scholarly journals In silico Analyses of Immune System Protein Interactome Network, Single-Cell RNA Sequencing of Human Tissues, and Artificial Neural Networks Reveal Potential Therapeutic Targets for Drug Repurposing Against COVID-19

2021 ◽  
Vol 12 ◽  
Author(s):  
Andrés López-Cortés ◽  
Patricia Guevara-Ramírez ◽  
Nikolaos C. Kyriakidis ◽  
Carlos Barba-Ostria ◽  
Ángela León Cáceres ◽  
...  

Background: There is pressing urgency to identify therapeutic targets and drugs that allow treating COVID-19 patients effectively.Methods: We performed in silico analyses of immune system protein interactome network, single-cell RNA sequencing of human tissues, and artificial neural networks to reveal potential therapeutic targets for drug repurposing against COVID-19.Results: We screened 1,584 high-confidence immune system proteins in ACE2 and TMPRSS2 co-expressing cells, finding 25 potential therapeutic targets significantly overexpressed in nasal goblet secretory cells, lung type II pneumocytes, and ileal absorptive enterocytes of patients with several immunopathologies. Then, we performed fully connected deep neural networks to find the best multitask classification model to predict the activity of 10,672 drugs, obtaining several approved drugs, compounds under investigation, and experimental compounds with the highest area under the receiver operating characteristics.Conclusion: After being effectively analyzed in clinical trials, these drugs can be considered for treatment of severe COVID-19 patients. Scripts can be downloaded at https://github.com/muntisa/immuno-drug-repurposing-COVID-19.

2020 ◽  
Author(s):  
Andrés López-Cortés ◽  
Patricia Guevara-Ramírez ◽  
Nikolaos C Kyriakidis ◽  
Carlos Barba-Ostria ◽  
Ángela León Cáceres ◽  
...  

There is pressing urgency to better understand the immunological underpinnings of the coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus clade 2 (SARS-CoV-2) in order to identify potential therapeutic targets and drugs that allow treating patients effectively. To fill in this gap, we performed in silico analyses of immune system protein interactome network, single-cell RNA sequencing of human tissues, and artificial neural networks to reveal potential therapeutic targets for drug repurposing against COVID-19. As results, the high-confidence protein interactome network was conformed by 1,588 nodes between immune system proteins and human proteins physically associated with SARS-CoV-2. Subsequently, we screened all these nodes in ACE2 and TMPRSS2 co-expressing cells according to the Alexandria Project, finding 75 potential therapeutic targets significantly overexpressed (Z score > 2) in nasal goblet secretory cells, lung type II pneumocytes, and ileal absorptive enterocytes of patients with several immunopathologies. Then, we performed fully connected deep neural networks to find the best multitask classification model to predict the activity of 10,672 drugs for 25 of the 75 aforementioned proteins. On one hand, we obtained 45 approved drugs, 16 compounds under investigation, and 35 experimental compounds with the highest area under the receiver operating characteristic (AUROCs) for 15 immune system proteins. On the other hand, we obtained 4 approved drugs, 9 compounds under investigation, and 16 experimental compounds with the highest multi-target affinities for 9 immune system proteins. In conclusion, computational structure-based drug discovery focused on immune system proteins is imperative to select potential drugs that, after being effectively analyzed in cell lines and clinical trials, these can be considered for treatment of complex symptoms of COVID-19 patients, and for co-therapies with drugs directly targeting SARS-CoV-2.


Author(s):  
Andrés López-Cortés ◽  
Patricia Guevara-Ramírez ◽  
Nikolaos C Kyriakidis ◽  
Carlos Barba-Ostria ◽  
Ángela León Cáceres ◽  
...  

There is pressing urgency to better understand the immunological underpinnings of the coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus clade 2 (SARS-CoV-2) in order to identify potential therapeutic targets and drugs that allow treating patients effectively. To fill in this gap, we performed in silico analyses of immune system protein interactome network, single-cell RNA sequencing of human tissues, and artificial neural networks to reveal potential therapeutic targets for drug repurposing against COVID-19. As results, the high-confidence protein interactome network was conformed by 1,588 nodes between immune system proteins and human proteins physically associated with SARS-CoV-2. Subsequently, we screened all these nodes in ACE2 and TMPRSS2 co-expressing cells according to the Alexandria Project, finding 75 potential therapeutic targets significantly overexpressed (Z score > 2) in nasal goblet secretory cells, lung type II pneumocytes, and ileal absorptive enterocytes of patients with several immunopathologies. Then, we performed fully connected deep neural networks to find the best multitask classification model to predict the activity of 10,672 drugs for 25 of the 75 aforementioned proteins. On one hand, we obtained 45 approved drugs, 16 compounds under investigation, and 35 experimental compounds with the highest area under the receiver operating characteristic (AUROCs) for 15 immune system proteins. On the other hand, we obtained 4 approved drugs, 9 compounds under investigation, and 16 experimental compounds with the highest multi-target affinities for 9 immune system proteins. In conclusion, computational structure-based drug discovery focused on immune system proteins is imperative to select potential drugs that, after being effectively analyzed in cell lines and clinical trials, these can be considered for treatment of complex symptoms of COVID-19 patients, and for co-therapies with drugs directly targeting SARS-CoV-2.


Author(s):  
Abdelkader A Metwally ◽  
Amira A Nayel ◽  
Rania M Hathout

In silico prediction of the in vivo efficacy of siRNA ionizable-lipid nanoparticles is desirable yet never achieved before. This study aims to computationally predict siRNA nanoparticles in vivo efficacy, which saves time and resources. A data set containing 120 entries was prepared by combining molecular descriptors of the ionizable lipids together with two nanoparticles formulation characteristics. Input descriptor combinations were selected by an evolutionary algorithm. Artificial neural networks, support vector machines and partial least squares regression were used for QSAR modeling. Depending on how the data set is split, two training sets and two external validation sets were prepared. Training and validation sets contained 90 and 30 entries respectively. The results showed the successful predictions of validation set log(dose) with R2val = 0.86 – 0.89 and 0.75 – 80 for validation sets one and two respectively. Artificial neural networks resulted in the best R2val for both validation sets. For predictions that have high bias, improvement of R2val from 0.47 to 0.96 was achieved by selecting the training set lipids lying within the applicability domain. In conclusion, in vivo performance of siRNA nanoparticles was successfully predicted by combining cheminformatics with machine learning techniques.


Author(s):  
И.А. Шаповалова

Современная иммунология не может успешно развиваться без помощи математического моделирования. Математические модели являются эффективным фильтром идей и индикатором правильности выбранных предположений, позволяют дать правильную интерпретацию результатам и выбирать критерии для оценки правильности, могут быть использованы как средство для визуализации результатов вычисления, что помогает дальнейшему развитию вычислительных алгоритмов. Исследование математической модели иммунной системы позволяет сравнивать теоретические и экспериментальные результаты и уточнять предположения, положенные в основу математического моделирования. Иммунная система является высокоразвитой биологической системой, функция которой заключается в выявлении и уничтожении чужеродного агента, поэтому она должна распознавать разнообразных возбудителей. Иммунная система способна к обучению, запоминанию, распознаванию образов, аналогичными свойствами обладают искусственные нейронные сети. Искусственные нейронные сети, подобно биологическим, являются вычислительной системой с огромным числом параллельно функционирующих простых процессоров с огромным числом связей. Нейросетевые алгоритмы используются в кластеризации, визуализации данных, контроле и оптимизации управляемых процессов, разработке искусственных нейронных сетей. В работе исследуется математическая модель иммунной системы, которая моделируется с помощью искусственной нейронной сети и описывается системой дифференциальных уравнений с запаздыванием. При анализе модели используется аппарат математической теории оптимального управления, а именно принцип максимума для систем дифференциальных уравнений с запаздыванием в аргументе функции состояния и аппарат методов оптимизации, базирующийся на методе быстрого автоматического дифференцирования. Вместо традиционных методов программирования используется обучение полносвязной искусственной нейронной сети с помощью метода распространения ошибки. Modern immunology can not be developed successfully without the help of mathematical modeling. Mathematical models are an effective way filter and indicator of the correctness of the selected assumptions. Mathematical models allow us to give a correct interpretation of the results, to select criteria for evaluating the correctness and that help the development of the numerical methods and algorithm. The research of the mathematical model of the immune system allow to compare theoretical and experimental results and clarified mathematical assumptions laid down in the basis of mathematical modeling. The immune system is a highly developed biological system, whose function is to detect and destroy foreign substance, so it needs to recognize a variety of pathogens.The immune system is capable of learning to remember the recognitions of images. The similar properties possess artificial neural networks. Similar to biological ones artificial neural networks are computer systems with a huge number of parallel functioning simple processors and with a large number of connections. Neural networks algorithms are used in clustering, data visualization, control and optimization of processes, the development of artificial neural networks. In the article we consider mathematical model of immune system modeled with the help of artificial multi layer neural net described by the system of differential equations with delay in argument of state functions. The model is analyzed with the help of the theory of optimal control namely the maximum principle of Pontrjagin for the systems of differential equations with delay in argument of the state functions. The method of optimization is based on the method of fast automatic differentiations. Instead of traditional methods of programming the training of the fully connected neural networks and the error propagation method are used.


Author(s):  
José Antonio Seoane Fernández ◽  
Mónica Miguélez Rico

Our previous article presented several computational models inspired on biological models, such as neural networks, evolutionary computation, swarm intelligence, and the artificial immune system. It also explained the most common problems in bioinformatics to which these models can be applied. The present article presents a series of approaches to bioinformatics tasks that were developed by means of artificial intelligence techniques and focus on bioinspired algorithms such as artificial neural networks and evolutionary computation.


2021 ◽  
Vol 12 ◽  
Author(s):  
Yedam Yoo ◽  
Aroli Marcellinus ◽  
Da Un Jeong ◽  
Ki-Suk Kim ◽  
Ki Moo Lim

As part of the Comprehensive in vitro Proarrhythmia Assay initiative, methodologies for predicting the occurrence of drug-induced torsade de pointes via computer simulations have been developed and verified recently. However, their predictive performance still requires improvement. Herein, we propose an artificial neural networks (ANN) model that uses nine multiple input features, considering the action potential morphology, calcium transient morphology, and charge features to further improve the performance of drug toxicity evaluation. The voltage clamp experimental data for 28 drugs were augmented to 2,000 data entries using an uncertainty quantification technique. By applying these data to the modified O’Hara Rudy in silico model, nine features (dVm/dtmax, APresting, APD90, APD50, Caresting, CaD90, CaD50, qNet, and qInward) were calculated. These nine features were used as inputs to an ANN model to classify drug toxicity into high-risk, intermediate-risk, and low-risk groups. The model was trained with data from 12 drugs and tested using the data of the remaining 16 drugs. The proposed ANN model demonstrated an AUC of 0.92 in the high-risk group, 0.83 in the intermediate-risk group, and 0.98 in the low-risk group. This was higher than the classification performance of the method proposed in previous studies.


Sign in / Sign up

Export Citation Format

Share Document