ABSTRACT
High-order radiomic features have been shown to produce high performance models in a variety of scenarios. However, models trained without high-order features have shown similar performance, raising the question of whether high-order features are worth including given their increased computational burden. This comparative study investigates the impact of high-order features on model performance in CT-based Non-Small Cell Lung Cancer (NSCLC) and the potential uncertainty regarding their application in machine learning. Three categories of features were retrospectively retrieved from CT images of 347 NSCLC patients: first- and second-order statistical features, morphological features and transform (high-order) features. From these, three datasets were constructed: a "low-order" dataset (Lo) which included the first-order, second-order, and morphological features, a high-order dataset (Hi), and a combined dataset (Combo). A diverse selection of datasets, feature selection methods, and predictive models were included for the uncertainty analysis, with two-year survival as the study endpoint. AUC values were calculated for comparisons and Kruskal-Wallis testing was performed to determine significant differences. The Hi (AUC: 0.41-0.62) and Combo (AUC: 0.41-0.62) datasets generate significantly (P < 0.01) higher model performance than the Lo dataset (AUC: 0.42-0.58). High-order features are selected more often than low-order features for model training, comprising 87 % of selected features in the Combo dataset. High-order features are a source of data that can improve machine learning model performance. However, its impact strongly depends on various factors that may lead to inconsistent results. A clear approach to incorporate high-order features in radiomic studies requires further investigation.
ABSTRACT
Clinical resistance to rat sarcoma virus (Ras)-G12C inhibitors is a challenge. A subpopulation of cancer cells has been shown to undergo genomic and transcriptional alterations to facilitate drug resistance but the immediate adaptive effects on Ras signaling in response to these drugs at the single-cell level is not well understood. Here, we used Ras biosensors to profile the activity and signaling environment of endogenous Ras at the single-cell level. We found that a subpopulation of KRas-G12C cells treated with Ras-G12C-guanosine-diphosphate inhibitors underwent adaptive signaling and metabolic changes driven by wild-type Ras at the Golgi and mutant KRas at the mitochondria, respectively. Our Ras biosensors identified major vault protein as a mediator of Ras activation through its scaffolding of Ras signaling pathway components and metabolite channels. Overall, methods including ours that facilitate direct analysis on the single-cell level can report the adaptations that subpopulations of cells adopt in response to cancer therapies, thus providing insight into drug resistance.
ABSTRACT
Programming protein nanomaterials to respond to changes in environmental conditions is a current challenge for protein design and is important for targeted delivery of biologics. Here we describe the design of octahedral non-porous nanoparticles with a targeting antibody on the two-fold symmetry axis, a designed trimer programmed to disassemble below a tunable pH transition point on the three-fold axis, and a designed tetramer on the four-fold symmetry axis. Designed non-covalent interfaces guide cooperative nanoparticle assembly from independently purified components, and a cryo-EM density map closely matches the computational design model. The designed nanoparticles can package protein and nucleic acid payloads, are endocytosed following antibody-mediated targeting of cell surface receptors, and undergo tunable pH-dependent disassembly at pH values ranging between 5.9 and 6.7. The ability to incorporate almost any antibody into a non-porous pH-dependent nanoparticle opens up new routes to antibody-directed targeted delivery.
ABSTRACT
Immune checkpoint blockade (ICB) therapy holds promise for bringing long-lasting clinical gains for the treatment of cancer. However, studies show that only a fraction of patients respond to the treatment. In this regard, it is valuable to develop gene expression signatures based on RNA sequencing (RNAseq) data and machine learning methods to predict a patient's response to the ICB therapy, which contributes to more personalized treatment strategy and better management of cancer patients. However, due to the limited sample size of ICB trials with RNAseq data available and the vast number of candidate gene expression features, it is challenging to develop well-performed gene expression signatures. In this study, we used several published melanoma datasets and investigated approaches that can improve the construction of gene expression-based prediction models. We found that merging datasets from multiple studies and incorporating prior biological knowledge yielded prediction models with higher predictive accuracies. Our finding suggests that these two strategies are of high value to identify ICB response biomarkers in future studies.
Subject(s)
Immune Checkpoint Inhibitors , Melanoma , Humans , Immune Checkpoint Inhibitors/pharmacology , Immune Checkpoint Inhibitors/therapeutic use , Melanoma/drug therapy , Melanoma/genetics , Knowledge , Machine Learning , RNAABSTRACT
The utility of genetically encoded biosensors for sensing the activity of signaling proteins has been hampered by a lack of strategies for matching sensor sensitivity to the physiological concentration range of the target. Here we used computational protein design to generate intracellular sensors of Ras activity (LOCKR-based Sensor for Ras activity (Ras-LOCKR-S)) and proximity labelers of the Ras signaling environment (LOCKR-based, Ras activity-dependent Proximity Labeler (Ras-LOCKR-PL)). These tools allow the detection of endogenous Ras activity and labeling of the surrounding environment at subcellular resolution. Using these sensors in human cancer cell lines, we identified Ras-interacting proteins in oncogenic EML4-Alk granules and found that Src-Associated in Mitosis 68-kDa (SAM68) protein specifically enhances Ras activity in the granules. The ability to subcellularly localize endogenous Ras activity should deepen our understanding of Ras function in health and disease and may suggest potential therapeutic strategies.
ABSTRACT
Lung cancer subtyping based on gene expression data is important for identifying patient subgroups with differing survival prognosis to facilitate customized treatment strategies for each subtype of patients. Unsupervised clustering methods are the traditional approach for clustering patients into subtypes. However, since those methods cluster patients based only on gene expression data, the resulting clusters may not always be relevant to the survival outcome of interest. In recent years, semi-supervised and supervised methods have been proposed, which leverage the survival outcome data to identify clusters more relevant to survival prognosis. This paper aims to compare the performance of different clustering methods for identifying clinically prognostic lung cancer subtypes based on two lung adenocarcinoma datasets. For each method, we clustered patients into two clusters and assessed the difference in patient survival time between clusters. Unsupervised methods were found to have large logrank p-values and no significant results in most cases. Semi-supervised and supervised methods had improved performance over unsupervised methods and very significant p-values. These results indicate that unsupervised methods are not capable of identifying clusters with significant differences in survival prognosis in most cases, while supervised and semi-supervised methods can better cluster patients into clinically useful subtypes.
Subject(s)
Lung Neoplasms , Humans , Lung Neoplasms/diagnosis , Lung Neoplasms/genetics , Lung Neoplasms/metabolism , Cluster Analysis , Gene ExpressionABSTRACT
Recently developed covalent inhibitors for RasG12C provide the first pharmacological tools to target mutant Ras-driven cancers. However, the rapid development of resistance to current clinical Ras G12C inhibitors is common. Presumably, a subpopulation of RasG12C-expressing cells adapt their signaling to evade these inhibitors and the mechanisms for this phenomenon are unclear due to the lack of tools that can measure signaling with single-cell resolution. Here, we utilized recently developed Ras sensors to profile the environment of active Ras and to measure the activity of endogenous Ras in order to pair structure (Ras signalosome) to function (Ras activity), respectively, at a single-cell level. With this approach, we identified a subpopulation of KRasG12C cells treated with RasG12C-GDP inhibitors underwent oncogenic signaling and metabolic changes driven by WT Ras at the golgi and mutant Ras at the mitochondria, respectively. Our Ras sensors identified Major Vault Protein (MVP) as a mediator of Ras activation at both compartments by scaffolding Ras signaling pathway components and metabolite channels. We found that recently developed RasG12C-GTP inhibitors also led to MVP-mediated WT Ras signaling at the golgi, demonstrating that this a general mechanism RasG12C inhibitor resistance. Overall, single-cell analysis of structure-function relationships enabled the discovery of a RasG12C inhibitor-resistant subpopulation driven by MVP, providing insight into the complex and heterogenous rewiring occurring during drug resistance in cancer.
ABSTRACT
Protein quality control (PQC) is carried out in part by the chaperone Hsp70, in concert with adapters of the J-domain protein (JDP) family. The JDPs, also called Hsp40s, are thought to recruit Hsp70 into complexes with specific client proteins. However, the molecular principles regulating this process are not well understood. We describe the de novo design of a set of Hsp70 binding proteins that either inhibited or stimulated Hsp70's ATPase activity; a stimulating design promoted the refolding of denatured luciferase in vitro, similar to native JDPs. Targeting of this design to intracellular condensates resulted in their nearly complete dissolution. The designs inform our understanding of chaperone structure-function relationships and provide a general and modular way to target PQC systems to condensates and other cellular targets.
ABSTRACT
Endocytosis and lysosomal trafficking of cell surface receptors can be triggered by interaction with endogenous ligands. Therapeutic approaches such as LYTAC1,2 and KineTAC3, have taken advantage of this to target specific proteins for degradation by fusing modified native ligands to target binding proteins. While powerful, these approaches can be limited by possible competition with the endogenous ligand(s), the requirement in some cases for chemical modification that limits genetic encodability and can complicate manufacturing, and more generally, there may not be natural ligands which stimulate endocytosis through a given receptor. Here we describe general protein design approaches for designing endocytosis triggering binding proteins (EndoTags) that overcome these challenges. We present EndoTags for the IGF-2R, ASGPR, Sortillin, and Transferrin receptors, and show that fusing these tags to proteins which bind to soluble or transmembrane protein leads to lysosomal trafficking and target degradation; as these receptors have different tissue distributions, the different EndoTags could enable targeting of degradation to different tissues. The modularity and genetic encodability of EndoTags enables AND gate control for higher specificity targeted degradation, and the localized secretion of degraders from engineered cells. The tunability and modularity of our genetically encodable EndoTags should contribute to deciphering the relationship between receptor engagement and cellular trafficking, and they have considerable therapeutic potential as targeted degradation inducers, signaling activators for endocytosis-dependent pathways, and cellular uptake inducers for targeted antibody drug and RNA conjugates.
ABSTRACT
Programming protein nanomaterials to respond to changes in environmental conditions is a current challenge for protein design and important for targeted delivery of biologics. We describe the design of octahedral non-porous nanoparticles with the three symmetry axes (four-fold, three-fold, and two-fold) occupied by three distinct protein homooligomers: a de novo designed tetramer, an antibody of interest, and a designed trimer programmed to disassemble below a tunable pH transition point. The nanoparticles assemble cooperatively from independently purified components, and a cryo-EM density map reveals that the structure is very close to the computational design model. The designed nanoparticles can package a variety of molecular payloads, are endocytosed following antibody-mediated targeting of cell surface receptors, and undergo tunable pH-dependent disassembly at pH values ranging between to 5.9-6.7. To our knowledge, these are the first designed nanoparticles with more than two structural components and with finely tunable environmental sensitivity, and they provide new routes to antibody-directed targeted delivery.
ABSTRACT
De novo enzyme design has sought to introduce active sites and substrate-binding pockets that are predicted to catalyse a reaction of interest into geometrically compatible native scaffolds1,2, but has been limited by a lack of suitable protein structures and the complexity of native protein sequence-structure relationships. Here we describe a deep-learning-based 'family-wide hallucination' approach that generates large numbers of idealized protein structures containing diverse pocket shapes and designed sequences that encode them. We use these scaffolds to design artificial luciferases that selectively catalyse the oxidative chemiluminescence of the synthetic luciferin substrates diphenylterazine3 and 2-deoxycoelenterazine. The designed active sites position an arginine guanidinium group adjacent to an anion that develops during the reaction in a binding pocket with high shape complementarity. For both luciferin substrates, we obtain designed luciferases with high selectivity; the most active of these is a small (13.9 kDa) and thermostable (with a melting temperature higher than 95 °C) enzyme that has a catalytic efficiency on diphenylterazine (kcat/Km = 106 M-1 s-1) comparable to that of native luciferases, but a much higher substrate specificity. The creation of highly active and specific biocatalysts from scratch with broad applications in biomedicine is a key milestone for computational enzyme design, and our approach should enable generation of a wide range of luciferases and other enzymes.
Subject(s)
Deep Learning , Luciferases , Biocatalysis , Catalytic Domain , Enzyme Stability , Hot Temperature , Luciferases/chemistry , Luciferases/metabolism , Luciferins/metabolism , Luminescence , Oxidation-Reduction , Substrate SpecificityABSTRACT
Objective.While simulated low-dose CT images and phantom studies cannot fully approximate subjective and objective effects of deep learning (DL) denoising on image quality, live animal models may afford this assessment. This study is to investigate the potential of DL in CT dose reduction on image quality compared to iterative reconstruction (IR).Approach.The upper abdomen of a live 4 year old sheep was scanned on a CT scanner at different exposure levels. Images were reconstructed using FBP and ADMIRE with 5 strengths. A modularized DL network with 5 modules was used for image reconstruction via progressive denoising. Radiomic features were extracted from a region over the liver. Concordance correlation coefficient (CCC) was applied to quantify agreement between any two sets of radiomic features. Coefficient of variation was calculated to measure variation in a radiomic feature series. Structural similarity index (SSIM) was used to measure the similarity between any two images. Diagnostic quality, low-contrast detectability, and image texture were qualitatively evaluated by two radiologists. Pearson correlation coefficient was computed across all dose-reconstruction/denoising combinations.Results.A total of 66 image sets, with 405 radiomic features extracted from each, are analyzed. IR and DL can improve diagnostic quality and low-contrast detectability and similarly modulate image texture features. In terms of SSIM, DL has higher potential in preserving image structure. There is strong correlation between SSIM and radiologists' evaluations for diagnostic quality (0.559) and low-contrast detectability (0.635) but moderate correlation for texture (0.313). There is moderate correlation between CCC of radiomic features and radiologists' evaluation for diagnostic quality (0.397), low-contrast detectability (0.417), and texture (0.326), implying that improvement of image features may not relate to improvement of diagnostic quality.Conclusion.DL shows potential to further reduce radiation dose while preserving structural similarity, while IR is favored by radiologists and more predictably alters radiomic features.
Subject(s)
Deep Learning , Radiographic Image Interpretation, Computer-Assisted , Abdomen/diagnostic imaging , Algorithms , Animals , Drug Tapering , Phantoms, Imaging , Radiation Dosage , Radiographic Image Interpretation, Computer-Assisted/methods , Sheep , Tomography, X-Ray Computed/methodsABSTRACT
We designed a protein biosensor that uses thermodynamic coupling for sensitive and rapid detection of neutralizing antibodies against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants in serum. The biosensor is a switchable, caged luciferase-receptor-binding domain (RBD) construct that detects serum-antibody interference with the binding of virus RBD to angiotensin-converting enzyme 2 (ACE-2) as a proxy for neutralization. Our coupling approach does not require target modification and can better distinguish sample-to-sample differences in analyte binding affinity and abundance than traditional competition-based assays.
Subject(s)
Biosensing Techniques , COVID-19 , Antibodies, Neutralizing/chemistry , Antibodies, Viral/genetics , COVID-19/diagnosis , Humans , Neutralization Tests , SARS-CoV-2/genetics , Spike Glycoprotein, Coronavirus/chemistryABSTRACT
Fluorescence-based sensors are powerful molecular tools for studying the spatiotemporal regulation of cell signaling, which is often organized into discrete microdomains. Here, we present a protocol for using fluorescent sensors targeted to endogenous proteins (FluoSTEPs), a new class of fluorescent sensors in which the functional probe is exclusively reconstituted at an endogenously expressed protein of interest associated with a specific microdomain. FluoSTEPs allow microdomain-specific signaling activities to be measured with high selectivity without perturbing the native stoichiometry of signaling components. For complete details on the use and execution of this protocol, please refer to Zhang et al. (2020) and Tenner et al. (2021).
Subject(s)
Fluorescent Antibody Technique/methods , Protein Domains/physiology , Fluorescence , Fluorescent Dyes/chemistry , Protein Transport/physiology , Signal Transduction/physiology , Spatio-Temporal AnalysisABSTRACT
Numerous processes occur simultaneously in the cell both for normal function and in response to changes in the environment. The ability of cells to segregate biochemical reactions into separate compartments is essential to ensure specificity and efficiency in cellular processes. The discovery of liquid-liquid phase separation as a mechanism of compartmentalization has revised our thinking regarding the intracellular organization of molecular pathways such as signal transduction. Here, we highlight recent studies that advance our understanding of how phase separation impacts the organization of biochemical processes, with a particular focus on the tools used to study the functional impact of phase separation. In addition, we offer some of our perspectives on the pathological consequences of dysregulated phase separation in biochemical pathways.
ABSTRACT
With global vaccination efforts against SARS-CoV-2 underway, there is a need for rapid quantification methods for neutralizing antibodies elicited by vaccination and characterization of their strain dependence. Here, we describe a designed protein biosensor that enables sensitive and rapid detection of neutralizing antibodies against wild type and variant SARS-CoV-2 in serum samples. More generally, our thermodynamic coupling approach can better distinguish sample to sample differences in analyte binding affinity and abundance than traditional competition based assays.
ABSTRACT
Growing evidence suggests that many essential intracellular signaling events are compartmentalized within kinetically distinct microdomains in cells. Genetically encoded fluorescent biosensors are powerful tools to dissect compartmentalized signaling, but current approaches to probe these microdomains typically rely on biosensor fusion and overexpression of critical regulatory elements. Here, we present a novel class of biosensors named FluoSTEPs (fluorescent sensors targeted to endogenous proteins) that combine self-complementing split green fluorescent protein, CRISPR-mediated knock-in, and fluorescence resonance energy transfer biosensor technology to probe compartmentalized signaling dynamics in situ. We designed FluoSTEPs for simultaneously highlighting endogenous microdomains and reporting domain-specific, real-time signaling events including kinase activities, guanosine triphosphatase activation, and second messenger dynamics in live cells. A FluoSTEP for 3',5'-cyclic adenosine monophosphate (cAMP) revealed distinct cAMP dynamics within clathrin microdomains in response to stimulation of G protein-coupled receptors, showcasing the utility of FluoSTEPs in probing spatiotemporal regulation within endogenous signaling architectures.
Subject(s)
Biosensing Techniques , Cyclic AMP , Coloring Agents , Cyclic AMP/metabolism , Fluorescence Resonance Energy Transfer , Green Fluorescent Proteins/genetics , Signal TransductionABSTRACT
Protein kinases control nearly every facet of cellular function. These key signaling nodes integrate diverse pathway inputs to regulate complex physiological processes, and aberrant kinase signaling is linked to numerous pathologies. While fluorescent protein-based biosensors have revolutionized the study of kinase signaling by allowing direct, spatiotemporally precise kinase activity measurements in living cells, powerful new molecular tools capable of robustly tracking kinase activity dynamics across diverse experimental contexts are needed to fully dissect the role of kinase signaling in physiology and disease. Here, we report the development of an ultrasensitive, second-generation excitation-ratiometric protein kinase A (PKA) activity reporter (ExRai-AKAR2), obtained via high-throughput linker library screening, that enables sensitive and rapid monitoring of live-cell PKA activity across multiple fluorescence detection modalities, including plate reading, cell sorting and one- or two-photon imaging. Notably, in vivo visual cortex imaging in awake mice reveals highly dynamic neuronal PKA activity rapidly recruited by forced locomotion.
Subject(s)
Biosensing Techniques , Cyclic AMP-Dependent Protein Kinases/genetics , Myocytes, Cardiac/enzymology , Neurons/enzymology , Optical Imaging/methods , Alprostadil/pharmacology , Animals , Cyclic AMP-Dependent Protein Kinases/metabolism , Dihydroxyphenylalanine/pharmacology , Dinoprostone/pharmacology , Fluorescent Dyes/chemistry , Gene Expression , Gene Library , Genes, Reporter , Glucagon-Like Peptide 1/pharmacology , HEK293 Cells , HeLa Cells , High-Throughput Screening Assays , Hippocampus/cytology , Hippocampus/drug effects , Hippocampus/enzymology , Humans , Mice , Microscopy, Fluorescence, Multiphoton , Myocytes, Cardiac/drug effects , Myocytes, Cardiac/ultrastructure , Neurons/drug effects , Neurons/ultrastructure , Primary Cell Culture , Signal TransductionABSTRACT
The small GTPase RhoA is a central signaling enzyme that is involved in various cellular processes such as cytoskeletal dynamics, transcription, and cell cycle progression. Many signal transduction pathways activate RhoA-for instance, Gαq-coupled Histamine 1 Receptor signaling via Gαq-dependent activation of RhoGEFs such as p63. Although multiple upstream regulators of RhoA have been identified, the temporal regulation of RhoA and the coordination of different upstream components in its regulation have not been well characterized. In this study, live-cell measurement of RhoA activation revealed a biphasic increase of RhoA activity upon histamine stimulation. We showed that the first and second phase of RhoA activity are dependent on p63 and Ca2+/PKC, respectively, and further identified phosphorylation of serine 240 on p115 RhoGEF by PKC to be the mechanistic link between PKC and RhoA. Combined approaches of computational modeling and quantitative measurement revealed that the second phase of RhoA activation is insensitive to rapid turning off of the receptor and is required for maintaining RhoA-mediated transcription after the termination of the receptor signaling. Thus, two divergent pathways enable both rapid activation and persistent signaling in receptor-mediated RhoA signaling via intricate temporal regulation.