Extreme learning machine for predicting HLA-peptide binding

Machine learning techniques have been recognized as powerful tools for learning from data. One of the most popular learning techniques, the Back-Propagation (BP) Artificial Neural Networks, can be used as a computer model to predict peptides binding to the Human Leukocyte Antigens (HLA). The major advantage of computational screening is that it reduces the number of wet-lab experiments that need to be performed, significantly reducing the cost and time. A recently developed method, Extreme Learning Machine (ELM), which has superior properties over BP has been investigated to accomplish such tasks. In our work, we found that the ELM is as good as, if not better than, the BP in term of time complexity, accuracy deviations across experiments, and most importantly - prevention from over-fitting for prediction of peptide binding to HLA.

Sequence and tissue distribution of chicken cellular nucleic acid binding protein cDNA

We sequenced cDNAs coding for chicken cellular nucleic acid binding protein (CNBP). Two slightly different variations of the open reading frame were found, each of which translates into a protein with seven zinc finger domains. The longest transcript contains an in-frame insert of 3 bp. The sequence conservation between chick CNBP cDNAs with human, rat and mouse CNBP cDNAs is extreme, especially in the coding region, where the deduced amino acid sequence identity with human, rat and mouse CNBP is 99%. CNBP-like transcripts were also found in various tissues from insect, shrimp, fish and lizard. Regions with remarkable nucleotide conservation were also found in the 3' untranslated region, indicating important functions for these regions. Quantitative reverse transcription polymerase chain reaction (RT-PCR) indicated that in the chick, CNBP is present in all tissues examined in approximately equal ratios to total RNA. RT-PCR of total RNA isolated from different phyla indicate CNBP-like proteins art widespread throughout the animal kingdom. The extraordinary level of conservation suggests an important physiological role for CNBP. (C) 1997 Elsevier Science Inc.

Solution structure and proposed binding mechanism of a novel potassium channel toxin kappa-conotoxin PVIIA

Background: kappa-PVIIA is a 27-residue polypeptide isolated from the venom of Conus purpurascens and is the first member of a new class of conotoxins that block potassium channels. By comparison to other ion channels of eukaryotic cell membranes, voltage-sensitive potassium channels are relatively simple and methodology has been developed for mapping their interactions with small-peptide toxins, PVIIA, therefore, is a valuable new probe of potassium channel structure. This study of the solution structure and mode of channel binding of PVIIA forms the basis for mapping the interacting residues at the conotoxin-ion channel interface. Results: The three-dimensional structure of PVIIA resembles the triple-stranded beta sheet/cystine-knot motif formed by a number of toxic and inhibitory peptides. Subtle structural differences, predominantly in loops 2 and 4, are observed between PVIIA and other conotoxins with similar structural frameworks, however. Electrophysiological binding data suggest that PVIIA blocks channel currents by binding in a voltage-sensitive manner to the external vestibule and occluding the pore, Comparison of the electrostatic surface of PVIIA with that of the well-characterised potassium channel blocker charybdotoxin suggests a likely binding orientation for PVIIA, Conclusions: Although the structure of PVIIA is considerably different to that of the alpha K scorpion toxins, it has a similar mechanism of channel blockade. On the basis of a comparison of the structures of PVIIA and charybdotoxin, we suggest that Lys19 of PVIIA is the residue which is responsible for physically occluding the pore of the potassium channel.

Papillomavirus virus-like particles can deliver defined CTL epitopes to the MHC class I pathway

To evaluate an antigen delivery system in which exogenous antigen can target the major histocompatibility complex (MHC) class I pathway, a single human papillomavirus (HPV) 16 E7 cytotoxic T lymphocyte (CTL) epitope and a single HIV gp160 CTL epitope were separately fused to the C-terminus or bovine papillomavirus 1 (BPV1) L1 sequence to form hybrid BPV1L1 VLPs. Mice immunized with these hybrid VLPs mounted strong CTL responses against the relevant target cells in the absence of any adjuvants. In addition, the CTL responses induced by immunization with BPV1L1/HPV16E7CTL VLPs protected mice against challenge with E7-transformed tumor cells. Furthermore, a high titer-specific antibody response against BPV1L1 VLPs was also induced, and this antiserum could inhibit papillomavirus-induced agglutination of mouse erythrocytes, suggesting that the antibody may recognize conformational determinates relevant to virus neutralization. These data demonstrate that hybrid BPV1L1 VLPs can be used as carriers to target antigenic epitopes to both the MHC class I and class II pathways, providing a promising strategy for the design of vaccines to prevent virus infection, with the potential to elicit therapeutic virus-specific CTL responses. (C) 1998 Academic Press.

Molecular cloning reveals that the p160 myb-binding protein is a novel, predominantly nucleolar protein which may play a role in transactivation by Myb

We have previously detected two related murine nuclear proteins, p160 and p67, that can bind to the leucine zipper motif within the negative regulatory domain of the Myb transcription factor. We now describe the molecular cloning of cDNA corresponding to murine p160. The P160 gene is located on mouse chromosome 11, and related sequences are found on chromosomes 1 and 12. The predicted p160 protein is novel, and in agreement with previous studies, we find that the corresponding 4.5-kb mRNA is ubiquitously expressed. We showed that p67 is an N-terminal fragment of p160 which is generated by proteolytic cleavage in certain cell types. The protein encoded by the cloned p160 cDNA and an engineered protein (p67*) comprising the amino-terminal region of p160 exhibit binding specificities for the Myb and Jun leucine zipper regions identical to those of endogenous p160 and p67, respectively. This implies that the Myb-binding site of p160 lies within the N-terminal 580 residues and that the Jun-binding site is C-terminal to this position. Moreover, we show that p67* but not p160 can inhibit transactivation by Myb. Unexpectedly, immunofluorescence studies show that p160 is localized predominantly in the nucleolus. The implications of these results for possible functions of p160 are discussed.

MHCPEP, a database of MHC-binding peptides: update 1997

MHCPEP (http://wehih.wehi.edu.au/mhcpep/) is a curated database comprising over 13 000 peptide sequences known to bind MHC molecules, Entries are compiled from published reports as well as from direct submissions of experimental data, Each entry contains the peptide sequence, its MHC specificity and where available, experimental method, observed activity, binding affinity, source protein and anchor positions, as well as publication references, The present format of the database allows text string matching searches but can easily be converted for use in conjunction with sequence analysis packages. The database can be accessed via Internet using WWW or FTP.

The effect of protein binding on the hepatic first pass of O-acyl salicylate derivatives in the rat

In this work the in-situ perfused rat liver has been used to examine the effect of changing the protein content of the perfusate on the hepatic extraction of O-acyl esters of salicylic acid. The hepatic availability (F) of these solutes was studied at a flow-rate of 30 mt min(-1) with perfusate albumin concentrations of 0, 2, and 4% w/v. The hepatic availability of the esters was shown to decrease with increasing carbon-chain length in the O-acyl group; for all the esters the hepatic availability increased with increasing albumin concentration in the perfusate. The dispersion-model-derived efficiency number (R-N) Of the esters was shown to increase with increasing lipophilicity and decrease with increasing albumin concentration in the perfusate. The unbound fraction (f(u),) of the esters decreased with lipophilicity. R-N/f(u), for acetylsalicylic acid remained relatively constant as the albumin concentration was increased. However, R-N/f(u), for n-pentanoyl- and n-hexanoylsalicylic acids increased significantly as albumin concentration increased from 0% to 4%. Thus, for the more lipophilic solutes (n-pentanoyl- and n-hexanoylsalicylic acids) the presence of albumin apparently facilitates the uptake of unbound solute relative to acetylsalicylic acid.

High affinity binding of albicidin phytotoxins by the AlbA protein from Klebsiella oxytoca

Albicidins are a family of phytotoxins and antibiotics which play an important role in the pathogenesis of sugarcane leaf scald disease. The albA gene from Klebsiella oxytoca encodes a protein which inactivates albicidin by heat-reversible binding. Albicidin ligand binding to a recombinant AlbA protein, purified by means of a glutathione S-transferase gene fusion system, is an almost instant and saturable reaction. Kinetic and stoichiometric analysis of the binding reaction indicated the presence of a single high affinity binding site with a dissociation constant of 6.4 x 10(-8) M. The AlbA-albicidin complex is stable from 4 to 40 degrees C, from ph 5 to 9 and in high salt solutions. Treatment with protein denaturants released all bound albicidin. These properties indicate that AlbA may be a useful affinity matrix for selective purification of albicidin antibiotics. AlbA does not bind to p-nitrophenyl butyrate or alpha-naphthyl butyrate, the substrates of the albicidin detoxification enzyme AlbD from Pantoea dispersa. The potential exists to pyramid genes for different mechanisms in transgenic plants to protect plastid DNA replication from inhibition by albicidins.

Calcium is essential for the structural integrity of the cysteine-rich, ligand-binding repeat of the low-density lipoprotein receptor

Seven cysteine-rich repeats form the ligand-binding region of the low-density lipoprotein (LDL) receptor. Each of these repeats is assumed to bind a calcium ion, which is needed for association of the receptor with its ligands, LDL and beta-VLDL. The effects of metal ions on the folding of the reduced N-terminal cysteine-rich repeat have been examined by using reverse-phase high-performance liquid chromatography to follow the formation of fully oxidized isomers with different disulfide connectivities. in the absence of calcium many of the 15 possible isomers formed on oxidation, whereas in its presence the predominant product at equilibrium had the native disulfide bond connectivities. Other metals were far less effective at directing disulfide bond formation: Mn2+ partly mimicked the action of Ca2+, but Ba2+, Sr2+, and Mg2+ had little effect. This metal-ion specificity was also observed in two-dimensional H-1 NMR spectral studies: only Ca2+ induced the native three-dimensional fold. The two paramagnetic ions, Gd3+ and Mn2+, and Cd2+ did not promote adoption of a well-defined structure, and the two paramagnetic ions did not displace calcium ions. The location of calcium ion binding sites in the repeat was also explored by NMR spectroscopy. The absence of chemical shift changes for the side chain proton resonances of Asp26, Asp36, and Glu37 from pH 3.9 to 6.8 in the presence of calcium ions and their proximal location in the NMR structures implicated these side chains as calcium ligands. Deuterium exchange NMR experiments also revealed a network of hydrogen bonds that stabilizes the putative calcium-binding loop.

Analysis and application of an equilibrium model for in vitro bioassay systems with three components: Receptor, hormone and hormone-binding-protein

A simple theoretical framework is presented for bioassay studies using three component in vitro systems. An equilibrium model is used to derive equations useful for predicting changes in biological response after addition of hormone-binding-protein or as a consequence of increased hormone affinity. Sets of possible solutions for receptor occupancy and binding protein occupancy are found for typical values of receptor and binding protein affinity constants. Unique equilibrium solutions are dictated by the initial condition of total hormone concentration. According to the occupancy theory of drug action, increasing the affinity of a hormone for its receptor will result in a proportional increase in biological potency. However, the three component model predicts that the magnitude of increase in biological potency will be a small fraction of the proportional increase in affinity. With typical initial conditions a two-fold increase in hormone affinity for its receptor is predicted to result in only a 33% increase in biological response. Under the same conditions an Ii-fold increase in hormone affinity for receptor would be needed to produce a two-fold increase in biological potency. Some currently used bioassay systems may be unrecognized three component systems and gross errors in biopotency estimates will result if the effect of binding protein is not calculated. An algorithm derived from the three component model is used to predict changes in biological response after addition of binding protein to in vitro systems. The algorithm is tested by application to a published data set from an experimental study in an in vitro system (Lim et al., 1990, Endocrinology 127, 1287-1291). Predicted changes show good agreement (within 8%) with experimental observations. (C) 1998 Academic Press Limited.

Type specific and genotype cross reactive B epitopes of the L1 protein of HPV16 defined by a panel of monoclonal antibodies

Mouse monoclonal antibodies (mAbs) were raised against the major capsid protein, L1, of human papillomavirus type 16 (HPV16), produced in Escherichia coil with the expression plasmid pTrcL1. Epitope specificity could be assigned to 11 of these 12 antibodies using a series of linear peptides and fusion proteins from HPV16. One mAb (MC53) recognized a novel linear epitope that appears to be unique to the HPV16 genotype. A further 11 mAbs were characterized as recognizing novel and previously defined linear and conformational epitopes shared among more than one HPV genotype. The apparently genotype specific mAb could be useful for the development of diagnostic tests for vegetative virus infection in clinical specimens. (C) 1998 Academic Press.

Delivery of multiple CD8 cytotoxic T cell epitopes by DNA vaccination

Development of CD8 alpha beta CTL epitope-based vaccines requires an effective strategy capable of co-delivering large numbers of CTL epitopes, Here we describe a DNA plasmid encoding a polyepitope or polytope protein, which contained multiple contiguous minimal murine CTL epitopes, Mice vaccinated with this plasmid made MHC-restricted CTL responses to each of the epitopes, and protective CTL were demonstrated in recombinant vaccinia virus, influenza virus, and tumor challenge models, CTL responses generated by polytope DNA plasmid vaccination lasted for 1 yr, could be enhanced by co-delivering a gene for granulocyte-macrophage CSF, and appeared to be induced in the absence of CD4 T cell-mediated help, The ability to deliver large numbers of CTL epitopes using relatively small polytope constructs and DNA vaccination technology should find application in the design of human epitope-based CTL vaccines, in particular in vaccines against EBV, HIV, and certain cancers.

Relationship between peptide selectivities of human transporters associated with antigen processing and HLA class I molecules

Efficiency of presentation of a peptide epitope by a MHC class I molecule depends on two parameters: its binding to the MHC molecule and its generation by intracellular Ag processing. In contrast to the former parameter, the mechanisms underlying peptide selection in Ag processing are poorly understood. Peptide translocation by the TAP transporter is required for presentation of most epitopes and may modulate peptide supply to MHC class I molecules. To study the role of human TAP for peptide presentation by individual HLA class I molecules, we generated artificial neural networks capable of predicting the affinity of TAP for random sequence 9-mer peptides. Using neural network-based predictions of TAP affinity, we found that peptides eluted from three different HLA class I molecules had higher TAP affinities than control peptides with equal binding affinities for the same HLA class I molecules, suggesting that human TAP may contribute to epitope selection. In simulated TAP binding experiments with 408 HLA class I binding peptides, HLA class I molecules differed significantly with respect to TAP affinities of their ligands, As a result, some class I molecules, especially HLA-B27, may be particularly efficient in presentation of cytosolic peptides with low concentrations, while most class I molecules may predominantly present abundant cytosolic peptides.

Crystallization of a trimeric human T cell leukemia virus type 1 gp21 ectodomain fragment as a chimera with maltose-binding protein

We present a novel protein crystallization strategy, applied to the crystallization of human T cell leukemia virus type 1 (HTLV-1) transmembrane protein gp21 lacking the fusion peptide and the transmembrane domain, as a chimera with the Escherichia coli maltose binding protein (MBP). Crystals could not be obtained with a MBP/gp21 fusion protein in which fusion partners were separated by a flexible linker, but were obtained after connecting the MBP C-terminal alpha-helix to the predicted N-terminal alpha-helical sequence of gp21 via three alanine residues. The gp21 sequences conferred a trimeric structure to the soluble fusion proteins as assessed by sedimentation equilibrium and X-ray diffraction, consistent with the trimeric structures of other retroviral transmembrane proteins. The envelope protein precursor, gp62, is likewise trimeric when expressed in mammalian cells. Our results suggest that MBP may have a general application for the crystallization of proteins containing N-terminal alpha-helical sequences.

Folding, calcium binding, and structural characterization of a concatemer of the first and second ligand-binding modules of the low-density lipoprotein receptor

The ligand-binding domain of the low-density lipoprotein (LDL) receptor is comprised of seven tandemly repeated ligand-binding modules, each being approximately 40 amino acids long and containing six conserved cysteine residues. We have expressed and characterized a concatemer of the first two modules (LB1 and LB2) of the human LDL receptor. Oxidative folding of the recombinant concatemer (rLB(1-2)), in the presence of calcium ions, gave a single dominant isomer with six disulfide bonds. Peptic cleavage of the short Linker region that connects the last cysteine residue of LB1 and the first cysteine residue of LB2 yielded two discrete fragments, thus excluding the presence of intermodule disulfide bonds. The N-terminal module, LB1, reacted with a conformation-specific monoclonal antibody (IgG-C7) made to LB1 in the native LDL receptor. From this, we concluded that the first module was correctly folded, with the same set of disulfide bonds as LB1 of the LDL receptor. The disulfide bond connections of LB2 were identified from mass spectral analysis of fragments formed by digestion of the C-terminal peptic fragment with elastase. These data showed that the disulfide bonds of LB2 connected Cys(I) and Cys(III), Cys(II) and Cys(V), and Cys(IV) and Cys(VI). This pattern is identical to that found for recombinant LB1 and LB2. The concatemer has two high-affinity calcium-binding sites, one per module. An analysis of the secondary chemical shifts of C alpha protons shows that the conformations of LB1 and LB2 in the concatemer are very similar to those of the individual modules, with no evidence for strong interactions between the two modules.