Protein Secondary Structure prediction has been a central topic of research in Bioinformatics for decades. In spite of this, even the most sophisticated ab initio SS predictors are not able to reach the theoretical limit of three-state prediction accuracy (88–90%), while only a few predict more than the 3 traditional Helix, Strand and Coil classes. In this study we present tests on different models trained both on single sequence and evolutionary profile-based inputs and develop a new state-of-the-art system with Porter 5. Porter 5 is composed of ensembles of cascaded Bidirectional Recurrent Neural Networks and Convolutional Neural Networks, incorporates new input encoding techniques and is trained on a large set of protein structures. Porter 5 achieves 84% accuracy (81% SOV) when tested on 3 classes and 73% accuracy (70% SOV) on 8 classes on a large independent set. In our tests Porter 5 is 2% more accurate than its previous version and outperforms or matches the most recent predictors of secondary structure we tested. When Porter 5 is retrained on SCOPe based sets that eliminate homology between training/testing samples we obtain similar results. Porter is available as a web server and standalone program at http://distilldeep.ucd.ie/porter/ alongside all the datasets and alignments.

Motivation: Although secondary structure predictors have been developed for decades, current ab initio methods have still some way to go to reach their theoretical limits. Moreover, the continuous effort towards harnessing ever expanding data sets and more sophisticated, deeper Machine Learning techniques, has not come to an end. Results: Here we present Porter 5, the latest release of one of the best performing ab initio secondary structure predictors. Version 5 achieves 84% accuracy (84% SOV) when tested on 3 classes, and 73% accuracy (77% SOV) on 8 classes, on a large independent set, significantly outperforming all the most recent ab initio predictors we have tested. Availability: The web and standalone versions of Porter5 are available at

Predicting the three-dimensional structure of proteins is a long-standing challenge of computational biology, as the structure (or lack of a rigid structure) is well known to determine a protein's function. Predicting relative solvent accessibility (RSA) of amino acids within a protein is a significant step towards resolving the protein structure prediction challenge especially in cases in which structural information about a protein is not available by homology transfer. Today, arguably the core of the most powerful prediction methods for predicting RSA and other structural features of proteins is some form of Deep Learning, and all the state-of-the-art protein structure prediction tools rely on some Machine Learning algorithm. In this article we present a deep neural network architecture composed of stacks of Bidirectional Recurrent Neural Networks and Convolutional layers which is capable of mining information from long-range interactions within a protein sequence, and apply it to the prediction of protein RSA using a novel encoding method that we shall call "clipped". The final system we present, PaleAle 5.0, which is available as a public server, predicts RSA into two, three and four classes at an accuracy exceeding 80% in two classes, surpassing the performances of all the other predictors we have benchmarked.

Motivation The subcellular location of a protein can provide useful information for protein function prediction and drug design. Experimentally determining the subcellular location of a protein is an expensive and time-consuming task. Therefore, various computer-based tools have been developed, mostly using machine learning algorithms, to predict the subcellular location of proteins. Results Here, we present a neural network-based algorithm for protein subcellular location prediction. We introduce SCLpred-EMS a subcellular localization predictor powered by an ensemble of Deep N-to-1 Convolutional Neural Networks. SCLpred-EMS predicts the subcellular location of a protein into two classes, the endomembrane system and secretory pathway versus all others, with a Matthews correlation coefficient of 0.75–0.86 outperforming the other state-of-the-art web servers we tested. Availability and implementation SCLpred-EMS is freely available for academic users at http://distilldeep.ucd.ie/SCLpred2/. Contact catherine.mooney@ucd.ie

The power of computer simulations, including machine-learning, has become an inseparable part of scientific analysis of biological data. This has significantly impacted the field of cryogenic electron microscopy (cryo-EM), which has grown dramatically since the "resolution-revolution." Many maps are now solved at 3-4 Å or better resolution, although a significant proportion of maps deposited in the Electron Microscopy Data Bank are still at lower resolution, where the positions of atoms cannot be determined unambiguously. Additionally, cryo-EM maps are often characterized by a varying local resolution, partly due to conformational heterogeneity of the imaged molecule. To address such problems, many computational methods have been developed for cryo-EM map reconstruction and atomistic model building. Here, we review the development in algorithms and tools for building models in cryo-EM maps at different resolutions. We describe methods for model building, including rigid and flexible fitting of known models, model validation, small-molecule fitting, and model visualization. We provide examples of how these methods have been used to elucidate the structure and function of dynamic macromolecular machines.