AquaSense: Automated Sensitivity Analysis of Probabilistic Programs via Quantized Inference

Zhou, Zitong; Huang, Zixin; Misailovic, Sasa

doi:10.1007/978-3-031-45332-8_16

Cited by 1 publication

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tables A. 3 and A.4 show detailed prompts and examples of instruction generation. These instruction examples are also re-purposed to distinguish between chit-chat and API-specific data analysis questions from the user (Section 2.3).…”

Section: Instruction Generationmentioning

confidence: 99%

“…Over the years, substantial efforts have been made to address these data analysis challenges. These endeavors yield meaningful insights from two perspectives [3]: (1) computational researchers subset. The ChatBot service takes the user's data and instructions as input and determines whether the user is asking an API-specific data analysis question or engaging in chit-chat.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simplifying bioinformatics data analysis through conversation

Dong,

Zhou,

Jiang

et al. 2023

Preprint

View full text Add to dashboard Cite

The burgeoning field of bioinformatics has been revolutionized by the rapid growth of omics data, providing insights into various biological processes. However, the complexity of bioinformatics tools and the rapidly evolving nature of data analysis pipelines present significant challenges for researchers, especially those lacking extensive programming expertise. To address these challenges, we introduce BioMANIA, an artificial intelligence-driven, natural language-oriented bioinformatics data analysis pipeline. BioMANIA comprises two key components: a ChatBot generation pipeline and a user-friendly ChatBot back-end service. The generation pipeline takes as input an open-source (e.g., hosted in GitHub) and well-documented (e.g., hosted in ReadTheDocs) Python tool, extracting API attributes and generating synthetic instructions that train a ChatBot to understand and perform specific data analysis tasks. We identified 11 common issues to provide a practical guideline for designing more ChatBot-compatible tools, which we categorized into five groups, while analyzing 12 well-documented open-source Python tools across various bioinformatics settings. The ChatBot service then assists users in selecting the appropriate analysis API and parameters, significantly reducing the programming barrier. We applied BioMANIA to analyze single-cell gene expression data, demonstrating its effectiveness in simplifying complex omics data analysis. BioMANIA has the potential to transform the landscape of bioinformatics research, making data analysis more accessible and accelerating discoveries in the field.1

show abstract

Section: Instruction Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%