BiRDS - Binding Residue Detection from Protein Sequences using Deep ResNets

Protein-drug interactions play important roles in many biological processes and therapeutics. Prediction of the active binding site of a protein helps discover and optimise these interactions leading to the design of better ligand molecules. The tertiary structure of a protein determines the binding sites available to the drug molecule. A quick and accurate prediction of the binding site from sequence alone without utilising the three-dimensional structure is challenging. Deep Learning has been used in a variety of biochemical tasks and has been hugely successful. In this paper, a Residual Neural Network (leveraging skip connections) is implemented to predict a protein's most active binding site. An Annotated Database of Druggable Binding Sites from the Protein DataBank, sc-PDB, is used for training the network. Features extracted from the Multiple Sequence Alignments (MSAs) of the protein generated using DeepMSA, such as Position-Specific Scoring Matrix (PSSM), Secondary Structure (SS3), and Relative Solvent Accessibility (RSA), are provided as input to the network. A weighted binary cross-entropy loss function is used to counter the substantial imbalance in the two classes of binding and non-binding residues. The network performs very well on single-chain proteins, providing a pocket that has good interactions with a ligand.

3D Interaction Homology: Computational Titration of Aspartic Acid, Glutamic Acid and Histidine Can Create pH-Tunable Hydropathic Environment Maps

Aspartic acid, glutamic acid and histidine are ionizable residues occupying various protein environments and perform many different functions in structures. Their roles are tied to their acid/base equilibria, solvent exposure, and backbone conformations. We propose that the number of unique environments for ASP, GLU and HIS is quite limited. We generated maps of these residue's environments using a hydropathic scoring function to record the type and magnitude of interactions for each residue in a 2703-protein structural dataset. These maps are backbone-dependent and suggest the existence of new structural motifs for each residue type. Additionally, we developed an algorithm for tuning these maps to any pH, a potentially useful element for protein design and structure building. Here, we elucidate the complex interplay between secondary structure, relative solvent accessibility, and residue ionization states: the degree of protonation for ionizable residues increases with solvent accessibility, which in turn is notably dependent on backbone structure.

Molecular Dynamics Simulations of a Cytochrome P450 from Tepidiphilus thermophilus (P450-TT) Reveal How Its Substrate-Binding Channel Opens

Cytochrome P450s (P450) are important enzymes in biology with useful biochemical reactions in, for instance, drug and xenobiotics metabolisms, biotechnology, and health. Recently, the crystal structure of a new member of the CYP116B family has been resolved. This enzyme is a cytochrome P450 (CYP116B46) from Tepidiphilus thermophilus (P450-TT) and has potential for the oxy-functionalization of organic molecules such as fatty acids, terpenes, steroids, and statins. However, it was thought that the opening to its hitherto identified substrate channel was too small to allow organic molecules to enter. To investigate this, we performed molecular dynamics simulations on the enzyme. The results suggest that the crystal structure is not relaxed, possibly due to crystal packing effects, and that its tunnel structure is constrained. In addition, the simulations revealed two key amino acid residues at the mouth of the channel; a glutamyl and an arginyl. The glutamyl’s side chain tightens and relaxes the opening to the channel in conjunction with the arginyl’s, though the latter’s side chain is less dramatically changed after the initial relaxation of its conformations. Additionally, it was observed that the effect of increased temperature did not considerably affect the dynamics of the enzyme fold, including the relative solvent accessibility of the amino acid residues that make up the substrate channel wall even as compared to the changes that occurred at room temperature. Interestingly, the substrate channel became distinguishable as a prominent tunnel that is likely to accommodate small- to medium-sized organic molecules for bioconversions. That is, P450-TT has the ability to pass appropriate organic substrates to its active site through its elaborate substrate channel, and notably, is able to control or gate any molecules at the opening to this channel.

In-silico analysis of mutations in ANK1, SPTB, SPTA1, SLC4A1, and EPB4.2 genes responsible for Hereditary Spherocytosis

Hereditary spherocytosis (HS) is a rare inherited disorder of red blood cells which are characterized by spherical, doughnut-shaped with increase deformability that lead to the gallstones and splenomegaly. The role of mutation in the genes responsible for the regulation of synthesis of proteins and stucture of RBC is well know studied. It was found that there are five genes whose mutation result in hereditary spherocytosis.Therefore, we aimed to study the consequences of ANK1, EPB4.2, SPTA1, SPTB, and SLC4A1 non-synonymous mutaion by using advanced inslico methods. Studied for nsSNPs using insilico techniques including OMIN, clinVar, SIFT, Polyphen, homology modelling. Misssence nsSNP were identified in all the gene selected and their effect on the protein structure, stability and functioning was studies. The result showed that 52 nsSNPs are responsible for the changes in the shape of RBCs. After identifying the nsSNPs the structure of proteins were modelled and their RMSD, relative solvent accessibility, and protein stability were studied. Protein stability analysis revealed significant change in free energy (ΔΔG) of the most identified nsSNPs variants. These finding may be helpful for genotype-phenotype research as well as development in pharmacogenetic studies. Finally, this study unveil a significance of inslico methods to figure out highly pathogenic genomic variants affected the structure and functional of HS causing protein

Genomic mutations and changes in protein secondary structure and solvent accessibility of SARS-CoV-2 (COVID-19 virus)

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly pathogenic virus that has caused the global COVID-19 pandemic. Tracing the evolution and transmission of the virus is crucial to respond to and control the pandemic through appropriate intervention strategies. This paper reports and analyses genomic mutations in the coding regions of SARS-CoV-2 and their probable protein secondary structure and solvent accessibility changes, which are predicted using deep learning models. Prediction results suggest that mutation D614G in the virus spike protein, which has attracted much attention from researchers, is unlikely to make changes in protein secondary structure and relative solvent accessibility. Based on 6324 viral genome sequences, we create a spreadsheet dataset of point mutations that can facilitate the investigation of SARS-CoV-2 in many perspectives, especially in tracing the evolution and worldwide spread of the virus. Our analysis results also show that coding genes E, M, ORF6, ORF7a, ORF7b and ORF10 are most stable, potentially suitable to be targeted for vaccine and drug development.

Exploring Prediction of Antimicrobial Resistance Based on Protein Solvent Accessibility Variation

Antimicrobial resistance (AMR) is a significant and growing public health threat. Sequencing of bacterial isolates is becoming more common, and therefore automatic identification of resistant bacterial strains is of pivotal importance for efficient, wide-spread AMR detection. To support this approach, several AMR databases and gene identification algorithms have been recently developed. A key problem in AMR detection, however, is the need for computational approaches detecting potential novel AMR genes or variants, which are not included in the reference databases. Toward this direction, here we study the relation between AMR and relative solvent accessibility (RSA) of protein variants from an in silico perspective. We show how known AMR protein variants tend to correspond to exposed residues, while on the contrary their susceptible counterparts tend to be buried. Based on these findings, we develop RSA-AMR, a novel relative solvent accessibility-based AMR scoring system. This scoring system can be applied to any protein variant to estimate its propensity of altering the relative solvent accessibility, and potentially conferring (or hindering) AMR. We show how RSA-AMR score can be integrated with existing AMR detection algorithms to expand their range of applicability into detecting potential novel AMR variants, and provide a ten-fold increase in Specificity. The two main limitations of RSA-AMR score is that it is designed on single point changes, and a limited number of variants was available for model learning.

Genomic Mutations and Changes in Protein Secondary Structure and Solvent Accessibility of SARS-CoV-2 (COVID-19 Virus)

ABSTRACTSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly pathogenic virus that has caused the global COVID-19 pandemic. Tracing the evolution and transmission of the virus is crucial to respond to and control the pandemic through appropriate intervention strategies. This paper reports and analyses genomic mutations in the coding regions of SARS-CoV-2 and their probable protein secondary structure and solvent accessibility changes, which are predicted using deep learning models. Prediction results suggest that mutation D614G in the virus spike protein, which has attracted much attention from researchers, is unlikely to make changes in protein secondary structure and relative solvent accessibility. Based on 6,324 viral genome sequences, we create a spreadsheet dataset of point mutations that can facilitate the investigation of SARS-CoV-2 in many perspectives, especially in tracing the evolution and worldwide spread of the virus. Our analysis results also show that coding genes E, M, ORF6, ORF7a, ORF7b and ORF10 are most stable, potentially suitable to be targeted for vaccine and drug development.

Phylogenetic Analyses of Sites in Different Protein Structural Environments Result in Distinct Placements of the Metazoan Root

Phylogenomics, the use of large datasets to examine phylogeny, has revolutionized the study of evolutionary relationships. However, genome-scale data have not been able to resolve all relationships in the tree of life; this could reflect, at least in part, the poor-fit of the models used to analyze heterogeneous datasets. Some of the heterogeneity may reflect the different patterns of selection on proteins based on their structures. To test that hypothesis, we developed a pipeline to divide phylogenomic protein datasets into subsets based on secondary structure and relative solvent accessibility. We then tested whether amino acids in different structural environments had distinct signals for the topology of the deepest branches in the metazoan tree. We focused on a dataset that appeared to have a mixture of signals and we found that the most striking difference in phylogenetic signal reflected relative solvent accessibility. Analyses of exposed sites (residues located on the surface of proteins) yielded a tree that placed ctenophores sister to all other animals whereas sites buried inside proteins yielded a tree with a sponge+ctenophore clade. These differences in phylogenetic signal were not ameliorated when we conducted analyses using a set of maximum-likelihood profile mixture models. These models are very similar to the Bayesian CAT model, which has been used in many analyses of deep metazoan phylogeny. In contrast, analyses conducted after recoding amino acids to limit the impact of deviations from compositional stationarity increased the congruence in the estimates of phylogeny for exposed and buried sites; after recoding amino acid trees estimated using the exposed and buried site both supported placement of ctenophores sister to all other animals. Although the central conclusion of our analyses is that sites in different structural environments yield distinct trees when analyzed using models of protein evolution, our amino acid recoding analyses also have implications for metazoan evolution. Specifically, our results add to the evidence that ctenophores are the sister group of all other animals and they further suggest that the placozoa+cnidaria clade found in some other studies deserves more attention. Taken as a whole, these results provide striking evidence that it is necessary to achieve a better understanding of the constraints due to protein structure to improve phylogenetic estimation.

Brewery: deep learning and deeper profiles for the prediction of 1D protein structure annotations

Motivation Protein structural annotations (PSAs) are essential abstractions to deal with the prediction of protein structures. Many increasingly sophisticated PSAs have been devised in the last few decades. However, the need for annotations that are easy to compute, process and predict has not diminished. This is especially true for protein structures that are hardest to predict, such as novel folds. Results We propose Brewery, a suite of ab initio predictors of 1D PSAs. Brewery uses multiple sources of evolutionary information to achieve state-of-the-art predictions of secondary structure, structural motifs, relative solvent accessibility and contact density. Availability and implementation The web server, standalone program, Docker image and training sets of Brewery are available at http://distilldeep.ucd.ie/brewery/. Contact [email protected]