skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Friday, May 17 until 8:00 AM ET on Saturday, May 18 due to maintenance. We apologize for the inconvenience.


Search for: All records

Creators/Authors contains: "Caicedo, Juan"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset and an evaluation API to facilitate objective comparisons in future research and applications. 
    more » « less
  2. Observing changes in cellular phenotypes under experimental interventions is a powerful approach for studying biology and has many applications, including treatment design. Unfortunately, not all interventions can be tested experimentally, which limits our ability to study complex phenomena such as combinatorial treatments or continuous time or dose responses. In this work, we explore unbiased, image-based generative models to analyze phenotypic changes in cell morphology and tissue organization. The proposed approach is based on generative adversarial networks (GAN) conditioned on feature representations obtained with self-supervised learning. Our goal is to ensure that image-based phenotypes are accurately encoded in a latent space that can be later manipulated and used for generating images of novel phenotypic variations. We present an evaluation of our approach for phenotype analysis in a drug screen and a cancer tissue dataset. 
    more » « less
  3. Observing changes in cellular phenotypes under experimental interventions is a powerful approach for studying biology and has many applications, including treatment design. Unfortunately, not all interventions can be tested experimentally, which limits our ability to study complex phenomena such as combinatorial treatments or continuous time or dose responses. In this work, we explore unbiased, image-based generative models to analyze phenotypic changes in cell morphology and tissue organization. The proposed approach is based on generative adversarial networks (GAN) conditioned on feature representations obtained with self-supervised learning. Our goal is to ensure that image-based phenotypes are accurately encoded in a latent space that can be later manipulated and used for generating images of novel phenotypic variations. We present an evaluation of our approach for phenotype analysis in a drug screen and a cancer tissue dataset. 
    more » « less
  4. Free, publicly-accessible full text available December 11, 2024
  5. Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient. 
    more » « less
    Free, publicly-accessible full text available February 21, 2025
  6. Abstract

    Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data. Here, we present an improved strategy for learning representations of treatment effects from high-throughput imaging, following a causal interpretation. We use weakly supervised learning for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN. We evaluated our strategy on three publicly available Cell Painting datasets, and observed that the Cell Painting CNN improves performance in downstream analysis up to 30% with respect to classical features, while also being more computationally efficient.

     
    more » « less
  7. Abstract Predicting assay results for compounds virtually using chemical structures and phenotypic profiles has the potential to reduce the time and resources of screens for drug discovery. Here, we evaluate the relative strength of three high-throughput data sources—chemical structures, imaging (Cell Painting), and gene-expression profiles (L1000)—to predict compound bioactivity using a historical collection of 16,170 compounds tested in 270 assays for a total of 585,439 readouts. All three data modalities can predict compound activity for 6–10% of assays, and in combination they predict 21% of assays with high accuracy, which is a 2 to 3 times higher success rate than using a single modality alone. In practice, the accuracy of predictors could be lower and still be useful, increasing the assays that can be predicted from 37% with chemical structures alone up to 64% when combined with phenotypic data. Our study shows that unbiased phenotypic profiling can be leveraged to enhance compound bioactivity prediction to accelerate the early stages of the drug-discovery process. 
    more » « less
    Free, publicly-accessible full text available December 1, 2024
  8. Real-world deployment of computer vision systems, including in the discovery processes of biomedical research, requires causal representations that are invariant to contextual nuisances and generalize to new data. Leveraging the internal replicate structure of two novel single-cell fluorescent microscopy datasets, we propose generally applicable tests to assess the extent to which models learn causal representations across increasingly challenging levels of OODgeneralization. We show that despite seemingly strong performance as assessed by other established metrics, both naive and contemporary baselines designed to ward against confounding, collapse to random on these tests. We introduce a new method, Interventional Style Transfer (IST), that substantially improves OOD generalization by generating interventional training distributions in which spurious correlations between biological causes and nuisances are mitigated. We publish our code and datasets. 
    more » « less
    Free, publicly-accessible full text available July 1, 2024
  9. Smart Structures Technologies (SST) is receiving considerable attention as the demands for high performance in structural systems is increasing in recent years. Although both the academic and industrial worlds are seeking ways to utilize SST, there is a significant gap between engineering science in academia and engineering practice in the industry. To bridge the gap and facilitate the research infusion, San Francisco State University (SFSU) and the University of South Carolina (UofSC) collaborate with industrial partners to establish a Research Experiences for Undergraduates (REU) Site program, which provides undergraduate students a unique opportunity to experience research in both academic and industrial settings through cooperative research projects. In this paper, the development of the program, the two years implementation, as well as the lesson-learned, are discussed. 
    more » « less
  10. With increasing demands for high performance in structural systems, Smart Structures Technologies (SST) is receiving considerable attention as it has the potential to transform many fields in engineering, including civil, mechanical, aerospace, and geotechnical engineering. Both the academic and industrial worlds are seeking ways to utilize SST, however, there is a significant gap between the engineering science in academia and engineering practice in the industry. To respond to this challenge, San Francisco State University and the University of South Carolina collaborated with industrial partners to establish a Research Experiences for Undergraduates (REU) Site program, focusing on academia-industry collaborations in SST. This REU program intends to train undergraduate students to serve as the catalysts to facilitate the research infusion between academic and industrial partners. This student-driven joint venture between academia and industry is expected to establish a virtuous circle for knowledge exchange and contribute to advancing fundamental research and implementation of SST. The program features: formal training, workshops, and supplemental activities in the conduct of research in academia and industry; innovative research experience through engagement in projects with scientific and practical merits in both academic and industrial environments; experience in conducting laboratory experiments; and opportunities to present the research outcomes to the broader community at professional settings. This REU program provides engineering undergraduate students with unique research experience in both academic and industrial settings through cooperative research projects. Experiencing research in both worlds is expected to help students transition from a relatively dependent status to an independent status as their competence level increases. The joint efforts among two institutions and industry partners provide the project team with extensive access to valuable resources, such as expertise to offer a wider-range of informative training workshops, advanced equipment, valuable data sets, experienced mentors for the undergraduate researchers, and professional connections, that would facilitate a meaningful REU experience. Recruitment of participants targeted 20 collaborating minority and primarily undergraduate institutions (15 of them are Hispanic-Serving Institutions, HSI) with limited science, technology, engineering, and mathematics (STEM) research capabilities. The model developed through this program may help to exemplify the establishment of a sustainable collaboration model between academia and industry that helps address the nation's need for mature, independent, informed, and globally competitive STEM professionals and could be adapted to other disciplines. In this paper, the details of the first-year program are described. The challenges and lessons-learned on the collaboration between the two participating universities, communications with industrial partners, recruitment of the students, set up of the evaluation plans, and development and implementation of the program are discussed. The preliminary evaluation results and recommendations are also shared. 
    more » « less