PredMP: a web server for de novo prediction and visualization of membrane proteins

Discovery of Therapeutic Antibodies Targeting Complex Multi-Spanning Membrane Proteins

Complex integral membrane proteins, which are embedded in the cell surface lipid bilayer by multiple transmembrane spanning polypeptides, encompass families of proteins that are important target classes for drug discovery. These protein families include G protein-coupled receptors, ion channels, transporters, enzymes, and adhesion molecules. The high specificity of monoclonal antibodies and the ability to engineer their properties offers a significant opportunity to selectively bind these target proteins, allowing direct modulation of pharmacology or enabling other mechanisms of action such as cell killing. Isolation of antibodies that bind these types of membrane proteins and exhibit the desired pharmacological function has, however, remained challenging due to technical issues in preparing membrane protein antigens suitable for enabling and driving antibody drug discovery strategies. In this article, we review progress and emerging themes in defining discovery strategies for a generation of antibodies that target these complex membrane protein antigens. We also comment on how this field may develop with the emerging implementation of computational techniques, artificial intelligence, and machine learning.

Computational drug development for membrane protein targets

The application of computational biology in drug development for membrane protein targets has experienced a boost from recent developments in deep learning-driven structure prediction, increased speed and resolution of structure elucidation, machine learning structure-based design and the evaluation of big data. Recent protein structure predictions based on machine learning tools have delivered surprisingly reliable results for water-soluble and membrane proteins but have limitations for development of drugs that target membrane proteins. Structural transitions of membrane proteins have a central role during transmembrane signaling and are often influenced by therapeutic compounds. Resolving the structural and functional basis of dynamic transmembrane signaling networks, especially within the native membrane or cellular environment, remains a central challenge for drug development. Tackling this challenge will require an interplay between experimental and computational tools, such as super-resolution optical microscopy for quantification of the molecular interactions of cellular signaling networks and their modulation by potential drugs, cryo-electron microscopy for determination of the structural transitions of proteins in native cell membranes and entire cells, and computational tools for data analysis and prediction of the structure and function of cellular signaling networks, as well as generation of promising drug candidates.

The origin and structural evolution of de novo genes in Drosophila

Recent studies reveal that de novo gene origination from previously non-genic sequences is a common mechanism for gene innovation. These young genes provide an opportunity to study the structural and functional origins of proteins. Here, we combine high-quality base-level whole-genome alignments and computational structural modeling to study the origination, evolution, and protein structures of lineage-specific de novo genes. We identify 555 de novo gene candidates in D. melanogaster that originated within the Drosophilinae lineage. Sequence composition, evolutionary rates, and expression patterns indicate possible gradual functional or adaptive shifts with their gene ages. Surprisingly, we find little overall protein structural changes in candidates from the Drosophilinae lineage. We identify several candidates with potentially well-folded protein structures. Ancestral sequence reconstruction analysis reveals that most potentially well-folded candidates are often born well-folded. Single-cell RNA-seq analysis in testis shows that although most de novo gene candidates are enriched in spermatocytes, several young candidates are biased towards the early spermatogenesis stage, indicating potentially important but less emphasized roles of early germline cells in the de novo gene origination in testis. This study provides a systematic overview of the origin, evolution, and protein structural changes of Drosophilinae-specific de novo genes.

An off-the-shelf small extracellular vesicle nanomedicine for tumor targeting therapy

Small extracellular vesicles (sEVs) have shown excellent prospects as drug delivery systems for cancer therapy. However, the inherent non-targeting and short blood circulation characteristics severely restrict their practical applications as a delivery system. In addition, post-encapsulating drugs into sEVs also remains challenging. Here, we constructed an engineered cell line that secreted multifunctional sEVs (termed NBsEV204) with 7D12 (an anti-EGFR nanobody) and hCD47 decorations on their surface, as well as high levels of miR-204-5p encapsulation. NBsEV204 exhibited extended blood circulation and improved macrophage-mediated phagocytosis of tumor cells by blocking CD47 signaling. Importantly, NBsEV204 specifically targeted EGFR+ tumor cells and showed robust tumor-suppressive effects both in vitro and in vivo. Overall, this study provides a convenient and feasible method to produce off-the-shelf anticancer sEV nanomedicine, which exhibits tremendous potential for clinical translation.

A convolutional network and attention mechanism-based approach to predict protein-RNA binding residues

Protein-RNA interactions play a key role in various biological cellular processes, and many experimental and computational studies have been initiated to analyze their interactions. However, experimental determination is quite complex and expensive. Therefore, researchers have worked to develop efficient computational tools to detect protein-RNA binding residues. The accuracy of existing methods is limited by the features of the target and the performance of the computational models; there remains room for improvement. To solve the problem of the accurate detection of protein-RNA binding residues, we propose a convolutional network model named PBRPre based on improved MobileNet. First, by extracting the position information of the target complex and the 3-mer amino acid feature data, the position-specific scoring matrix (PSSM) is improved by using spatial neighbor smoothing processing and discrete wavelet transform to fully exploit the spatial structure information of the target and enrich the feature dataset. Second, the deep learning model MobileNet is used to integrate and optimize the potential features in the target complexes; then, by introducing the Vision Transformer (ViT) network classification layer, the deep-level information of the target is mined to enhance the processing ability of the model for global information and to improve the detection accuracy of the classifiers. The results show that the AUC value of the model can reach 0.866 in the independent testing dataset, which shows that PBRPre can effectively realize the detection of protein-RNA binding residues. All datasets and resource codes of PBRPre are available at https://github.com/linglewu/PBRPre for academic use.

Protein-RNA interaction prediction with deep learning: structure matters

Protein-RNA interactions are of vital importance to a variety of cellular activities. Both experimental and computational techniques have been developed to study the interactions. Because of the limitation of the previous database, especially the lack of protein structure data, most of the existing computational methods rely heavily on the sequence data, with only a small portion of the methods utilizing the structural information. Recently, AlphaFold has revolutionized the entire protein and biology field. Foreseeably, the protein-RNA interaction prediction will also be promoted significantly in the upcoming years. In this work, we give a thorough review of this field, surveying both the binding site and binding preference prediction problems and covering the commonly used datasets, features and models. We also point out the potential challenges and opportunities in this field. This survey summarizes the development of the RNA-binding protein-RNA interaction field in the past and foresees its future development in the post-AlphaFold era.

Extending the Horizon of Homology Detection with Coevolution-based Structure Prediction

Traditional sequence analysis algorithms fail to identify distant homologies when they lie beyond a detection horizon. In this review, we discuss how co-evolution-based contact and distance prediction methods are pushing back this homology detection horizon, thereby yielding new functional insights and experimentally testable hypotheses. Based on correlated substitutions, these methods divine three-dimensional constraints among amino acids in protein sequences that were previously devoid of all annotated domains and repeats. The new algorithms discern hidden structure in an otherwise featureless sequence landscape. Their revelatory impact promises to be as profound as the use, by archaeologists, of ground-penetrating radar to discern long-hidden, subterranean structures. As examples of this, we describe how triplicated structures reflecting longin domains in MON1A-like proteins, or UVR-like repeats in DISC1, emerge from their predicted contact and distance maps. These methods also help to resolve structures that do not conform to a "beads-on-a-string" model of protein domains. In one such example, we describe CFAP298 whose ubiquitin-like domain was previously challenging to perceive owing to a large sequence insertion within it. More generally, the new algorithms permit an easier appreciation of domain families and folds whose evolution involved structural insertion or rearrangement. As we exemplify with α1-antitrypsin, coevolution-based predicted contacts may also yield insights into protein dynamics and conformational change. This new combination of structure prediction (using innovative co-evolution based methods) and homology inference (using more traditional sequence analysis approaches) shows great promise for bringing into view a sea of evolutionary relationships that had hitherto lain far beyond the horizon of homology detection.

Diverse Scientific Benchmarks for Implicit Membrane Energy Functions

Energy functions are fundamental to biomolecular modeling. Their success depends on robust physical formalisms, efficient optimization, and high-resolution data for training and validation. Over the past 20 years, progress in each area has advanced soluble protein energy functions. Yet, energy functions for membrane proteins lag behind due to sparse and low-quality data, leading to overfit tools. To overcome this challenge, we assembled a suite of 12 tests on independent data sets varying in size, diversity, and resolution. The tests probe an energy function's ability to capture membrane protein orientation, stability, sequence, and structure. Here, we present the tests and use the franklin2019 energy function to demonstrate them. We then identify areas for energy function improvement and discuss potential future integration with machine-learning-based optimization methods. The tests are available through the Rosetta Benchmark Server (https://benchmark.graylab.jhu.edu/) and GitHub (https://github.com/rfalford12/Implicit-Membrane-Energy-Function-Benchmark).

Analysis and Classification of Hepatitis Infections Using Raman Spectroscopy and Multiscale Convolutional Neural Networks

Hepatitis infections represent a major health concern worldwide. Numerous computer-aided approaches have been devised for the early detection of hepatitis. In this study, we propose a method for the analysis and classification of cases of hepatitis-B virus ( HBV), hepatitis-C virus (HCV), and healthy subjects using Raman spectroscopy and a multiscale convolutional neural network (MSCNN). In particular, serum samples of HBV-infected patients (435 cases), HCV-infected patients (374 cases), and healthy persons (499 cases) are analyzed via Raman spectroscopy. The differences between Raman peaks in the measured serum spectra indicate specific biomolecular differences among the three classes. The dimensionality of the spectral data is reduced through principal component analysis. Subsequently, features are extracted, and then feature normalization is applied. Next, the extracted features are used to train different classifiers, namely MSCNN, a single-scale convolutional neural network, and other traditional classifiers. Among these classifiers, the MSCNN model achieved the best outcomes with a precision of 98.89%, sensitivity of 97.44%, specificity of 94.54%, and accuracy of 94.92%. Overall, the results demonstrate that Raman spectral analysis and MSCNN can be effectively utilized for rapid screening of hepatitis B and C cases.

Guardians of the Cell: State-of-the-Art of Membrane Proteins from a Computational Point-of-View

Membrane proteins (MPs) encompass a large family of proteins with distinct cellular functions, and although representing over 50% of existing pharmaceutical drug targets, their structural and functional information is still very scarce. Over the last years, in silico analysis and algorithm development were essential to characterize MPs and overcome some limitations of experimental approaches. The optimization and improvement of these methods remain an ongoing process, with key advances in MPs' structure, folding, and interface prediction being continuously tackled. Herein, we discuss the latest trends in computational methods toward a deeper understanding of the atomistic and mechanistic details of MPs.

Decoy selection for protein structure prediction via extreme gradient boosting and ranking

Background

Identifying one or more biologically-active/native decoys from millions of non-native decoys is one of the major challenges in computational structural biology. The extreme lack of balance in positive and negative samples (native and non-native decoys) in a decoy set makes the problem even more complicated. Consensus methods show varied success in handling the challenge of decoy selection despite some issues associated with clustering large decoy sets and decoy sets that do not show much structural similarity. Recent investigations into energy landscape-based decoy selection approaches show promises. However, lack of generalization over varied test cases remains a bottleneck for these methods.

Results

We propose a novel decoy selection method, ML-Select, a machine learning framework that exploits the energy landscape associated with the structure space probed through a template-free decoy generation. The proposed method outperforms both clustering and energy ranking-based methods, all the while consistently offering better performance on varied test-cases. Moreover, ML-Select shows promising results even for the decoy sets consisting of mostly low-quality decoys.

Conclusions

ML-Select is a useful method for decoy selection. This work suggests further research in finding more effective ways to adopt machine learning frameworks in achieving robust performance for decoy selection in template-free protein structure prediction.

A novel bispecific chimeric PD1-DAP10/NKG2D receptor augments NK92-cell therapy efficacy for human gastric cancer SGC-7901 cell

Cell-based immunotherapy continues to be a promising avenue for cancers that standard therapy has failed. Although the specificity, avidity, and efficacy of infused cells have improved, immunocytotherapy still faces substantial hurdles. To this end, we developed a structure-based rational design approach and constructed a novel Dual Targeting Chimeric Receptor (DTCR) PD1-DAP10/NKG2D comprising the truncated ectodomain of PD1 fused to a key co-stimulatory receptor DAP10, and subsequently harnessed the activating receptor NKG2D, which evaluated the capacity of solid tumor cell killing. Retroviral transduction of DTCR dramatically increased NK92 cell surface expression of PD1 and NKG2D, which boosted robust cytotoxicity against human gastric cell SGC-7901. Chimeric receptor DTCR stimulation elicited a significant increase of TNF-α and TRAIL, which can trigger apoptosis of SGC-7901 cells. More importantly, DTCR-NK92 cells had considerable antitumor activity in the solid tumor cell SGC-7901-bearing mice model. Collectively, we demonstrated that expression of DTCR markedly augmented the cytotoxic potential of NK92 cells against solid tumor cells, and this potentially promising treatment modality will facilitate clinical translation of potent NK-tailored chimeric receptor strategy for a generalized cellular therapy that may be conducive to treat a wide range of solid tumors.

SPOT-Fold: Fragment-Free Protein Structure Prediction Guided by Predicted Backbone Structure and Contact Map

Protein structure determination has long been one of the most challenging problems in molecular biology for the past 60 years. Here we present an ab initio protein tertiary-structure prediction method assisted by predicted contact maps from SPOT-Contact and predicted dihedral angles from SPIDER 3. These predicted properties were then fed to the crystallography and NMR system (CNS) for restrained structure modeling. The resulted structures are first evaluated by the potential energy calculated by CNS, followed by dDFIRE energy function for model selections. The method called SPOT-Fold has been tested on 241 CASP targets between 67 and 670 amino acid residues, 60 randomly selected globular proteins under 100 amino acids. The method has a comparable accuracy to other contact-map-based modeling techniques. © 2019 Wiley Periodicals, Inc.

Analysis of distance-based protein structure prediction by deep learning in CASP13

This paper reports the CASP13 results of distance-based contact prediction, threading, and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free-modeling) targets with a median multiple sequence alignment (MSA) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time-consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2, and L long-range contact precision of 70%, 58%, and 45%, respectively, and predicted correct folds (TMscore > 0.5) for 18 of 32 targets. Further, RaptorX predicted correct folds for all FM targets with >300 residues (T0950-D1, T0969-D1, and T1000-D2) and generated the best 3D models for T0950-D1 and T0969-D1 among all groups. This CASP13 test confirms our previous findings: (a) predicted distance is more useful than contacts for both template-based and free modeling; and (b) structure modeling may be improved by integrating template and coevolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.

Estimating statistical significance of local protein profile-profile alignments

BACKGROUND

Alignment of sequence families described by profiles provides a sensitive means for establishing homology between proteins and is important in protein evolutionary, structural, and functional studies. In the context of a steadily growing amount of sequence data, estimating the statistical significance of alignments, including profile-profile alignments, plays a key role in alignment-based homology search algorithms. Still, it is an open question as to what and whether one type of distribution governs profile-profile alignment score, especially when profile-profile substitution scores involve such terms as secondary structure predictions.

RESULTS

This study presents a methodology for estimating the statistical significance of this type of alignments. The methodology rests on a new algorithm developed for generating random profiles such that their alignment scores are distributed similarly to those obtained for real unrelated profiles. We show that improvements in statistical accuracy and sensitivity and high-quality alignment rate result from statistically characterizing alignments by establishing the dependence of statistical parameters on various measures associated with both individual and pairwise profile characteristics. Implemented in the COMER software, the proposed methodology yielded an increase of up to 34.2% in the number of true positives and up to 61.8% in the number of high-quality alignments with respect to the previous version of the COMER method.

CONCLUSIONS

The more accurate estimation of statistical significance is implemented in the COMER method, which is now more sensitive and provides an increased rate of high-quality profile-profile alignments. The results of the present study also suggest directions for future research.

Structure-based rational design of a novel chimeric PD1-NKG2D receptor for natural killer cells

Chimeric antigen receptor (CAR)-engineered natural killer (NK) cells have the potential to provide the potential for the implementation of allogeneic "off-the-shelf" cellular therapy against cancers. Currently, most CARs are not optimized for NK cells, so new NK-tailored CARs are needed. Here, a major activating receptor of NK cells, NKG2D was harnessed to design different chimeric receptors that mediate strong NK cell signaling. In these NKG2D signaling-based chimeric receptors, the extracellular domain of inhibitory receptor PD-1 was employed to reverse the immune escape mediated by PD-1 ligands in the solid tumors. To achieve the rational design of chimeric PD1-NKG2D receptors, we developed a transmembrane protein tertiary structure prediction program (PredMP & I-TASSER) and optimized the conformation of the PD-1 ectodomain by genetically altering the sequences encoding the hinge and intracellular domain. Finally, we identified a chimeric PD1-NKG2D receptor containing NKG2D hinge region and 4-1BB co-stimulatory domain to exhibit stable surface expression and mediate in vitro cytotoxicity of NK92 cells against various tumor cells. This strategy now provides a promising approach for the computer-aided design (CAD) of potent NK cell-tailored chimeric receptors with NKG2D signaling.

Deep learning-based component identification for the Raman spectra of mixtures

Raman spectroscopy is widely used as a fingerprint technique for molecular identification. However, Raman spectra contain molecular information from multiple components and interferences from noise and instrumentation. Thus, component identification using Raman spectra is still challenging, especially for mixtures. In this study, a novel approach entitled deep learning-based component identification (DeepCID) was proposed to solve this problem. Convolution neural network (CNN) models were established to predict the presence of components in mixtures. Comparative studies showed that DeepCID could learn spectral features and identify components in both simulated and real Raman spectral datasets of mixtures with higher accuracy and significantly lower false positive rates. In addition, DeepCID showed better sensitivity when compared with the logistic regression (LR) with L1-regularization, k-nearest neighbor (kNN), random forest (RF) and back propagation artificial neural network (BP-ANN) models for ternary mixture spectral datasets. In conclusion, DeepCID is a promising method for solving the component identification problem in the Raman spectra of mixtures.