Ahmad, R. S. | bioRxiv Science

bioRxiv2026

BioVix: An Integrated Large Language Model Framework for Data Visualization, Graph Interpretation, and Literature-Aware Scientific Validation

The application of Large Language Models (LLMs) for generating data visualizations through natural language interaction represents a promising advance in AI-assisted scientific analysis. However, existing LLM-based tools largely emphasize graph generation, while research workflows require not only visualization but also rigorous interpretation and validation against established scholarly evidence. Despite advances in visualization technologies, no single tool currently integrates literature references with visualization while also generating insights from graphical data. To address this gap, we present BioVix, a web-based LLM-driven framework that integrates interactive data visualization, natural-language querying, and automated retrieval of relevant academic literature. BioVix enables users to upload datasets, generate complex visualizations, interpret graphical patterns, and contextualize findings through literature references within a unified workflow. The system employs a multi-model architecture combining DeepSeek V3.1 for code and logic generation, Qwen2.5-VL-32B-Instruct for multimodal interpretation, and GPT-OSS-20B for conversational reasoning, coordinated through structured prompt engineering. BioVix was evaluated across diverse biological domains, including proteomic expression profiling, epigenomic peak annotation, and clinical diabetes data, demonstrating its flexibility in handling heterogeneous datasets and supporting exploratory, literature-aware analysis. While BioVix substantially streamlines exploratory research workflows, its LLM-generated outputs are intended to support, not replace, expert judgment, and users should independently verify results before scientific reporting. BioVix is openly available via public deployment on Hugging Face (https://huggingface.co/spaces/MuhammadZain10/BioVix), with source code provided through GitHub (https://github.com/MuhammadZain-Butt/BioVix).

bioinformatics↗

bioRxiv2025

XtractPAV: An Automated Pipeline for Identifying Presence-Absence Variations Across Multiple Genomes

MotivationPresence-absence variations (PAVs) significantly influence phenotypic diversity across and within species by modulating functional modules involved in stress responsiveness, adaptation, and developmental processes. This modulation ultimately contributes to genetic diversity at both inter- and intra-species levels. However, existing tools for detecting PAVs offer limitations in achieving optimal analysis because they lack scalable workflows for multi-genome comparisons and frequently necessitate manual integration. To address these challenges, we developed XtractPAV, an end-to-end pipeline that automates the extraction, annotation, and interactive visualization of PAVs across large-scale genomic datasets. ResultsXtractPAV was evaluated using assembled genomes of both eukaryotic and prokaryotic organisms, including Pyrus communis, Arabidopsis thaliana, Mus musculus, and Salmonella enterica, to assess its ability to detect the genomic variations across diverse species. The performance of XtractPAV was benchmarked against other established pipelines, demonstrating superior precision and a more comprehensive extraction of PAV segments. Notably, our pipeline not only identified the known PAVs from the reference set but also revealed novel variations in genes associated with various functions such as flowering time regulation and disease resistance. Furthermore, the automated report generation feature of XtractPAV produces publication-ready summaries of PAV distributions and related metrics. AvailabilityXtractPAV is freely accessible at https://github.com/SherazAhmadd/XtractPAV and on the XtractPAV webpage. The Package includes all requisite files, a user manual, test data, and a license permitting non-commercial use. Supplementary materialSupplementary data are accessible online at Bioinformatics.

bioinformatics↗