Biomedical subjects

John Hawkins

Publications and source records attributed to John Hawkins.

7 recordsLinked to original sources

PubMed2006

Detecting and sorting targeting peptides with neural networks and support vector machines.

This paper presents a composite multi-layer classifier system for predicting the subcellular localization of proteins based on their amino acid sequence. The work is an extension of our previous predictor PProwler v1.1 which is itself built upon the series of predictors SignalP and TargetP. In this study we outline experiments conducted to improve the classifier design. The major improvement came from using Support Vector machines as a "smart gate" sorting the outputs of several different targeting peptide detection networks. Our final model (PProwler v1.2) gives MCC values of 0.873 for non-plant and 0.849 for plant proteins. The model improves upon the accuracy of our previous subcellular localization predictor (PProwler v1.1) by 2% for plant data (which represents 7.5% improvement upon TargetP).

Amino Acid Sequence↗

PubMed2005

Pharmacological preconditioning with sildenafil: Basic mechanisms and clinical implications.

The phosphodiesterase type-5 (PDE5) inhibitor, sildenafil, is the first drug developed for treatment of erectile dysfunction in patients. Experimental data in animals show that sildenafil has a preconditioning-like cardioprotective effect against ischemia/reperfusion injury in the intact heart. Mechanistic studies suggest that sildenafil exerts cardioprotection through NO generated from eNOS/iNOS, activation of protein kinase C/ERK signaling and opening of mitochondrial ATP-sensitive potassium channels. Additional studies show that the drug attenuates cell death resulting from necrosis and apoptosis, and increases the Bcl2/Bax ratio through NO signaling in adult cardiomyocytes. Emerging new data also suggest that sildenafil may be used clinically for treatment of pulmonary arterial hypertension and endothelial dysfunction. Future demonstration of the cardioprotective effect in patients with the relatively safe and effective FDA-approved PDE5 inhibitors such as sildenafil could have an enormous impact on bringing the long-studied phenomenon of ischemic and pharmacologic preconditioning to the clinical forefront.

3',5'-Cyclic-GMP Phosphodiesterases↗

PubMed2005

Prediction of subcellular localization using sequence-biased recurrent networks.

MOTIVATION: Targeting peptides direct nascent proteins to their specific subcellular compartment. Knowledge of targeting signals enables informed drug design and reliable annotation of gene products. However, due to the low similarity of such sequences and the dynamical nature of the sorting process, the computational prediction of subcellular localization of proteins is challenging. RESULTS: We contrast the use of feed forward models as employed by the popular TargetP/SignalP predictors with a sequence-biased recurrent network model. The models are evaluated in terms of performance at the residue level and at the sequence level, and demonstrate that recurrent networks improve the overall prediction performance. Compared to the original results reported for TargetP, an ensemble of the tested models increases the accuracy by 6 and 5% on non-plant and plant data, respectively. AVAILABILITY: The Protein Prowler incorporating the recurrent network predictor described in this paper is available online at http://pprowler.imb.uq.edu.au/

Algorithms↗

PubMed2005

Improved access to sequential motifs: a note on the architectural bias of recurrent networks.

For many biological sequence problems the available data occupies only sparse regions of the problem space. To use machine learning effectively for the analysis of sparse data we must employ architectures with an appropriate bias. By experimentation we show that the bias of recurrent neural networks--recently analyzed by Tino et al. and Hammer and Tino--offers superior access to motifs (sequential patterns) compared to the, in bioinformatics, standardly used feedforward neural networks.

Computational Biology↗

PubMed2004

Cardioprotection with phosphodiesterase-5 inhibition--a novel preconditioning strategy.

Phosphodiesterase type-5 (PDE-5) inhibitors including sildenafil, vardenafil and tadalafil are a new class of vasoactive drugs that have been developed for treatment of erectile dysfunction in patients. A growing number of studies in recent years suggest that sildenafil may be used clinically for treatment of pulmonary hypertension and endothelial dysfunction. In addition, recent studies primarily from our laboratory suggested that sildenafil has preconditioning-like powerful cardioprotective effect in the animal models of ischemia-reperfusion injury. Sildenafil has been found to exert cardioprotection through nitric oxide generated from endothelial and/or inducible nitric oxide synthases and opening of mitochondrial ATP-sensitive potassium channels. Future demonstration of the cardioprotective effect in patients with the relatively safe and effective FDA-approved PDE-5 inhibitors, such as sildenafil, could have an enormous impact on bringing the long-studied phenomena of ischemic and pharmacologic preconditioning to the clinical forefront.

3',5'-Cyclic-GMP Phosphodiesterases↗

PubMed2002

Sildenafil (Viagra) induces powerful cardioprotective effect via opening of mitochondrial K(ATP) channels in rabbits.

Sildenafil citrate (Viagra) is the pharmacological agent used to treat erectile dysfunction in men. Because this drug has a vasodilatory effect, we hypothesized that such an action may induce a preconditioning-like cardioprotective effect via opening of mitochondrial ATP-sensitive K (K(ATP)) channels. Rabbits were treated with sildenafil citrate (0.7 mg/kg iv) either 30 min (acute phase) or 24 h (delayed phase) before 30 min of ischemia and 3 h of reperfusion. Mitochondrial K(ATP) channel blocker 5-hydroxydecanoate (5-HD, 5 mg/kg iv) was given 10 min before ischemia-reperfusion. Infarct size was measured by tetrazolium staining. Sildenafil caused reduction in arterial blood pressure within 2 min of treatment, which returned to nearly baseline levels 3 min later. The infarct size (% risk area, means +/- SE) reduced from 33.8 +/- 1.7 in control rabbits to 10.8 +/- 0.9 during the acute phase (68% reduction, P < 0.05) and 19.9 +/- 2.0 during the delayed phase (41% reduction, P < 0.05). 5-HD abolished protection with an increase in infarct size to 35.6 +/- 0.4% and 36.8 +/- 1.6% during the acute and delayed phase, respectively (P < 0.05). Similar acute and delayed cardioprotective effects were observed when sildenafil was administered orally. Systemic hemodynamics also decreased after oral administration of the drug. However, these changes were mild and occurred slowly. For the first time, we demonstrate that sildenafil induces acute and delayed protective effects against ischemia-reperfusion injury, which are mediated by opening of mitochondrial K(ATP) channels.

Administration, Oral↗

PubMedDate not supplied

The applicability of recurrent neural networks for biological sequence analysis.

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Algorithms↗