Residue-residue contact prediction is a fundamental problem in protein structure prediction. Hower, despite considerable research efforts, contact prediction methods are still largely unreliable. Here we introduce a novel deep machine-learning architecture which consists of a multidimensional stack of learning modules. For contact prediction, the idea is implemented as a three-dimensional stack of Neural Networks NNk ij, where i and j index the spatial coordinates of the contact map and k indexes "time". The temporal dimension is introduced to capture the fact that protein folding is not an instantaneous process, but rather a progressive refinement. Networks at level k in the stack can be trained in supervised fashion to refine the predictions produced by the previous level, hence addressing the problem of vanishing gradients, typical of deep architectures. Increased accuracy and generalization capabilities of this approach are established by rigorous comparison with other classical machine learning approaches for contact prediction. The deep approach leads to an accuracy for difficult long-range contacts of about 30%, roughly 10% above the state-of-the-art. Many variations in the architectures and the training algorithms are possible, leaving room for further improvements. Furthermore, the approach is applicable to other problems with strong underlying spatial and temporal components.

Deep spatio-temporal architectures and learning for protein structure prediction / Pietro Di Lena; Ken Nagata; Pierre Baldi. - ELETTRONICO. - (2012), pp. 512-520. (Intervento presentato al convegno 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 tenutosi a Lake Tahoe, NV, United States nel 3-6 December 2012).

Deep spatio-temporal architectures and learning for protein structure prediction

DI LENA, PIETRO;
2012

Abstract

Residue-residue contact prediction is a fundamental problem in protein structure prediction. Hower, despite considerable research efforts, contact prediction methods are still largely unreliable. Here we introduce a novel deep machine-learning architecture which consists of a multidimensional stack of learning modules. For contact prediction, the idea is implemented as a three-dimensional stack of Neural Networks NNk ij, where i and j index the spatial coordinates of the contact map and k indexes "time". The temporal dimension is introduced to capture the fact that protein folding is not an instantaneous process, but rather a progressive refinement. Networks at level k in the stack can be trained in supervised fashion to refine the predictions produced by the previous level, hence addressing the problem of vanishing gradients, typical of deep architectures. Increased accuracy and generalization capabilities of this approach are established by rigorous comparison with other classical machine learning approaches for contact prediction. The deep approach leads to an accuracy for difficult long-range contacts of about 30%, roughly 10% above the state-of-the-art. Many variations in the architectures and the training algorithms are possible, leaving room for further improvements. Furthermore, the approach is applicable to other problems with strong underlying spatial and temporal components.
2012
Advances in Neural Information Processing Systems 25
512
520
Deep spatio-temporal architectures and learning for protein structure prediction / Pietro Di Lena; Ken Nagata; Pierre Baldi. - ELETTRONICO. - (2012), pp. 512-520. (Intervento presentato al convegno 26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 tenutosi a Lake Tahoe, NV, United States nel 3-6 December 2012).
Pietro Di Lena; Ken Nagata; Pierre Baldi
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/149648
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 33
  • ???jsp.display-item.citation.isi??? ND
social impact