Predicting kinase inhibitors using bioactivity matrix derived informer sets.

Prediction of compounds that are active against a desired biological target is a common step in drug discovery efforts. Virtual screening methods seek some active-enriched fraction of a library for experimental testing. Where data are too scarce to train supervised learning models for compound prioritization, initial screening must provide the necessary data. Commonly, such an initial library is selected on the basis of chemical diversity by some pseudo-random process (for example, the first few plates of a larger library) or by selecting an entire smaller library. These approaches may not produce a sufficient number or diversity of actives. An alternative approach is to select an informer set of screening compounds on the basis of chemogenomic information from previous testing of compounds against a large number of targets. We compare different ways of using chemogenomic data to choose a small informer set of compounds based on previously measured bioactivity data. We develop this Informer-Based-Ranking (IBR) approach using the Published Kinase Inhibitor Sets (PKIS) as the chemogenomic data to select the informer sets. We test the informer compounds on a target that is not part of the chemogenomic data, then predict the activity of the remaining compounds based on the experimental informer data and the chemogenomic data. Through new chemical screening experiments, we demonstrate the utility of IBR strategies in a prospective test on three kinase targets not included in the PKIS.

Large-scale linear rankSVM.

Linear rankSVM is one of the widely used methods for learning to rank. Although its performance may be inferior to nonlinear methods such as kernel rankSVM and gradient boosting decision trees, linear rankSVM is useful to quickly produce a baseline model. Furthermore, following its recent development for classification, linear rankSVM may give competitive performance for large and sparse data. A great deal of works have studied linear rankSVM. The focus is on the computational efficiency when the number of preference pairs is large. In this letter, we systematically study existing works, discuss their advantages and disadvantages, and propose an efficient algorithm. We discuss different implementation issues and extensions with detailed experiments. Finally, we develop a robust linear rankSVM tool for public use.

A study on L2-loss (squared hinge-loss) multiclass SVM.

Crammer and Singer's method is one of the most popular multiclass support vector machines (SVMs). It considers L1 loss (hinge loss) in a complicated optimization problem. In SVM, squared hinge loss (L2 loss) is a common alternative to L1 loss, but surprisingly we have not seen any paper studying the details of Crammer and Singer's method using L2 loss. In this letter, we conduct a thorough investigation. We show that the derivation is not trivial and has some subtle differences from the L1 case. Details provided in this work can be a useful reference for those who intend to use Crammer and Singer's method with L2 loss. They do not need a tedious process to derive everything by themselves. Furthermore, we present some new results on and discussion of both L1- and L2-loss formulations.

Identification and characterization of immunoglobulin tau (IgT) in Asian Seabass (Lates calcarifer) and mucosal immune response to nervous necrosis virus.

Mucosal immunity plays a critical role in the protection of teleost fish against infection, but mucosal immunoglobulin of important aquaculture species unique to Southeast Asia remained greatly understudied. In this study, the sequence of immunoglobulin T (IgT) from Asian sea bass (ASB) is described for the first time. IgT of ASB possesses the characteristic structure of immunoglobulin with a variable heavy chain and four CH4 domains. The CH2-CH4 domains and full-length IgT were expressed and CH2-CH4 specific antibody was validated against full-length IgT expressed in Sf9 III cells. Subsequent use of the anti-CH2-CH4 antibody in immunofluorescence staining confirmed the presence of IgT-positive cells in the ASB gill and intestine. The constitutive expression of ASB IgT was characterized in different tissues and in response to red-spotted grouper nervous necrosis virus (RGNNV) infection. The highest basal expression of secretory IgT (sIgT) was observed in the mucosal and lymphoid tissues such as the gills, intestine and head kidney. Following NNV infection, IgT expression was upregulated in the head kidney and mucosal tissues. Moreover, a significant increase in localized IgT was found in gills and intestines of infected fish on day 14 post-infection. Interestingly, a significant increase in NNV-specific IgT secretion was only observed in the gills of the infected group. Our results suggest that ASB IgT may play an important role in the adaptive mucosal immune responses against viral infection and could potentially be adapted as a tool for the evaluation of prospective mucosal vaccines and adjuvants for the species.

Characterization of a Broadly Neutralizing Monoclonal Antibody against SARS-CoV-2 Variants.

The constant mutation of SARS-CoV-2 has led to the emergence of new variants, which call for urgent effective therapeutic interventions. The trimeric spike (S) protein of SARS-CoV-2 is highly immunogenic with the receptor-binding domain (RBD) that binds first to the cellular receptor angiotensin-converting enzyme 2 (ACE2) and is therefore the target of many neutralizing antibodies. In this study, we characterized a broadly neutralizing monoclonal antibody (mAb) 9G8, which shows potent neutralization against the authentic SARS-CoV-2 wild-type (WT), Alpha (B.1.1.7), and Delta (1.617.2) viruses. Furthermore, mAb 9G8 also displayed a prominent neutralizing efficacy in the SARS-CoV-2 surrogate virus neutralization test (sVNT) against the Epsilon (B.1.429/7), Kappa (B.1.617.1), Gamma (P.1), Beta (B.1.351), and Delta Plus (1.617.2.1) RBD variants in addition to the variants mentioned above. Based on our in vitro escape mutant studies, we proved that the mutations V483F and Y489H within the RBD were involved in ACE2 binding and caused the neutralizing evasion of the virus from mAb 9G8. The development of such a cross-reactive neutralizing antibody against majority of the SARS-CoV-2 variants provides an important insight into pursuing future therapeutic agents for the prevention and treatment of COVID-19.