NetSurfP-2.0: improved prediction of protein structural features by integrated deep learning

By Michael Schantz Klausen, Martin Closter Jespersen, Henrik Nielsen, Kamilla Kjærgaard Jensen, Vanessa Isabell Jurtz, Casper Kaae Sønderby, M. Sommer, Ole Winther, Morten Nielsen, Bent Petersen and 1 more. 2018

550 citations recorded by the source corpus.

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unravelling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed. Here, we present an updated and extended version of the NetSurfP tool (http://www.cbs.dtu.dk/services/NetSurfP-2.0/), that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences. We assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1,000 proteins in less than 2 hours, and complete proteomes in less than 1 day.

Subfields: Materials Chemistry, Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

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

In Materials Chemistry

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

BERTology Meets Biology: Interpreting Attention in Protein Language Models (2020, methodology): “For the analysis of secondary structure and binding sites we use the Secondary Structure dataset (Rao et al., 2019; Berman et al., 2000; Moult et al., 2018; Klausen et al., 2019) from TAPE.”
Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “…a vector of size 50 which included a one-hot encoding (20 features), the profiles of evolutionary information (20 features) from HHblits as published previously [46], the state transition probabilities of the Hidden-Markov-Model (7 features) and 3 features describing the local alignment diversity.”
Modeling the language of life – Deep Learning Protein Sequences (2019, methodology): “(i) DeepProf 37 (14,000=14k free parameters): Each residue was described by a vector of size 50 which 38 included a one-hot encoding (20 features), the profiles of evolutionary information (20 features) 39 from HHblits as published previously [45], the state transition probabilities of the Hidden40 ”
ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Learning (2021, methodology): “7. https://github.com/agemagician/ProtTrans/tree/master/Benchmark”
Self-Supervised Contrastive Learning of Protein Representations By Mutual Information Maximization (2020, background): “Given the diversity of biological use cases, embedding evaluations should be made on a case-by-case basis.”
Bilingual language model for protein sequence and structure (2024, unknown): “0 training data [40] and measured performance on three test sets (CASP12 [38], CASP14 [41] and NEW364 [4]).”