Deep transfer learning in the assessment of the quality of protein models

By David Ménendez Hurtado, Karolis Uziela, Arne Elofsson. 2018

36 citations recorded by the source corpus.

MOTIVATION: Proteins fold into complex structures that are crucial for their biological functions. Experimental determination of protein structures is costly and therefore limited to a small fraction of all known proteins. Hence, different computational structure prediction methods are necessary for the modelling of the vast majority of all proteins. In most structure prediction pipelines, the last step is to select the best available model and to estimate its accuracy. This model quality estimation problem has been growing in importance during the last decade, and progress is believed to be important for large scale modelling of proteins. The current generation of model quality estimation programs performs well at separating incorrect and good models, but fails to consistently identify the best possible model. State-of-the-art model quality assessment methods use a combination of features that describe a model and the agreement of the model with features predicted from the protein sequence. RESULTS: We first introduce a deep neural network architecture to predict model quality using significantly fewer input features than state-of-the-art methods. Thereafter, we propose a methodology to train the deep network that leverages the comparative structure of the problem. We also show the possibility of applying transfer learning on databases of known protein structures. We demonstrate its viability by reaching state-of-the-art performance using only a reduced set of input features and a coarse description of the models. AVAILABILITY: The code will be freely available for download at github.com/ElofssonLab/ProQ4.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Learning from Protein Structure with Geometric Vector Perceptrons (2020, methodology): “, 2019) and ProQ4 (Hurtado et al., 2018) employ one-dimensional deep convolutional networks on top of sequential representations.”
Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, background): “In a similar vein, in the context of predicting protein structures, Hurtado et al. [114] shows that a deep NN can be pre-trained on a large database of already-known protein structures to enhance performance.”
GraphQA: protein model quality assessment using graph convolutional networks (2020, methodology): “Following Hurtado et al. (2018), we also add two residue-level statistics computed using Multiple Sequence Alignment (MSA) (Rost et al., 1994), namely self-information and partial entropy , each described by a 23-dimensional vector.”
PconsC4: fast, free, easy, and accurate contact predictions (2018, methodology): “To include secondary structure information but remain independent of external predictors, we took the pre-trained network from ProQ4 (Men´endez Hurtado et al. , 2018), that takes all the one-dimensional inputs and predicts secondary structure, dihedral angles, and surface accessibility for each…”