About

Christopher P. Calderon is an Associate Research Professor in the Department of Chemical and Biological Engineering at the University of Colorado Boulder. His research involves developing new statistics and machine learning applications for use in the basic physical and life sciences as well as industrial applications. His work focuses on data-driven modeling and hypothesis testing associated with noisy, correlated data such as images and time series data. Calderon has a particular interest in interdisciplinary research collaboration that leverages advances in machine learning and statistics to analyze images and signals recorded in nano to micro scale experimental systems. His research applications include time series analysis of single-molecule measurements to characterize biomolecules in both in vivo and in vitro environments, supervised and unsupervised machine learning and image analysis applied to high-throughput devices, and the analysis of noisy trace chemical detector signals in agricultural and military contexts. Calderon’s contributions are centered around the analysis of biological and chemical data, single-molecule experimental data, and sensor measurements, with a focus on classification, detection, and change point event analysis.

Research topics

• Computer Science
• Biology
• Artificial Intelligence
• Chemistry
• Biophysics
• Mathematics
• Materials science
• Biochemistry
• Cell biology
• Nanotechnology
• Physics
• Optics
• Biological system
• Statistics
• Composite material

Selected publications

• Representative training data sets are critical for accurate machine-learning classification of microscopy images of particles formed by lipase-catalyzed polysorbate hydrolysis

  Journal of Pharmaceutical Sciences · 2025-01-16 · 1 citations

  article
  PublisherDOI

• Unsupervised Machine Learning‐Based Process Analytical Tools for Near Real‐Time Cell Morphology Analysis During CAR‐T Cell Manufacturing

  Biotechnology and Bioengineering · 2025-06-16 · 5 citations

  articleCorresponding

  Cell therapies like Chimeric Antigen Receptor (CAR)-T cell therapy deliver living cells to patients as active pharmaceutical ingredients. Manufacturing of these cells is complex, often yielding, heterogeneous products and high failure rates. Quality control (QC) assays used in CAR-T cell production primarily provide end-point product testing. Real-time process monitoring would be ideal to reduce failure rates and ensure final product quality. However, current analytical tools often fall short due to the heterogeneity of CAR-T cell products and their sensitivity to process changes. In this study, we showcase unsupervised image-based machine learning as a process analytical tool (PAT) for near real-time process monitoring during the production of CAR-T cells. Flow imaging microscopy (FIM) images of T cells collected from nine healthy donors were recorded during the activation, lentiviral-based transduction (expressing CD19 CAR protein), and expansion stages of CAR-T cell production. These images were used to train a Variational Autoencoder (VAE), allowing quantitative tracking of changes in cell morphologies during the various stages of production of CAR-T cells from each donor. Findings include observation of a new, transient population in T cells transduced to express CAR protein. This population was absent in T cells that were not transduced. The density of the new population was proportional to the transduction efficiency determined by traditional stain-based flow cytometry assays. Together, this study demonstrates the utility of using VAEs as a PAT tool for monitoring patient-to-patient variability and early detection of process deviations/upsets.

  PublisherDOI

• Motion of VAPB molecules reveals ER–mitochondria contact site subdomains

  Nature · 2024 · 114 citations

  • Cell biology
  • Biophysics
  • Chemistry

  , a clear understanding of their nanoscale organization and regulation is still lacking. Here we combine three-dimensional electron microscopy with high-speed molecular tracking of a model organelle tether, Vesicle-associated membrane protein (VAMP)-associated protein B (VAPB), to map the structure and diffusion landscape of ERMCSs. We uncovered dynamic subdomains within VAPB contact sites that correlate with ER membrane curvature and undergo rapid remodelling. We show that VAPB molecules enter and leave ERMCSs within seconds, despite the contact site itself remaining stable over much longer time scales. This metastability allows ERMCSs to remodel with changes in the physiological environment to accommodate metabolic needs of the cell. An amyotrophic lateral sclerosis-associated mutation in VAPB perturbs these subdomains, likely impairing their remodelling capacity and resulting in impaired interorganelle communication. These results establish high-speed single-molecule imaging as a new tool for mapping the structure of contact site interfaces and reveal that the diffusion landscape of VAPB at contact sites is a crucial component of ERMCS homeostasis.

  PublisherOA PDFDOI

• Stain-Free Approach to Determine and Monitor Cell Heath Using Supervised and Unsupervised Image-Based Deep Learning

  Journal of Pharmaceutical Sciences · 2024-05-06 · 9 citations

  articleOpen access
  PublisherOA PDFDOI

• Supervised and unsupervised machine learning approaches for monitoring subvisible particles within an aluminum‐salt adjuvanted vaccine formulation

  Biotechnology and Bioengineering · 2024-02-19 · 6 citations

  article

  Suspensions of protein antigens adsorbed to aluminum-salt adjuvants are used in many vaccines and require mixing during vial filling operations to prevent sedimentation. However, the mixing of vaccine formulations may generate undesirable particles that are difficult to detect against the background of suspended adjuvant particles. We simulated the mixing of a suspension containing a protein antigen adsorbed to an aluminum-salt adjuvant using a recirculating peristaltic pump and used flow imaging microscopy to record images of particles within the pumped suspensions. Supervised convolutional neural networks (CNNs) were used to analyze the images and create "fingerprints" of particle morphology distributions, allowing detection of new particles generated during pumping. These results were compared to those obtained from an unsupervised machine learning algorithm relying on variational autoencoders (VAEs) that were also used to detect new particles generated during pumping. Analyses of images conducted by applying both supervised CNNs and VAEs found that rates of generation of new particles were higher in aluminum-salt adjuvant suspensions containing protein antigen than placebo suspensions containing only adjuvant. Finally, front-face fluorescence measurements of the vaccine suspensions indicated changes in solvent exposure of tryptophan residues in the protein that occurred concomitantly with new particle generation during pumping.

  PublisherDOI

• Features in Backgrounds of Microscopy Images Introduce Biases in Machine Learning Analyses

  Journal of Pharmaceutical Sciences · 2024-03-12 · 3 citations

  article
  PublisherDOI

• Interfacial Adsorption Controls Particle Formation in Antibody Formulations Subjected to Extensional Flows and Hydrodynamic Shear

  Journal of Pharmaceutical Sciences · 2023-07-13 · 18 citations

  articleOpen access
  PublisherOA PDFDOI

• Biotherapeutics Evaluation Using Artificial Intelligence Assisted Image Analysis

  Microscopy and Microanalysis · 2022-07-22

  articleOpen access

  Journal Article Biotherapeutics Evaluation Using Artificial Intelligence Assisted Image Analysis Get access Charudharshini Srinivasan, Charudharshini Srinivasan Division of Product Quality Research, Office of Testing and Research, Office of Pharmaceutical Quality, Center for Drug Evaluation Research, US Food and Drug Administration, Silver Spring, MD, USA Corresponding authors: Charudharshini.Srinivasan@fda.hhs.gov, Chris.Calderon@UrsaAnalytics.com Search for other works by this author on: Oxford Academic Google Scholar Christopher Calderon, Christopher Calderon Ursa Analytics and University of Colorado Boulder Corresponding authors: Charudharshini.Srinivasan@fda.hhs.gov, Chris.Calderon@UrsaAnalytics.com Search for other works by this author on: Oxford Academic Google Scholar Youlong Ma, Youlong Ma Division of Product Quality Research, Office of Testing and Research, Office of Pharmaceutical Quality, Center for Drug Evaluation Research, US Food and Drug Administration, Silver Spring, MD, USA Search for other works by this author on: Oxford Academic Google Scholar Dean Ripple, Dean Ripple National Institute of Standards and Technology (NIST) Search for other works by this author on: Oxford Academic Google Scholar Muhammad Ashraf, Muhammad Ashraf Division of Product Quality Research, Office of Testing and Research, Office of Pharmaceutical Quality, Center for Drug Evaluation Research, US Food and Drug Administration, Silver Spring, MD, USA Search for other works by this author on: Oxford Academic Google Scholar Thomas O'Connor Thomas O'Connor Division of Product Quality Research, Office of Testing and Research, Office of Pharmaceutical Quality, Center for Drug Evaluation Research, US Food and Drug Administration, Silver Spring, MD, USA Search for other works by this author on: Oxford Academic Google Scholar Microscopy and Microanalysis, Volume 28, Issue S1, 1 August 2022, Pages 3150–3152, https://doi.org/10.1017/S1431927622011709 Published: 01 August 2022

  PublisherOA PDFDOI

• Motion of single molecular tethers reveals dynamic subdomains at ER-mitochondria contact sites

  bioRxiv (Cold Spring Harbor Laboratory) · 2022-09-03 · 9 citations

  preprintOpen access

  To coordinate cellular physiology, eukaryotic cells rely on the inter-organelle transfer of molecules at specialized organelle-organelle contact sites 1,2 . Endoplasmic reticulum-mitochondria contact sites (ERMCSs) are particularly vital communication hubs, playing key roles in the exchange of signaling molecules, lipids, and metabolites 3 . ERMCSs are maintained by interactions between complementary tethering molecules on the surface of each organelle 4,5 . However, due to the extreme sensitivity of these membrane interfaces to experimental perturbation 6,7 , a clear understanding of their nanoscale structure and regulation is still lacking. Here, we combine 3D electron microscopy with high-speed molecular tracking of a model organelle tether, VAPB, to map the structure and diffusion landscape of ERMCSs. From EM reconstructions, we identified subdomains within the contact site where ER membranes dramatically deform to match local mitochondrial curvature. In parallel live cell experiments, we observed that the VAPB tethers that mediate this interface were not immobile, but rather highly dynamic, entering and leaving the site in seconds. These subdomains enlarged during nutrient stress, indicating ERMCSs can readily remodel under different physiological conditions. An ALS-associated mutation in VAPB altered the normal fluidity of contact sites, likely perturbing effective communication across the contact site and preventing remodeling. These results establish high speed single molecule imaging as a new tool for mapping the structure of contact site interfaces and suggest that the diffusion landscape of VAPB is a crucial component of ERMCS homeostasis.

  PublisherOA PDFDOI

• Testing Precision Limits of Neural Network-Based Quality Control Metrics in High-Throughput Digital Microscopy

  Pharmaceutical Research · 2022-01-26 · 10 citations

  article1st authorCorresponding
  PublisherDOI

Recent grants

• SBIR Phase I: Tracking Algorithms for Uncovering Complex Dynamic Interactions in Live Cells

  NSF · $150k · 2013–2013

• Quantitative Biotherapeutic Particle Characterization via Deep Neural Networks

  NIH · $222k · 2018–2021

Frequent coauthors

• Theodore W. Randolph

  University of Colorado Boulder

  16 shared

• Austin L. Daniels

  University of Colorado Boulder

  6 shared

• David N. Greenblott

  University of Colorado Boulder

  6 shared

• Jean‐Baptiste Masson

  6 shared

• Karunesh Arora

  5 shared

• Jonathon Nixon‐Abell

  Howard Hughes Medical Institute

  5 shared

• Federica Riccio

  Janelia Research Campus

  5 shared

• Gleb Shtengel

  Janelia Research Campus

  4 shared

Education

• B.S.

  Purdue University

• Ph.D.

  Princeton University

Awards & honors

• NIH "Nanobiology" Postdoctoral Fellow (2009)
• NSF VIGRE Fellow (2006)
• Gordon Wu Fellowship in Engineering from Princeton U. (2001)
• Lottes Memorial Award from Purdue U. (2001)