Biology subjects

Conley, S. D.

Publications and source records attributed to Conley, S. D..

3 recordsLinked to original sources

bioRxiv2026

PantheonOS: An Evolvable Multi-Agent Framework for Automatic Genomics Discovery

The convergence of large language model-powered autonomous agent systems and single-cell biology promises a paradigm shift in biomedical discovery. However, existing biological agent systems, building upon single-agent architectures, are narrowly specialized or overly general, limiting applications to routine analyses. We introduce PantheonOS (https://PantheonOS.stanford.edu), an evolvable, privacy-preserving multi-agent framework designed to reconcile generality with domain specificity. Critically, PantheonOS enables agentic code evolution, allowing evolving state-of-the-art batch correction and our reinforcement-learning augmented gene panel selection algorithms to achieve super-human performance. PantheonOS drives biological discoveries across systems: uncovering asymmetric paracrine Cer1-Nodal inhibition in proximal-distal axis formation of novel early mouse embryo 3D data; integrating human fetal heart multi-omics with whole-heart data to reveal molecular programs underpin heart diseases; and adaptively selecting virtual cell models to predict cardiac regulatory and perturbation effects. Together, PantheonOS points towards a future where scientific discoveries are increasingly driven by self-evolving AI systems across biology and beyond. Websitehttps://pantheonos.stanford.edu Ecosystemhttps://github.com/aristoteleo SummaryLarge language model-powered agent systems are driving a paradigm shift in scientific discovery by automating, scaling, and accelerating data analysis. This transformation is particularly profound in biology, where the rapid expansion of single-cell and spatial genomics has effectively reshaped the field into a data-intensive science. However, existing biological agent systems are typically constrained to single-agent designs, are narrowly specialized, or are overly general without sufficient domain expertise, limiting their applicability to routine or shallow analyses. Here, we introduce PantheonOS (https://pantheonos.stanford.edu), an evolvable, privacy-preserving, and general-purpose multi-agent framework designed to reconcile generality with deep domain specificity. PantheonOS provides an abstract, extensible architecture that enables customized agent composition and supports end-to-end single-cell and multi-omics analysis, spanning reinforcement-learning-augmented gene panel design, raw FASTQ processing, multimodal data integration, and three-dimensional spatial genomics reconstruction. Central to this framework, Pantheon-Evolve enables agentic code evolution, allowing the system to autonomously improve state-of-the-art batch-correction algorithms and new reinforcement-learning based gene panel design algorithms, achieving performance beyond manually designed baselines. We demonstrate the power of PantheonOS across multiple biological domains. In early mouse embryogenesis, PantheonOS automatically reconstructs three-dimensional spatial gene expression landscapes and resolves asymmetric Cer1 expression and paracrine Cer1-Nodal inhibition, revealing a robust proximal-distal axis at embryonic day six (E6.0). In human development, PantheonOS integrates fetal heart single-cell multi-omics with whole-heart 3D MERFISH+ data at post-conception week 12, uncovering spatially resolved molecular programs underlying heart disease ontogeny. Finally, an intelligent model-routing mechanism enables PantheonOS to adaptively select optimal virtual cell models across heterogeneous tasks, revealing minimal regulatory networks of cardiogenesis and predicting spatially resolved perturbation effects in the developing heart. Together, PantheonOS establishes a foundation for fully automated, evolvable, and domain-aware agentic analysis in genomics, and points toward a future in which scientific discovery is increasingly driven by self-improving AI systems across biology and beyond.

bioinformatics↗

bioRxiv2019

A molecular cell atlas of the human lung from single cell RNA sequencing

Although single cell RNA sequencing studies have begun providing compendia of cell expression profiles, it has proven more difficult to systematically identify and localize all molecular cell types in individual organs to create a full molecular cell atlas. Here we describe droplet- and plate-based single cell RNA sequencing applied to [~]75,000 human lung and blood cells, combined with a multi-pronged cell annotation approach, which have allowed us to define the gene expression profiles and anatomical locations of 58 cell populations in the human lung, including 41 of 45 previously known cell types or subtypes and 14 new ones. This comprehensive molecular atlas elucidates the biochemical functions of lung cell types and the cell-selective transcription factors and optimal markers for making and monitoring them; defines the cell targets of circulating hormones and predicts local signaling interactions including sources and targets of chemokines in immune cell trafficking and expression changes on lung homing; and identifies the cell types directly affected by lung disease genes and respiratory viruses. Comparison to mouse identified 17 molecular types that appear to have been gained or lost during lung evolution and others whose expression profiles have been substantially altered, revealing extensive plasticity of cell types and cell-type-specific gene expression during organ evolution including expression switches between cell types. This atlas provides the molecular foundation for investigating how lung cell identities, functions, and interactions are achieved in development and tissue engineering and altered in disease and evolution.

genomics↗

bioRxiv2017

Index Switching Causes "Spreading-Of-Signal" Among Multiplexed Samples In Illumina HiSeq 4000 DNA Sequencing

Illumina-based next generation sequencing (NGS) has accelerated biomedical discovery through its ability to generate thousands of gigabases of sequencing output per run at a fraction of the time and cost of conventional technologies. The process typically involves four basic steps: library preparation, cluster generation, sequencing, and data analysis. In 2015, a new chemistry of cluster generation was introduced in the newer Illumina machines (HiSeq 3000/4000/X Ten) called exclusion amplification (ExAmp), which was a fundamental shift from the earlier method of random cluster generation by bridge amplification on a non-patterned flow cell. The ExAmp chemistry, in conjunction with patterned flow cells containing nanowells at fixed locations, increases cluster density on the flow cell, thereby reducing the cost per run. It also increases sequence read quality, especially for longer read lengths (up to 150 base pairs). This advance has been widely adopted for genome sequencing because greater sequencing depth can be achieved for lower cost without compromising the quality of longer reads. We show that this promising chemistry is problematic, however, when multiplexing samples. We discovered that up to 5-10% of sequencing reads (or signals) are incorrectly assigned from a given sample to other samples in a multiplexed pool. We provide evidence that this \"spreading-of-signals\" arises from low levels of free index primers present in the pool. These index primers can prime pooled library fragments at random via complementary 3 ends, and get extended by DNA polymerase, creating a new library molecule with a new index before binding to the patterned flow cell to generate a cluster for sequencing. This causes the resulting read from that cluster to be assigned to a different sample, causing the spread of signals within multiplexed samples. We show that low levels of free index primers persist after the most common library purification procedure recommended by Illumina, and that the amount of signal spreading among samples is proportional to the level of free index primer present in the library pool. This artifact causes homogenization and misclassification of cells in single cell RNA-seq experiments. Therefore, all data generated in this way must now be carefully re-examined to ensure that \"spreading-of-signals\" has not compromised data analysis and conclusions. Re-sequencing samples using an older technology that uses conventional bridge amplification for cluster generation, or improved library cleanup strategies to remove free index primers, can minimize or eliminate this signal spreading artifact.

molecular biology↗