ترغب بنشر مسار تعليمي؟ اضغط هنا

Predicting membrane protein contacts from non-membrane proteins by deep transfer learning

267   0   0.0 ( 0 )
 نشر من قبل Jinbo Xu
 تاريخ النشر 2017
والبحث باللغة English




اسأل ChatGPT حول البحث

Computational prediction of membrane protein (MP) structures is very challenging partially due to lack of sufficient solved structures for homology modeling. Recently direct evolutionary coupling analysis (DCA) sheds some light on protein contact prediction and accordingly, contact-assisted folding, but DCA is effective only on some very large-sized families since it uses information only in a single protein family. This paper presents a deep transfer learning method that can significantly improve MP contact prediction by learning contact patterns and complex sequence-contact relationship from thousands of non-membrane proteins (non-MPs). Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0.69, better than our deep model trained by only MPs (0.63) and much better than a representative DCA method CCMpred (0.47) and the CASP11 winner MetaPSICOV (0.55). The accuracy of our deep model can be further improved to 0.72 when trained by a mix of non-MPs and MPs. When only contacts in transmembrane regions are evaluated, our method has top L/10 long-range accuracy 0.62, 0.57, and 0.53 when trained by a mix of non-MPs and MPs, by non-MPs only, and by MPs only, respectively, still much better than MetaPSICOV (0.45) and CCMpred (0.40). All these results suggest that sequence-structure relationship learned by our deep model from non-MPs generalizes well to MP contact prediction. Improved contact prediction also leads to better contact-assisted folding. Using only top predicted contacts as restraints, our deep learning method can fold 160 and 200 of 510 MPs with TMscore>0.6 when trained by non-MPs only and by a mix of non-MPs and MPs, respectively, while CCMpred and MetaPSICOV can do so for only 56 and 77 MPs, respectively. Our contact-assisted folding also greatly outperforms homology modeling.



قيم البحث

اقرأ أيضاً

90 - Sheng Wang , Zhen Li , Yizhou Yu 2017
Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling. Here we describe a high-throughput deep transfer learning method that first predicts MP contacts by learning from non-membrane proteins (non-MPs) and then predicting three-dimensional structure models using the predicted contacts as distance restraints. Tested on 510 non-redundant MPs, our method has contact prediction accuracy at least 0.18 better than existing methods, predicts correct folds for 218 MPs (TMscore at least 0.6), and generates three-dimensional models with RMSD less than 4 Angstrom and 5 Angstrom for 57 and 108 MPs, respectively. A rigorous blind test in the continuous automated model evaluation (CAMEO) project shows that our method predicted high-resolution three-dimensional models for two recent test MPs of 210 residues with RMSD close to 2 Angstrom. We estimated that our method could predict correct folds for between 1,345 and 1,871 reviewed human multi-pass MPs including a few hundred new folds, which shall facilitate the discovery of drugs targeting at membrane proteins.
Understanding protein folding has been one of the great challenges in biochemistry and molecular biophysics. Over the past 50 years, many thermodynamic and kinetic studies have been performed addressing the stability of globular proteins. In comparis on, advances in the membrane protein folding field lag far behind. Although membrane proteins constitute about a third of the proteins encoded in known genomes, stability studies on membrane proteins have been impaired due to experimental limitations. Furthermore, no systematic experimental strategies are available for folding these biomolecules in vitro. Common denaturing agents such as chaotropes usually do not work on helical membrane proteins, and ionic detergents have been successful denaturants only in few cases. Refolding a membrane protein seems to be a craftsman work, which is relatively straightforward for transmembrane {beta}-barrel proteins but challenging for {alpha}-helical membrane proteins. Additional complexities emerge in multidomain membrane proteins, data interpretation being one of the most critical. In this review, we will describe some recent efforts in understanding the folding mechanism of membrane proteins that have been reversibly refolded allowing both thermodynamic and kinetic analysis. This information will be discussed in the context of current paradigms in the protein folding field.
Protein-RNA interactions are of vital importance to a variety of cellular activities. Both experimental and computational techniques have been developed to study the interactions. Due to the limitation of the previous database, especially the lack of protein structure data, most of the existing computational methods rely heavily on the sequence data, with only a small portion of the methods utilizing the structural information. Recently, AlphaFold has revolutionized the entire protein and biology field. Foreseeably, the protein-RNA interaction prediction will also be promoted significantly in the upcoming years. In this work, we give a thorough review of this field, surveying both the binding site and binding preference prediction problems and covering the commonly used datasets, features, and models. We also point out the potential challenges and opportunities in this field. This survey summarizes the development of the RBP-RNA interaction field in the past and foresees its future development in the post-AlphaFold era.
Motivated by the biologically important and complex phenomena of Abeta peptide aggregation in Alzheimers disease, we introduce a model and simulation methodology for studying protein aggregation that includes extra-cellular aggregation, aggregation o n the cell-surface assisted by a membrane bound protein, and in addition, supply, clearance, production and sequestration of peptides and proteins. The model is used to produce equilibrium and kinetic-aggregation phase diagrams for aggregation onset and of reduced stable Abeta monomer concentrations due to aggregation. The methodology we implemented permits modeling of a phenomenon involving orders of magnitude differences in time scales and concentrations which can be retained in the simulation. We demonstrate how to identify ranges of parameter values that give monomer concentration depletion upon aggregation similar to that observed in Alzheimers disease. We show how very different behavior can be obtained as reaction parameters and protein concentrations vary, and discuss the difficulty reconciling results of experiments from two vastly different concentration regimes. The latter is an important general issue in relating in-vitro and mice based experiments to humans.
127 - Ryo Urano , 2014
We propose an improved prediction method of the tertiary structures of $alpha$-helical membrane proteins based on the replica-exchange method by taking into account helix deformations. Our method allows wide applications because transmembrane helices of native membrane proteins are often distorted. In order to test the effectiveness of the present method, we applied it to the structure predictions of glycophorin A and phospholamban. The results were in accord with experiments.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا