Estimation of protein secondary structure from FTIR spectra using neural networks

2001-05-30
Severcan, M
Severcan, Feride
Haris, PI
Secondary structure of proteins have been predicted using neural networks (NN) from their Fourier transform infrared spectra. Leave-one-out approach has been used to demonstrate the applicability of the method. A form of cross-validation is used to train NN to prevent the overfitting problem. Multiple neural network outputs are averaged to reduce the variance of predictions. The networks realized have been tested and rms errors of 7.7% for alpha -helix, 6.4% for beta -sheet and 4.8% for turns have been achieved. These results indicate that the methodology introduced is effective and estimation accuracies are in some cases better than those previously reported in the literature.
JOURNAL OF MOLECULAR STRUCTURE

Suggestions

Analysis of the Raman frequencies close to the lambda-phase transition in NH4Cl
Yurtseven, Hasan Hamit (Elsevier BV, 2007-05-27)
This study gives our analysis of the Raman frequencies for the lattice modes of v(5)TO(174 cm(-1)), v(5)TO(144 cm(-1)) and v(7)TA(93 cm(-1)), and an internal mode of v(2)(1708 cm(-1)) as functions of temperature in NH4Cl close to its lambda-phase transition (T-lambda = 241.2 K, P = 0). This analysis is performed using a power-law formula with the critical exponent beta for the order parameter according to the soft mode-hard mode coupling model.
Melatonin induces opposite effects on order and dynamics of anionic DPPG model membranes
Sahin, Ipek; Severcan, Feride; Kazanci, Nadide (Elsevier BV, 2007-05-27)
The temperature and concentration induced effects of melatonin on anionic dipalmitoyl phosphatidylglycerol (DPPG) multilamellar liposomes (MLVs) were investigated by using Fourier transform infrared (FTIR) spectroscopy and differential scanning calorimetry (DSC). The results show that melatonin does not perturb the phase transition profile, while a decrease in the main transition temperature (T-m) is noticed at high melatonin concentrations (15, 24 and 30 mol Low concentrations of melatonin (3, 6 and 9 mol ...
Modeling of dispersion in a polymeric chromatographic monolith
Koku, Harun; Schure, Mark R.; Lenhoff, Abraham M. (Elsevier BV, 2012-05-11)
Dispersion in a commercial polymeric monolith was simulated on a sample geometry obtained by direct imaging using high-resolution electron microscopy. A parallelized random walk algorithm, implemented using a velocity field obtained previously by the lattice-Boltzmann method, was used to model mass transfer. Both point particles and probes of finite size were studied. Dispersion simulations with point particles using periodic boundaries resulted in plate heights that varied almost linearly with flow rate, a...
Calculation of the Raman frequencies using volume data close to the tricritical and second order phase transitions in NH4Cl
Yurtseven, Hasan Hamit (Elsevier BV, 2009-04-30)
We calculate here the Raman frequencies of the v(5) TO(174 cm(-1)) and v(2) (1708 cm(-1)) modes as a function of temperature in the region of the tricritical (P = 1.6 kbar) and the second order (P = 2.8 kbar) phase transitions in NH4Cl. This calculation of the Raman frequencies is performed through the mode Gruneisen parameter by using the experimental length-change data obtained at zero pressure where the NH4Cl crystal exhibits a weakly first order phase transition (T-lambda = 242 K). The predicted Raman f...
Raman bandwidths calculated for the librational ( a -phase) and internal (8, d loc and d phases) modes in solid N 2 using pseudospin-phonon coupling (PS) and energy-fluctuation (EF) models
Yurtseven, Hasan Hamit (Elsevier BV, 2020-10-01)
This study gives the calculation of the Raman bandwidths using the models of the pseudospin-phonon coupling (PS) and energy fluctuation (EF) where the Raman frequency calculated from the molecular field theory, is considered as the order parameter close to the phase transitions in nitrogen. In particular, we study the temperature dependence of the Raman bandwidths and frequency shifts of the Eg librational mode (zero pressure) and the internal modes of and (at various pressures) for the solid nitrogen by ...
Citation Formats
M. Severcan, F. Severcan, and P. Haris, “Estimation of protein secondary structure from FTIR spectra using neural networks,” JOURNAL OF MOLECULAR STRUCTURE, pp. 383–387, 2001, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/52320.