Abstract
A variety of functionally important protein properties, such as secondary structure, transmembrane topology and solvent accessibility, can be encoded as a labeling of amino acids. Indeed, the prediction of such properties from the primary amino acid sequence is one of the core projects of computational biology. Accordingly, a panoply of approaches have been developed for predicting such properties; however, most such approaches focus on solving a single task at a time. Motivated by recent, successful work in natural language processing, we propose to use multitask learning to train a single, joint model that exploits the dependencies among these various labeling tasks. We describe a deep neural network architecture that, given a protein sequence, outputs a host of predicted local properties, including secondary structure, solvent accessibility, transmembrane topology, signal peptides and DNA-binding residues. The network is trained jointly on all these tasks in a supervised fashion, augmented with a novel form of semi-supervised learning in which the model is trained to distinguish between local patterns from natural and synthetic protein sequences. The task-independent architecture of the network obviates the need for task-specific feature engineering. We demonstrate that, for all of the tasks that we considered, our approach leads to statistically significant improvements in performance, relative to a single task neural network approach, and that the resulting model achieves state-of-the-art performance.
Highlights
Proteins participate in every major biological process within every living cell
We focus on predicting local functional properties, which can be summarized as a labeling of amino acids
Training for this task is achieved by assigning a positive label to genuine fragments of natural language, and negative labels to fragments that have been synthetically generated. This task involves learning to predict whether the given text sequence exists naturally in the English languague. Motivated by this language model, we propose an auxiliary task aiming to model the local patterns of amino acids that naturally occur in protein sequences
Summary
Proteins participate in every major biological process within every living cell. elucidating protein function is a central endeavor of molecular biology. Analogous to functional labeling of amino acids, natural language can be annotated with tags indicating synonymous pairs of words, parts of speech, larger syntactic entities, named entities, semantic roles, etc. These labelings exhibit strong dependencies across tasks. Essential to the success of the Collobert and Weston system is the use of a deep neural network [3,4], which is able to learn a hierarchy of features that are relevant to the tasks at hand given very basic inputs. Our work makes use of all three of these components–multitask learning, deep learning and an analog of the language model–to predict local protein properties
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
