Understanding the Power of Evolutionary Computation for GPU Code Optimization

Achieving high performance for GPU codes requires developers to have significant knowledge in parallel programming and GPU architectures, and in-depth understanding of the application. This combination makes it challenging to find performance optimizations for GPU-based applications, especially in scientific computing. This paper shows that significant speedups can be achieved on two quite different scientific workloads using the tool, GEVO, to improve performance over human-optimized GPU code. GEVO uses evolutionary computation to find code edits that improve the runtime of a multiple sequence alignment kernel and a SARS-CoV-2 simulation by 28.9% and 29% respectively. Further, when GEVO begins with an early, unoptimized version of the sequence alignment program, it finds an impressive 30 times speedup-a performance improvement similar to that of the hand-tuned version. This work presents an in-depth analysis of the discovered optimizations, revealing that the primary sources of improvement vary across applications;that most of the optimizations generalize across GPU architectures;and that several of the most important optimizations involve significant code interdependencies. The results showcase the potential of automated program optimization tools to help reduce the optimization burden for scientific computing developers and enhance performance portability for domain-specific accelerators. © 2022 IEEE.

Fxr as a new therapeutic target for COVID-19

Background: Despite recent advances, the management of COVID19 is complicated by vaccine availability, the modest efficacy of existing treatments, and the potential for viral resistance. Therefore, there is a pressing need for new prophylactic and therapeutic agents. Modifying the expression of the SARS-CoV-2 entry receptor ACE2 could prevent viral infection and limit disease progression. Here, we identify that ACE2 expression is controlled by the transcription factor farnesoid X receptor (FXR) and demonstrate that ACE2 downregulation through FXR antagonism, using approved drugs, such as ursodeoxycholic acid (UDCA), could represent a novel therapeutic strategy to complement current approaches. Methods: Primary cholangiocyte, pulmonary and intestinal organoids were propagated using established protocols. Marker expression was assessed using singlecell RNA sequencing, QPCR, immunofluorescence and flow cytometry. FXR binding on DNA was assessed with chromatin immunoprecipitation. SARS-CoV-2 was isolated from bronchoalveolar lavage of a COVID19 patient. Viral load was measured via QPCR. Human livers not used for transplantation were perfused ex-situ using the metra (OrganOx) normothermic perfusion device. Serum ACE2 activity was measured with commercial kits. Patient data from the COVID-Hep and SECURE-Liver registries were compared using propensity score matching. Results: FXR activation directly upregulated ACE2 transcription in organoids from COVID19 affected tissues, including the biliary, gastrointestinal and respiratory systems. Conversely, FXR antagonism with z-guggulsterone or UDCA, had the opposite effect. Importantly, both drugs reduced susceptibility to SARS-CoV-2 infection in lung, cholangiocyte and gut organoids. Furthermore, systemic administration of UDCA in human organs perfused ex-situ downregulated ACE2 and reduced SARS-CoV-2 infection ex-vivo. Oral UDCA rapidly reduced serum ACE2 in vivo. Registry data showed a correlation between UDCA administration and better clinical outcomes in COVID19 patients, including hospitalisation, ICU admission, mechanical ventilation and death. Conclusion: We discovered FXR as a novel therapeutic target against SARS-CoV-2 and we identified approved FXR inhibitors which could be repurposed to potentially treat COVID19, paving the road for future clinical trials to validate these results.

Fxr antagonists as new agents for COVID19

Introduction The management of COVID19 is complicated by vaccine availability, the modest efficacy of existing treatments, and the potential for viral resistance. Therefore, there is a pressing need for new prophylactic and therapeutic agents. The viral receptor ACE2 is an ideal target as it is required for SARS-CoV-2 entry in host cells. Modifying ACE2 expression could prevent infection and/or limit disease progression. Nevertheless, the mechanisms controlling ACE2 expression remain elusive. Aims To identify pathways controlling the transcriptional regulation of ACE2, and exploit them to reduce SARS-CoV-2 infection. Methods Organoids from primary biliary, intestinal and pulmonary epithelia were derived and cultured as previously described. Single-cell RNA sequencing, QPCR, immunofluorescence and flow cytometry were used to assess marker expression. Chromatin immunoprecipitation was used to assess FXR binding on DNA. Bronchoalveolar lavage SARS-CoV-2 patient isolates were used for infection experiments. Human livers not used for transplantation were connected to the metra (OrganOx) normothermic perfusion device and perfused ex-situ using therapeutic doses of UDCA for 12 hours. ACE2 activity was measured following manufacturer's instructions. Patient data from the COVID-Hep and SECURE-Liver registries were compared using propensity score matching for sex, age and Child-Turcotte-Pugh score. Results We first demonstrated that cholangiocytes are susceptible to SARS-CoV-2 infection in vivo and in organoid culture. We then used cholangiocyte organoids to identify FXR as a transcriptional regulator of ACE2. We validated our results in pulmonary and intestinal organoids, showing that ACE2 regulation by FXR represents a broad mechanism present in multiple COVID19-affected tissues. We then demonstrated that approved FXR inhibitors, such as ursodeoxycholic acid (UDCA) and z-guggulsterone (ZGG), decrease ACE2 levels and reduce viral infection in vitro in primary biliary, intestinal and pulmonary organoids. We interrogated the impact of systemic UDCA administration in human livers perfused ex-situ, demonstrating reduced ACE2 levels and SARS-CoV-2 infection. Furthermore, we showed that commencing UDCA treatment lowers ACE2 levels in primary biliary cholangitis (PBC) patients. Finally, we identified a correlation between UDCA treatment and better clinical outcome in COVID-19 patients, including hospitalisation, ICU admission, mechanical ventilation and death, using registry data. Conclusion We identified FXR as a novel master regulator of ACE2 expression. Using a bench-to-bedside approach we combined in vitro, ex-vivo and patient data to demonstrate the efficacy of ACE2 downregulation against SARS-CoV-2 infection and identified approved and inexpensive drugs (UDCA, ZGG) which could be repurposed as prophylactic and therapeutic agents against SARS-CoV-2 infection, paving the road for future clinical trials.

Internet of Medical Things: Enabling Key Technologies

Across the World the Covid-19 pandemic has created a huge burden on the medical field. Technologies including Internet of Things (IoT) have been playing a vital role to create digital remote health services during a time of social distancing and isolation. IoT has rapidly expanded into the Healthcare field in recent years. The joining of Healthcare with IoT is named Internet of Medical Things (IoMT) and has significantly advanced many technologies with it. This paper is going to examine emerging technologies associated with IoMT as a whole and the embodiment of this technology including: Big-Data, Artificial Intelligence (AI), 5G, and Blockchain and how they are being utilized currently in the field. We will also present how these technologies can help combat the current pandemic.

A Multimodality Machine Learning Approach to Differentiate Severe and Nonsevere COVID-19: Model Development and Validation.

BACKGROUND: Effectively and efficiently diagnosing patients who have COVID-19 with the accurate clinical type of the disease is essential to achieve optimal outcomes for the patients as well as to reduce the risk of overloading the health care system. Currently, severe and nonsevere COVID-19 types are differentiated by only a few features, which do not comprehensively characterize the complicated pathological, physiological, and immunological responses to SARS-CoV-2 infection in the different disease types. In addition, these type-defining features may not be readily testable at the time of diagnosis. OBJECTIVE: In this study, we aimed to use a machine learning approach to understand COVID-19 more comprehensively, accurately differentiate severe and nonsevere COVID-19 clinical types based on multiple medical features, and provide reliable predictions of the clinical type of the disease. METHODS: For this study, we recruited 214 confirmed patients with nonsevere COVID-19 and 148 patients with severe COVID-19. The clinical characteristics (26 features) and laboratory test results (26 features) upon admission were acquired as two input modalities. Exploratory analyses demonstrated that these features differed substantially between two clinical types. Machine learning random forest models based on all the features in each modality as well as on the top 5 features in each modality combined were developed and validated to differentiate COVID-19 clinical types. RESULTS: Using clinical and laboratory results independently as input, the random forest models achieved >90% and >95% predictive accuracy, respectively. The importance scores of the input features were further evaluated, and the top 5 features from each modality were identified (age, hypertension, cardiovascular disease, gender, and diabetes for the clinical features modality, and dimerized plasmin fragment D, high sensitivity troponin I, absolute neutrophil count, interleukin 6, and lactate dehydrogenase for the laboratory testing modality, in descending order). Using these top 10 multimodal features as the only input instead of all 52 features combined, the random forest model was able to achieve 97% predictive accuracy. CONCLUSIONS: Our findings shed light on how the human body reacts to SARS-CoV-2 infection as a unit and provide insights on effectively evaluating the disease severity of patients with COVID-19 based on more common medical features when gold standard features are not available. We suggest that clinical information can be used as an initial screening tool for self-evaluation and triage, while laboratory test results should be applied when accuracy is the priority.

Accurately Differentiating COVID-19, Other Viral Infection, and Healthy Individuals Using Multimodal Features via Late Fusion Learning (preprint)

Effectively identifying COVID-19 patients using non-PCR clinical data is critical for the optimal clinical outcomes. Currently, there is a lack of comprehensive understanding of various biomedical features and appropriate technical approaches to accurately detecting COVID-19 patients. In this study, we recruited 214 confirmed COVID-19 patients in non-severe (NS) and 148 in severe (S) clinical type, 198 non-infected healthy (H) participants and 129 non-COVID viral pneumonia (V) patients. The participants' clinical information (23 features), lab testing results (10 features), and thoracic CT scans upon admission were acquired as three input feature modalities. To enable late fusion of multimodality data, we developed a deep learning model to extract a 10-feature high-level representation of the CT scans. Exploratory analyses showed substantial differences of all features among the four classes. Three machine learning models (k-nearest neighbor kNN, random forest RF, and support vector machine SVM) were developed based on the 43 features combined from all three modalities to differentiate four classes (NS, S, V, and H) at once. All three models had high accuracy to differentiate the overall four classes (95.4%-97.7%) and each individual class (90.6%-99.9%). Multimodal features provided substantial performance gain from using any single feature modality. Compared to existing binary classification benchmarks often focusing on single feature modality, this study provided a novel and effective breakthrough for clinical applications. Findings and the analytical workflow can be used as clinical decision support for current COVID-19 and other clinical applications with high-dimensional multimodal biomedical features.