Contribution of machine learning approaches in response to SARS-CoV-2 infection

Abstract

Problem The lately emerged SARS-CoV-2 infection, which has put the whole world in an aberrant demanding situation, has generated an urgent need for developing effective responses through artificial intelligence (AI). Aim This paper aims to overview the recent applications of machine learning techniques contributing to prevention, diagnosis, monitoring, and treatment of coronavirus disease (SARS-CoV-2). Methods A progressive investigation of the recent publications up to November 2020, related to AI approaches towards managing the challenges of COVID-19 infection was made. Results For patient diagnosis and screening, Convolutional Neural Network (CNN) and Support Vector Machine (SVM) are broadly applied for classification purposes. Moreover, Deep Neural Network (DNN) and homology modeling are the most used SARS-CoV-2 drug repurposing models. Conclusion While the fields of diagnosis of the SARS-CoV-2 infection by medical image processing and its dissemination pattern through machine learning have been sufficiently studied, some areas such as treatment outcome in patients and drug development need to be further investigated using AI approaches.

Towards Privacy Paradigm Shift Due to the Pandemic: A Brief Perspective

“…Furthermore, the machine learning methods have demonstrated effectiveness in COVID-19's diagnosis (e.g., dissemination patterns analysis, cases classifications, and predictions etc.) [73]. During the pandemic times, AI has proven a powerful tool for public health authorities to mitigate the disease spread and building resilience against it [74][75][76][77].…”

Artificial intelligence-driven drug repurposing and structural biology for SARS-CoV-2

“…The recent applications of AI in the case of COVID-19 include the virtual screening of both repurposed drugs as well as new chemical entities ( Fig. 1 ) ( Keshavarzi ArshadiWebb et al, 2020 ; Zhou et al, 2020a ; Mottaqi et al, 2021 ; Piccialli et al, 2021 ). ML-based molecular docking has been utilized extensively for virtual screening and drug repurposing.…”

Aprendizagem Profunda Aplicada à Classificação do SARS-CoV-2

“…Segundo [6], [15] e [16] para obter melhores resultados, a classificac ¸ão viral baseada em AF, aplicam recursos de inteligência artificial baseada aprendizagem de máquina (Machine Learning -ML) para realizar a extrac ¸ão de características nas sequências genômicas utilizadas. Estudos recentes, apontam que algoritmos e técnicas de ML, têm sido amplamente utilizada em pesquisas relacionadas a genômica, incluindo a classificac ¸ão viral, por oferecer um conjunto de métodos, capazes de identificar padrões altamente complexos de forma automatizada, eficiente e com o mínimo de intervenc ¸ão humana [17], [18].…”

“…Trabalhos embasados na literatura, tem mostrado que técnicas de aprendizagem de máquina baseadas em aprendizagem profunda (Deep Learning -DL) apresentam excelentes resultados para aplicac ¸ões voltadas á sequências genômicas, incluindo problemas de classificac ¸ão [19], [20]. Os trabalhos de [21] e [18] revelam que, dentre os mais diversos algoritmos de ML, as redes neurais convolucionais (Convolutional Neural Network -CNN) vem sendo bastante utilizadas para análises de dados com base em sequências genômicas, por serem capazes de extrair características intrínsecas das sequências, e apresentarem resultados promissores em suas aplicac ¸ões. Contudo, a maior parte dessas ferramentas e técnicas, fazem uso de sequências genômicas de comprimento limitado, ou são voltadas para outras finalidades como predic ¸ão de proteínas [22], [23].…”