PRAXIS-VirtualCell: A Programmable and Trustworthy Framework for Agentic Virtual Cell Experiments

Zhenyu Ma; Xukai Jiang

Home/Archive/arXiv

arXiv · 2609.29221

PRAXIS-VirtualCell: A Programmable and Trustworthy Framework for Agentic Virtual Cell Experiments

Zhenyu Ma·Xukai Jiang

View original source ↗Read source document ↗Export metadata ↓

Abstract

Virtual cells are evolving from single-task predictive models toward programmable biological simulation systems, yet heterogeneous data, models, and validation evidence still lack a unified organizational framework. Here, we present PRAXIS-VirtualCell, a modular framework that organizes biological data, predictive models, perturbations, adapters, execution environments, and validation evidence to enable reproducible and auditable virtual experiments. The system supports cross-species tasks spanning Escherichia coli, Saccharomyces cerevisiae, and human K562 cells, while using biological contracts and evidence-aware execution to distinguish supported predictions from extrapolation and abstention. By further integrating agentic orchestration, PRAXIS-VirtualCell automatically translates natural-language questions into traceable virtual experiments, providing a unified runtime foundation for trustworthy and scalable Virtual Cell systems.

Explore related subjects

q-bio.QM

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Zhenyu Ma, Xukai Jiang. 2026-09-24. PRAXIS-VirtualCell: A Programmable and Trustworthy Framework for Agentic Virtual Cell Experiments. https://arxiv.org/abs/2609.29221

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

KEEP EXPLORING

Related papers

arXiv2026

Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

Predicting clinical outcomes from preclinical data is essential for selecting safe and effective drug combinations and for reducing late-stage failures. AI models use molecular structure and target annotations, and do not leverage the perturbation readouts that report how a compound acts in a cellular context. Here we introduce Madrigal, a multimodal AI model that learns from structural, pathway, cell-viability, and transcriptomic data. Madrigal aligns these modalities across 21,842 compounds into a shared latent space and predicts combination outcomes even for drugs observed in only a subset of the data modalities. Trained on 158 expert-curated and 795 patient-reported combination outcomes, Madrigal outperforms single-modality and state-of-the-art multimodal methods. Ablations show that modality alignment and multimodal input each improve predictive performance. Madrigal predicts elevated risk for combinations that share membrane transporters. In head-to-head trials that compare two combination arms,the arm with the higher observed incidence of neutropenia, anemia, alopecia, or hypoglycemia receives the higher predicted risk in 25 of 28 comparisons. In MASH, Madrigal ranks resmetirom among the candidates with favorable predicted safety when paired with type 2 diabetes drugs. Madrigal also improves adverse-event prediction in a longitudinal patient cohort and an independent oncology cohort and predicts efficacy in primary acute myeloid leukemia samples and patient-derived xenografts.

q-bio.QM↗

arXiv2026

ProteoEM: probabilistic protein abundance estimation from iterative affinity traces

Single-molecule affinity mapping enables molecular-level measurement of proteins and proteoforms, but imperfect and nonspecific probe binding makes individual affinity traces compatible with multiple molecular identities. Accurate abundance estimation therefore requires apportionment of ambiguous traces by weight rather than assignment to a single candidate. We developed ProteoEM, an expectation-maximization framework for weighted proteoform quantification, inspired by transcript abundance estimation methods for RNA sequencing and released as an open-source Python package. ProteoEM evaluates each molecule against every candidate using fixed, pre-calibrated probe-response rates held separate from the abundance estimate, while retaining the full likelihood of the observed affinity features. The framework estimates proteoform abundances, reports indistinguishable proteoforms as groups when measurements cannot separate them, and accounts for differential observation yields to distinguish the composition of observed molecules from that of the source sample. In simulations, ProteoEM accurately recovered the underlying molecular composition where approaches that reduce each trace to a hard yes/no call introduced substantial errors. ProteoEM's performance was insensitive to a moderate, uniform calibration error but was biased by informative missing data and by proteoforms absent from the reference. When observation yields were known, it also recovered source-sample composition from observed molecular counts. ProteoEM provides an open-source, reproducible framework for quantitative analysis of single-molecule affinity measurements, and these results motivate validation on experimental molecule-level data.

q-bio.QM↗

arXiv2026

BreCol: Benchmarking Classical and Deep-Learning Methods for Microbiome-Based Cancer Detection

DNA sequencing of the gut microbial community shows promise for cancer detection, but questions remain about the generalizability of results across studies. We propose BreCol, a benchmark of 2,040 16S rRNA gene sequencing runs across 26 studies spanning breast cancer, colorectal cancer, and healthy cohorts. Train-test splits are made within pre-2023 studies, while holdout evaluation uses studies from 2023 onward, reflecting temporal separation from training data. Classical models reach test/holdout AUCs of 0.77/0.60 for cancer diagnosis and 1.00/0.83 for cancer type prediction. We train the models on both cancer types simultaneously and find that colorectal cancer is often easier to detect than breast cancer. We also evaluate two deep learning models: HyenaDNA, a long-range sequence model that pools hidden states for classification, and SetBERT, a transformer that produces contextualized embeddings over sets of reads. Both deep learning models underperform the best classical methods on holdout data, though tuning training set size and the classification head yields modest gains. Our classical pipeline uses unsupervised clustering to derive features from tetramer frequencies, preserving within-run compositional signal and achieving near state-of-the-art performance without relying on taxonomic assignments. BreCol data and associated code are publicly available.

q-bio.QM↗