Geometric parameters that affect the behavior of logic-gated CAR T cells.

Clinical applications of CAR-T cells are limited by the scarcity of tumor-specific targets and are often afflicted with the same on-target/off-tumor toxicities that plague other cancer treatments. A new promising strategy to enforce tumor selectivity is the use of logic-gated, two-receptor systems. One well-described application is termed Tmod™, which originally utilized a blocking inhibitory receptor directed towards HLA-I target antigens to create a protective NOT gate. Here we show that the function of Tmod blockers targeting non-HLA-I antigens is dependent on the height of the blocker antigen and is generally compatible with small, membrane-proximal targets. We compensate for this apparent limitation by incorporating modular hinge units to artificially extend or retract the ligand-binding domains relative to the effector cell surface, thereby modulating Tmod activator and blocker function. By accounting for structural differences between activator and blocker targets, we developed a set of simple geometric parameters for Tmod receptor design that enables targeting of blocker antigens beyond HLA-I, thereby broadening the applications of logic-gated cell therapies.

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening.

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends.

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

Data augmentation and multimodal learning for predicting drug response in patient-derived xenografts from gene expressions and histology images.

Patient-derived xenografts (PDXs) are an appealing platform for preclinical drug studies. A primary challenge in modeling drug response prediction (DRP) with PDXs and neural networks (NNs) is the limited number of drug response samples. We investigate multimodal neural network (MM-Net) and data augmentation for DRP in PDXs. The MM-Net learns to predict response using drug descriptors, gene expressions (GE), and histology whole-slide images (WSIs). We explore whether combining WSIs with GE improves predictions as compared with models that use GE alone. We propose two data augmentation methods which allow us training multimodal and unimodal NNs without changing architectures with a single larger dataset: 1) combine single-drug and drug-pair treatments by homogenizing drug representations, and 2) augment drug-pairs which doubles the sample size of all drug-pair samples. Unimodal NNs which use GE are compared to assess the contribution of data augmentation. The NN that uses the original and the augmented drug-pair treatments as well as single-drug treatments outperforms NNs that ignore either the augmented drug-pairs or the single-drug treatments. In assessing the multimodal learning based on the MCC metric, MM-Net outperforms all the baselines. Our results show that data augmentation and integration of histology images with GE can improve prediction performance of drug response in PDXs.

AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection.

Protein-ligand docking is a computational method for identifying drug leads. The method is capable of narrowing a vast library of compounds down to a tractable size for downstream simulation or experimental testing and is widely used in drug discovery. While there has been progress in accelerating scoring of compounds with artificial intelligence, few works have bridged these successes back to the virtual screening community in terms of utility and forward-looking development. We demonstrate the power of high-speed ML models by scoring 1 billion molecules in under a day (50 k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate AI-based models as a pre-filter to a standard docking workflow. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that another order of magnitude speedup must come from model accuracy rather than computing speed. In order to drive another order of magnitude of acceleration, we share a benchmark dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100 × or even 1000 × faster than current techniques and reduce missing top hits. The technique outlined aims to be a fast drop-in replacement for docking for screening billion-scale molecular libraries.

Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models.

Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to a treatment. Anti-cancer drug response prediction is of paramount importance for both drug development and patient treatment design. Although various computational methods and data have been used to develop drug response prediction models, it remains a challenging problem due to the complexities of cancer mechanisms and cancer-drug interactions. To better characterize the interaction between cancer and drugs, we investigate the feasibility of integrating computationally derived features of molecular mechanisms of action into prediction models. Specifically, we add docking scores of drug molecules and target proteins in combination with cancer gene expressions and molecular drug descriptors for building response models. The results demonstrate a marginal improvement in drug response prediction performance when adding docking scores as additional features, through tests on large drug screening data. We discuss the limitations of the current approach and provide the research community with a baseline dataset of the large-scale computational docking for anti-cancer drugs.

Protocol for high-throughput cloning, expression, purification, and evaluation of bispecific antibodies.

Bispecific antibodies are a powerful new class of therapeutics, but their development often requires enormous amounts of time and resources. Here, we describe a high-throughput protocol for cloning, expressing, purifying, and evaluating bispecific antibodies. This protocol enables the rapid screening of large panels of bispecific molecules to identify top candidates for further development. For complete details on the use and execution of this protocol, please refer to Estes et al. (2021).

A cross-study analysis of drug response prediction in cancer cell lines.

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomics of Drug Sensitivity in Cancer, Cancer Cell Line Encyclopedia and Genentech Cell Line Screening Initiative (gCSI). Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening.

Pandemic drugs at pandemic speed: infrastructure for accelerating COVID-19 drug discovery with hybrid machine learning- and physics-based simulations on high-performance computers.

The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case, developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers.

Converting tabular data into images for deep learning with convolutional neural networks.

Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.

Enhancing the Prefusion Conformational Stability of SARS-CoV-2 Spike Protein Through Structure-Guided Design.

The worldwide pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is unprecedented and the impact on public health and the global economy continues to be devastating. Although early therapies such as prophylactic antibodies and vaccines show great promise, there are concerns about the long-term efficacy and universal applicability of these therapies as the virus continues to mutate. Thus, protein-based immunogens that can quickly respond to viral changes remain of continued interest. The Spike protein, the main immunogen of this virus, displays a highly dynamic trimeric structure that presents a challenge for therapeutic development. Here, guided by the structure of the Spike trimer, we rationally design new Spike constructs that show a uniquely high stability profile while simultaneously remaining locked into the immunogen-desirable prefusion state. Furthermore, our approach emphasizes the relationship between the highly conserved S2 region and structurally dynamic Receptor Binding Domains (RBD) to enable vaccine development as well as the generation of antibodies able to resist viral mutation.

Learning curves for drug response prediction in cancer cell lines.

BACKGROUND: Motivated by the size and availability of cell line drug sensitivity data, researchers have been developing machine learning (ML) models for predicting drug response to advance cancer treatment. As drug sensitivity studies continue generating drug response data, a common question is whether the generalization performance of existing prediction models can be further improved with more training data. METHODS: We utilize empirical learning curves for evaluating and comparing the data scaling properties of two neural networks (NNs) and two gradient boosting decision tree (GBDT) models trained on four cell line drug screening datasets. The learning curves are accurately fitted to a power law model, providing a framework for assessing the data scaling behavior of these models. RESULTS: The curves demonstrate that no single model dominates in terms of prediction performance across all datasets and training sizes, thus suggesting that the actual shape of these curves depends on the unique pair of an ML model and a dataset. The multi-input NN (mNN), in which gene expressions of cancer cells and molecular drug descriptors are input into separate subnetworks, outperforms a single-input NN (sNN), where the cell and drug features are concatenated for the input layer. In contrast, a GBDT with hyperparameter tuning exhibits superior performance as compared with both NNs at the lower range of training set sizes for two of the tested datasets, whereas the mNN consistently performs better at the higher range of training sizes. Moreover, the trajectory of the curves suggests that increasing the sample size is expected to further improve prediction scores of both NNs. These observations demonstrate the benefit of using learning curves to evaluate prediction models, providing a broader perspective on the overall data scaling characteristics. CONCLUSIONS: A fitted power law learning curve provides a forward-looking metric for analyzing prediction performance and can serve as a co-design tool to guide experimental biologists and computational scientists in the design of future experiments in prospective research studies.

Ensemble transfer learning for the prediction of anti-cancer drug response.

Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the power of transfer learning for three drug response prediction applications including drug repurposing, precision oncology, and new drug development, through different data partition schemes in cross-validation. We extend the classic transfer learning framework through ensemble and demonstrate its general utility with three representative prediction algorithms including a gradient boosting model and two deep neural networks. The ensemble transfer learning framework is tested on benchmark in vitro drug screening datasets. The results demonstrate that our framework broadly improves the prediction performance in all three drug response prediction applications with all three prediction algorithms.

Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models.

The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted p-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.

Cryo-EM Structures of Human Drosha and DGCR8 in Complex with Primary MicroRNA.

Metazoan microRNAs require specific maturation steps initiated by Microprocessor, comprising Drosha and DGCR8. Lack of structural information for the assembled complex has hindered an understanding of how Microprocessor recognizes primary microRNA transcripts (pri-miRNAs). Here we present a cryoelectron microscopy structure of human Microprocessor with a pri-miRNA docked in the active site, poised for cleavage. The basal junction is recognized by a four-way intramolecular junction in Drosha, triggered by the Belt and Wedge regions that clamp over the ssRNA. The belt is important for efficiency and accuracy of pri-miRNA processing. Two dsRBDs form a molecular ruler to measure the stem length between the two dsRNA-ssRNA junctions. The specific organization of the dsRBDs near the apical junction is independent of Drosha core domains, as observed in a second structure in the partially docked state. Collectively, we derive a molecular model to explain how Microprocessor recognizes a pri-miRNA and accurately identifies the cleavage site.

RNA Specificity and Autoregulation of DDX17, a Modulator of MicroRNA Biogenesis.

DDX17, a DEAD-box ATPase, is a multifunctional helicase important for various RNA functions, including microRNA maturation. Key questions for DDX17 include how it recognizes target RNAs and influences their structures, as well as how its ATPase activity may be regulated. Through crystal structures and biochemical assays, we show the ability of the core catalytic domains of DDX17 to recognize specific sequences in target RNAs. The RNA sequence preference of the catalytic core is critical for DDX17 to directly bind and remodel a specific region of primary microRNAs 3' to the mature sequence, and consequently enhance processing by Drosha. Furthermore, we identify an intramolecular interaction between the N-terminal tail and the DEAD domain of DDX17 to have an autoregulatory role in controlling the ATPase activity. Thus, we provide the molecular basis for how cognate RNA recognition and functional outcomes are linked for DDX17.

Publisher Correction: Heme enables proper positioning of Drosha and DGCR8 on primary microRNAs.

The original version of this Article contained an error in Fig. 1. In panel d, the model on the right of the panel was incorrectly labeled '+Heme', and should have read '- Heme'. This has now been corrected in both the PDF and HTML versions of the Article.

Heme enables proper positioning of Drosha and DGCR8 on primary microRNAs.

MicroRNAs regulate the expression of many proteins and require specific maturation steps. Primary microRNA transcripts (pri-miRs) are cleaved by Microprocessor, a complex containing the RNase Drosha and its partner protein, DGCR8. Although DGCR8 is known to bind heme, the molecular role of heme in pri-miR processing is unknown. Here we show that heme is critical for Microprocessor to process pri-miRs with high fidelity. Furthermore, the degree of inherent heme dependence varies for different pri-miRs. Heme-dependent pri-miRs fail to properly recruit Drosha, but heme-bound DGCR8 can correct erroneous binding events. Rather than changing the oligomerization state, heme induces a conformational change in DGCR8. Finally, we demonstrate that heme activates DGCR8 to recognize pri-miRs by specifically binding the terminal loop near the 3' single-stranded segment.

Preconditioning-induced CXCL12 upregulation minimizes leukocyte infiltration after stroke in ischemia-tolerant mice.

Repetitive hypoxic preconditioning creates long-lasting, endogenous protection in a mouse model of stroke, characterized by reductions in leukocyte-endothelial adherence, inflammation, and infarct volumes. The constitutively expressed chemokine CXCL12 can be upregulated by hypoxia and limits leukocyte entry into brain parenchyma during central nervous system inflammatory autoimmune disease. We therefore hypothesized that the sustained tolerance to stroke induced by repetitive hypoxic preconditioning is mediated, in part, by long-term CXCL12 upregulation at the blood-brain barrier (BBB). In male Swiss Webster mice, repetitive hypoxic preconditioning elevated cortical CXCL12 protein levels, and the number of cortical CXCL12+ microvessels, for at least two weeks after the last hypoxic exposure. Repetitive hypoxic preconditioning-treated mice maintained more CXCL12-positive vessels than untreated controls following transient focal stroke, despite cortical decreases in CXCL12 mRNA and protein. Continuous administration of the CXCL12 receptor (CXCR4) antagonist AMD3100 for two weeks following repetitive hypoxic preconditioning countered the increase in CXCL12-positive microvessels, both prior to and following stroke. AMD3100 blocked the protective post-stroke reductions in leukocyte diapedesis, including macrophages and NK cells, and blocked the protective effect of repetitive hypoxic preconditioning on lesion volume, but had no effect on blood-brain barrier dysfunction. These data suggest that CXCL12 upregulation prior to stroke onset, and its actions following stroke, contribute to the endogenous, anti-inflammatory phenotype induced by repetitive hypoxic preconditioning.