bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.08.26.747436

From Prompt to Provenance: BloClaw, a Capability-Gated AI4S Workstation for Auditable Computational Biology

qin, y.·Pang, J.·Zhang, X.
View original source ↗Export metadata ↓

Abstract

Scientific agents can produce plausible answers while remaining unable to establish whether the computation behind an answer is executable, recoverable, or reproducible. We present BloClaw, an AI4S workstation built around a simple principle: a scientific agent should know what it can do, show how it did it, and state what remains unvalidated. Each capability declares an execution state, input constraints, dependencies, expected outputs, and scientific limitations. Natural-language requests are translated into structured tasks, validated against this registry, executed through scientific tools, and recorded in a provenance-aware Living Lab Notebook. The system is designed to detect invalid inputs, failed tool calls, missing dependencies, and remote timeouts, and to route them to repair, retry, or escalation. The implemented and tested scope comprises RDKit-based molecular property and rule screening, protein structure analysis, docking-pose inspection, 3D visualization, and structured reporting. We demonstrate the workflow on a PubChem-retrieved osimertinib structure and a supplied 6LU7 docking artifact: the former yields deterministic descriptors (molecular weight 499.619 Da, cLogP 4.5098, TPSA 87.55 A^2), while the latter contains 2,387 protein ATOM records, 309 residues, and nine pose records. These examples are workflow demonstrations, not efficacy or affinity studies. Beyond retrospective prediction, the manuscript specifies a prior-minimized constructive mode in which a desired function is compiled into explicit physical, chemical, and systems constraints, candidate mechanisms are simulated, and observations are reintroduced for calibration and falsification; this is a proposed extension rather than a result of the present case studies. We describe an evaluation protocol that compares BloClaw with a standard single-agent workflow and fixed-script execution using task completion, scientific correctness, recovery success, provenance completeness, reproducibility, human review time, latency, and cost. This manuscript reports the system design, verified capability boundary, deterministic software artifacts, and a reproducible evaluation protocol; it does not claim benchmark improvements before those experiments are run. BloClaw is an execution and accountability layer for AI-assisted research, complementing expert review and experimental validation rather than replacing them.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

qin, y., Pang, J., Zhang, X.. 2026-09-01. From Prompt to Provenance: BloClaw, a Capability-Gated AI4S Workstation for Auditable Computational Biology. https://doi.org/10.64898/2026.08.26.747436

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

Discover connections

Preprint resourcePreprint subjectbioinformatics subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related preprints

bioRxiv2026

Digital twins forecast individual immune trajectories

The human immune system differs markedly between individuals and changes in response to infection, vaccination and treatment. AI virtual cells are being built to simulate cellular responses to perturbation. Yet these models, like most immune-response predictors, describe each person by a single pre-challenge measurement and forecast change from patterns pooled across people. Digital twins, updated with every new observation of an individual, could forecast how that person's immune state changes. Here we present ImmuneTwins, which builds these twins from single-cell profiles by personalizing a shared virtual-cell model with each individual's observations. In two external populations, ImmuneTwins reduced immune-age error by 32% and 42% relative to the best existing method. During repeated influenza vaccination, its twins predicted the direction of immune-cell change 35% more accurately than the best published method, and their error fell by 27% as observations accumulated. The twins revealed that immune cells and plasma proteins recover about half their deviation from a persistent personal reference within 90 days, whereas response size varies between challenges. They further localized B-cell remodelling in exceptional longevity and anticipated patient-specific immune trajectories during myeloma treatment. These results establish virtual-cell digital twins for forecasting individual immune change and identifying each person's characteristic immune features.

bioinformatics↗
bioRxiv2026

Alignment-Free k-mer Analysis Reveals Age-Associated k-mer Signals in Canine Buccal DNA and Cell-Free DNA

Aging is associated with progressive molecular and cellular changes that alter chromatin organization, epigenetic regulation, and microbial community structure. While DNA methylation-based biomarkers have demonstrated age-prediction performance, the potential of alignment-free sequence analysis for detecting age-associated signals remains unexplored. We performed a k-mer-based analysis of whole-genome sequencing datasets from two canine cohorts: 1,187 buccal DNA samples and 100 cell-free DNA (cfDNA) samples. Age-associated k-mers were identified through correlation analysis, and sequence motifs and nucleotide composition patterns were characterized across both sample types. Ridge regression models were used to predict age from k-mer frequency profiles, and synthetic datasets were generated under biological compositional assumptions to evaluate potential drivers of the observed signals. Age-associated k-mer signals were identified in both buccal DNA and cfDNA, with substantially stronger patterns observed in buccal samples. Buccal-derived k-mers exhibited more pronounced motif patterns, stronger GC and AT enrichment trends, and improved age-prediction performance relative to cfDNA. Nucleotide enrichment trends differed between sample types, suggesting that distinct biological processes may contribute to age-associated sequence composition changes in buccal DNA and cfDNA. Simulation analyses successfully reproduced major enrichment trends observed empirically, and age-associated signals were largely preserved following restriction to read-start sequence composition. These findings demonstrate that alignment-free k-mer analysis can detect age-associated sequence composition signals in canine DNA and highlight its potential as a computationally efficient complementary approach for aging biomarker discovery.

bioinformatics↗
bioRxiv2026

Does a map-level insulation constraint improve sequence-based prediction of 3D genome folding? A Stage 1 Registered Report with a reverse-complement-equivariant state-space model (HiFold-Mamba)

Background. Sequence-to-contact-map models are trained with pixel-wise losses, although the features of interest (insulation, domain boundaries, loops) are summaries of the map. Insulationbased losses help Hi-C resolution enhancement. No pre-specified test has asked whether they improve sequence-based prediction, judged against annotations independent of the training data. Proposed study. HiFold-Mamba predicts 448 x 448 maps at 2,048 bp from 1,048,576 bp of DNA on the DNALongBench contact-map task. Every component is reverse-complement-equivariant: convolutional tower, bidirectional Mamba blocks, multi-scale mixer and symmetric pairwise head. We pre-register three hypotheses: >> H1: it exceeds each of three trained baselines (reproduced Akita, a parameter-matched Transformer and a parameter-matched CNN) by [≥]0.01 stratum-adjusted correlation (SCC). >> H2: an insulation and boundary loss, computed from the predicted map with the operator used on the observed map, improves boundary AUROC and loop AP against independent 4DN boundary calls and ENCODE CTCF ChIA-PET loops, at equal training steps and without loss of SCC. >> H3: pretraining plus few-shot adaptation beats training from scratch on four held-out cell lines.Tests use a paired bootstrap over 237 one-megabase test blocks (one-sided = 0.025). Pilot data. >> Verification. The benchmark target, the window coordinates and the networks equivariance were verified. >> Locus-shared reference. Copying other cell lines measured maps at the same locus matches published Akita on the benchmarks SCC (0.227 vs. 0.230). >> SCC weightings. Two weightings in common use weight distance strata in opposite directions and agree only moderately ({rho} = 0.54). >> Comparison rule. In simulations calibrated on the pilot data, a per-block-best comparison against several baselines has no power. We therefore test against each baseline, which gives [≥] 90 % power at a true gain of 0.02 when between-model correlation is [≥] 0.95. >> H2 positive control. On validation windows, observed maps recover the independent boundaries (AUROC 0.61 - 0.91) and loops (0.86 - 0.90). This fixed the insulation window and showed that these annotations are largely shared across cell types.

bioinformatics↗