From Deep Mutational Mapping of Allosteric Protein Landscapes to Deep Learning of Allostery and Hidden Allosteric Sites: Zooming in on "Allosteric Intersection" of Biochemical and Big Data Approaches.

The recent advances in artificial intelligence (AI) and machine learning have driven the design of new expert systems and automated workflows that are able to model complex chemical and biological phenomena. In recent years, machine learning approaches have been developed and actively deployed to facilitate computational and experimental studies of protein dynamics and allosteric mechanisms. In this review, we discuss in detail new developments along two major directions of allosteric research through the lens of data-intensive biochemical approaches and AI-based computational methods. Despite considerable progress in applications of AI methods for protein structure and dynamics studies, the intersection between allosteric regulation, the emerging structural biology technologies and AI approaches remains largely unexplored, calling for the development of AI-augmented integrative structural biology. In this review, we focus on the latest remarkable progress in deep high-throughput mining and comprehensive mapping of allosteric protein landscapes and allosteric regulatory mechanisms as well as on the new developments in AI methods for prediction and characterization of allosteric binding sites on the proteome level. We also discuss new AI-augmented structural biology approaches that expand our knowledge of the universe of protein dynamics and allostery. We conclude with an outlook and highlight the importance of developing an open science infrastructure for machine learning studies of allosteric regulation and validation of computational approaches using integrative studies of allosteric mechanisms. The development of community-accessible tools that uniquely leverage the existing experimental and simulation knowledgebase to enable interrogation of the allosteric functions can provide a much-needed boost to further innovation and integration of experimental and computational technologies empowered by booming AI field.

Machine learning and protein allostery.

The fundamental biological importance and complexity of allosterically regulated proteins stem from their central role in signal transduction and cellular processes. Recently, machine-learning approaches have been developed and actively deployed to facilitate theoretical and experimental studies of protein dynamics and allosteric mechanisms. In this review, we survey recent developments in applications of machine-learning methods for studies of allosteric mechanisms, prediction of allosteric effects and allostery-related physicochemical properties, and allosteric protein engineering. We also review the applications of machine-learning strategies for characterization of allosteric mechanisms and drug design targeting SARS-CoV-2. Continuous development and task-specific adaptation of machine-learning methods for protein allosteric mechanisms will have an increasingly important role in bridging a wide spectrum of data-intensive experimental and theoretical technologies.

Exploring and Learning the Universe of Protein Allostery Using Artificial Intelligence Augmented Biophysical and Computational Approaches.

Allosteric mechanisms are commonly employed regulatory tools used by proteins to orchestrate complex biochemical processes and control communications in cells. The quantitative understanding and characterization of allosteric molecular events are among major challenges in modern biology and require integration of innovative computational experimental approaches to obtain atomistic-level knowledge of the allosteric states, interactions, and dynamic conformational landscapes. The growing body of computational and experimental studies empowered by emerging artificial intelligence (AI) technologies has opened up new paradigms for exploring and learning the universe of protein allostery from first principles. In this review we analyze recent developments in high-throughput deep mutational scanning of allosteric protein functions; applications and latest adaptations of Alpha-fold structural prediction methods for studies of protein dynamics and allostery; new frontiers in integrating machine learning and enhanced sampling techniques for characterization of allostery; and recent advances in structural biology approaches for studies of allosteric systems. We also highlight recent computational and experimental studies of the SARS-CoV-2 spike (S) proteins revealing an important and often hidden role of allosteric regulation driving functional conformational changes, binding interactions with the host receptor, and mutational escape mechanisms of S proteins which are critical for viral infection. We conclude with a summary and outlook of future directions suggesting that AI-augmented biophysical and computer simulation approaches are beginning to transform studies of protein allostery toward systematic characterization of allosteric landscapes, hidden allosteric states, and mechanisms which may bring about a new revolution in molecular biology and drug discovery.

Computational investigation of peptidomimetics as potential inhibitors of SARS-CoV-2 spike protein.

Several variants of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) were observed since the outbreak of the global pandemic at the end of 2019. The trimeric spike glycoprotein of the SARS-CoV-2 virus is crucial for the viral access to the host cell by interacting with the human angiotensin converting enzyme 2 (ACE2). Most of the mutations take place in the receptor-binding domain (RBD) of the S1 subunit of the trimeric spike glycoprotein. In this work, we targeted both S1 and S2 subunits of the spike protein in the wild type (WT) and the Omicron variant guided by the interaction of the neutralizing monoclonal antibodies. Virtual screening of two different peptidomimetics databases, ChEMBL and ChemDiv databases, was carried out against both S1 and S2 subunits. The use of these two databases provided diversity and enhanced the chance of finding protein-protein interaction inhibitors (PPIIs). Multi-layered filtration, based on physicochemical properties and docking scores, of nearly 114,000 compounds found in the ChEMBL database and nearly 14,000 compounds in the ChemDiv database was employed. Four peptidomimetics compounds were effective against both the WT and the Omicron S1 subunit with the minimum binding free energy of -25 kcal/mol. Five peptidomimetics compounds were effective against the S2 subunit with the minimum binding free energy of -19 kcal/mol. The dynamical cross-correlation matrix insinuated that the mutations of the RBD in the Omicron variant of the SARS-CoV-2 virus altered the correlated conformational motion of the different regions of the protein.Communicated by Ramaswamy H. Sarma.

Allosteric control of ACE2 peptidase domain dynamics.

The Angiotensin Converting Enzyme 2 (ACE2) assists the regulation of blood pressure and is the main target of the coronaviruses responsible for SARS and COVID19. The catalytic function of ACE2 relies on the opening and closing motion of its peptidase domain (PD). In this study, we investigated the possibility of allosterically controlling the ACE2 PD functional dynamics. After confirming that ACE2 PD binding site opening-closing motion is dominant in characterizing its conformational landscape, we observed that few mutations in the viral receptor binding domain fragments were able to impart different effects on the binding site opening of ACE2 PD. This showed that binding to the solvent exposed area of ACE2 PD can effectively alter the conformational profile of the protein, and thus likely its catalytic function. Using a targeted machine learning model and relative entropy-based statistical analysis, we proposed the mechanism for the allosteric perturbation that regulates the ACE2 PD binding site dynamics at atomistic level. The key residues and the source of the allosteric regulation of ACE PD dynamics are also presented.

Protective characteristics of COVID-19 convalescent and post-vaccination IgG antibodies (preprint)

Soon after commencement of the SARS-CoV-2 disease outbreak of 2019 (COVID-19), it became evident that the receptor-binding domain of the viral spike protein is the target of neutralizing antibodies that comprise a critical element of protective immunity to the virus. This study addresses the relative lack of information regarding actual antibody concentrations in convalescent plasma samples from COVID-19 patients and extends these analyses to post-vaccination samples to estimate protective IgG antibody (Ab) levels. Both sample populations were similar and a protective Ab level of 7.5 g/ml was determined, based on 95% of the normal distribution of the post-vaccination population. The results of this study have implications for future vaccine development, projection of protective efficacy duration, and understanding of the immune response to SARS-CoV-2 infection.

Predicting Potential SARS-COV-2 Drugs-In Depth Drug Database Screening Using Deep Neural Network Framework SSnet, Classical Virtual Screening and Docking.

Severe Acute Respiratory Syndrome Corona Virus 2 has altered life on a global scale. A concerted effort from research labs around the world resulted in the identification of potential pharmaceutical treatments for CoVID-19 using existing drugs, as well as the discovery of multiple vaccines. During an urgent crisis, rapidly identifying potential new treatments requires global and cross-discipline cooperation, together with an enhanced open-access research model to distribute new ideas and leads. Herein, we introduce an application of a deep neural network based drug screening method, validating it using a docking algorithm on approved drugs for drug repurposing efforts, and extending the screen to a large library of 750,000 compounds for de novo drug discovery effort. The results of large library screens are incorporated into an open-access web interface to allow researchers from diverse fields to target molecules of interest. Our combined approach allows for both the identification of existing drugs that may be able to be repurposed and de novo design of ACE2-regulatory compounds. Through these efforts we demonstrate the utility of a new machine learning algorithm for drug discovery, SSnet, that can function as a tool to triage large molecular libraries to identify classes of molecules with possible efficacy.

Deciphering the protein motion of S1 subunit in SARS-CoV-2 spike glycoprotein through integrated computational methods.

The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a major worldwide public health emergency that has infected over 8 million people. Spike glycoprotein, especially the partially open state of S1 subunit, in SARS-CoV-2 is considered vital for its infection with human host cell. However, the mechanism elucidating the transition from the closed state to the partially open state still remains unclear. In this study, we applied a series of computational methods, including Markov state model, transition path theory and random forest to analyze the S1 motion. Our results showed a promising complete conformational movement of the receptor-binding domain, from buried, partially open, to detached states. We also estimated the transition probability among these states. Based on the asymmetry in both the dynamics behavior and the accumulated alpha carbon (Cα) importance, we further suggested a relation among chains in the trimer spike protein, which leads to a deeper understanding on protein motions of the S1 subunit.Communicated by Ramaswamy H. Sarma.

Treatment of pancreatic diseases and prevention of infection during outbreak of 2019 coronavirus disease / 中华外科杂志

Objective@#To explorethe proper protective measures for pancreaticdiseases treatment during theoutbreak of 2019 coronavirus disease(COVID-19).@*Method@#Clinical data of four cases of patients that suffered COVID-19from February 2nd, 2020 to February 9th, 2020 in pancreatic surgery were reviewed.After the first patientscuffednosocomial infection of COVID-19, the general protective measures in our department wereupdated.Only one patient was admitted to each room alone, with no more than one caregiver.The body temperature of care givers was measuredtwice a day.Primary protections were applied to all staff.The floor was sterilized using disinfectant with an effective chlorine concentration of 1000 mg/L.The protective measures for interventional procedures were as follow.Primary protection was applied to the operators ofcentral venipuncture catheter, percutaneous abdominal/pleural drainage, percutaneous retroperitoneal drainage, percutaneous transhepatic cholangial drainage and other surgical procedures with local anesthesiaand epidural anesthesia.Secondary protection was applied to the operators of endoscopic retrograde cholangiopancreatography and surgical procedures with general anesthesia.@*Results@#During Feb 2nd, 2020 to Feb 9th, 2020, four patients in our department were diagnosed with COVID-19, of which one was died of COVID-19, two were cured, and one is still in hospital for COVID-19.After the update ofprotective measures in our department, no more nosocomial infection of COVID-19occurred.Two central venipuncture catheter, three percutaneous abdominal/pleural drainage, one percutaneous retroperitoneal drainage, one percuteneous transhepatic cholecyst drainage and one open surgery with general anesthesia were performed with no infection of operators.@*Conclusions@#The caregivers of patients are potential infection source of COVID-19.Enhanced protective measures including the management measures of caregivers can decrease the risk of nosocomial infection of COVID-19.

Highly accurate and sensitive diagnostic detection of SARS-CoV-2 by digital PCR (preprint)

BACKGROUND: The outbreak of COVID-19 caused by a novel Coronavirus (termed SARS-CoV-2) has spread to over 140 countries around the world. Currently, reverse transcription quantitative qPCR (RT-qPCR) is used as the gold standard for diagnostics of SARS-CoV-2. However, the positive rate of RT-qPCR assay of pharyngeal swab samples are reported to vary from 30~60%. More accurate and sensitive methods are urgently needed to support the quality assurance of the RT-qPCR or as an alternative diagnostic approach. METHODSWe established a reverse transcription digital PCR (RT-dPCR) protocol to detect SARS-CoV-2 on 194 clinical pharyngeal swab samples, including 103 suspected patients, 75 close contacts and 16 supposed convalescents. RESULTS: The limit of blanks (LoBs) of the RT-dPCR assays were ~1.6, ~1.6 and ~0.8 copies/reaction for ORF 1ab, N and E genes, respectively. The limit of detection (LoD) was 2 copies/reaction. For the 103 fever suspected patients, the sensitivity of SARS-CoV-2 detection was significantly improved from 28.2% by RT-qPCR to 87.4% by RT-dPCR. For close contacts, the suspect rate was greatly decreased from 21% down to 1%. The overall sensitivity, specificity and diagnostic accuracy of RT-dPCR were 90%, 100% and 93 %, respectively. In addition, quantification of the viral load for convalescents by RT-dPCR showed that a longer observation period was needed in the hospital for elderly patients. CONCLUSION: RT-dPCR could be a confirmatory method for suspected patients diagnosed by RT-qPCR. Furthermore, RT-dPCR was more sensitive and suitable for low viral load specimens from the both patients under isolation and those under observation who may not be exhibiting clinical symptoms.