MOTIVATION: Non-linear ordinary differential equation (ODE) models that contain numerous parameters are suitable for inferring an emulated gene regulatory network (eGRN). However, the number of experimental measurements is usually far smaller than the number of parameters of the eGRN model that leads to an underdetermined problem. There is no unique solution to the inference problem for an eGRN using insufficient measurements. RESULTS: This work proposes an evolutionary modelling algorithm (EMA) that is based on evolutionary intelligence to cope with the underdetermined problem. EMA uses an intelligent genetic algorithm to solve the large-scale parameter optimization problem. An EMA-based method, GREMA, infers a novel type of gene regulatory network with confidence levels for every inferred regulation. The higher the confidence level is, the more accurate the inferred regulation is. GREMA gradually determines the regulations of an eGRN with confidence levels in descending order using either an S-system or a Hill function-based ODE model. The experimental results showed that the regulations with high-confidence levels are more accurate and robust than regulations with low-confidence levels. Evolutionary intelligence enhanced the mean accuracy of GREMA by 19.2% when using the S-system model with benchmark datasets. An increase in the number of experimental measurements may increase the mean confidence level of the inferred regulations. GREMA performed well compared with existing methods that have been previously applied to the same S-system, DREAM4 challenge and SOS DNA repair benchmark datasets. AVAILABILITY AND IMPLEMENTATION: All of the datasets that were used and the GREMA-based tool are freely available at https://nctuiclab.github.io/GREMA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Dear JAMIA Editors, As coronavirus disease 2019 (COVID-19) has become a global pandemic, we read with great interest the perspective by Turer et al1 on electronic personal protective equipment (ePPE). While they defined ePPE as “telemedicine tools used by on-site emergency providers to evaluate patients physically in the emergency department (ED) to avoid physical proximity,” we would like to share our hospital’s experience regarding the utility of ePPE in the negative-pressure isolation ward. Information technology has been implicated in infection control measures in various aspects.2,3 In Taiwan, patients with probable and confirmed COVID-19 were admitted into negative-pressure isolation wards. We have deployed several strategies using information technology to facilitate patient care in the negative-pressure isolation ward during the COVID-19 pandemic. With an increasing number of cases, the demand for N95 respiratory masks and PPE may rapidly exceed the supply, and critical supply shortages occur in many parts of the world.4 Donning and removing PPE is also time-consuming and brings much stress to the healthcare staff. Therefore, reducing the need of entering the negative-pressure isolation rooms is imperative, and we apply several strategies in our hospital. By optimizing the workflow, the nursing staff give medications and perform nursing care while delivering breakfast, lunch, and dinner. The medications are simplified, and those with once-daily dosing are preferred. In addition to the video monitoring equipment, we introduce a continuous contact-free monitoring system in the isolation ward, which monitors the heart rate, respiration, and postural status using a single-frequency continuous-wave radar and monitors the body temperature using an infrared thermal sensor.5 The nursing staff are able to get real-time information about the vital signs and conditions of the patients, so we are able to limit the times that the nursing staff enter the rooms to about 3 times daily. Some patients develop respiratory failure and require mechanical ventilation. The monitoring and control modules of ventilators are set outside the isolation room, connecting to the rest of the ventilator (the pneumatic system) in the room with an extension wire or Bluetooth technology (Some ventilators can even upload the monitoring data to the cloud via Wi-Fi). Without wearing PPE, respiratory therapists and physicians are able to have the monitoring data in hand and adjust the ventilator settings outside the isolation room. Psychological care is provided by psychiatrists via a teleconference system. Although the patients can talk with their family and friends with videotelephony software, a few patients may still develop psychological problems such as anxiety, helplessness, and emotional distress in the isolation rooms. Through regular talks with the patients via the teleconference system, the psychiatrists can help support the patients’ mental health remotely. This also avoids the unnecessary needs of extra nursing care, reducing the consumption of PPE. We adopted an electronic signature system so that the patients can sign informed consent forms (ICFs) on a tablet in their rooms. If paper-based ICFs were used, the signed ICF would be removed from the room after patient discharge and disinfected with ultraviolet light. With the electronic signature system, the signed ICFs are timely uploaded to the hospital information system. In summary, with the assistance of modern information technology, we can provide better and efficient care to patients with COVID-19 in the negative-pressure isolation ward, with limited consumption of epidemic prevention materials, especially PPE. Our experience demonstrates that ePPE could be applied in many aspects of the healthcare system. This study was supported by Kaohsiung Medical University Hospital (grants KMUH-C01 [to M-JT], KMUH-C27 [to S-FJ], and KMUH-C28 [to W-TT]). M-JT conceived the strategy, drafted the manuscript, and edited and approved the manuscript for submission. W-TT, H-SP, C-KH, and A-NC deployed the strategy and edited and approved the manuscript for submission. S-FJ, M-KH, and M-FH conceived the strategy and edited and approved the manuscript for submission. The authors thank all colleagues for the efforts against COVID-19. None declared.

Motivation: Numerous ubiquitination sites remain undiscovered because of the limitations of mass spectrometry-based methods. Existing prediction methods use randomly selected non-validated sites as non-ubiquitination sites to train ubiquitination site prediction models. Results: We propose an evolutionary screening algorithm (ESA) to select effective negatives among non-validated sites and an ESA-based prediction method, ESA-UbiSite, to identify human ubiquitination sites. The ESA selects non-validated sites least likely to be ubiquitination sites as training negatives. Moreover, the ESA and ESA-UbiSite use a set of well-selected physicochemical properties together with a support vector machine for accurate prediction. Experimental results show that ESA-UbiSite with effective negatives achieved 0.92 test accuracy and a Matthews's correlation coefficient of 0.48, better than existing prediction methods. The ESA increased ESA-UbiSite's test accuracy from 0.75 to 0.92 and can improve other post-translational modification site prediction methods. Availability and Implementation: An ESA-UbiSite-based web server has been established at http://iclab.life.nctu.edu.tw/iclab_webtools/ESAUbiSite/ . Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Protein-protein interactions (PPIs) are involved in various biological processes, and underlying mechanism of the interactions plays a crucial role in therapeutics and protein engineering. Most machine learning approaches have been developed for predicting the binding affinity of protein-protein complexes based on structure and functional information. This work aims to predict the binding affinity of heterodimeric protein complexes from sequences only. RESULTS: This work proposes a support vector machine (SVM) based binding affinity classifier, called SVM-BAC, to classify heterodimeric protein complexes based on the prediction of their binding affinity. SVM-BAC identified 14 of 580 sequence descriptors (physicochemical, energetic and conformational properties of the 20 amino acids) to classify 216 heterodimeric protein complexes into low and high binding affinity. SVM-BAC yielded the training accuracy, sensitivity, specificity, AUC and test accuracy of 85.80%, 0.89, 0.83, 0.86 and 83.33%, respectively, better than existing machine learning algorithms. The 14 features and support vector regression were further used to estimate the binding affinities (Pkd) of 200 heterodimeric protein complexes. Prediction performance of a Jackknife test was the correlation coefficient of 0.34 and mean absolute error of 1.4. We further analyze three informative physicochemical properties according to their contribution to prediction performance. Results reveal that the following properties are effective in predicting the binding affinity of heterodimeric protein complexes: apparent partition energy based on buried molar fractions, relations between chemical structure and biological activity in principal component analysis IV, and normalized frequency of beta turn. CONCLUSIONS: The proposed sequence-based prediction method SVM-BAC uses an optimal feature selection method to identify 14 informative features to classify and predict binding affinity of heterodimeric protein complexes. The characterization analysis revealed that the average numbers of beta turns and hydrogen bonds at protein-protein interfaces in high binding affinity complexes are more than those in low binding affinity complexes.