Biology subjects

Van Valen, D. A.

Publications and source records attributed to Van Valen, D. A..

12 recordsLinked to original sources

bioRxiv2026

Automated assembly of protein complexes from cryo-EM maps with structure-informed Monte Carlo Tree Search

Structural cell biology aims to visualize functional molecules as they carry out their biological roles in their native cellular context. However, macromolecular complexes in situ have thus far been resolved predominantly at intermediate resolutions, complicating protein identification and structural modeling due to the vast combinatorial space of possible components within a proteome. Here, we developed Cryosearch, a GPU-accelerated framework for automated assembly of macromolecular complexes from proteome-scale monomer libraries. Cryosearch implements Monte Carlo tree search with correlation-based rewards to identify combinations of protein domains that collectively best explain density maps. This approach enables autonomous de novo assembly of molecular complexes from intermediate-resolution maps.

bioinformatics↗

bioRxiv2025

Uncovering the molecular basis of kinase activity and substrate recognition with phospho-PCA

Protein kinases relay information to various cellular processes, and their dysregulation underlies numerous human diseases. Despite their importance, our understanding of how kinase domains and their variants impact protein stability, catalytic activity, and substrate recognition is incomplete. In this work, we develop the phosphorylation protein complementation assay (phospho-PCA), which enables quantitative measurements of kinase-substrate interactions by coupling them to the growth of bud-ding yeast, thereby enabling deep mutational scanning of kinase domains. When combined with deep mutational scans targeting folding stability and Bayesian modeling, phospho-PCA can disentangle the relative impact of mutations on kinase domain stability, catalytic activity, and substrate specificity. We demonstrate the accuracy and breadth of phospho-PCA, showing its applicability to both tyrosine and serine/threonine kinase domains. We then apply our method to three closely related protein kinases with distinct substrate preferences, evaluating over 15,000 kinase variants against a panel of three substrates for both catalytic activity and substrate specificity. The resulting dataset constitutes the largest and most detailed variant-to-function map assembled for this enzyme family to date, revealing numerous mutations that alter kinase activity and substrate specificity. Physics-based modeling reveals how these mutations operate through diverse mechanisms, including long-range allosteric communication, to alter both activity and substrate specificity. Given its scalability, we believe phospho-PCA can measure the functional impact of variants across the entire human kinome.

molecular biology↗

bioRxiv2025

Flow Autoencoders are Effective Protein Tokenizers

AO_SCPLOWBSTRACTC_SCPLOWProtein structure tokenizers enable the creation of multimodal models of protein structure, sequence, and function. Current approaches to protein structure tok-enization rely on bespoke components that are invariant to spatial symmetries, but that are challenging to optimize and scale. We present Kanzi, a flow-based tokenizer for tokenization and generation of protein structures. Kanzi consists of a diffusion autoencoder trained with a flow matching loss. We show that this approach simplifies several aspects of protein structure tokenizers: frame-based representations can be replaced with global coordinates, complex losses are replaced with a single flow matching loss, and SE(3)-invariant attention operations can be replaced with standard attention. We find that these changes stabilize the training of parameter-efficient models that outperform existing to- kenizers on reconstruction metrics at a fraction of the model size and training cost. An autoregressive model trained with Kanzi outperforms similar generative models that operate over tokens, although it does not yet match the performance of state-of-the-art continuous diffusion models. Code is available here: https://github.com/rdilip/kanzi/.

bioengineering↗

bioRxiv2025

CellTune: An integrative software for accurate cell classification in spatial proteomics

Spatial proteomics measures multiple proteins in situ, capturing tissue complexity. However, cell classification in densely packed tissues remains challenging due to the lack of efficient classification algorithms, annotation tools, and high-quality labeled datasets to benchmark computational methods. We introduce CellTune, an integrated software for analysis of large spatial proteomics datasets, which streamlines precise cell classification through an optimized human-in-the-loop active learning workflow. It advances core capabilities across within a unified, intuitive, and code-free interface. To evaluate CellTune, we created CellTuneDepot, a resource of 40k manually-annotated cells and 3.5 million high-quality labeled cells across 60 cell types. CellTune outperforms alternative methods, achieving accuracy comparable to human performance while enabling increased classification resolution and discovery of novel cell types. Together, CellTune and CellTuneDepot provide researchers with a tool for state-of-the-art classification accuracy and resolution at scale to drive biological insights.

bioinformatics↗

bioRxiv2024

Cellular behavior analysis from live-cell imaging of TCR T cell-cancer cell interactions

T cell therapies, such as chimeric antigen receptor (CAR) T cells and T cell receptor (TCR) T cells, are a growing class of anti-cancer treatments. However, expansion to novel indications and beyond last-line treatment requires engineering cells dynamic population behaviors. Here we develop the tools for cellular behavior analysis of T cells from live-cell imaging, a common and inexpensive experimental setup used to evaluate engineered T cells. We first develop a state-of-the-art segmentation and tracking pipeline, Caliban, based on human-in-the-loop deep learning. We then build the Occident pipeline to collect a catalog of phenotypes that characterize cell populations, morphology, movement, and interactions in co-cultures of modified T cells and antigen-presenting tumor cells. We use Caliban and Occident to interrogate how interactions between T cells and cancer cells differ when beneficial knock-outs of RASA2 and CUL5 are introduced into TCR T cells. We apply spatiotemporal models to quantify T cell recruitment and proliferation after interactions with cancer cells. We discover that, compared to a safe harbor knockout control, RASA2 knockout T cells have longer interaction times with cancer cells leading to greater T cell activation and killing efficacy, while CUL5 knockout T cells have increased proliferation rates leading to greater numbers of T cells for hunting. Together, segmentation and tracking from Caliban and phenotype quantification from Occident enable cellular behavior analysis to better engineer T cell therapies for improved cancer treatment.

cell biology↗

bioRxiv2024

Generalized cell phenotyping for spatial proteomics with language-informed vision models

We present DeepCell Types, a novel approach to cell phenotyping for spatial proteomics that addresses the challenge of generalization across diverse datasets with varying marker panels collected across different platforms. Our approach utilizes a transformer with channel-wise attention to create a language-informed vision model; this models semantic understanding of the underlying marker panel enables it to learn from and adapt to heterogeneous datasets. Leveraging a curated, diverse dataset named Expanded TissueNet with cell type labels spanning the literature and the NIH Human BioMolecular Atlas Program (HuBMAP) consortium, our model demonstrates robust performance across various cell types, tissues, and imaging modalities. Comprehensive benchmarking shows that our method outperforms existing approaches on cell-type prediction and, from the same model, predicts marker positivity competitively with a dedicated specialist; it further matches manual expert gating and adapts to new data with modest fine-tuning, well past what baselines reach when trained from scratch. This work equips the spatial proteomics community with a single, continuously improvable phenotyping model that generalizes to new marker panels and can be fine-tuned efficiently when needed. We release both DeepCell Types and Expanded TissueNet as open-source resources.

bioinformatics↗

bioRxiv2024

Automated classification of cellular expression in multiplexed imaging data with Nimbus

Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197 million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pre-trained model that uses the underlying images to classify marker expression across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use at https://github.com/angelolab/Nimbus-Inference.

bioinformatics↗

bioRxiv2023

A Foundation Model for Cell Segmentation

Cells are a fundamental unit of biological organization, and identifying them in imaging data - cell segmentation - is a critical task for various cellular imaging experiments. While deep learning methods have led to substantial progress on this problem, most models are specialist models that work well for specific domains but cannot be applied across domains or scale well with large amounts of data. In this work, we present CellSAM, a universal model for cell segmentation that generalizes across diverse cellular imaging data. CellSAM builds on top of the Segment Anything Model (SAM) by developing a prompt engineering approach for mask generation. We train an object detector, CellFinder, to automatically detect cells and prompt SAM to generate segmentations. We show that this approach allows a single model to achieve human-level performance for segmenting images of mammalian cells, yeast, and bacteria collected across various imaging modalities. We show that CellSAM has strong zero-shot performance and can be improved with a few examples via few-shot learning. Additionally, we demonstrate how CellSAM can be applied across diverse bioimage analysis workflows. A deployed version of CellSAM is available at https://cellsam.deepcell.org/.

bioinformatics↗

bioRxiv2023

Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning

Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually-tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from MERFSIH, seqFISH, or ISS experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.

bioinformatics↗

bioRxiv2022

A microwell platform for high-throughput longitudinal phenotyping and selective retrieval of organoids

Organoids are powerful experimental models for studying the ontogeny and progression of diseases including cancer. Organoids are conventionally cultured in bulk using an extracellular matrix mimic. However, organoids in bulk culture physically overlap, making it impossible to track the growth of individual organoids over time in high throughput. Moreover, local spatial variations in bulk matrix properties make it difficult to assess whether observed phenotypic heterogeneity between organoids results from intrinsic cell differences or microenvironment variability. Here, we developed a microwell-based method that enables high-throughput quantification of image-based parameters for organoids grown from single cells, which can be retrieved from their microwells for sequencing and molecular profiling. Coupled with a deep-learning image processing pipeline, we characterized phenotypic traits including growth rates, cellular movement, and apical-basal polarity in two CRISPR-engineered human gastric organoid models, identifying genomic changes associated with increased growth rate and changes in accessibility and expression correlated with apical-basal polarity.

bioengineering↗

bioRxiv2022

Modulation of bacterial cell size and growth rate via activation of a cell envelope stress response

Fluctuating conditions and diverse stresses are typical in natural environments. In response, cells mount complex responses across multiple scales, including adjusting their shape to withstand stress. In enterobacteria, the Rcs phosphorelay is activated by cell envelope damage and by changes to periplasmic dimensions and cell width. Here, we investigated the physiological and morphological consequences of Rcs activation in Escherichia coli in the absence of stresses, using an inducible version of RcsF that mislocalizes to the inner membrane, RcsFIM. Expression of RcsFIM immediately reduced cellular growth rate and the added length per cell cycle in a manner that was directly dependent on induction levels, but independent of Rcs-induced capsule production. At the same time, cells increased intracellular concentration of the cell division protein FtsZ, and decreased the distance between division rings in filamentous cells. Depletion of the Rcs negative regulator IgaA phenocopied RcsFIM induction, indicating that IgaA is essential due to growth inhibition in its absence. However, A22 treatment did not affect growth rate or FtsZ intracellular concentration, despite activating the Rcs system. These findings suggest that the effect of Rcs activation on FtsZ levels is mediated indirectly through growth-rate changes, and highlight feedbacks among the Rcs stress response, growth dynamics, and cell-size control.

microbiology↗

bioRxiv2019

Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning

While live-cell imaging is a powerful approach to studying the dynamics of cellular systems, converting these imaging data into quantitative, single-cell records of cellular behavior has been a longstanding challenge. Deep learning methods have proven capable of performing cell segmentation--a critical task for analyzing live-cell imaging data--but their performance in cell tracking has been limited by a lack of dynamic datasets with temporally consistent single-cell labels. We bridge this gap through the integrated development of labeling and deep learning methodology. We present a new framework for scalable, human-in-the-loop labeling of live-cell imaging movies, which we use to label a large collection of movies of fluorescently labeled cell nuclei. We use these data to create a new deep-learning-based cell-tracking method that achieves state-of-the-art performance in cell tracking. We have made all of the data, code, and software publicly available with permissive open-source licensing through the DeepCell projects web portal https://deepcell.org.

systems biology↗