High-throughput Screening Data Research Articles

Binding Activity Classification of Anti-SARS-CoV-2 Molecules using Deep Learning Across Multiple Assays

The coronavirus disease-2019 (COVID-19) pandemic, caused by severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2), has urgently necessitated effective therapeutic solutions, with a focus on rapidly identifying and classifying potential small-molecule drugs. Given traditional methods’ labor-intensive and time-consuming nature, deep learning has emerged as an essential tool for efficiently processing and extracting insights from complex biological data. To utilize deep learning techniques, particularly deep neural networks (DNN) enhanced with the synthetic minority oversampling technique (SMOTE), to enhance the classification of binding activities in anti-SARS-CoV-2 molecules across various bioassays. We used 11 bioassay datasets covering various SARS-CoV-2 interactions and inhibitory mechanisms. These assays ranged from spike-ACE2 protein-protein interaction to ACE2 enzymatic activity and 3CL enzymatic activity. To address the prevalent class imbalance in these datasets, the SMOTE technique was employed to generate new samples for the minority class. In our model-building approach, we divided the dataset into 80% training and 20% test sets, reserving 10% of the training set for validation. Our approach involved employing a DNN that integrates ReLU and sigmoid activation functions, incorporates batch normalization, and uses Adam optimization. The hyperparameters and architecture of the DNN were optimized through various tests on layers, minibatch sizes, epoch sizes, and learning rates. A 40% dropout rate was incorporated to mitigate overfitting. For model evaluation, we computed performance metrics, such as balanced accuracy (BACC), precision, recall, F1 score, Matthews’ correlation coefficient (MCC), and area under the curve (AUC). The performance of the DNN across 11 bioassay test sets revealed varying outcomes, significantly influenced by the ratios of active-to-inactive compounds. Assays, such as AlphaLISA and CoV-PPE, demonstrated robust performance across various metrics, including BACC, precision, recall, and AUC, when configured with more balanced ratios (1:3 and 1:1, respectively). This suggests the effective identification of active compounds in both cases. In contrast, assays with higher imbalance ratios, such as 3CL (1:38) and cytopathic effect (1:15), demonstrated higher recall but lower precision, highlighting challenges in accurately identifying active compounds among numerous inactive compounds. However, even in these challenging settings, the model achieved favorable BACC and recall scores. Overall, the DNN model generally performed well, as indicated by the BACC, MCC, and AUC values, especially when considering the degree of dataset imbalance in each assay. This study demonstrates the significant impact of deep learning, particularly DNN models enhanced with SMOTE, in improving the identification of active compounds in bioassay datasets for COVID-19 drug discovery, outperforming traditional machine learning models. Furthermore, this study highlights the efficacy of advanced computational techniques in addressing high-throughput screening data imbalances.

Integration of Computational Pipeline to Streamline Efficacious Drug Nomination and Biomarker Discovery in Glioblastoma.

Glioblastoma multiforme (GBM) is the deadliest, most heterogeneous, and most common brain cancer in adults. Not only is there an urgent need to identify efficacious therapeutics, but there is also a great need to pair these therapeutics with biomarkers that can help tailor treatment to the right patient populations. We built patient drug response models by integrating patient tumor transcriptome data with high-throughput cell line drug screening data as well as Bayesian networks to infer relationships between patient gene expression and drug response. Through these discovery pipelines, we identified agents of interest for GBM to be effective across five independent patient cohorts and in a mouse avatar model: among them are a number of MEK inhibitors (MEKis). We also predicted phosphoglycerate dehydrogenase enzyme (PHGDH) gene expression levels to be causally associated with MEKi efficacy, where knockdown of this gene increased tumor sensitivity to MEKi and overexpression led to MEKi resistance. Overall, our work demonstrated the power of integrating computational approaches. In doing so, we quickly nominated several drugs with varying known mechanisms of action that can efficaciously target GBM. By simultaneously identifying biomarkers with these drugs, we also provide tools to select the right patient populations for subsequent evaluation.

MMSyn: A New Multimodal Deep Learning Framework for Enhanced Prediction of Synergistic Drug Combinations.

Combination therapy is a promising strategy for the successful treatment of cancer. The large number of possible combinations, however, mean that it is laborious and expensive to screen for synergistic drug combinations in vitro. Nevertheless, because of the availability of high-throughput screening data and advances in computational techniques, deep learning (DL) can be a useful tool for the prediction of synergistic drug combinations. In this study, we proposed a multimodal DL framework, MMSyn, for the prediction of synergistic drug combinations. First, features embedded in the drug molecules were extracted: structure, fingerprint, and string encoding. Then, gene expression data, DNA copy number, and pathway activity were used to describe cancer cell lines. Finally, these processed features were integrated using an attention mechanism and an interaction module and then input into a multilayer perceptron to predict drug synergy. Experimental results showed that our method outperformed five state-of-the-art DL methods and three traditional machine learning models for drug combination prediction. We verified that MMSyn achieved superior performance in stratified cross-validation settings using both the drug combination and cell line data. Moreover, we performed a set of ablation experiments to illustrate the effectiveness of each component and the efficacy of our model. In addition, our visual representation and case studies further confirmed the effectiveness of our model. All results showed that MMSyn can be used as a powerful tool for the prediction of synergistic drug combinations.

Enhancing the Small-Scale Screenable Biological Space beyond Known Chemogenomics Libraries with Gray Chemical Matter─Compounds with Novel Mechanisms from High-Throughput Screening Profiles.

Phenotypic assays have become an established approach to drug discovery. Greater disease relevance is often achieved through cellular models with increased complexity and more detailed readouts, such as gene expression or advanced imaging. However, the intricate nature and cost of these assays impose limitations on their screening capacity, often restricting screens to well-characterized small compound sets such as chemogenomics libraries. Here, we outline a cheminformatics approach to identify a small set of compounds with likely novel mechanisms of action (MoAs), expanding the MoA search space for throughput limited phenotypic assays. Our approach is based on mining existing large-scale, phenotypic high-throughput screening (HTS) data. It enables the identification of chemotypes that exhibit selectivity across multiple cell-based assays, which are characterized by persistent and broad structure activity relationships (SAR). We validate the effectiveness of our approach in broad cellular profiling assays (Cell Painting, DRUG-seq, and Promotor Signature Profiling) and chemical proteomics experiments. These experiments revealed that the compounds behave similarly to known chemogenetic libraries, but with a notable bias toward novel protein targets. To foster collaboration and advance research in this area, we have curated a public set of such compounds based on the PubChem BioAssay dataset and made it available for use by the scientific community.

Machine Learning Assisted Hit Prioritization for High Throughput Screening in Drug Discovery.

Efficient prioritization of bioactive compounds from high throughput screening campaigns is a fundamental challenge for accelerating drug development efforts. In this study, we present the first data-driven approach to simultaneously detect assay interferents and prioritize true bioactive compounds. By analyzing the learning dynamics during training of a gradient boosting model on noisy high throughput screening data using a novel formulation of sample influence, we are able to distinguish between compounds exhibiting the desired biological response and those producing assay artifacts. Therefore, our method enables false positive and true positive detection without relying on prior screens or assay interference mechanisms, making it applicable to any high throughput screening campaign. We demonstrate that our approach consistently excludes assay interferents with different mechanisms and prioritizes biologically relevant compounds more efficiently than all tested baselines, including a retrospective case study simulating its use in a real drug discovery campaign. Finally, our tool is extremely computationally efficient, requiring less than 30 s per assay on low-resource hardware. As such, our findings show that our method is an ideal addition to existing false positive detection tools and can be used to guide further pharmacological optimization after high throughput screening campaigns.

APPLICATION OF SUPPORT VECTOR MACHINE FOR CLASS IMBALANCE LEARNING TO PREDICT ANTICANCER COMPOUNDS OF MEDICINAL PLANTS IN WEST SULAWESI

Indonesian medicinal plants, such as turmeric and soursop, have shown promising anticancer properties through their bioactive compounds, like curcumin and extracts from soursop. Despite many extensive studies on medicinal plants in Indonesia, research revealing the activity of natural products in West Sulawesi is still limited, and the studies focus mainly on ethnobotanical research. In this work, we propose a machine-learning approach to predict the anticancer activity of compounds in medicinal plants in West Sulawesi by leveraging high throughput-screening data, especially molecular information from a public database. We applied Support Vector Machine (SVM) with five sampling techniques to address data imbalance. We also evaluated the performance in selecting the best combination in handling class imbalance learning in our dataset. The result shows that undersampling and ADSYN methods can improve the prediction of anticancer activity. Based on the two methods of balancing data, we have ten potential anticancer compounds from three medicinal plants in West Sulawesi.

Using birth-death processes to infer tumor subpopulation structure from live-cell imaging drug screening data.

Tumor heterogeneity is a complex and widely recognized trait that poses significant challenges in developing effective cancer therapies. In particular, many tumors harbor a variety of subpopulations with distinct therapeutic response characteristics. Characterizing this heterogeneity by determining the subpopulation structure within a tumor enables more precise and successful treatment strategies. In our prior work, we developed PhenoPop, a computational framework for unravelling the drug-response subpopulation structure within a tumor from bulk high-throughput drug screening data. However, the deterministic nature of the underlying models driving PhenoPop restricts the model fit and the information it can extract from the data. As an advancement, we propose a stochastic model based on the linear birth-death process to address this limitation. Our model can formulate a dynamic variance along the horizon of the experiment so that the model uses more information from the data to provide a more robust estimation. In addition, the newly proposed model can be readily adapted to situations where the experimental data exhibits a positive time correlation. We test our model on simulated data (in silico) and experimental data (in vitro), which supports our argument about its advantages.

Abstract A015: Predicting efficacious drugs and drug-biomarker relationships for targeted glioblastoma treatment

Abstract Glioblastoma multiforme (GBM) is the deadliest, most heterogeneous, and common brain cancer in adults. Despite major advancements in neurosurgery as well as chemotherapy and radiotherapy techniques, overall prognosis has changed little over the decades. Not only is there an urgent need to identify efficacious therapeutics but there is also a great need to pair these therapeutics with biomarkers that can help tailor treatment to the right patient populations given the heterogeneous nature of the disease. Here, we implement several machine learning and statistical based pipelines for drug and biomarker discovery, leveraging previous work building patient drug response models using high-throughput cell line drug screening data as well as Bayesian network structure learning. Through these discovery pipelines, we identified multiple agents of interest for GBM, including MEK inhibitors (MEKis). MEKis were consistently predicted to be effective against GBM in multiple cross platform (microarray and RNA-sequencing) patient and patient derived xenograft (PDX) datasets. Additionally, they were experimentally shown to be more efficacious in tumor samples than standard of care agents (Temozolomide and Carmustine). We also predicted PHGDH gene expression levels to be causally associated with MEKi efficacy, which increased tumor sensitivity to a MEKi (Trametinib) during experimental testing in GBM cell lines with knockdown. These findings support our drug and biomarker discovery pipelines as an effective strategy to unite multiple cross platform and cross species datasets to help achieve GBM precision medicine. They also demonstrate that patient PHGDH levels can help inform Trametinib response in the fight against GBM. Citation Format: Danielle Maeser, Robert Gruener, Robert Galvin, Stephanie Huang, Tomo Koga, Florina Grigore. Predicting efficacious drugs and drug-biomarker relationships for targeted glioblastoma treatment [abstract]. In: Proceedings of the AACR Special Conference on Brain Cancer; 2023 Oct 19-22; Minneapolis, Minnesota. Philadelphia (PA): AACR; Cancer Res 2024;84(5 Suppl_1):Abstract nr A015.

Metamorphosis of human health risk assessment with artificial intelligence (AI) - a new paradigm in pharmaco-toxicological sciences

Toxicological Science, especially in the last five decades, has witnessed rapid evolution of different tools and techniques developed to address diverse issues related to studies dealing with adverse health effects of a variety of poisons, drugs, chemicals,ever-growing list of xenobiotics and human diseases. Traditionally these studies are performed using suitable animal (in vivo) models. There was a time when toxicologists/pharmacologists were searching models alternate to animal toxicity testing (Doke and Dhawale, 2015). Improved cell culture techniques, knowledge on stem cells and other microbiological systems led to the development of in vitro toxicology. It was soon followed by DNA chips, micro fluidics, in silico toxicology , toxicogenomics and computational toxicology. Several platforms are now discussing machine learning (ML) and artificial intelligence (AI) together as future tools of computational toxicology. For decades, quantitative structure-activity relationship (QSAR) methods have been employed to study the effects of drugs/chemicals (Cai et al., 2022). However, AI methods for toxicity assessment ranging from ADMEtox to AI4TOX provide evidence to the immense potential of AI. Intriguingly, a few problems between theoretical developments and practice of AI by end users have been recognized. AI is now being employed in cancer care. According to WHO (2022), cancer is responsible for 9.3 million deaths per year. AI is being used for cancer grading, classification, follow up services and diagnostic accuracy. However, certain limitations viz. testing, validation, certification and auditing need to be addressed (Cabral et al., (2023). Potential of AI in diabetic care and management has recently been recognized. The huge burden of diabetic patients in India can be managed through AI tools. Diabetic risk can be predicted using genomic data, to diagnose diabetes using EHR data and to identify diabetes related complications i.e. retinopathy and nephropathy (Singhla et al., 2019). Application of AI in the management of cardiovascular diseases like myocardial infarction has been highlighted with special reference to Chinese medicine (Chen et al., 2022). There exists experimental evidence that AI tools can be used to assess, monitor and manage Parkinsons' disease (Bounsall et al., 2023). Perspectives of the application of AI in complimentary and alternative medicine were reviewed by Chu et al. (2022). Several regulatory agencies are now adopting the concept of 3R ie., replacement, reduction and refinement of animal testing (EU REACH/3R principles; Toxicology 21 of U.S. Government) ( Maestri, 2021).The application of AI in clinical toxicology through converging data resources, algorithms, real world information from sensors and health records has also been discussed (Sinha et al. 2021). Plausibility of toxicity prediction using AI tools was recently reviewed by Santin et al. (2021). Application of AI in recently emerged science of nanotoxicology is also being sought. The need for nanotoxicity databases, powerful nano descriptors, new modeling approaches, molecular mechanism analyses and designing of next generation nanomaterials are being debated ( Jha et al., 2014; Yan et al., 2023). U.S. Food and Drug Administration (USFDA) has recently initiated and AI program in Toxicology known as AI4TOX. This program mainly consists of four initiatives- AnimalGAN- to predict animal toxicology data for untested chemicals ( /about –fda/nctr-research-focus-areas/animalgan-initiative); SafetAI- to develop novel deep learning methods for toxicological endpoints (/about-fda/nctr-research-focus-areas/safetai-initiative); BERTox- to develop the most advanced AI powered Natural Language Processing (NPL) (/about-fda/nctr-research-focus-areas/bertox initiative) and PathologAI- to develop an effective and accurate framework for analysis of histopathological data from animal studies (/ about-fda/nctr-research-focus-areas/pathologai-initiative). Recently, Society of Toxicology (SOT) annual meeting held at Nashville from March 19-23, focused on a question-“How could AI be used for risk assessment?” There exists some skepticism weather AI may be used in human health risk assessment? How AI could be applied -to prioritize pharmaceutical/environmental chemicals, to identify potential off targets and decipher the mechanisms of toxicity and detect pathological effects? A Symposium session devoted to AI summarized international collaborative computational projects like CERaPP, COmPara and CATOMOS that have been designed to streamline the regulatory and safety assessments (Hartung, 2023). High throughput screening data (HTS) to predict drug induced liver injury (DILI) using AI is also being generated. AI can identify mechanisms for off target effects in drug development. AI can also be plausibly used to predict genotoxicity. Can AI tools automate the analysis of developmental or physiologically based assays? These discussions held during the symposium indicate exciting potential of AI in health risk assessment. It is speculated that, tools of nanotechnology hybridized with AI can metamorphose human health risk assessment to an extent that has never been achieved before.

Accelerating operation optimization of complex chemical processes: A novel framework integrating artificial neural network and mixed-integer linear programming

We present an automated framework that integrates rectified linear unit activated artificial neural network (ReLU-ANN) and mixed-integer linear programming (MILP) to enable efficient operational-level optimization of complex chemical processes. Initially, data is generated through rigorous simulations to pre-train surrogate models based on ReLU-ANN (classification and regression), and subsequently, MILP is employed for optimization by linearly formulating these models. This novel framework efficiently handles complex convergence constraints through a classification neural network which will be used for high-throughput screening data for regression, while simultaneously implementing an 'optimizing while learning' strategy. By iteratively updating the neural network based on optimization feedback, our approach streamlines the optimization process and ensure the feasibility of optimum solution. To demonstrate the versatility and robustness of our proposed framework, we examine three representative chemical processes: extractive distillation, organic Rankine cycle, and methanol synthesis. Our results reveal the framework’s potential in enhancing optimization effect while concurrently reducing computational time, surpassing the capabilities of typical optimization algorithms. As for the three processes, optimization effectiveness improved by 10.11%, 28.69%, and 5.45%, respectively, while execution time were reduced by 71.71%, 54.49%, and 59.38%. This notable enhancement in optimization efficiency stems from a substantial reduction in costly while ineffective objective function evaluations. By seamless integration of ReLU-ANN and MILP, our proposed framework holds promise for improving the optimization of complex chemical processes, yielding superior results within significantly reduced timeframes compared to traditional approaches.

High throughput screening for rapid and reliable prediction of monovalent antibody binding behavior in flowthrough mode.

Flowthrough (FT) anion exchange (AEX) chromatography is a widely used polishing step for the purification of monoclonal antibody (mAb) formats. To accelerate downstream process development, high throughput screening (HTS) tools have proven useful. In this study, the binding behavior of six monovalent mAbs (mvAbs) was investigated by HTS in batch binding mode on different AEX and mixed-mode resins at process-relevant pH and NaCl concentrations. The HTS entailed the evaluation of mvAb partition coefficients (Kp ) and visualization of results in surface-response models. Interestingly, the HTS data grouped the mvAbs into either a strong-binding group or a weak-binding/FT group independent of theoretical Isoelectric point. Mapping the charged and hydrophobic patches by in silico protein surface property analyses revealed that the distribution of patches play a major role in predicting FT behavior. Importantly, the conditions identified by HTS were successfully verified by 1 mL on-column experiments. Finally, employing the optimal FT conditions (7-9 mS/cm and pH 7.0) at a mini-pilot scale (CV = 259 mL) resulted in 99% yield and a 21-23-fold reduction of host cell protein to <100 ppm, depending on the varying host cell protein (HCP) levels in the load. This work opens the possibility of using HTS in FT mode to accelerate downstream process development for mvAb candidates in early research.

Lies and Liabilities: Computational Assessment of High-Throughput Screening Hits to Identify Artifact Compounds.

Hits from high-throughput screening (HTS) of chemical libraries are often false positives due to their interference with assay detection technology. In response, we generated the largest publicly available library of chemical liabilities and developed "Liability Predictor," a free web tool to predict HTS artifacts. More specifically, we generated, curated, and integrated HTS data sets for thiol reactivity, redox activity, and luciferase (firefly and nano) activity and developed and validated quantitative structure-interference relationship (QSIR) models to predict these nuisance behaviors. The resulting models showed 58-78% external balanced accuracy for 256 external compounds per assay. QSIR models developed and validated herein identify nuisance compounds among experimental hits more reliably than do popular PAINS filters. Both the models and the curated data sets were implemented in "Liability Predictor," publicly available at https://liability.mml.unc.edu/. "Liability Predictor" may be used as part of chemical library design or for triaging HTS hits.

SDPS-32 A CLINICALLY COMPATIBLE IN VITRO DRUG-SCREENING PLATFORM IDENTIFIES THERAPEUTIC VULNERABILITIES IN PRIMARY CULTURES OF BRAIN METASTASES

Abstract Approximately 20% of cancer patients (including lung, melanoma, breast, renal, and colorectal cancer patients) develop brain metastases. Current systemic therapies often show limited efficacy for brain metastasis treatment and support palliative care only. In this preclinical study, short-term cultured primary cancer cells from brain metastasis patients were molecularly characterized using next-generation sequencing and functionally evaluated using high-throughput in vitro drug screening to identify pharmacological treatment sensitivities. Next-generation sequencing identified matched genetic alterations between brain metastasis tissues and corresponding patient-derived cultured cancer cells. Mutant allele frequencies indicated that short-term cultures of cancer cells reflect the existence of distinct subpopulations of cancer cells within brain metastases. This indicates that our short-term cultured primary brain metastasis cells are suitable models for recapitulating heterogeneity in the sensitivity of tumor cells to anti-cancer drugs. Employing our in-house high-throughput in vitro drug screening platform, we screened the primary cultures from the brain metastasis patients for response to 267 anticancer compounds, and integrated the molecular and high-throughput drug screening data sets. Our preclinical study provides proof-of-concept for combining molecular profiling with in vitro drug screening for improved prediction of therapeutic vulnerabilities in brain metastasis patients. This approach could advance the use of patient-derived cancer cells in clinical practice and might eventually facilitate decision-making for personalized drug treatment.

Integrative analysis of functional genomic screening and clinical data identifies a protective role for spironolactone in severe COVID-19

We demonstrate that integrative analysis of CRISPR screening datasets enables network-based prioritization of prescription drugs modulating viral entry in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) by developing a network-based approach called Rapid proXimity Guidance for Repurposing Investigational Drugs (RxGRID). We use our results to guide a propensity-score-matched, retrospective cohort study of 64,349 COVID-19 patients, showing that a top candidate drug, spironolactone, is associated with improved clinical prognosis, measured by intensive care unit (ICU) admission and mechanical ventilation rates. Finally, we show that spironolactone exerts a dose-dependent inhibitory effect on viral entry in human lung epithelial cells. Our RxGRID method presents a computational framework, implemented as an open-source software package, enabling genomics researchers to identify drugs likely to modulate a molecular phenotype of interest based on high-throughput screening data. Our results, derived from this method and supported by experimental and clinical analysis, add additional supporting evidence for a potential protective role of the potassium-sparing diuretic spironolactone in severe COVID-19.

MF-PCBA: Multifidelity High-Throughput Screening Benchmarks for Drug Discovery and Machine Learning.

High-throughput screening (HTS), as one of the key techniques in drug discovery, is frequently used to identify promising drug candidates in a largely automated and cost-effective way. One of the necessary conditions for successful HTS campaigns is a large and diverse compound library, enabling hundreds of thousands of activity measurements per project. Such collections of data hold great promise for computational and experimental drug discovery efforts, especially when leveraged in combination with modern deep learning techniques, and can potentially lead to improved drug activity predictions and cheaper and more effective experimental design. However, existing collections of machine-learning-ready public datasets do not exploit the multiple data modalities present in real-world HTS projects. Thus, the largest fraction of experimental measurements, corresponding to hundreds of thousands of "noisy" activity values from primary screening, are effectively ignored in the majority of machine learning models of HTS data. To address these limitations, we introduce Multifidelity PubChem BioAssay (MF-PCBA), a curated collection of 60 datasets that includes two data modalities for each dataset, corresponding to primary and confirmatory screening, an aspect that we call multifidelity. Multifidelity data accurately reflect real-world HTS conventions and present a new, challenging task for machine learning: the integration of low- and high-fidelity measurements through molecular representation learning, taking into account the orders-of-magnitude difference in size between the primary and confirmatory screens. Here we detail the steps taken to assemble MF-PCBA in terms of data acquisition from PubChem and the filtering steps required to curate the raw data. We also provide an evaluation of a recent deep-learning-based method for multifidelity integration across the introduced datasets, demonstrating the benefit of leveraging all HTS modalities, and a discussion in terms of the roughness of the molecular activity landscape. In total, MF-PCBA contains over 16.6 million unique molecule-protein interactions. The datasets can be easily assembled by using the source code available at https://github.com/davidbuterez/mf-pcba.

QHTSWaterfall: 3-dimensional visualization software for quantitative high-throughput screening (qHTS) data

High throughput screening (HTS) is widely used in drug discovery and chemical biology to identify and characterize agents having pharmacologic properties often by evaluation of large chemical libraries. Standard HTS data can be simply plotted as an x–y graph usually represented as % activity of a compound tested at a single concentration vs compound ID, whereas quantitative HTS (qHTS) data incorporates a third axis represented by concentration. By virtue of the additional data points arising from the compound titration and the incorporation of logistic fit parameters that define the concentration–response curve, such as EC50 and Hill slope, qHTS data has been challenging to display on a single graph. Here we provide a flexible solution to the rapid plotting of complete qHTS data sets to produce a 3-axis plot we call qHTS Waterfall Plots. The software described here can be generally applied to any 3-axis dataset and is available as both an R package and an R shiny application.Graphical

Integrating high-throughput exposure assessment and in vitro screening data to prioritize endocrine-active potential and dietary risks of pesticides and veterinary drug residues in animal products.

New approach methodologies in toxicology, such as in vitro high-throughput screening (HTS), can minimize the use of experimental animals and allow mechanism-based predictions of in vivo toxicity. HTS data has been increasingly used in the regulatory context; however, only a few studies integrated dietary exposure and HTS data to foster chemical prioritization in food. Additionally, the endocrine-associated risk of veterinary drug residues in food is yet to be fully characterized. This study aims to systematically compare the translated HTS data with the acceptable daily intake (ADI) values and prioritize the pesticides and veterinary drug residues (n=294) in food using the exposure-activity ratio (EAR) and Toxicological Prioritization index (ToxPi). The dietary exposure assessment was accomplished using a stochastic human exposure and dose simulation high-throughput model (SHEDS-HT). We selected 76 HTS assays from 12 nuclear receptors to represent the molecular initiating event (MIE) of endocrine-disrupting phenotypes. Chemical prioritization was achieved using 4 methods (i.e., EAR-OED, EAR-ADI, ToxPi-exposure+ADI, and ToxPi-exposure+endocrine score), where the consensus prioritized chemicals were fipronil, furazolidone, oxolinic acid, and oxytetracycline for the Taiwanese population. This case study demonstrates the utility of HTS data in fostering regulatory decisions on chemicals, especially for those lacking comprehensive toxicity data.

National Cancer Institute (NCI) Program for Natural Product Discovery: Exploring NCI-60 Screening Data of Natural Product Samples with Artificial Neural Networks.

National Cancer Institute (NCI) Program for Natural Product Discovery is a new initiative aimed at creating new technologies for natural product-based drug discovery. Here, we present the development of a neural network-based bioinformatics platform for visualization and analysis of natural product high-throughput screening data using the NCI's 60 human tumor cell anticancer drug screen. We demonstrate how the tool enables visualization of similar patterns of response that can be parsed both chemically and taxonomically, grouping NCI-60 biological profiles in one easy-to-use bioinformatics interface.

AI4DR: Development and implementation of an annotation system for high-throughput dose-response experiments

One of the common strategies to identify novel chemical matter in drug discovery consists in performing a High Throughput Screening (HTS). However, the large amount of data generated at the dose-response (DR) step of an HTS campaign requires a careful analysis to detect artifacts and correct erroneous datapoints before validating the experiments. This step which requires to review each DR experiment can be time consuming and prone to human errors or inconsistencies. AI4DR is a system that has been developed for the classification of DR curves based on a Convolutional Neural Network (CNN) acting on normalized images of the DR curves. AI4DR allows the annotation in minutes of thousands of curves among 14 categories to help the High Throughput Screening biologists in their analyses. Several categories are associated with active and inactive compounds, other categories correspond to features of interest such as the presence of noise, a weaker effect at high doses, or a suspiciously weak or strong slope at the inflexion point of the DR curves of actives. The classifier has been trained on an algorithmically generated dataset curated and refined by experts, tested using real screening campaigns and improved using thousands of annotations by experts. The solution is deployed using a MLFlow model server interfaced with the Genedata Screener data analysis software used by the end users. AI4DR improves the consistency, the robustness, and the speed of HTS data analysis as well as reducing the human effort to identify faster new medicines for patients.

High throughput image processing software for analyzing hiPSC-CM sarcomere physiology and cardiac fibroblast activation.

Heart disease is the leading cause of death worldwide and discovering therapies that treat its underlying cause is paramount to improving survivability and patient health. Since heart disease often results in detrimental remodeling of heart tissue, high-throughput screening (HTS) using cardiomyocytes and cardiac fibroblasts is frequently used for drug discovery. A major challenge in analyzing HTS data is ensuring that analysis is both fast and minimally biased. In many forms of heart disease and remodeling, cardiomyocytes will suffer from loss of sarcomeres and sarcomere disarray, while fibroblasts will often express increased α-smooth muscle actin (α-SMA) stress fibers when activated into myofibroblasts. Two custom MATLAB HTS image processing scripts named ‘Tamarack’ and ‘Porcupine’ were developed for quantifying human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) sarcomere morphology and cardiac fibroblast activation, respectively. Both scripts use wavelet transforms to detect subcellular structures that are of interest for analyzing phenotypes at the cellular level. Tamarack enables quantification of sarcomere metrics, including sarcomere count, length, orientation, and α-actinin rich areas. Porcupine enables quantification of fibroblast activation metrics, including α-SMA stress fiber count, length, orientation, nuclei and α-SMA overlap, and F-actin and α-SMA overlap. Both scripts enable analysis of other cellular features, such as nuclei count and stain intensity/protein expression. Tamarack obtained statistically significant results when comparing control hiPSC-CMs with hiPSC-CMs subjected to siRNA knockdowns of genes of interest. Porcupine was validated by analyzing fibroblasts with increasing concentrations of TGF-β which induced increasing activation. By developing technology for analyzing cardiomyocyte and fibroblast imaged-based screens, drug candidates can be efficiently evaluated without bias on cell types that are relevant to human heart disease. This research may help expand drug candidate portfolios and improve the number of treatments available to patients worldwide.