scholarly journals Leveraging high-throughput screening data, deep neural networks, and conditional generative adversarial networks to advance predictive toxicology

2021 ◽  
Vol 17 (7) ◽  
pp. e1009135
Author(s):  
Adrian J. Green ◽  
Martin J. Mohlenkamp ◽  
Jhuma Das ◽  
Meenal Chaudhari ◽  
Lisa Truong ◽  
...  
Keyword(s):  
Neural Networks ◽  
High Throughput ◽  
Environmental Protection Agency ◽  
High Throughput Screening ◽  
Deep Neural Networks ◽  
Generative Adversarial Networks ◽  
Support Vector ◽  
Large Set ◽  
Toxicity Data

There are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) and computational methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional generative adversarial network (cGAN) or deep neural networks (DNN), and leveraging this large set of toxicity data we could efficiently predict toxic outcomes of untested chemicals. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo toxicity and chemical data were used to train two neural network generators. The first was a DNN (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train generators to produce toxicity data. Our results showed that Go-ZT significantly outperformed the cGAN, support vector machine, random forest and multilayer perceptron models in cross-validation, and when tested against an external test dataset. By combining both Go-ZT and GAN-ZT, our consensus model improved the SE, SP, PPV, and Kappa, to 71.4%, 95.9%, 71.4% and 0.673, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.837. Considering their potential use as prescreening tools, these models could provide in vivo toxicity predictions and insight into the hundreds of thousands of untested chemicals to prioritize compounds for HT testing.

scholarly journals Leveraging high-throughput screening data and conditional generative adversarial networks to advance predictive toxicology

2020 ◽  
Author(s):  
Adrian J. Green ◽  
Martin J. Mohlenkamp ◽  
Jhuma Das ◽  
Meenal Chaudhari ◽  
Lisa Truong ◽  
...  
Keyword(s):  
High Throughput ◽  
High Throughput Screening ◽  
Chemical Structure ◽  
Structural Information ◽  
Generative Adversarial Networks ◽  
Toxicity Data ◽  
Generative Adversarial Network ◽  
Structure Information ◽  
Adversarial Network

AbstractThere are currently 85,000 chemicals registered with the Environmental Protection Agency (EPA) under the Toxic Substances Control Act, but only a small fraction have measured toxicological data. To address this gap, high-throughput screening (HTS) methods are vital. As part of one such HTS effort, embryonic zebrafish were used to examine a suite of morphological and mortality endpoints at six concentrations from over 1,000 unique chemicals found in the ToxCast library (phase 1 and 2). We hypothesized that by using a conditional Generative Adversarial Network (cGAN) and leveraging this large set of toxicity data, plus chemical structure information, we could efficiently predict toxic outcomes of untested chemicals. CAS numbers for each chemical were used to generate textual files containing three-dimensional structural information for each chemical. Utilizing a novel method in this space, we converted the 3D structural information into a weighted set of points while retaining all information about the structure. In vivo toxicity and chemical data were used to train two neural network generators. The first used regression (Go-ZT) while the second utilized cGAN architecture (GAN-ZT) to train a generator to produce toxicity data. Our results showed that both Go-ZT and GAN-ZT models produce similar results, but the cGAN achieved a higher sensitivity (SE) value of 85.7% vs 71.4%. Conversely, Go-ZT attained higher specificity (SP), positive predictive value (PPV), and Kappa results of 67.3%, 23.4%, and 0.21 compared to 24.5%, 14.0%, and 0.03 for the cGAN, respectively. By combining both Go-ZT and GAN-ZT, our consensus model improved the SP, PPV, and Kappa, to 75.5%, 25.0%, and 0.211, respectively, resulting in an area under the receiver operating characteristic (AUROC) of 0.663. Considering their potential use as prescreening tools, these models could provide in vivo toxicity predictions and insight into untested areas of the chemical space to prioritize compounds for HT testing.SummaryA conditional Generative Adversarial Network (cGAN) can leverage a large chemical set of experimental toxicity data plus chemical structure information to predict the toxicity of untested compounds.

scholarly journals Investigating Molecular Mechanisms of Immunotoxicity and the Utility of ToxCast for Immunotoxicity Screening of Chemicals Added to Food

2021 ◽  
Vol 18 (7) ◽  
pp. 3332
Author(s):  
Olga V. Naidenko ◽  
David Q. Andrews ◽  
Alexis M. Temkin ◽  
Tasha Stoiber ◽  
Uloma Igara Uche ◽  
...  
Keyword(s):  
Immune System ◽  
High Throughput ◽  
Environmental Protection Agency ◽  
High Throughput Screening ◽  
Molecular Mechanisms ◽  
Specific Activity ◽  
Laboratory Animals ◽  
In Vitro Assays ◽  
Toxicological Studies

The development of high-throughput screening methodologies may decrease the need for laboratory animals for toxicity testing. Here, we investigate the potential of assessing immunotoxicity with high-throughput screening data from the U.S. Environmental Protection Agency ToxCast program. As case studies, we analyzed the most common chemicals added to food as well as per- and polyfluoroalkyl substances (PFAS) shown to migrate to food from packaging materials or processing equipment. The antioxidant preservative tert-butylhydroquinone (TBHQ) showed activity both in ToxCast assays and in classical immunological assays, suggesting that it may affect the immune response in people. From the PFAS group, we identified eight substances that can migrate from food contact materials and have ToxCast data. In epidemiological and toxicological studies, PFAS suppress the immune system and decrease the response to vaccination. However, most PFAS show weak or no activity in immune-related ToxCast assays. This lack of concordance between toxicological and high-throughput data for common PFAS indicates the current limitations of in vitro screening for analyzing immunotoxicity. High-throughput in vitro assays show promise for providing mechanistic data relevant for immune risk assessment. In contrast, the lack of immune-specific activity in the existing high-throughput assays cannot validate the safety of a chemical for the immune system.

scholarly journals High-throughput screening and rational design of biofunctionalized surfaces with optimized biocompatibility and antimicrobial activity

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Zhou Fang ◽  
Junjian Chen ◽  
Ye Zhu ◽  
Guansong Hu ◽  
Haoqian Xin ◽  
...  
Keyword(s):  
Antimicrobial Activity ◽  
High Throughput ◽  
High Throughput Screening ◽  
Rational Design ◽  
Click Reaction ◽  
Reaction Times ◽  
Great Promise ◽  
Biomaterial Surfaces

AbstractPeptides are widely used for surface modification to develop improved implants, such as cell adhesion RGD peptide and antimicrobial peptide (AMP). However, it is a daunting challenge to identify an optimized condition with the two peptides showing their intended activities and the parameters for reaching such a condition. Herein, we develop a high-throughput strategy, preparing titanium (Ti) surfaces with a gradient in peptide density by click reaction as a platform, to screen the positions with desired functions. Such positions are corresponding to optimized molecular parameters (peptide densities/ratios) and associated preparation parameters (reaction times/reactant concentrations). These parameters are then extracted to prepare nongradient mono- and dual-peptide functionalized Ti surfaces with desired biocompatibility or/and antimicrobial activity in vitro and in vivo. We also demonstrate this strategy could be extended to other materials. Here, we show that the high-throughput versatile strategy holds great promise for rational design and preparation of functional biomaterial surfaces.

414 Deep Neural Networks: A Survey Tool for Obstructive Sleep Apnea Prediction

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A164-A164
Author(s):  
Pahnwat Taweesedt ◽  
JungYoon Kim ◽  
Jaehyun Park ◽  
Jangwoon Park ◽  
Munish Sharma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Deep Neural Networks ◽  
Support Vector ◽  
Learning Models ◽  
Obstructive Sleep ◽  
Screening Questionnaires ◽  
Machine Learning Models

Abstract Introduction Obstructive sleep apnea (OSA) is a common sleep-related breathing disorder with an estimation of one billion people. Full-night polysomnography is considered the gold standard for OSA diagnosis. However, it is time-consuming, expensive and is not readily available in many parts of the world. Many screening questionnaires and scores have been proposed for OSA prediction with high sensitivity and low specificity. The present study is intended to develop models with various machine learning techniques to predict the severity of OSA by incorporating features from multiple questionnaires. Methods Subjects who underwent full-night polysomnography in Torr sleep center, Texas and completed 5 OSA screening questionnaires/scores were included. OSA was diagnosed by using Apnea-Hypopnea Index ≥ 5. We trained five different machine learning models including Deep Neural Networks with the scaled principal component analysis (DNN-PCA), Random Forest (RF), Adaptive Boosting classifier (ABC), and K-Nearest Neighbors classifier (KNC) and Support Vector Machine Classifier (SVMC). Training:Testing subject ratio of 65:35 was used. All features including demographic data, body measurement, snoring and sleepiness history were obtained from 5 OSA screening questionnaires/scores (STOP-BANG questionnaires, Berlin questionnaires, NoSAS score, NAMES score and No-Apnea score). Performance parametrics were used to compare between machine learning models. Results Of 180 subjects, 51.5 % of subjects were male with mean (SD) age of 53.6 (15.1). One hundred and nineteen subjects were diagnosed with OSA. Area Under the Receiver Operating Characteristic Curve (AUROC) of DNN-PCA, RF, ABC, KNC, SVMC, STOP-BANG questionnaire, Berlin questionnaire, NoSAS score, NAMES score, and No-Apnea score were 0.85, 0.68, 0.52, 0.74, 0.75, 0.61, 0.63, 0,61, 0.58 and 0,58 respectively. DNN-PCA showed the highest AUROC with sensitivity of 0.79, specificity of 0.67, positive-predictivity of 0.93, F1 score of 0.86, and accuracy of 0.77. Conclusion Our result showed that DNN-PCA outperforms OSA screening questionnaires, scores and other machine learning models. Support (if any):

scholarly journals A Microfluidic Spheroid Culture Device with a Concentration Gradient Generator for High-Throughput Screening of Drug Efficacy

Molecules ◽  
2018 ◽  
Vol 23 (12) ◽  
pp. 3355 ◽  
Author(s):  
Wanyoung Lim ◽  
Sungsu Park
Keyword(s):  
High Throughput ◽  
Concentration Gradient ◽  
High Throughput Screening ◽  
3D Cell Culture ◽  
Drug Efficacy ◽  
Cancer Drug ◽  
Spheroid Culture ◽  
Gradient Generator ◽  
Micro Channels

Three-dimensional (3D) cell culture is considered more clinically relevant in mimicking the structural and physiological conditions of tumors in vivo compared to two-dimensional cell cultures. In recent years, high-throughput screening (HTS) in 3D cell arrays has been extensively used for drug discovery because of its usability and applicability. Herein, we developed a microfluidic spheroid culture device (μFSCD) with a concentration gradient generator (CGG) that enabled cells to form spheroids and grow in the presence of cancer drug gradients. The device is composed of concave microwells with several serpentine micro-channels which generate a concentration gradient. Once the colon cancer cells (HCT116) formed a single spheroid (approximately 120 μm in diameter) in each microwell, spheroids were perfused in the presence of the cancer drug gradient irinotecan for three days. The number of spheroids, roundness, and cell viability, were inversely proportional to the drug concentration. These results suggest that the μFSCD with a CGG has the potential to become an HTS platform for screening the efficacy of cancer drugs.

scholarly journals Reconfigurable Binary Neural Network Accelerator with Adaptive Parallelism Scheme

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 230
Author(s):  
Jaechan Cho ◽  
Yongchul Jung ◽  
Seongjoo Lee ◽  
Yunho Jung
Keyword(s):  
Neural Networks ◽  
High Throughput ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Throughput Performance ◽  
Adaptive Parallelism ◽  
Sensor Applications ◽  
Binary Neural Network ◽  
Target Layer ◽  
Network Topologies

Binary neural networks (BNNs) have attracted significant interest for the implementation of deep neural networks (DNNs) on resource-constrained edge devices, and various BNN accelerator architectures have been proposed to achieve higher efficiency. BNN accelerators can be divided into two categories: streaming and layer accelerators. Although streaming accelerators designed for a specific BNN network topology provide high throughput, they are infeasible for various sensor applications in edge AI because of their complexity and inflexibility. In contrast, layer accelerators with reasonable resources can support various network topologies, but they operate with the same parallelism for all the layers of the BNN, which degrades throughput performance at certain layers. To overcome this problem, we propose a BNN accelerator with adaptive parallelism that offers high throughput performance in all layers. The proposed accelerator analyzes target layer parameters and operates with optimal parallelism using reasonable resources. In addition, this architecture is able to fully compute all types of BNN layers thanks to its reconfigurability, and it can achieve a higher area–speed efficiency than existing accelerators. In performance evaluation using state-of-the-art BNN topologies, the designed BNN accelerator achieved an area–speed efficiency 9.69 times higher than previous FPGA implementations and 24% higher than existing VLSI implementations for BNNs.

scholarly journals Uncertainty-Informed Deep Transfer Learning of PFAS Toxicity

2021 ◽  
Author(s):  
Jeremy Feinstein ◽  
ganesh sivaraman ◽  
Kurt Picel ◽  
Brian Peters ◽  
Alvaro Vazquez-Mayagoitia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
High Throughput ◽  
High Throughput Screening ◽  
Organic Chemical ◽  
Learning Method ◽  
Toxicity Data ◽  
Chemical Structures ◽  
Machine Learning Methods ◽  
Computational Methodology

In this article, we present our recent study on computational methodology for predicting the toxicity of PFAS known as “forever chemicals” based on chemical structures through evaluation of multiple machine learning methods. To address the scarcity of PFAS toxicity data, a deep “transfer learning” method has been investigated by leveraging toxicity information over the entire organic chemical domain and an uncertainty-informed workflow by incorporating SelectiveNet architecture, which can support future guidance of high throughput screening with knowledge of chemical structures, has been developed.

Bidirectional deep neural networks to integrate RNA and DNA data for predicting outcome for patients with hepatocellular carcinoma

2021 ◽  
Author(s):  
Guojun Huang ◽  
Cheng Wang ◽  
Xi Fu
Keyword(s):  
Hepatocellular Carcinoma ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Support Vector ◽  
Machine Model ◽  
Mrna Expression Data ◽  
Machine Learning Approach ◽  
Patient Profiling ◽  
Predicting Outcome ◽  
Subgroup Classification

Aims: Individualized patient profiling is instrumental for personalized management in hepatocellular carcinoma (HCC). This study built a model based on bidirectional deep neural networks (BiDNNs), an unsupervised machine-learning approach, to integrate multi-omics data and predict survival in HCC. Methods: DNA methylation and mRNA expression data for HCC samples from the TCGA database were integrated using BiDNNs. With optimal clusters as labels, a support vector machine model was developed to predict survival. Results: Using the BiDNN-based model, samples were clustered into two survival subgroups. The survival subgroup classification was an independent prognostic factor. BiDNNs were superior to multimodal autoencoders. Conclusion: This study constructed and validated a BiDNN-based model for predicting prognosis in HCC, with implications for individualized therapies in HCC.

Sign in / Sign up

Export Citation Format

Share Document