Delays in appropriate antibiotic therapy are a key determinant for deleterious outcomes among pat... more Delays in appropriate antibiotic therapy are a key determinant for deleterious outcomes among patients with vancomycin-resistant Enterococcus (VRE) bloodstream infections (BSIs). This was a multi-center pre/post-implementation study, assessing the impact of a molecular rapid diagnostic test (Verigene® GP-BC, Luminex Corporation, Northbrook, IL, USA) on outcomes of adult patients with VRE BSIs. The primary outcome was time to optimal therapy (TOT). Multivariable logistic and Cox proportional hazard regression models were used to determine the independent associations of post-implementation, TOT, early vs. delayed therapy, and mortality. A total of 104 patients with VRE BSIs were included: 50 and 54 in the pre- and post-implementation periods, respectively. The post- vs. pre-implementation group was associated with a 1.8-fold faster rate to optimized therapy (adjusted risk ratio, 1.841 [95% CI 1.234–2.746]), 6-fold higher likelihood to receive early effective therapy (<24 h, adjust...
2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), 2016
The importance of automatic particle tracking for analyzing microscopy image data to discover hid... more The importance of automatic particle tracking for analyzing microscopy image data to discover hidden knowledge of complex biological systems has motivated the development of many tracking approaches. We have developed a new tracking approach that exploits information from multiple image scales and multiple time points, and directly combines the information in the optimization procedure. Our approach allows selecting an appropriate scale of a particle by using temporal information. Many-to-one and one-to-many associations are supported to deal with occlusion and deocclusion of particles. We have successfully applied our approach to real fluorescence microscopy image sequences displaying avian leukosis virus particles and quantified the performance.
Designing novel molecules with targeted biological activities and optimized physicochemical prope... more Designing novel molecules with targeted biological activities and optimized physicochemical properties is a challenging endeavor in drug discovery. Recent developments in artificial intelligence have enhanced the early steps of de novo drug design and compound optimization. Herein, we present a generative adversarial network trained to design new chemical matter that satisfies a given biological signature. Our model, called pqsar2cpd, is based on the activity of compounds across multiple assays obtained via pQSAR (profile-quantitative structure–activity relationships). We applied pqsar2cpd to Chagas disease and designed a novel molecule that was experimentally confirmed to inhibit growth of parasites in vitro at low micromolar concentrations. Altogether, this approach bridges chemistry and biology into one single framework for the design of novel molecules with promising biological activity.
Recent advances in generative modelling allow designing novel compounds through deep neural netwo... more Recent advances in generative modelling allow designing novel compounds through deep neural networks. One such neural network model, JT-VAE (the Junction Tree Variational Auto-Encoder), excels at proposing chemically valid structures. Here, on the basis of JT-VAE, we built a generative modelling approach, JAEGER, for finding novel chemical matter with desired bioactivity. Using JAEGER, we designed compounds to inhibit malaria. To prioritize the compounds for synthesis, we used the in-house pQSAR (Profile-QSAR) program, a massively multitask bioactivity model based on 12,000 Novartis assays. On the basis of pQSAR activity predictions, we selected, synthesized and experimentally profiled two compounds. Both compounds exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria. The compounds also showed low activity in a cytotoxicity assay. Our findings show that JAEGER is a viable approach for finding novel active compounds for drug discovery. Tropical diseases, such as malaria, can develop resistance to specific drugs. Godinez and colleagues present here a generative design approach to find new anti-malarial drugs to circumvent this resistance.
Open AcceResearch Human endogenous retrovirus HERV-K(HML-2) encodes a stable signal peptide with ... more Open AcceResearch Human endogenous retrovirus HERV-K(HML-2) encodes a stable signal peptide with biological properties distinct from Rec
Combination therapies are common in many therapeutic contexts, including infectious diseases and ... more Combination therapies are common in many therapeutic contexts, including infectious diseases and cancer. A common approach for evaluating combinations in vitro is to assess effects on cell growth as synergistic, antagonistic, or neutral using "checkerboard" experiments to systematically sample combinations of agents in multiple doses. To further understand the effects of antibiotic combinations, we employed high-content imaging to study the morphological changes caused by combination treatments in checkerboard experiments. Using an automated, unsupervised image analysis approach to group morphologies, and an "expert-in-the-loop" to annotate them, we attributed the heterogeneous morphological changes ofEscherichia coli cells to varying doses of both single-agent and combination treatments. We identified patterns of morphological change, including morphological potentiation, competition, and the emergence of unexpected morphologies. We found these frequently did not correlate with synergistic or antagonistic effects on viability, suggesting morphological approaches may provide a distinctive signature of the biological interaction between compounds over a range of conditions. Among the unexpected morphologies we observed, there were transitional changes associated with intermediate doses of compounds and uncharacterized phenotypes associated with well-studied antibiotics. Our approach exemplifies how unsupervised image analysis and expert knowledge can be combined to reckon with complex phenotypic changes arising from combination screening, dose titrations, or polypharmacology. In this way, quantification of morphological diversity across treatment conditions could aid in analysis and prioritization of complementary pairings of antibiotic agents by more closely capturing the true signature of the integrated cellular response.
2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009
ABSTRACT We are investigating the dynamical relationships exhibited by virus particles via fluore... more ABSTRACT We are investigating the dynamical relationships exhibited by virus particles via fluorescence time-lapse microscopy. To obtain a quantitative description of each particle over time, these objects are tracked. To derive an explicit characterization of each particle as well as to identify interesting transient behaviors, the intensity over time of each particle needs to be analyzed. We have developed an approach based on hybrid stochastic systems for identifying behaviors of interest. We employ a hybrid particle filter for estimating the behavior of individual particles. The approach has been successfully applied to particles tracked in synthetic image sequences as well as in real image sequences displaying HIV-1 particles.
Recent advances in generative modeling allow designing novel compounds through deep neural networ... more Recent advances in generative modeling allow designing novel compounds through deep neural networks. One such neural network model, the Junction Tree Variational Auto- Encoder (JT-VAE), excels at proposing chemically valid structures. Based on JT-VAE, we built a generative modeling approach (JAEGER) for finding novel chemical matter with desired bioactivity. Using JAEGER, we designed compounds to inhibit malaria. To prioritize the compounds for synthesis, we used the in-house Profile-QSAR (pQSAR) program, a massively-multitask bioactivity model based on 12,000 Novartis assays. Based on the pQSAR activity predictions, we selected, synthesized, and experimentally profiled two compounds. Both compounds exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria. The compounds also showed low activity in a cytotoxicity assay. Our findin...
Explicit and tractable characterizations of the dynamical behavior of virus particles are pivotal... more Explicit and tractable characterizations of the dynamical behavior of virus particles are pivotal for a thorough understanding of the infection mechanisms of viruses. This thesis deals with the problem of extracting symbolic representations of the dynamical behavior of fluorescent particles from fluorescence microscopy image sequences. The focus is on the behavior of virus particles such as fusion with the cell membrane. A numerical representation is obtained by tracking the particles in the image sequences. We have investigated probabilistic tracking approaches, including approaches based on the Kalman filter as well as based on particle filters. For reasons of efficiency and robustness, we developed a tracking approach based on the probabilistic data association (PDA) algorithm in combination with an ellipsoidal sampling scheme that exploits effectively the image data via parametric appearance models. To track objects in close proximity, we compute the support that each image posi...
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011
Tracking subcellular structures displayed as ‘particles’ in fluorescence microscopy images yields... more Tracking subcellular structures displayed as ‘particles’ in fluorescence microscopy images yields quantitative descriptions of the underlying dynamical processes. We have developed an approach for tracking multiple fluorescent particles. Our approach includes a localization scheme using probabilistic data association that combines a top-down strategy driven by the Kalman filter and a bottom-up strategy using standard localization algorithms for fluorescent particles. The combined scheme yields multiple positions that are incorporated to the filter via a combined innovation. To track objects in close proximity, we introduce a support map that adjusts the association probabilities. By using the combined localization scheme in conjunction with the Kalman filter we integrate localization and position estimation. The approach has been successfully applied to synthetic images as well as to real microscopy image sequences and the performance has been quantified.
Large-scale cellular imaging and phenotyping is a widely adopted strategy for understanding biolo... more Large-scale cellular imaging and phenotyping is a widely adopted strategy for understanding biological systems and chemical perturbations. Quantitative analysis of cellular images for identifying phenotypic changes is a key challenge within this strategy, and has recently seen promising progress with approaches based on deep neural networks. However, studies so far require either pre-segmented images as input or manual phenotype annotations for training, or both. To address these limitations, we have developed an unsupervised approach that exploits the inherent groupings within cellular imaging datasets to define surrogate classes that are used to train a multi-scale convolutional neural network. The trained network takes as input full-resolution microscopy images, and, without the need for segmentation, yields as output feature vectors that support phenotypic profiling. Benchmarked on two diverse benchmark datasets, the proposed approach yields accurate phenotypic predictions as we...
Beta-lactam antibiotics comprise one of the earliest known classes of antibiotic therapies. These... more Beta-lactam antibiotics comprise one of the earliest known classes of antibiotic therapies. These molecules covalently inhibit enzymes from the family of penicillin-binding proteins, which are essential to the construction of the bacterial cell wall. As a result, beta-lactams have long been known to cause striking changes to cellular morphology. The exact nature of the changes tend to vary by the precise PBPs engaged in the cell since beta-lactams exhibit a range of PBP enzyme specificity. The traditional method for exploring beta-lactam polyspecificity is a gel-based binding assay which is low-throughput and typically run ex situ in cell extracts. Here, we describe a medium-throughput, image-based assay combined with machine learning methods to automatically profile the activity of beta-lactams in E. coli cells. By testing for morphological change across a panel of strains with perturbations to individual PBP enzymes, our approach automatically and quantifiably relates different be...
Proceedings of the National Academy of Sciences, 2019
Significance Vessel cooption is a strategy that many tumors employ to progress without creating n... more Significance Vessel cooption is a strategy that many tumors employ to progress without creating new blood vessels but by exploiting preexisting vessels of the host tissue. In addition to promoting tumor growth, cooption is also associated with tumor resistance to antiangiogenic therapy. Despite the importance of this mode of tumor progression, the molecular and cellular mechanisms are not fully understood. Here, we combine intravital microscopy imaging and mathematical modeling to explore the dynamics of individual cancer cell cooption and collective response of the coopted cancer cells during antiangiogenic treatment. We also provide guidelines for effective therapeutic strategies that combine inhibition of both angiogenesis and cooption.
Although essential for many cellular processes, the sequence of structural and molecular events d... more Although essential for many cellular processes, the sequence of structural and molecular events during clathrin-mediated endocytosis remains elusive. While it was long believed that clathrin-coated pits grow with a constant curvature, it was recently suggested that clathrin first assembles to form flat structures that then bend while maintaining a constant surface area. Here, we combine correlative electron and light microscopy and mathematical growth laws to study the ultrastructural rearrangements of the clathrin coat during endocytosis in BSC-1 mammalian cells. We confirm that clathrin coats initially grow flat and demonstrate that curvature begins when around 70% of the final clathrin content is acquired. We find that this transition is marked by a change in the clathrin to clathrin-adaptor protein AP2 ratio and that membrane tension suppresses this transition. Our results support the notion that BSC-1 mammalian cells dynamically regulate the flat-to-curved transition in clathri...
Although essential for many cellular processes, the sequence of structural and molecular events d... more Although essential for many cellular processes, the sequence of structural and molecular events during clathrin-mediated endocytosis remains elusive. While it was believed that clathrin-coated pits grow with a constant curvature, it was recently suggested that clathrin first assembles to form a flat structure and then bends while maintaining a constant surface area. Here, we combine correlative electron and light microscopy and mathematical modelling to quantify the sequence of ultrastructural rearrangements of the clathrin coat during endocytosis in mammalian cells. We confirm that clathrin-coated structures can initially grow flat and that lattice curvature does not show a direct correlation with clathrin coat assembly. We demonstrate that curvature begins when 70% of the final clathrin content is acquired. We find that this transition is marked by a change in the clathrin to clathrin-adaptor protein AP2 ratio and that membrane tension suppresses this transition. Our results suppo...
Identifying phenotypes based on high-content cellular images is challenging. Conventional image a... more Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, incl...
Delays in appropriate antibiotic therapy are a key determinant for deleterious outcomes among pat... more Delays in appropriate antibiotic therapy are a key determinant for deleterious outcomes among patients with vancomycin-resistant Enterococcus (VRE) bloodstream infections (BSIs). This was a multi-center pre/post-implementation study, assessing the impact of a molecular rapid diagnostic test (Verigene® GP-BC, Luminex Corporation, Northbrook, IL, USA) on outcomes of adult patients with VRE BSIs. The primary outcome was time to optimal therapy (TOT). Multivariable logistic and Cox proportional hazard regression models were used to determine the independent associations of post-implementation, TOT, early vs. delayed therapy, and mortality. A total of 104 patients with VRE BSIs were included: 50 and 54 in the pre- and post-implementation periods, respectively. The post- vs. pre-implementation group was associated with a 1.8-fold faster rate to optimized therapy (adjusted risk ratio, 1.841 [95% CI 1.234–2.746]), 6-fold higher likelihood to receive early effective therapy (<24 h, adjust...
2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), 2016
The importance of automatic particle tracking for analyzing microscopy image data to discover hid... more The importance of automatic particle tracking for analyzing microscopy image data to discover hidden knowledge of complex biological systems has motivated the development of many tracking approaches. We have developed a new tracking approach that exploits information from multiple image scales and multiple time points, and directly combines the information in the optimization procedure. Our approach allows selecting an appropriate scale of a particle by using temporal information. Many-to-one and one-to-many associations are supported to deal with occlusion and deocclusion of particles. We have successfully applied our approach to real fluorescence microscopy image sequences displaying avian leukosis virus particles and quantified the performance.
Designing novel molecules with targeted biological activities and optimized physicochemical prope... more Designing novel molecules with targeted biological activities and optimized physicochemical properties is a challenging endeavor in drug discovery. Recent developments in artificial intelligence have enhanced the early steps of de novo drug design and compound optimization. Herein, we present a generative adversarial network trained to design new chemical matter that satisfies a given biological signature. Our model, called pqsar2cpd, is based on the activity of compounds across multiple assays obtained via pQSAR (profile-quantitative structure–activity relationships). We applied pqsar2cpd to Chagas disease and designed a novel molecule that was experimentally confirmed to inhibit growth of parasites in vitro at low micromolar concentrations. Altogether, this approach bridges chemistry and biology into one single framework for the design of novel molecules with promising biological activity.
Recent advances in generative modelling allow designing novel compounds through deep neural netwo... more Recent advances in generative modelling allow designing novel compounds through deep neural networks. One such neural network model, JT-VAE (the Junction Tree Variational Auto-Encoder), excels at proposing chemically valid structures. Here, on the basis of JT-VAE, we built a generative modelling approach, JAEGER, for finding novel chemical matter with desired bioactivity. Using JAEGER, we designed compounds to inhibit malaria. To prioritize the compounds for synthesis, we used the in-house pQSAR (Profile-QSAR) program, a massively multitask bioactivity model based on 12,000 Novartis assays. On the basis of pQSAR activity predictions, we selected, synthesized and experimentally profiled two compounds. Both compounds exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria. The compounds also showed low activity in a cytotoxicity assay. Our findings show that JAEGER is a viable approach for finding novel active compounds for drug discovery. Tropical diseases, such as malaria, can develop resistance to specific drugs. Godinez and colleagues present here a generative design approach to find new anti-malarial drugs to circumvent this resistance.
Open AcceResearch Human endogenous retrovirus HERV-K(HML-2) encodes a stable signal peptide with ... more Open AcceResearch Human endogenous retrovirus HERV-K(HML-2) encodes a stable signal peptide with biological properties distinct from Rec
Combination therapies are common in many therapeutic contexts, including infectious diseases and ... more Combination therapies are common in many therapeutic contexts, including infectious diseases and cancer. A common approach for evaluating combinations in vitro is to assess effects on cell growth as synergistic, antagonistic, or neutral using "checkerboard" experiments to systematically sample combinations of agents in multiple doses. To further understand the effects of antibiotic combinations, we employed high-content imaging to study the morphological changes caused by combination treatments in checkerboard experiments. Using an automated, unsupervised image analysis approach to group morphologies, and an "expert-in-the-loop" to annotate them, we attributed the heterogeneous morphological changes ofEscherichia coli cells to varying doses of both single-agent and combination treatments. We identified patterns of morphological change, including morphological potentiation, competition, and the emergence of unexpected morphologies. We found these frequently did not correlate with synergistic or antagonistic effects on viability, suggesting morphological approaches may provide a distinctive signature of the biological interaction between compounds over a range of conditions. Among the unexpected morphologies we observed, there were transitional changes associated with intermediate doses of compounds and uncharacterized phenotypes associated with well-studied antibiotics. Our approach exemplifies how unsupervised image analysis and expert knowledge can be combined to reckon with complex phenotypic changes arising from combination screening, dose titrations, or polypharmacology. In this way, quantification of morphological diversity across treatment conditions could aid in analysis and prioritization of complementary pairings of antibiotic agents by more closely capturing the true signature of the integrated cellular response.
2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009
ABSTRACT We are investigating the dynamical relationships exhibited by virus particles via fluore... more ABSTRACT We are investigating the dynamical relationships exhibited by virus particles via fluorescence time-lapse microscopy. To obtain a quantitative description of each particle over time, these objects are tracked. To derive an explicit characterization of each particle as well as to identify interesting transient behaviors, the intensity over time of each particle needs to be analyzed. We have developed an approach based on hybrid stochastic systems for identifying behaviors of interest. We employ a hybrid particle filter for estimating the behavior of individual particles. The approach has been successfully applied to particles tracked in synthetic image sequences as well as in real image sequences displaying HIV-1 particles.
Recent advances in generative modeling allow designing novel compounds through deep neural networ... more Recent advances in generative modeling allow designing novel compounds through deep neural networks. One such neural network model, the Junction Tree Variational Auto- Encoder (JT-VAE), excels at proposing chemically valid structures. Based on JT-VAE, we built a generative modeling approach (JAEGER) for finding novel chemical matter with desired bioactivity. Using JAEGER, we designed compounds to inhibit malaria. To prioritize the compounds for synthesis, we used the in-house Profile-QSAR (pQSAR) program, a massively-multitask bioactivity model based on 12,000 Novartis assays. Based on the pQSAR activity predictions, we selected, synthesized, and experimentally profiled two compounds. Both compounds exhibited low nanomolar activity in a malaria proliferation assay as well as a biochemical assay measuring activity against PI(4)K, which is an essential kinase that regulates intracellular development in malaria. The compounds also showed low activity in a cytotoxicity assay. Our findin...
Explicit and tractable characterizations of the dynamical behavior of virus particles are pivotal... more Explicit and tractable characterizations of the dynamical behavior of virus particles are pivotal for a thorough understanding of the infection mechanisms of viruses. This thesis deals with the problem of extracting symbolic representations of the dynamical behavior of fluorescent particles from fluorescence microscopy image sequences. The focus is on the behavior of virus particles such as fusion with the cell membrane. A numerical representation is obtained by tracking the particles in the image sequences. We have investigated probabilistic tracking approaches, including approaches based on the Kalman filter as well as based on particle filters. For reasons of efficiency and robustness, we developed a tracking approach based on the probabilistic data association (PDA) algorithm in combination with an ellipsoidal sampling scheme that exploits effectively the image data via parametric appearance models. To track objects in close proximity, we compute the support that each image posi...
2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2011
Tracking subcellular structures displayed as ‘particles’ in fluorescence microscopy images yields... more Tracking subcellular structures displayed as ‘particles’ in fluorescence microscopy images yields quantitative descriptions of the underlying dynamical processes. We have developed an approach for tracking multiple fluorescent particles. Our approach includes a localization scheme using probabilistic data association that combines a top-down strategy driven by the Kalman filter and a bottom-up strategy using standard localization algorithms for fluorescent particles. The combined scheme yields multiple positions that are incorporated to the filter via a combined innovation. To track objects in close proximity, we introduce a support map that adjusts the association probabilities. By using the combined localization scheme in conjunction with the Kalman filter we integrate localization and position estimation. The approach has been successfully applied to synthetic images as well as to real microscopy image sequences and the performance has been quantified.
Large-scale cellular imaging and phenotyping is a widely adopted strategy for understanding biolo... more Large-scale cellular imaging and phenotyping is a widely adopted strategy for understanding biological systems and chemical perturbations. Quantitative analysis of cellular images for identifying phenotypic changes is a key challenge within this strategy, and has recently seen promising progress with approaches based on deep neural networks. However, studies so far require either pre-segmented images as input or manual phenotype annotations for training, or both. To address these limitations, we have developed an unsupervised approach that exploits the inherent groupings within cellular imaging datasets to define surrogate classes that are used to train a multi-scale convolutional neural network. The trained network takes as input full-resolution microscopy images, and, without the need for segmentation, yields as output feature vectors that support phenotypic profiling. Benchmarked on two diverse benchmark datasets, the proposed approach yields accurate phenotypic predictions as we...
Beta-lactam antibiotics comprise one of the earliest known classes of antibiotic therapies. These... more Beta-lactam antibiotics comprise one of the earliest known classes of antibiotic therapies. These molecules covalently inhibit enzymes from the family of penicillin-binding proteins, which are essential to the construction of the bacterial cell wall. As a result, beta-lactams have long been known to cause striking changes to cellular morphology. The exact nature of the changes tend to vary by the precise PBPs engaged in the cell since beta-lactams exhibit a range of PBP enzyme specificity. The traditional method for exploring beta-lactam polyspecificity is a gel-based binding assay which is low-throughput and typically run ex situ in cell extracts. Here, we describe a medium-throughput, image-based assay combined with machine learning methods to automatically profile the activity of beta-lactams in E. coli cells. By testing for morphological change across a panel of strains with perturbations to individual PBP enzymes, our approach automatically and quantifiably relates different be...
Proceedings of the National Academy of Sciences, 2019
Significance Vessel cooption is a strategy that many tumors employ to progress without creating n... more Significance Vessel cooption is a strategy that many tumors employ to progress without creating new blood vessels but by exploiting preexisting vessels of the host tissue. In addition to promoting tumor growth, cooption is also associated with tumor resistance to antiangiogenic therapy. Despite the importance of this mode of tumor progression, the molecular and cellular mechanisms are not fully understood. Here, we combine intravital microscopy imaging and mathematical modeling to explore the dynamics of individual cancer cell cooption and collective response of the coopted cancer cells during antiangiogenic treatment. We also provide guidelines for effective therapeutic strategies that combine inhibition of both angiogenesis and cooption.
Although essential for many cellular processes, the sequence of structural and molecular events d... more Although essential for many cellular processes, the sequence of structural and molecular events during clathrin-mediated endocytosis remains elusive. While it was long believed that clathrin-coated pits grow with a constant curvature, it was recently suggested that clathrin first assembles to form flat structures that then bend while maintaining a constant surface area. Here, we combine correlative electron and light microscopy and mathematical growth laws to study the ultrastructural rearrangements of the clathrin coat during endocytosis in BSC-1 mammalian cells. We confirm that clathrin coats initially grow flat and demonstrate that curvature begins when around 70% of the final clathrin content is acquired. We find that this transition is marked by a change in the clathrin to clathrin-adaptor protein AP2 ratio and that membrane tension suppresses this transition. Our results support the notion that BSC-1 mammalian cells dynamically regulate the flat-to-curved transition in clathri...
Although essential for many cellular processes, the sequence of structural and molecular events d... more Although essential for many cellular processes, the sequence of structural and molecular events during clathrin-mediated endocytosis remains elusive. While it was believed that clathrin-coated pits grow with a constant curvature, it was recently suggested that clathrin first assembles to form a flat structure and then bends while maintaining a constant surface area. Here, we combine correlative electron and light microscopy and mathematical modelling to quantify the sequence of ultrastructural rearrangements of the clathrin coat during endocytosis in mammalian cells. We confirm that clathrin-coated structures can initially grow flat and that lattice curvature does not show a direct correlation with clathrin coat assembly. We demonstrate that curvature begins when 70% of the final clathrin content is acquired. We find that this transition is marked by a change in the clathrin to clathrin-adaptor protein AP2 ratio and that membrane tension suppresses this transition. Our results suppo...
Identifying phenotypes based on high-content cellular images is challenging. Conventional image a... more Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, incl...
Uploads
Papers