Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.10.28.762630

The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code

Riffle, M.·Zelter, A.·MacCoss, M. J.
View original source ↗Export metadata ↓

Abstract

Scientists presented with quantitative data often face two related problems: confidence that an analysis is statistically and computationally correct, and provenance sufficient to reproduce the resulting figures and conclusions. Large language models (LLMs) can make sophisticated analyses accessible through a collaborative, conversational interface, but unstructured use can worsen both problems by producing plausible but incorrect results and obscuring the steps that produced them. Here we present the Findings Workflow, a free, open-source Claude Code plugin designed to retain the flexibility of conversational LLM-assisted analysis while placing it within a structured, verifiable, and reproducible environment. The workflow uses staged, gated progression to ensure the science, metadata, and data are understood and tested data loaders are built before downstream analysis begins. Specialized subagents perform statistical analysis, programming, visualization, research, reporting, and validation, with independent review incorporated throughout. The plugin also provides vetted analysis templates, conventions, and methodological guidance that serve as trusted sources of opinion when deciding how analyses should be performed. Scientists remain actively involved throughout, exploring their data and directing the analysis through natural-language conversation, while the workflow supplies structure, verification, and persistent state around that collaboration. Findings are recorded automatically together with the data, code, methods, figures, and provenance needed to reproduce them. We demonstrate the workflow with a worked example that reproduces central findings from a published plasma extracellular vesicle proteomics dataset examining Alzheimer's disease (Mag-Net). Together, these features are designed to make LLM-assisted scientific analysis easier to trust, inspect, and reproduce without sacrificing its conversational and exploratory nature.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Riffle, M., Zelter, A., MacCoss, M. J.. 2026-11-01. The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code. https://doi.org/10.64898/2026.10.28.762630

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Cross-modal transfer enables zero-shot prediction of drug responses across cell types

Genetic perturbation responses capture the functional consequences of gene-level interventions, providing functional information for drug-response prediction beyond baseline gene expression. Within the same cellular context, genetic and chemical perturbations engage shared regulatory networks, providing a biological basis for transferring response information between perturbation modalities. Here we introduce GRAFT, a framework that combines genetic-to-chemical transfer with cross-context prediction to infer drug-induced transcriptional responses without drug measurements in the target context. Across benchmarked LINCS and external contexts, GRAFT improved response correlation, directional agreement and magnitude reconstruction over competing methods, particularly for drugs with context-dependent responses. GRAFT-Adapt further refines predictions of unmeasured responses using a small number of drug measurements from the target context. GRAFT-Atlas spans 13 cellular contexts and 7,856 drug catalog entries, comprising 102,128 predictions for drug-context combinations. The atlas captured recognizable pharmacological neighborhoods, shared functional programs, context-dependent transcriptional changes and structural-functional associations supported by molecular docking. Across ten iPSC lines from distinct donors, GRAFT identified candidate inter-donor differences, with functional support for selected candidates from measured genetic perturbation responses. Together, GRAFT enables perturbation-informed prediction and comparison of drug responses across cellular contexts.

bioinformatics↗
bioRxiv2026

Interpreting graph neural networks reveals microbial association patterns in inflammatory bowel diseases

Traditional machine learning models trained on gut microbiome abundance profiles can distinguish individuals with inflammatory bowel disease (IBD) from non-IBD individuals. However, their interpretation typically considers taxa in isolation, making it difficult to understand how associations between taxa contribute to predictions. Here, we inferred individual-specific microbial association networks from longitudinal metagenomics data of 106 individuals in HMP2/iHMP and used them to train and interpret graph neural network (GNN) models, which we compared with abundance-based models such as Random Forest (RF). Although RF achieved higher predictive performance (AUPRC ~0.59 vs 0.446), interpreting the GNNs revealed that their predictions relied on a densely connected module of co-abundant Bacteroidales species. Unlike the taxa prioritized by RF, these species were not differentially abundant between conditions. In an independent cohort, this module carried most of the predictive signal, and removing its associations reduced performance to near chance. These results show that coordinated association structure, rather than abundance shifts alone, is a feature of the IBD gut microbiome, and that interpreting GNNs can uncover such patterns that complement abundance-based analyses.

bioinformatics↗
bioRxiv2026

FateDriver: Weakly supervised dual-view graph learning for transition-specific prioritization of candidate regulators in cellular reprogramming

Cellular reprogramming supports regenerative medicine, yet the endogenous regulators of a specified source-to-target transition remain incompletely defined. Existing computational methods rank candidate regulators from network topology, trajectory dynamics, or cell-state labels, leaving unused the factors experimentally delivered to induce the transition. We present FateDriver, a weakly supervised dual-view graph neural network that jointly represents cells and genes from single-cell transcriptomes, treats the delivered factors as sparse gene-level labels, and ranks the remaining genes for a specified transition under a positive--unlabeled formulation. Across two OSKM datasets and one GMT dataset, FateDriver ranked first or second among six methods in recovering externally curated reference genes, exceeded a supervision-matched non-graph model despite weaker co-expression with the delivered factors, and achieved the highest recovery of protein targets of pluripotency-inducing chemical cocktails in both OSKM datasets. Holding either the source or the endpoint fixed yielded distinct candidate programs, including a DDX58--interferon axis associated with cells lacking endogenous pluripotency markers. Applying the same framework to candidate source--target pairs prioritized distinct candidate origins for two in vivo partially reprogrammed intestinal populations. FateDriver converts sparse experimental knowledge into transition-specific hypotheses for regulator prioritization from single-cell trajectories.

bioinformatics↗