Refine
Year of publication
- 2020 (2) (remove)
Document Type
- Article (2)
Language
- English (2) (remove)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- 2019-nCoV (1)
- COVID-19 (1)
- Experts (1)
- Feedback loop (1)
- Machine learning (1)
- Machine teaching (1)
- antiviral (1)
- aprotinin (1)
- drug discovery (1)
- severe acute respiratory syndrome coronavirus (1)
Institute
- Medizin (2) (remove)
This article discusses the counterpart of interactive machine learning, i.e., human learning while being in the loop in a human-machine collaboration. For such cases we propose the use of a Contradiction Matrix to assess the overlap and the contradictions of human and machine predictions. We show in a small-scaled user study with experts in the area of pneumology (1) that machine-learning based systems can classify X-rays with respect to diseases with a meaningful accuracy, (2) humans partly use contradictions to reconsider their initial diagnosis, and (3) that this leads to a higher overlap between human and machine diagnoses at the end of the collaboration situation. We argue that disclosure of information on diagnosis uncertainty can be beneficial to make the human expert reconsider her or his initial assessment which may ultimately result in a deliberate agreement. In the light of the observations from our project, it becomes apparent that collaborative learning in such a human-in-the-loop scenario could lead to mutual benefits for both human learning and interactive machine learning. Bearing the differences in reasoning and learning processes of humans and intelligent systems in mind, we argue that interdisciplinary research teams have the best chances at tackling this undertaking and generating valuable insights.
Severe acute respiratory syndrome virus 2 (SARS-CoV-2) is the cause of the current coronavirus disease 19 (COVID-19) pandemic. Protease inhibitors are under consideration as virus entry inhibitors that prevent the cleavage of the coronavirus spike (S) protein by cellular proteases. Herein, we showed that the protease inhibitor aprotinin (but not the protease inhibitor SERPINA1/alpha-1 antitrypsin) inhibited SARS-CoV-2 replication in therapeutically achievable concentrations. An analysis of proteomics and translatome data indicated that SARS-CoV-2 replication is associated with a downregulation of host cell protease inhibitors. Hence, aprotinin may compensate for downregulated host cell proteases during later virus replication cycles. Aprotinin displayed anti-SARS-CoV-2 activity in different cell types (Caco2, Calu-3, and primary bronchial epithelial cell air–liquid interface cultures) and against four virus isolates. In conclusion, therapeutic aprotinin concentrations exert anti-SARS-CoV-2 activity. An approved aprotinin aerosol may have potential for the early local control of SARS-CoV-2 replication and the prevention of COVID-19 progression to a severe, systemic disease.