Search for: All records

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.

 

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. 

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. 

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. 

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. 

Greenhouse gases trap heat within our atmosphere, leading to an unnatural increase in temperature. Carbon dioxide and its equivalent emissions have been a large focus when considering sustainability in the civil engineering field, with a reduction of global warming potential being a top priority. According to a 2017 report by the World Green Building Council, the construction and usage of buildings account for 39 percent of human carbon emissions in the United States, almost one third of which are from the extraction, manufacturing, and transportation of materials. Substituting wood for high emission materials could greatly reduce carbon if harvested and disposed of in a controlled way. To investigate this important issue, San Francisco State University and University of South Carolina partnered with Skidmore, Owings & Merrill LLP, a world leader in designing high-rise buildings, through a National Science Foundation (NSF) Research Experience for Undergraduates (REU) Site program, to investigate and quantify the embodied carbons of various slab system designs using a high-rise residential complex in San Francisco as a case study. Three concept designs were considered: a concrete building with cementitious replacement, a concrete building without cementitious replacement, and a concrete building with cementitious replacement and nail-laminated timber wood inlays inserted into various areas of the superstructure slabs. The composite structural slab system has the potential to surpass the limitations of wood-framed structures yet incorporate the carbon sequestration that makes wood a more sustainable material. The results show that wood substitution could decrease overall emissions from the aforementioned designs and reduce the environmental footprint of the construction industry. 

Greenhouse gases trap heat within our atmosphere, leading to an unnatural increase in temperature. Carbon dioxide and its equivalent emissions have been a large focus when considering sustainability in the civil engineering field, with a reduction of global warming potential being a top priority. According to a 2017 report by the World Green Building Council, the construction and usage of buildings account for 39 percent of human carbon emissions in the United States, almost one third of which are from the extraction, manufacturing, and transportation of materials. Substituting wood for high emission materials could greatly reduce carbon if harvested and disposed of in a controlled way. To investigate this important issue, San Francisco State University and University of South Carolina partnered with Skidmore, Owings & Merrill LLP, a world leader in designing high-rise buildings, through a National Science Foundation (NSF) Research Experience for Undergraduates (REU) Site program, to investigate and quantify the embodied carbons of various slab system designs using a high-rise residential complex in San Francisco as a case study. Three concept designs were considered: a concrete building with cementitious replacement, a concrete building without cementitious replacement, and a concrete building with cementitious replacement and naillaminated timber wood inlays inserted into various areas of the superstructure slabs. The composite structural slab system has the potential to surpass the limitations of wood-framed structures yet incorporate the carbon sequestration that makes wood a more sustainable material. The results show that wood substitution could decrease overall emissions from the aforementioned designs and reduce the environmental footprint of the construction industry. 

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 undergraduate mentors, 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 will be described. The challenges and lesson-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 will be discussed. The preliminary evaluation results and recommendations will also be shared. 

The gap between research in academia and industry is narrowing as collaboration between the two becomes critical. Topology optimization has the potential to reduce the carbon footprint by minimizing material usage within the design space based on given loading conditions. While being a useful tool in the design phase of the engineering process, its complexity has hindered its progression and integration in actual design. As a result, the advantages of topology optimization have yet to be implemented into common engineering practice. To facilitate the implementation and promote the usage of topology optimization, San Francisco State University and the University of South Carolina collaborated with ARUP, a world leader in structural designs, to develop an Automated Topology Optimization Platform (ATOP) to synchronize commonly used industry software programs and provide a user-friendly and automated solution to perform topology optimization. ATOP allows for users to form a conceptual understanding of a structure’s ideal shape and design in terms of ideal material placement by iterating various parameters such as volume fraction, and minimum and maximum member size at the start of a project. With the developed platform, a high-rise building design from the literature was first adopted to validate the results from ATOP, after which an actual design project from ARUP was utilized to fully explore its functionality and versatility. Results show that ATOP has the potential to create aesthetic and structurally sound designs through an automated and intelligent process. 

The gap between research in academia and industry is narrowing as collaboration between the two becomes critical. Topology optimization has the potential to reduce the carbon footprint by minimizing material usage within the design space based on given loading conditions. While being a useful tool in the design phase of the engineering process, its complexity has hindered its progression and integration in actual design. As a result, the advantages of topology optimization have yet to be implemented into common engineering practice. To facilitate the implementation and promote the usage of topology optimization, San Francisco State University and the University of South Carolina collaborated with ARUP, a world leader in structural designs, to develop an Automated Topology Optimization Platform (ATOP) to synchronize commonly used industry software programs and provide a user-friendly and automated solution to perform topology optimization. ATOP allows for users to form a conceptual understanding of a structure’s ideal shape and design in terms of ideal material placement by iterating various parameters such as volume fraction, and minimum and maximum member size at the start of a project. With developed platform, a high-rise building design from the literature was first adopted to validate the results from ATOP, after which an actual design project from ARUP was utilized to fully explore its functionality and versatility. Results show that ATOP has the potential to create aesthetic and structurally sound designs through an automated and intelligent process.