SSpro/ACCpro 5: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, machine learning and structural similarity

By Christophe Nicolas Magnan, Pierre Baldi. 2014

365 citations recorded by the source corpus.

Subfields: Materials Chemistry, 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 Materials Chemistry

In Molecular Biology

Citations in the corpus

DeepSF: deep convolutional neural network for mapping protein sequences to folds (2017, methodology): “We generated predicted secondary structure using four methods: SCRATCH (Magnan and Baldi, 2014), DeepCNF (Wang et al.”
Assessment of Contact Predictions in CASP12: Co-Evolution and Deep Learning Coming of Age (2017, methodology): “IGBteam G310 Deep learning approach combining evolutionary information, coevolution information, CCMpred(51) and FreeContact(25) predictions, and predicted secondary structure and relative solvent accessibility using SSpro and ACCpro.(57) MetaPSICOV(31) G013 A neural network-based method inferring c”
RaptorX-Property: a web server for protein structure property prediction (2016, methodology): “Since SOLVPRED, SPINE-X and ACCpro predict real-valued relative solvent accessibility, we use the same 10% / 40% threshold as our ACC definition to re-label their output.”
Deep learning methods in protein structure prediction (2020, methodology): “SSpro/ACCpro5 [30] SS, SA BRNN-CNN PSI-BLAST”
Template-based and free modeling of I-TASSER and QUARK pipelines using predicted contact maps in CASP12 (2017, methodology): “Since the TM-scores of QUARK models for T0868 PSSpred necessitates the use of programs that can predict more specific detailed types of secondary structures, 50,51 which are essential to the modeling of the global fold of FM targets such as T0868.”
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks (2018, methodology): “Although 3D structure data of proteins is often a luxury and their prediction remains a challenge without templates, it has been of much progress to predict protein structural properties from sequences (Cheng et al. , 2005; Magnan and Baldi, 2014; Wang et al. , 2016a).”
Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13 (2019, background): “24,25 Theprofileorsequenceofthetargetwassearchedagainstthetemplate profile/sequence library by a number of sequence alignment tools (eg, BLAST, 26 CSI-BLAST/CS-BLAST, 27 PSI-BLAST, 22 COMPASS, 28 FFAS, 29 HHSearch, 30 HHblits, 23 HMMER, 31 JackHMMER, 32 SAM, 33 PRC, 34 RaptorX, 35 I-TASSER/MUSTER…”
Sixty-five years of the long march in protein secondary structure prediction: the final stretch? (2016, methodology): “Examples are HYPROSP [83], PROTEUS [84], MUPRED [85], DISTILL [86], GOR V [87], SPSSMPred [88], FLOPRED [89] and Protein Secondary Structure Prediction with Homology Analysis (SSpro) [90].”
Capturing non‐local interactions by long short‐term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility (2017, background): “Bidirectional Recurrent Neural Networks (BRNNs) (Schuster and Paliwal, 1997) can exploit both preceding and following dependencies across the whole sequence and have been used in a number of bioinformatic studies (Baldi et al., 1999; Pollastri et al., 2002a; Mirabello and Pollastri, 2013; Magnan and”
AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling (2016, methodology): “DNdisorder uses deep belief network (DBN) while DisoPred3-ab uses support vector machine (SVM) and NN for prediction; (iii) for SS8 prediction, we compare our method with SSpro5-ab [34] and RaptorX-SS8 [46].”