bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.02.17.706322

Multi-Model AI Consensus Pipeline for Automated Data Extraction in Plant Science Meta-Analysis

Halpern, M.
View original source ↗Export metadata ↓

Abstract

BackgroundData extraction is the primary bottleneck in meta-analysis, consuming weeks of researcher time with single-extractor error rates of 17.7%. Existing LLM-based systems achieve only 26-36% accuracy on continuous outcomes, and no study has validated AI-extracted continuous data against multiple independent datasets using formal equivalence testing. MethodsA single AI agent (Claude Opus 4.6) extracted treatment means, control means, sample sizes, and variance measures from source PDFs across five published agricultural meta-analyses spanning zinc biofortification, biostimulant efficacy, biochar amendments, predator biocontrol, and elevated CO2 effects on plant mineral nutrition. Observations were matched to reference standards using an LLM-driven alignment method. Validation employed proportional TOST equivalence testing, ICC(3,1), Bland-Altman analysis, and source-type stratification. ResultsAcross five datasets, the agent produced 1,149 matched observations from 136 papers. Pearson correlations ranged from 0.984 to 0.999. Proportional TOST confirmed statistical equivalence for all five datasets (all p < 0.05). Table-sourced observations achieved 5.5x lower median error than figure-sourced observations. Aggregate effects were reproduced within 0.01-1.61 pp of published values. Independent duplicate runs confirmed extraction stability (within 0.09-0.23 pp). ConclusionsA single AI agent achieves statistical equivalence with human-extracted meta-analysis data across five independent agricultural datasets. The approach reduces extraction cost by approximately one to two orders of magnitude while maintaining accuracy sufficient for aggregate meta-analytic pooling. HighlightsO_ST_ABSWhat is already knownC_ST_ABSO_LIData extraction is the primary bottleneck in meta-analysis, with single-extractor error rates of 17.7% C_LIO_LIExisting LLM-based extraction systems achieve only 26-36% accuracy on continuous outcomes C_LIO_LINo study has validated AI extraction against multiple independent datasets using formal equivalence testing C_LI What is newO_LIA single AI agent achieves statistical equivalence with human-extracted data across five agricultural meta-analyses (1,149 observations, 136 papers) C_LIO_LILLM-driven alignment resolves the previously underappreciated bottleneck of moderator matching, improving correlations from 0.377-0.812 to 0.984-0.997 without changing extracted values C_LIO_LITable-sourced observations achieve 5.5x lower error than figure-sourced data C_LI Potential impact for RSM readersO_LIProvides a validated, reproducible workflow for AI-assisted data extraction in meta-analysis C_LIO_LIDemonstrates that most apparent "extraction error" in validation studies is actually alignment error C_LIO_LIOffers practical quality signals (source-type labeling) for downstream meta-analysts C_LI

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Halpern, M.. 2026-02-18. Multi-Model AI Consensus Pipeline for Automated Data Extraction in Plant Science Meta-Analysis. https://doi.org/10.64898/2026.02.17.706322

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

KEEP EXPLORING

Related preprints

bioRxiv2026

Senescence-associated KRAS upregulation in peripheral T cells links to premature coronary artery disease

Aims: Premature coronary artery disease (PCAD) lacks specific molecular drivers, and the role of immunosenescence is unclear. We investigated whether aging-related gene dysregulation in T cells contributes to PCAD. Methods: We combined bulk transcriptomics of PBMCs from 12 PCAD patients and 21 controls, single-cell RNA sequencing of PBMCs and human atherosclerotic plaques, weighted gene co-expression network analysis, gene perturbation network analysis, and molecular docking. Results: KRAS was identified as a hub gene intersecting PCAD-associated genes and aging-related genes. Single-cell analysis showed KRAS upregulation predominantly in effector CD8+ T cells, which exhibited the highest senescence scores that were further elevated in disease. Network perturbation of KRAS strongly impacted the cell killing pathway. KRAS-high effector CD8+ T cells were detected in coronary and carotid plaques, displaying enhanced cytotoxicity, exhaustion, and senescence features. Additionally, a candidate small molecule was computationally predicted to bind inactive KRAS. Conclusions: Elevated KRAS expression in senescent, cytotoxic CD8+ T cells is associated with PCAD, bridging immunosenescence and premature atherosclerosis. This finding provides a novel biomarker candidate and potential therapeutic entry point, awaiting further functional validation.

bioinformatics↗
bioRxiv2026

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.

bioinformatics↗
bioRxiv2026

Benchmarking single-cell foundation models for aging biology

Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating ten general-purpose scFMs, three aging-specific models and conventional methods across five biological questions using more than 2.5 million single cell transcriptomes. Using frozen pretrained representations, Geneformer performed best among scFMs for chronological age prediction and age pseudotime concordance, although 2,000 highly variable genes achieved higher mean performance. Several scFMs captured positive molecular age shifts across three disease contexts, consistent with reported aging-associated changes. SCimilarity performed well for rare cellular state identification across out-of-distribution datasets, exceeding aging specific models and conventional baselines. At the gene level, scGPT showed the highest recovery of reference TF target interactions, including aging-related regulatory hubs. Overall, scFMs supported diverse aging analyses, but performance depended on the biological question, highlighting their utility for rare cellular state identification and regulatory analysis.

bioinformatics↗