Overview Of Artificial Neural Networks

The basic building blocks of proteins are amino acids, the biuret reaction tests for protein. A solution of sodium hydroxide is added to a sample then a few drops of copper sulphate solution, if positive – the solution will turn mauve. There are 20 different amino acids and they can be joined in any order. Therefore there can be many different functions. A protein consists of one or more polypeptide chains (a polypeptide chain being multiple amino acids joined together via condensation, producing a peptide bond). Different proteins have different shapes as the shapes are determined by the sequence of amino acids.

Dr. N.A.S states that one of the antiretrovirals blocks translation of RNA into the proteins required to make new viruses. Some of the current antiretrovirals include reverse transcriptase, fusion and entry, protease, and integrase inhibitors;6,10 however there is not an inhibitor that blocks translation of rna into proteins on the market. Targeting inhibitors specific to HIV has made ARVs increasingly effective and less harmful to humans.

Since we have already known the amino sequence of the protein in previous step, we can narrow down the targeting ubiquitin ligase based on existing research data such as papers, NCBI data.

A protein has multiple existing structures, these are the primary, secondary, tertiary and quaternary structures which occur progressively. A protein is essentially a sequence of amino acids which are bonded adjacently, and interact with one another in various ways depending on the R group that the amino acid contains. There are 20 different amino acids which are able to be arranged in any given order, thus giving rise to a potential 2.433x1018 (4.s.f) different combinations, and therefore interactions between the various amino acids.

I propose to use computational techniques to determine which drug treatment for epilepsy is best by comparing the structure of each drug with the active site of the affected enzymes. The purpose of this computational query is to determine which drug facilitates the best interaction with the active site of the enzymes and prevents epileptic seizures. By visualizing the structure of the molecules and active sites of the enzymes with the use of Spartan’14, the 2D and 3D shape how these molecules will interact with the active sites of the enzymes can be determined. The drug that is considered to be the best will be characterized as having the highest affinity for the active site of the enzyme, which can be determined by the finding the drug with the molecular shape that is closest in shape to the active site of the enzyme according to the lock and key model of enzyme interactions. This information will allow doctors to have more knowledge on which drugs are better to prescribe to epileptic patients, but it will also be useful to drug developers so that they can design drugs with similar structures in order to treat epilepsy.

For the second part of the experiment, one had to use the knowledge learn from viewing protein molecules in FirstGlance in Jmol to analyze the protein PDB ID: 4EEY. The analysis of this protein was done using the RSCB protein data bank (PDB) at (http://www.rcsb.org/pdb/home/home.do).2

While the possibility of amino acid to analog replacement could theoretically occur owing to the existence of analogs

It seems these days that the building blocks of proteins, affectionately known as "amino acids", are tiny little gold nuggets that bestow superhuman powers upon anyone lucky enough to stumble upon them in a sports gel, capsule, fizzy drink or cocktail. After all, these little guys are starting to get put by nutrition supplement manufacturers into just about everything, from your engineered pre-workout snack, to your during workout beverage, to your post-workout smoothie mix.

Polyphen2.0 (Polymorphism Phenotyping) a multi-sequence alignment server predicts the functional impact of an amino acid substitution. The prediction is a straightforward empirical rule which is automatically applied to the structural, sequence, and phylogenetic information, and readily characterizes the amino acid substitution (Ramensky et al. 2002). To determine the effect of variants on the protein secondary structure, inter chain contents, functional sites, and binding sites, Polyphen2.0 utilizes PDB (Protein Data Bank), DSSP (Dictionary of secondary structures in protein), and three-dimensional structure databases (Ramensky et al. 2002). We submitted the query in the form of the protein sequence with the mutational position of two amino

In most instances, protein molecules are usually embedded from hundreds to thousands of amino acids. A repertoire of twenty different amino acids, joined in any possible sequence allows the existence of an inconceivably large number of proteins that is infinite in nature.

the subset of MHC-I binding peptides. Using a curated repository of MHC-I epitopes from the Immune Epitope Database (IEDB) (Vita et al., 2009), we evaluated the biochemical properties of aas that discriminate between immunogenic epitopes and non-immunogenic self-peptides. We found a strong bias towards hydrophobicity in aa residues of immunogenic CTL epitopes that is highly selective for exposed TCR contact residues. Using these criteria, we trained an artificial neural network (ANN) model to identify immunogenic CTL epitopes from a data set and empirically assessed our prediction model for 3 human immunodeficiency virus 1 (HIV-1) Gag protein variants in a murine model of immunogenicity. We demonstrate the utility of this ANN

Once mammalian orthologs have been assigned, the data can be analysed in various bioinformatic programs, listed in table.1.

When analyzing the secondary structure predictions of the query sequence from the five prediction programs, the majority of the programs seemed to detect the presence of one long, uninterrupted helix on the N-terminal side of the pilE protein. However, some programs, such as PORTER (Pollastri et al., 2005) and SSpro (Magnan et al., 2014) indicated the presence of two helices interrupted by a small gap of random coils. While these results appear to contradict each other at first, upon further inspection, this can be explained by the fact that when two helices are very close to each other, some algorithms may erroneously pick it up as 1 long helix since secondary prediction programs are not 100% accurate. Thus, in the consensus secondary

To investigate the distribution of PI-induced mutational changes in HIV-1 across Gag and protease regions, Codoner et al. sequenced the HIV-1 Gag-protease coding region from longitudinal plasma samples from four patients receiving PI treatment over a 9-year period. Sequence analysis confirmed that HIV-1, in response to PIs, demonstrates a stepwise accumulation of Gag cleavage site mutations (CSM) at the following positions: V128I in the p17/p24 junction; S373P and I376V at the p2/NC junction; A431V at the NC/p1 junction; K436R at the NC/p1 junction and P453A at the p1/p6 junction (Codoner et al, 2017). Of these Gag CSM, A431V and K436R have been previously associated with drug resistance mutations in the protease and V128I, A431V, K436R

Cytotoxic (CD8+) T cell epitopes as MHC class I ligand were predicted using NetCTL 1.2 [34], a server based on neural network architecture, for each of the 12 HLA class I super types defined by Lund et al. in [35] (A1, A2, A3, A24, A26, B7, B8, B27, B39, B44, B58, B62). Previously selected FASTA sequence of the polymerase protein was submitted to that server with the parameter of threshold level set at 0.5 to have sensitivity and specificity of 0.89 and 0.94 respectively. This would be helpful for finding more epitopes effectively. An integrated value of transporter of antigenic peptide (TAP) transport efficiency, MHC-I binding and proteosomal cleavage efficiency