G
Gianluca Pollastri
Researcher at University College Dublin
Publications - 84
Citations - 5658
Gianluca Pollastri is an academic researcher from University College Dublin. The author has contributed to research in topics: Protein structure prediction & Artificial neural network. The author has an hindex of 35, co-authored 81 publications receiving 4924 citations. Previous affiliations of Gianluca Pollastri include University of California, Irvine.
Papers
More filters
Journal ArticleDOI
Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles.
TL;DR: This paper used ensembles of bidirectional recurrent neural network architectures, PSI-BLAST-derived profiles, and a large non-redundant training set to derive two new predictors: SSpro and SSpro8.
Journal ArticleDOI
Exploiting the past and the future in protein secondary structure prediction.
TL;DR: A family of novel architectures which can learn to make predictions based on variable ranges of dependencies are introduced, extending recurrent neural networks and introducing non-causal bidirectional dynamics to capture both upstream and downstream information.
Journal ArticleDOI
Porter: a new, accurate server for protein secondary structure prediction
TL;DR: Porter's accuracy, tested by rigorous 5-fold cross-validation on a large set of proteins, exceeds 79%, significantly above a copy of the state-of-the-art SSpro server, better than any system published to date.
Journal ArticleDOI
Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules
TL;DR: A brief overview of deep learning methods is presented and in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties, by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph.
Journal ArticleDOI
Towards the Improved Discovery and Design of Functional Peptides: Common Features of Diverse Classes Permit Generalized Prediction of Bioactivity
TL;DR: It is concluded that there are general shared features of bioactive peptides across different functional classes, indicating that computational prediction may accelerate the discovery of novel bio active peptides and aid in the improved design of existing peptides, across many functional classes.