid chromatography-mass spectrometry-based quantitative proteomics can measure the expression of thousands of proteins from biological samples and has been increasingly applied in cancer research. Identifying differentially expressed proteins (DEPs) between tumors and normal controls is commonly used to investigate carcinogenesis mechanisms. While differential expression analysis (DEA) at an individual level is desired to identify patient-specific molecular defects for better patient stratification, most statistical DEP analysis methods only identify deregulated proteins at the population level. To date, robust individualized DEA algorithms have been proposed for ribonucleic acid data, but their performance on proteomics data is underexplored. Herein, we performed a systematic evaluation on five individualized DEA algorithms for proteins on cancer proteomic datasets from seven cancer types. Results show that the within-sample relative expression orderings (REOs) of protein pairs in normal tissues were highly stable, providing the basis for individualized DEA for proteins using REOs. Moreover, individualized DEA algorithms achieve higher precision in detecting sample-specific deregulated proteins than population-level methods. To facilitate the utilization of individualized DEA algorithms in proteomics for prognostic biomarker discovery and personalized medicine, we provide Individualized DEP Analysis IDEPAXMBD (XMBD: Xiamen Big Data, a biomedical open software initiative in the National Institute for Data Science in Health and Medicine, Xiamen University, China.) (https://github.com/xmuyulab/IDEPA-XMBD), which is a user-friendly and open-source Python toolkit that integrates individualized DEA algorithms for DEP-associated deregulation pattern recognition.