Catherine Mooney

Accurate prediction of protein secondary structure and solvent accessibility by consensus combiners of sequence and structure information

BackgroundStructural properties of proteins such as secondary structure and solvent accessibility contribute to three-dimensional structure prediction, not only in the ab initio case but also when homology information to known structures is available. Structural properties are also routinely used in protein analysis even when homology is available, largely because homology modelling is lower throughput than, say, secondary structure prediction. Nonetheless, predictors of secondary structure and solvent accessibility are virtually always ab initio.ResultsHere we develop high-throughput machine learning systems for the prediction of protein secondary structure and solvent accessibility that exploit homology to proteins of known structure, where available, in the form of simple structural frequency profiles extracted from sets of PDB templates. We compare these systems to their state-of-the-art ab initio counterparts, and with a number of baselines in which secondary structures and solvent accessibilities are extracted directly from the templates. We show that structural information from templates greatly improves secondary structure and solvent accessibility prediction quality, and that, on average, the systems significantly enrich the information contained in the templates. For sequence similarity exceeding 30%, secondary structure prediction quality is approximately 90%, close to its theoretical maximum, and 2-class solvent accessibility roughly 85%. Gains are robust with respect to template selection noise, and significant for marginal sequence similarity and for short alignments, supporting the claim that these improved predictions may prove beneficial beyond the case in which clear homology is available.ConclusionThe predictive system are publicly available at the address http://distill.ucd.ie.

Towards the Improved Discovery and Design of Functional Peptides: Common Features of Diverse Classes Permit Generalized Prediction of Bioactivity

The conventional wisdom is that certain classes of bioactive peptides have specific structural features that endow their particular functions. Accordingly, predictions of bioactivity have focused on particular subgroups, such as antimicrobial peptides. We hypothesized that bioactive peptides may share more general features, and assessed this by contrasting the predictive power of existing antimicrobial predictors as well as a novel general predictor, PeptideRanker, across different classes of peptides. We observed that existing antimicrobial predictors had reasonable predictive power to identify peptides of certain other classes i.e. toxin and venom peptides. We trained two general predictors of peptide bioactivity, one focused on short peptides (4–20 amino acids) and one focused on long peptides ( amino acids). These general predictors had performance that was typically as good as, or better than, that of specific predictors. We noted some striking differences in the features of short peptide and long peptide predictions, in particular, high scoring short peptides favour phenylalanine. This is consistent with the hypothesis that short and long peptides have different functional constraints, perhaps reflecting the difficulty for typical short peptides in supporting independent tertiary structure. We conclude that there are general shared features of bioactive peptides across different functional classes, indicating that computational prediction may accelerate the discovery of novel bioactive peptides and aid in the improved design of existing peptides, across many functional classes. An implementation of the predictive method, PeptideRanker, may be used to identify among a set of peptides those that may be more likely to be bioactive.

Distill: a suite of web servers for the prediction of one-, two- and three-dimensional structural features of proteins

BackgroundWe describe Distill, a suite of servers for the prediction of protein structural features: secondary structure; relative solvent accessibility; contact density; backbone structural motifs; residue contact maps at 6, 8 and 12 Angstrom; coarse protein topology. The servers are based on large-scale ensembles of recursive neural networks and trained on large, up-to-date, non-redundant subsets of the Protein Data Bank. Together with structural feature predictions, Distill includes a server for prediction of Cαtraces for short proteins (up to 200 amino acids).ResultsThe servers are state-of-the-art, with secondary structure predicted correctly for nearly 80% of residues (currently the top performance on EVA), 2-class solvent accessibility nearly 80% correct, and contact maps exceeding 50% precision on the top non-diagonal contacts. A preliminary implementation of the predictor of protein Cαtraces featured among the top 20 Novel Fold predictors at the last CASP6 experiment as group Distill (ID 0348). The majority of the servers, including the Cαtrace predictor, now take into account homology information from the PDB, when available, resulting in greatly improved reliability.ConclusionAll predictions are freely available through a simple joint web interface and the results are returned by email. In a single submission the user can send protein sequences for a total of up to 32k residues to all or a selection of the servers. Distill is accessible at the address: http://distill.ucd.ie/distill/.

Inhibition of dipeptidyl peptidase IV and xanthine oxidase by amino acids and dipeptides

Xanthine oxidase (XO) and dipeptidyl peptidase IV (DPP-IV) inhibition by amino acids and dipeptides was studied. Trp and Trp-containing dipeptides (Arg-Trp, Trp-Val, Val-Trp, Lys-Trp and Ile-Trp) inhibited XO. Three amino acids (Met, Leu and Trp) and eight dipeptides (Phe-Leu, Trp-Val, His-Leu, Glu-Lys, Ala-Leu, Val-Ala, Ser-Leu and Gly-Leu) inhibited DPP-IV. Trp and Trp-Val were multifunctional inhibitors of XO and DPP-IV. Lineweaver and Burk analysis showed that Trp was a non-competitive inhibitor of XO and a competitive inhibitor of DPP-IV. Molecular docking with Autodock Vina was used to better understand the interaction of the peptides with the active site of the enzyme. Because of the non-competitive inhibition observed, docking of Trp-Val to the secondary binding sites of XO and DPP-IV is required. Trp-Val was predicted to be intestinally neutral (between 25% and 75% peptide remaining after 60 min simulated intestinal digestion). These results are of significance for the reduction of reactive oxygen species (ROS) and the increase of the half-life of incretins by food-derived peptides.

In silico approaches to predict the potential of milk protein-derived peptides as dipeptidyl peptidase IV (DPP-IV) inhibitors.

Molecular docking of a library of all 8000 possible tripeptides to the active site of DPP-IV was used to determine their binding potential. A number of tripeptides were selected for experimental testing, however, there was no direct correlation between the Vina score and their in vitro DPP-IV inhibitory properties. While Trp-Trp-Trp, the peptide with the best docking score, was a moderate DPP-IV inhibitor (IC50 216μM), Lineweaver and Burk analysis revealed its action to be non-competitive. This suggested that it may not bind to the active site of DPP-IV as assumed in the docking prediction. Furthermore, there was no significant link between DPP-IV inhibition and the physicochemical properties of the peptides (molecular mass, hydrophobicity, hydrophobic moment (μH), isoelectric point (pI) and charge). LIGPLOTs indicated that competitive inhibitory peptides were predicted to have both hydrophobic and hydrogen bond interactions with the active site of DPP-IV. DPP-IV inhibitory peptides generally had a hydrophobic or aromatic amino acid at the N-terminus, preferentially a Trp for non-competitive inhibitors and a broader range of residues for competitive inhibitors (Ile, Leu, Val, Phe, Trp or Tyr). Two of the potent DPP-IV inhibitors, Ile-Pro-Ile and Trp-Pro (IC50 values of 3.5 and 44.2μM, respectively), were predicted to be gastrointestinally/intestinally stable. This work highlights the needs to test the assumptions (i.e. competitive binding) of any integrated strategy of computational and experimental screening, in optimizing screening. Future strategies targeting allosteric mechanisms may need to rely more on structure-activity relationship modeling, rather than on docking, in computationally selecting peptides for screening.

Prediction of Short Linear Protein Binding Regions

Short linear motifs in proteins (typically 3-12 residues in length) play key roles in protein-protein interactions by frequently binding specifically to peptide binding domains within interacting proteins. Their tendency to be found in disordered segments of proteins has meant that they have often been overlooked. Here we present SLiMPred (short linear motif predictor), the first general de novo method designed to computationally predict such regions in protein primary sequences independent of experimentally defined homologs and interactors. The method applies machine learning techniques to predict new motifs based on annotated instances from the Eukaryotic Linear Motif database, as well as structural, biophysical, and biochemical features derived from the protein primary sequence. We have integrated these data sources and benchmarked the predictive accuracy of the method, and found that it performs equivalently to a predictor of protein binding regions in disordered regions, in addition to having predictive power for other classes of motif sites such as polyproline II helix motifs and short linear motifs lying in ordered regions. It will be useful in predicting peptides involved in potential protein associations and will aid in the functional characterization of proteins, especially of proteins lacking experimental information on structures and interactions. We conclude that, despite the diversity of motif sequences and structures, SLiMPred is a valuable tool for prioritizing potential interaction motifs in proteins.

Beyond the Twilight Zone: Automated prediction of structural properties of proteins by recursive neural networks and remote homology information

The prediction of 1D structural properties of proteins is an important step toward the prediction of protein structure and function, not only in the ab initio case but also when homology information to known structures is available. Despite this the vast majority of 1D predictors do not incorporate homology information into the prediction process. We develop a novel structural alignment method, SAMD, which we use to build alignments of putative remote homologues that we compress into templates of structural frequency profiles. We use these templates as additional input to ensembles of recursive neural networks, which we specialise for the prediction of query sequences that show only remote homology to any Protein Data Bank structure. We predict four 1D structural properties – secondary structure, relative solvent accessibility, backbone structural motifs, and contact density. Secondary structure prediction accuracy, tested by five‐fold cross‐validation on a large set of proteins allowing less than 25% sequence identity between training and test set and query sequences and templates, exceeds 82%, outperforming its ab initio counterpart, other state‐of‐the‐art secondary structure predictors (Jpred 3 and PSIPRED) and two other systems based on PSI‐BLAST and COMPASS templates. We show that structural information from homologues improves prediction accuracy well beyond the Twilight Zone of sequence similarity, even below 5% sequence identity, for all four structural properties. Significant improvement over the extraction of structural information directly from PDB templates suggests that the combination of sequence and template information is more informative than templates alone. Proteins 2009.

De Novo protein subcellular localization prediction by N-to-1 neural networks

SUMMARY Knowledge of the subcellular location of a protein provides valuable information about its function and possible interaction with other proteins. In the post-genomic era, fast and accurate predictors of subcellular location are required if this abundance of sequence data is to be fully exploited. We have developed a subcellular localization predictor (SCLpred), which predicts the location of a protein into four classes for animals and fungi and five classes for plants (secreted, cytoplasm, nucleus, mitochondrion and chloroplast) using machine learning models trained on large non-redundant sets of protein sequences. The algorithm powering SCLpred is a novel Neural Network (N-to-1 Neural Network, or N1-NN) we have developed, which is capable of mapping whole sequences into single properties (a functional class, in this work) without resorting to predefined transformations, but rather by adaptively compressing the sequence into a hidden feature vector. We benchmark SCLpred against other publicly available predictors using two benchmarks including a new subset of Swiss-Prot Release 2010_06. We show that SCLpred surpasses the state of the art. The N1-NN algorithm is fully general and may be applied to a host of problems of similar shape, that is, in which a whole sequence needs to be mapped into a fixed-size array of properties, and the adaptive compression it operates may shed light on the space of protein sequences. AVAILABILITY The predictive systems described in this article are publicly available as a web server at http://distill.ucd.ie/distill/. CONTACT gianluca.pollastri@ucd.ie.

CPPpred: prediction of cell penetrating peptides

Cell penetrating peptides (CPPs) are attracting much attention as a means of overcoming the inherently poor cellular uptake of various bioactive molecules. Here, we introduce CPPpred, a web server for the prediction of CPPs using a N-to-1 neural network. The server takes one or more peptide sequences, between 5 and 30 amino acids in length, as input and returns a prediction of how likely each peptide is to be cell penetrating. CPPpred was developed with redundancy reduced training and test sets, offering an advantage over the only other currently available CPP prediction method.

microRNA targeting of the P2X7 purinoceptor opposes a contralateral epileptogenic focus in the hippocampus

The ATP-gated ionotropic P2X7 receptor (P2X7R) modulates glial activation, cytokine production and neurotransmitter release following brain injury. Levels of the P2X7R are increased in experimental and human epilepsy but the mechanisms controlling P2X7R expression remain poorly understood. Here we investigated P2X7R responses after focal-onset status epilepticus in mice, comparing changes in the damaged, ipsilateral hippocampus to the spared, contralateral hippocampus. P2X7R-gated inward currents were suppressed in the contralateral hippocampus and P2rx7 mRNA was selectively uploaded into the RNA-induced silencing complex (RISC), suggesting microRNA targeting. Analysis of RISC-loaded microRNAs using a high-throughput platform, as well as functional assays, suggested the P2X7R is a target of microRNA-22. Inhibition of microRNA-22 increased P2X7R expression and cytokine levels in the contralateral hippocampus after status epilepticus and resulted in more frequent spontaneous seizures in mice. The major pro-inflammatory and hyperexcitability effects of microRNA-22 silencing were prevented in P2rx7−/− mice or by treatment with a specific P2X7R antagonist. Finally, in vivo injection of microRNA-22 mimics transiently suppressed spontaneous seizures in mice. The present study supports a role for post-transcriptional regulation of the P2X7R and suggests therapeutic targeting of microRNA-22 may prevent inflammation and development of a secondary epileptogenic focus in the brain.