Explore the vast range of titles available.

High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on-demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high-quality X-ray crystal structures, or manual cherry-picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug-like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small-molecule drug discovery.

Recent advances in multiplexed single‐cell transcriptomics experiments facilitate the high‐throughput study of drug and genetic perturbations. However, an exhaustive exploration of the combinatorial perturbation space is experimentally unfeasible. Therefore, computational methods are needed to predict, interpret, and prioritize perturbations. Here, we present the compositional perturbation autoencoder (CPA), which combines the interpretability of linear models with the flexibility of deep‐learning approaches for single‐cell response modeling. CPA learns to in silico predict transcriptional perturbation response at the single‐cell level for unseen dosages, cell types, time points, and species. Using newly generated single‐cell drug combination data, we validate that CPA can predict unseen drug combinations while outperforming baseline models. Additionally, the architecture's modularity enables incorporating the chemical representation of the drugs, allowing the prediction of cellular response to completely unseen drugs. Furthermore, CPA is also applicable to genetic combinatorial screens. We demonstrate this by imputing in silico 5,329 missing combinations (97.6% of all possibilities) in a single‐cell Perturb‐seq experiment with diverse genetic interactions. We envision CPA will facilitate efficient experimental design and hypothesis generation by enabling in silico response prediction at the single‐cell level and thus accelerate therapeutic applications using single‐cell technologies. Synopsis The compositional perturbation autoencoder (CPA) is a deep learning model for predicting the transcriptomic responses of single cells to single or combinatorial treatments from drugs and genetic manipulations. CPA can be trained on highly multiplexed, single‐cell experiments with thousands of conditions to predict unmeasured phenotypes (e.g., specific dose responses). It can generalize to predict responses to small molecules never seen in the training by adding priors on chemical space. Validations using a newly generated combinatorial drug perturbation dataset demonstrate the accuracy of CPA in predicting unseen drug combinations. CPA is also applicable to genetic combinatorial screens, as shown by imputing in silico 5,329 missing combinations in a single‐cell perturb‐seq experiment with diverse genetic interactions. Graphical Abstract The compositional perturbation autoencoder (CPA) is a deep learning model for predicting the transcriptomic responses of single cells to single or combinatorial treatments from drugs and genetic manipulations.

High‐throughput (HT) screening drug discovery, during which thousands or millions of compounds are screened, remains the key methodology for identifying active chemical matter in early drug discovery pipelines. Recent technological developments in mass spectrometry (MS) and automation have revolutionized the application of MS for use in HT screens. These methods allow the targeting of unlabelled biomolecules in HT assays, thereby expanding the breadth of targets for which HT assays can be developed compared to traditional approaches. Moreover, these label‐free MS assays are often cheaper, faster, and more physiologically relevant than competing assay technologies. In this review, we will describe current MS techniques used in drug discovery and explain their advantages and disadvantages. We will highlight the power of mass spectrometry in label‐free in vitro assays, and its application for setting up multiplexed cellular phenotypic assays, providing an exciting new tool for screening compounds in cell lines, and even primary cells. Finally, we will give an outlook on how technological advances will increase the future use and the capabilities of mass spectrometry in drug discovery. Graphical Abstract This Review summarizes advantages and disadvantages of high‐throughput mass spectrometry techniques used in drug discovery and discusses how technological advances could increase the capabilities of mass spectrometry in drug discovery in the future.

Understanding the tissue-specific genetic controls of protein levels is essential to uncover mechanisms of post-transcriptional gene regulation. In this study, we generated a genomic atlas of protein levels in three tissues relevant to neurological disorders (brain, cerebrospinal fluid and plasma) by profiling thousands of proteins from participants with and without Alzheimer’s disease. We identified 274, 127 and 32 protein quantitative trait loci (pQTLs) for cerebrospinal fluid, plasma and brain, respectively. cis-pQTLs were more likely to be tissue shared, but trans-pQTLs tended to be tissue specific. Between 48.0% and 76.6% of pQTLs did not co-localize with expression, splicing, DNA methylation or histone acetylation QTLs. Using Mendelian randomization, we nominated proteins implicated in neurological diseases, including Alzheimer’s disease, Parkinson’s disease and stroke. This first multi-tissue study will be instrumental to map signals from genome-wide association studies onto functional genes, to discover pathways and to identify drug targets for neurological diseases. Yang et al. generated a genomic atlas of protein levels in brain, cerebrospinal fluid and plasma and used human genetics approaches to identify proteins implicated in neurological diseases as well as druggable targets.

Screening drugs on patient biopsies from solid tumours has immense potential, but is challenging due to the small amount of available material. To address this, we present here a plug-based microfluidics platform for functional screening of drug combinations. Integrated Braille valves allow changing the plug composition on demand and enable collecting >1200 data points (56 different conditions with at least 20 replicates each) per biopsy. After deriving and validating efficient and specific drug combinations for two genetically different pancreatic cancer cell lines and xenograft mouse models, we additionally screen live cells from human solid tumours with no need for ex vivo culturing steps, and obtain highly specific sensitivity profiles. The entire workflow can be completed within 48 h at assay costs of less than US$ 150 per patient. We believe this can pave the way for rapid determination of optimal personalized cancer therapies. Cancer patients exhibit specific sensitivities toward drug combinations that cannot be easily predicted. Here the authors setup a microfluidic platform that allows testing of multiple drug combinations correctly predicting sensitivity in vivo and they use it on patients biopsies to define effective drugs.

Single-cell analysis reveals aspects of cellular physiology not evident from population-based studies, particularly in the case of highly multiplexed methods such as mass cytometry (CyTOF) able to correlate the levels of multiple signalling, differentiation and cell fate markers. Immunofluorescence (IF) microscopy adds information on cell morphology and the microenvironment that are not obtained using flow-based techniques, but the multiplicity of conventional IF is limited. This has motivated development of imaging methods that require specialized instrumentation, exotic reagents or proprietary protocols that are difficult to reproduce in most laboratories. Here we report a public-domain method for achieving high multiplicity single-cell IF using cyclic immunofluorescence (CycIF), a simple and versatile procedure in which four-colour staining alternates with chemical inactivation of fluorophores to progressively build a multichannel image. Because CycIF uses standard reagents and instrumentation and is no more expensive than conventional IF, it is suitable for high-throughput assays and screening applications. Multiplexed single cell measurements provide insight into connections between cell state and phenotype. Here Lin et al. present CycIF, a high throughput, public domain immunofluorescence method for multiplexed single-cell analysis of adherent cells following live-cell imaging.

High-throughput screening platform for the testing of small bioactive molecules that promote oligodendrocyte differentiation and remyelination: a new path to the discovery of potential drugs for multiple sclerosis. Functional screening for compounds that promote remyelination represents a major hurdle in the development of rational therapeutics for multiple sclerosis. Screening for remyelination is problematic, as myelination requires the presence of axons. Standard methods do not resolve cell-autonomous effects and are not suited for high-throughput formats. Here we describe a binary indicant for myelination using micropillar arrays (BIMA). Engineered with conical dimensions, micropillars permit resolution of the extent and length of membrane wrapping from a single two-dimensional image. Confocal imaging acquired from the base to the tip of the pillars allows for detection of concentric wrapping observed as 'rings' of myelin. The platform is formatted in 96-well plates, amenable to semiautomated random acquisition and automated detection and quantification. Upon screening 1,000 bioactive molecules, we identified a cluster of antimuscarinic compounds that enhance oligodendrocyte differentiation and remyelination. Our findings demonstrate a new high-throughput screening platform for potential regenerative therapeutics in multiple sclerosis.

Success in synthetic biology and metabolic engineering is quickly becoming ‘test’ limited within the design–build–test cycle. Commonly used methods for high-throughput screening, including fluorescence-activated cell sorting (FACS) and microtiter plates, have intracellular product and throughput limitations. A growing alternative to these challenges is the use of microfluidic microdroplet-based methods, which offer the advantages of microtiter plates with the throughput and ease of flow-based approaches. In this review, we examine available microdroplet technologies and their applications from droplet generation to sensing and finally sorting and evaluation for metabolic engineering applications. Additionally, we cover recent microdroplet advances, including the ability to perform mass spectrometry (MS) on individual microdroplets and dispense them into microtiter plates after sorting via fluorescence-activated droplet sorting (FADS). Microdroplets provide a high-throughput screening platform for secreted molecules with the speed of FACS and the phenotype–genotype linkage of microtiter plates.Microdroplet systems can be used as both a screening and selection platform for metabolic engineering applications.Recent advances include integrating microdroplet systems with MS or automated dispensing to broaden the horizon of potential applications.Improvements in standardization of microfluidics tools and experimental design will be necessary to commercialize these assays and make them more accessible to less experienced users in the future.The flexibility of microfluidics sorting has been demonstrated for many different small molecules, including natural products, as well as improved protein secretion.

Cardiotoxicity has historically been a major cause of drug removal from the pharmaceutical market. Several chemotherapeutic compounds have been noted for their propensities to induce dangerous cardiac-specific side effects such as arrhythmias or cardiomyocyte apoptosis. However, improved preclinical screening methodologies have enabled cardiotoxic compounds to be identified earlier in the drug development pipeline. Human induced pluripotent stem cell–derived cardiomyocytes (hiPSC-CMs) can be used to screen for drug-induced alterations in cardiac cellular contractility, electrophysiology, and viability. We previously established a novel ‘cardiac safety index’ (CSI) as a metric that can evaluate potential cardiotoxic drugs via high-throughput screening of hiPSC-CMs. This metric quantitatively examines drug-induced alterations in CM function, using several in vitro readouts, and normalizes the resulting toxicity values to the in vivo maximum drug blood plasma concentration seen in preclinical or clinical pharmacokinetic models. In this ~1-month-long protocol, we describe how to differentiate hiPSCs into hiPSC-CMs and subsequently implement contractility and cytotoxicity assays that can evaluate drug-induced cardiotoxicity in hiPSC-CMs. We also describe how to carry out the calculations needed to generate the CSI metric from these quantitative toxicity measurements.

The ability to rapidly assay morphological and intracellular molecular variations within large heterogeneous populations of cells is essential for understanding and exploiting cellular heterogeneity. Optofluidic time-stretch microscopy is a powerful method for meeting this goal, as it enables high-throughput imaging flow cytometry for large-scale single-cell analysis of various cell types ranging from human blood to algae, enabling a unique class of biological, medical, pharmaceutical, and green energy applications. Here, we describe how to perform high-throughput imaging flow cytometry by optofluidic time-stretch microscopy. Specifically, this protocol provides step-by-step instructions on how to build an optical time-stretch microscope and a cell-focusing microfluidic device for optofluidic time-stretch microscopy, use it for high-throughput single-cell image acquisition with sub-micrometer resolution at >10,000 cells per s, conduct image construction and enhancement, perform image analysis for large-scale single-cell analysis, and use computational tools such as compressive sensing and machine learning for handling the cellular ‘big data’. Assuming all components are readily available, a research team of three to four members with an intermediate level of experience with optics, electronics, microfluidics, digital signal processing, and sample preparation can complete this protocol in a time frame of 1 month.