next up previous
Next: [2] ionize.aa Up: CHNOSZ examples Previous: [1] iprotein

[4] protein

## Don't show: data(thermo)
thermo$obigt: 1809 aqueous, 3368 total species
## End(Don't show) ## thermodynamic properties and activity diagrams prot4 <- c("LYSC_CHICK", "BPT1_BOVIN", "CYC_BOVIN", "MYG_PHYCA") # aqueous protein properties (nonionized) subcrt(prot4, T=seq(0, 200, 10))$out
aa2eos: found LYSC_CHICK (C613H959N193O185S10, 129 residues) aa2eos: found BPT1_BOVIN (C284H438N84O79S7, 58 residues) aa2eos: found CYC_BOVIN (C517H825N143O150S4, 104 residues) aa2eos: found MYG_PHYCA (C783H1240N216O216S2, 153 residues) subcrt: 4 species at 21 values of T and P (wet) $LYSC_CHICK T P rho logK G H S V Cp 1 0.01 1.000000 0.9998289 3217.694 -4021787 -10423733 3684.406 10049.21 4409.319 2 10.00 1.000000 0.9996022 3133.252 -4059468 -10373500 3864.899 10237.76 5535.776 3 20.00 1.000000 0.9982319 3055.935 -4099126 -10314612 4069.218 10369.12 6187.957 4 30.00 1.000000 0.9956535 2985.235 -4140887 -10250529 4284.136 10466.03 6599.770 5 40.00 1.000000 0.9922098 2920.568 -4184822 -10183059 4503.082 10540.70 6877.280 6 50.00 1.000000 0.9880295 2861.386 -4230950 -10113250 4722.506 10600.23 7073.981 7 60.00 1.000000 0.9831991 2807.193 -4279267 -10041750 4940.401 10649.02 7219.249 8 70.00 1.000000 0.9777800 2757.538 -4329749 -9968979 5155.613 10689.97 7330.339 9 80.00 1.000000 0.9718175 2712.017 -4382368 -9895221 5367.477 10725.05 7417.960 10 90.00 1.000000 0.9653461 2670.266 -4430187 -9820674 5575.630 10755.69 7489.084 11 100.00 1.013220 0.9583926 2631.960 -4493864 -9745475 5779.892 10782.93 7548.444 12 110.00 1.432410 0.9509951 2596.746 -4552560 -9669631 5980.181 10807.55 7599.301 13 120.00 1.984829 0.9431552 2564.408 -4613204 -9593275 6176.538 10830.19 7644.338 14 130.00 2.700203 0.9348829 2534.704 -4675749 -9516451 6369.032 10851.38 7685.250 15 140.00 3.611948 0.9261835 2507.420 -4602150 -9439183 6557.773 10871.56 7723.653 16 150.00 4.757169 0.9170577 2482.359 -4806358 -9361481 6742.892 10891.15 7760.881 17 160.00 6.176634 0.9075019 2459.343 -4874328 -9283339 6924.545 10910.53 7798.171 18 170.00 7.914706 0.8975079 2438.213 -4944014 -9204742 5722.899 10930.08 7836.758 19 180.00 10.019272 0.8870627 2418.822 -5015372 -9125660 7278.141 10950.23 7877.965 20 190.00 12.541651 0.8761489 2401.036 -5088356 -9046048 7450.471 10971.45 7923.307 21 200.00 15.536499 0.8647434 2384.733 -5162925 -8965847 7620.111 10994.29 7974.628 $BPT1_BOVIN T P rho logK G H S V Cp 1 0.01 1.000000 0.9998289 1253.8480 -1567181 -4428560 1687.401 4644.919 2005.038 2 10.00 1.000000 0.9996022 1222.9284 -1584437 -4405649 1769.721 4727.578 2529.809 3 20.00 1.000000 0.9982319 1194.7489 -1602595 -4378706 1863.205 4785.225 2833.863 4 30.00 1.000000 0.9956535 1169.1231 -1621717 -4349339 1961.693 4827.819 3026.060 5 40.00 1.000000 0.9922098 1145.8293 -1641835 -4318390 2062.124 4860.704 3155.771 6 50.00 1.000000 0.9880295 1124.6580 -1662960 -4286348 2162.841 4886.985 3247.896 7 60.00 1.000000 0.9831991 1105.4166 -1685090 -4253512 2262.907 4908.596 3316.114 8 70.00 1.000000 0.9777800 1087.9305 -1708215 -4220078 2361.783 4926.805 3368.463 9 80.00 1.000000 0.9718175 1072.0420 -1732321 -4186178 2459.157 4942.487 3409.939 10 90.00 1.000000 0.9653461 1057.6095 -1757392 -4151904 2554.859 4956.266 3443.799 11 100.00 1.013220 0.9583926 1044.5051 -1783410 -4117319 2648.802 4968.608 3472.263 12 110.00 1.432410 0.9509951 1032.5879 -1810311 -4082425 2602.951 4979.856 3496.899 13 120.00 1.984829 0.9431552 1021.7753 -1838108 -4047283 2831.322 4990.304 3518.884 14 130.00 2.700203 0.9348829 1011.9737 -1866780 -4011912 2919.949 5000.194 3539.131 15 140.00 3.611948 0.9261835 1003.0984 -1896307 -3976322 3006.884 5009.735 2868.394 16 150.00 4.757169 0.9170577 995.0727 -1926666 -3940515 3092.191 5019.123 3577.337 17 160.00 6.176634 0.9075019 987.8274 -1957838 -3904487 3175.944 5028.547 3596.589 18 170.00 7.914706 0.8975079 981.2993 -1989800 -3868227 3258.226 5038.206 3616.793 19 180.00 10.019272 0.8870627 975.4314 -2022535 -3831718 3339.129 5048.316 3638.649 20 190.00 12.541651 0.8761489 970.1714 -2056020 -3794934 3418.753 5059.125 3662.978 21 200.00 15.536499 0.8647434 965.4722 -2090239 -3757843 3497.210 5070.931 3690.788 $CYC_BOVIN T P rho logK G H S V Cp 1 0.01 1.000000 0.9998289 2789.974 -3487181 -8799781 3008.116 8151.661 3627.513 2 10.00 1.000000 0.9996022 2715.289 -3517952 -8758419 3156.735 8332.039 4560.624 3 20.00 1.000000 0.9982319 2646.818 -2860350 -8709892 3325.108 8457.507 5100.293 4 30.00 1.000000 0.9956535 2584.114 -3584483 -8657068 3502.266 8549.889 5440.551 5 40.00 1.000000 0.9922098 2526.665 -3620406 -8601448 3682.758 8620.885 5669.360 6 50.00 1.000000 0.9880295 2473.995 -3658139 -8543902 3863.636 8677.285 5831.081 7 60.00 1.000000 0.9831991 2425.669 -3697675 -8484968 4043.236 8723.305 5950.064 8 70.00 1.000000 0.9777800 2381.298 -3738996 -8424995 4220.598 8761.704 6040.602 9 80.00 1.000000 0.9718175 2340.529 -3782077 -8364220 4395.169 8794.371 6111.551 10 90.00 1.000000 0.9653461 2303.046 -3826889 -8302810 4566.643 8822.647 6168.661 11 100.00 1.013220 0.9583926 2268.565 -3873397 -8240878 4734.867 8847.515 6215.817 12 110.00 1.432410 0.9509951 2236.785 -3921484 -8178434 4899.769 8869.695 6255.735 13 120.00 1.984829 0.9431552 2207.514 -3971175 -8115591 5061.378 8889.779 6290.410 14 130.00 2.700203 0.9348829 2180.543 -4022431 -8052388 5219.744 8908.232 6321.348 15 140.00 3.611948 0.9261835 2155.685 -4075213 -7988849 5374.951 8925.441 6349.746 16 150.00 4.757169 0.9170577 2132.769 -4129481 -7924986 5527.099 8941.746 6376.606 17 160.00 6.176634 0.9075019 2111.642 -4185197 -7860803 5676.303 8957.451 6402.822 18 170.00 7.914706 0.8975079 2092.163 -4242322 -7796293 5822.690 8972.851 6429.249 19 180.00 10.019272 0.8870627 2074.205 -4300818 -7731441 5966.399 8988.244 6456.769 20 190.00 12.541651 0.8761489 2057.652 -4360647 -7666221 6107.574 9003.948 6486.359 21 200.00 15.536499 0.8647434 2042.398 -4421774 -7600599 6246.373 9020.326 6519.172 $MYG_PHYCA T P rho logK G H S V Cp 1 0.01 1.000000 0.9998289 3831.183 -4788585 -12737799 4401.893 12332.91 6173.064 2 10.00 1.000000 0.9996022 3730.881 -4833761 -12669191 4648.440 12593.40 7436.952 3 20.00 1.000000 0.9982319 3639.270 -4881592 -12590864 4920.221 12774.60 8168.077 4 30.00 1.000000 0.9956535 2865.706 -4932200 -12506715 5202.441 12908.02 8629.181 5 40.00 1.000000 0.9922098 3479.462 -4985651 -12418777 5487.812 13010.55 8939.382 6 50.00 1.000000 0.9880295 3409.867 -5041953 -12328227 5772.431 13092.02 9158.751 7 60.00 1.000000 0.9831991 3346.307 -5101089 -12235793 6054.122 13158.49 9320.267 8 70.00 1.000000 0.9777800 3288.234 -5163022 -12141949 6331.655 13213.96 9443.289 9 80.00 1.000000 0.9718175 3235.152 -5227706 -12047016 6604.348 13261.16 9539.818 10 90.00 1.000000 0.9653461 3186.619 -5295092 -11951215 6871.847 13302.02 9617.647 11 100.00 1.013220 0.9583926 3142.236 -5365121 -11854703 7134.001 13337.96 9682.049 12 110.00 1.432410 0.9509951 3101.576 -5437616 -11757480 7390.761 13301.02 9736.713 13 120.00 1.984829 0.9431552 3064.373 -5512608 -11659706 7642.215 13399.05 9784.356 14 130.00 2.700203 0.9348829 3030.336 -5590037 -11561431 7888.478 13425.73 9827.036 15 140.00 3.611948 0.9261835 2999.202 -5669839 -11462687 8129.703 13450.62 9866.397 16 150.00 4.757169 0.9170577 2970.734 -5751953 -11363487 8366.065 13474.20 9903.823 17 160.00 6.176634 0.9075019 2944.716 -5836318 -11263834 8597.759 13496.93 9940.560 18 170.00 7.914706 0.8975079 2920.953 -5922875 -11163714 8824.992 13519.22 9977.810 19 180.00 10.019272 0.8870627 2899.266 -6011562 -11063103 9047.984 13541.51 10016.822 20 190.00 12.541651 0.8761489 2879.495 -6102323 -10961963 9266.965 13564.26 10058.994 21 200.00 15.536499 0.8647434 2861.490 -6195100 -10860240 9482.184 13588.00 10105.986
# T-logfO2 activity diagram basis("CHNOS")
C H N O S ispecies logact state CO2 1 0 0 2 0 69 -3 aq H2O 0 2 0 1 0 1 0 liq NH3 0 3 1 0 0 68 -4 aq H2S 0 2 0 0 1 70 -7 aq O2 0 0 0 2 0 3095 -80 gas
species(prot4)
CO2 H2O NH3 H2S O2 ispecies logact state name 1 613 180 193 10 -610.5 3369 -3 aq LYSC_CHICK 2 284 86 84 7 -287.5 3301 -3 aq BPT1_BOVIN 3 517 194 143 4 -539.0 3371 -3 aq CYC_BOVIN 4 783 294 216 2 -822.0 3372 -3 aq MYG_PHYCA
a <- affinity(T=c(0, 200), O2=c(-80, -40))
energy.args: pressure is Psat energy.args: variable 1 is T at 128 values from 273.15 to 473.15 K energy.args: variable 2 is log_f(O2) at 128 values from -80 to -40 subcrt: 9 species at 128 values of T and P (wet)
diagram(a)
balance: coefficients are protein length diagram: plotting A/2.303RT from affinity(), divided by balancing coefficients

Image protein1

 

## one way to calculate the standard Gibbs energy of a ## reaction to form an ionized protein at 100 degrees and pH 8 basis("CHNOS+") # do this to auto-balance the formation reaction
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 69 -3 aq H2O 0 2 0 1 0 0 1 0 liq NH3 0 3 1 0 0 0 68 -4 aq H2S 0 2 0 0 1 0 70 -7 aq O2 0 0 0 2 0 0 3095 -80 gas H+ 0 1 0 0 0 1 3 -7 aq
Gr.nonionized <- subcrt("LYSC_CHICK", 1, T=100)$out$G
subcrt: 1 species at 373.15 K and 1.01 bar (wet) subcrt: reaction is not balanced; it is missing this composition: C H N O S -613 -959 -193 -185 -10 subcrt: adding missing composition from basis definition and restarting... subcrt: 6 species at 373.15 K and 1.01 bar (wet)
basis("pH", 8)
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 69 -3 aq H2O 0 2 0 1 0 0 1 0 liq NH3 0 3 1 0 0 0 68 -4 aq H2S 0 2 0 0 1 0 70 -7 aq O2 0 0 0 2 0 0 3095 -80 gas H+ 0 1 0 0 0 1 3 -8 aq
pinfo <- protein.info("LYSC_CHICK", round.it=FALSE, T=100)
subcrt: 1 species at 373.15 K and 1.01 bar (wet) subcrt: 18 species at 373.15 K and 1.01 bar (wet) subcrt: 18 species at 373.15 K and 1.01 bar (wet)
Gr.ionization <- pinfo$G.Z - pinfo$G # standard Gibbs energy of the reaction # in cal/mol ionized protein: Gr.ionized <- Gr.nonionized + Gr.ionization # in cal/mol ionized residue: Gr.ionized_residue <- Gr.ionized/protein.length("LYSC_CHICK") ## Standard molal entropy of a protein reaction basis("CHNOS")
C H N O S ispecies logact state CO2 1 0 0 2 0 69 -3 aq H2O 0 2 0 1 0 1 0 liq NH3 0 3 1 0 0 68 -4 aq H2S 0 2 0 0 1 70 -7 aq O2 0 0 0 2 0 3095 -80 gas
# here we provide the reaction coefficients of the # proteins (per protein backbone); 'subcrt' function calculates # the coefficients of the basis species in the reaction s <- subcrt(c("CSG_METTL","CSG_METJA"), c(-1/530,1/530), T=seq(0, 350, length.out=50))
aa2eos: found CSG_METTL (C2484H4000N638O844S7, 530 residues) aa2eos: found CSG_METJA (C2555H4032N640O865S14, 530 residues) subcrt: 2 species at 50 values of T and P (wet) subcrt: reaction is not balanced; it is missing this composition: C H N O S -0.133962264 -0.060377358 -0.003773585 -0.039622642 -0.013207547 subcrt: adding missing composition from basis definition and restarting... subcrt: 7 species at 50 values of T and P (wet)
thermo.plot.new(xlim=range(s$out$T), ylim=range(s$out$S), xlab=axis.label("T"), ylab=axis.label("DS0r")) lines(s$out$T, s$out$S) # do it at high pressure as well s <- subcrt(c("CSG_METTL","CSG_METJA"), c(-1/530,1/530), T=seq(0,350,length.out=50), P=3000)
subcrt: 2 species at 50 values of T and P (wet) subcrt: reaction is not balanced; it is missing this composition: C H N O S -0.133962264 -0.060377358 -0.003773585 -0.039622642 -0.013207547 subcrt: adding missing composition from basis definition and restarting... subcrt: 7 species at 50 values of T and P (wet)
lines(s$out$T, s$out$S, lty=2) # label the plot title(main=paste("Standard molal entropy\n", "P = Psat (solid), P = 3000 bar (dashed)")) s$reaction$coeff <- round(s$reaction$coeff, 3) dsr <- describe.reaction(s$reaction, iname=c(1,2)) text(170, -3, dsr, cex=0.8)

Image protein2

 

### Equilibrium activity diagrams ## surface-layer proteins from Methanococcus and others ## as a function of oxygen fugacity, after Dick, 2008, Fig. 5b # use old properties of [Met] to reproduce this example data(thermo)
thermo$obigt: 1809 aqueous, 3368 total species
add.obigt()
add.obigt: using default file: /home/jedick/R/x86_64-slackware-linux-gnu-library/3.3/CHNOSZ/extdata/thermo/OBIGT-2.csv add.obigt: read 305 rows; made 84 replacements, 221 additions, units = cal add.obigt: use data(thermo) to restore default database
# make our protein list organisms <- c("METSC", "METJA", "METFE", "HALJP", "METVO", "METBU", "ACEKI", "GEOSE", "BACLI", "AERSA") proteins <- c(rep("CSG", 6), rep("SLAP", 4)) proteins <- paste(proteins, organisms, sep="_") # load the basis species and proteins basis("CHNOS+")
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 69 -3 aq H2O 0 2 0 1 0 0 1 0 liq NH3 0 3 1 0 0 0 68 -4 aq H2S 0 2 0 0 1 0 70 -7 aq O2 0 0 0 2 0 0 3095 -80 gas H+ 0 1 0 0 0 1 3 -7 aq
species(proteins)
CO2 H2O NH3 H2S O2 H+ ispecies logact state name 1 2812 1066 747 16 -2909.0 0 3590 -3 aq CSG_METSC 2 2555 1042 640 14 -2643.5 0 3591 -3 aq CSG_METJA 3 2815 1071 747 14 -2914.5 0 3592 -3 aq CSG_METFE 4 3669 1367 971 0 -3608.5 0 3593 -3 aq CSG_HALJP 5 2575 1070 645 11 -2668.0 0 3594 -3 aq CSG_METVO 6 1362 519 286 4 -1400.5 0 3595 -3 aq CSG_METBU 7 3584 1431 926 4 -3730.5 0 3596 -3 aq SLAP_ACEKI 8 5676 2320 1489 3 -5904.5 0 3597 -3 aq SLAP_GEOSE 9 3977 1594 1068 2 -4131.0 0 3598 -3 aq SLAP_BACLI 10 2250 861 618 2 -2322.5 0 3599 -3 aq SLAP_AERSA
# calculate affinities; we go to lower logfO2 than Dick, 2008 # and find an interesting convergence of stabilities there a <- affinity(O2=c(-100, -65))
energy.args: temperature is 25 C energy.args: pressure is Psat energy.args: variable 1 is log_f(O2) at 128 values from -100 to -65 subcrt: 16 species at 298.15 K and 1 bar (wet) subcrt: 18 species at 298.15 K and 1 bar (wet)
# try normalize=FALSE to make Fig. 5a in the paper e <- equilibrate(a, normalize=TRUE)
balance: coefficients are protein length equilibrate: balancing coefficients are 571 530 571 828 553 278 736 1198 844 481 equilibrate: logarithm of total protein length is 0.81888541459401 equilibrate: using 'normalize' for molar formulas
d <- diagram(e, ylim=c(-5, -1), legend.x=NA, names=organisms) # add water stability line abline(v=-83.1, lty=2) title(main="Surface-layer proteins, after Dick, 2008")

Image protein3

 

# checking the geometry of the diagram # most preominant along the x-axis stopifnot(organisms[unique(which.pmax(e$loga.equil))] == c("METFE", "METJA", "METVO", "HALJP")) # stability order close to logfO2=-83.1 stopifnot(order(as.data.frame(e$loga.equil)[62,], decreasing=TRUE)==c(2, 6, 7, 5, 3, 1, 9, 8, 10, 4)) # reset thermodynamic database data(thermo)
thermo$obigt: 1809 aqueous, 3368 total species
## relative stabilities of bovine proteins ## as a function of temperature along a glutathione redox buffer mod.buffer("GSH-GSSG", c("GSH","GSSG"), logact=c(-3, -7))
mod.buffer: changed state and/or logact of GSH GSSG in GSH-GSSG buffer.
basis(c("CO2", "H2O", "NH4+", "SO4-2", "H2", "H+"), c(-1, 0, -4, -4, 999, -7))
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 69 -1 aq H2O 0 2 0 1 0 0 1 0 liq NH4+ 0 4 1 0 0 1 18 -4 aq SO4-2 0 0 0 4 1 -2 24 -4 aq H2 0 2 0 0 0 0 66 999 aq H+ 0 1 0 0 0 1 3 -7 aq
basis("H2", "GSH-GSSG")
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 69 -1 aq H2O 0 2 0 1 0 0 1 0 liq NH4+ 0 4 1 0 0 1 18 -4 aq SO4-2 0 0 0 4 1 -2 24 -4 aq H2 0 2 0 0 0 0 66 GSH-GSSG aq H+ 0 1 0 0 0 1 3 -7 aq
basis("CO2", "gas")
C H N O S Z ispecies logact state CO2 1 0 0 2 0 0 3087 -1 gas H2O 0 2 0 1 0 0 1 0 liq NH4+ 0 4 1 0 0 1 18 -4 aq SO4-2 0 0 0 4 1 -2 24 -4 aq H2 0 2 0 0 0 0 66 GSH-GSSG aq H+ 0 1 0 0 0 1 3 -7 aq
prot <- c("CYC", "RNAS1", "BPT1", "ALBU", "INS", "PRIO") species(prot, "BOVIN")
CO2 H2O NH4+ SO4-2 H2 H+ ispecies logact state name 1 517 -900 143 4 1094 -135 3369 -3 aq CYC_BOVIN 2 575 -1005 171 12 1191 -147 3301 -3 aq RNAS1_BOVIN 3 284 -517 84 7 603 -70 3371 -3 aq BPT1_BOVIN 4 2934 -5127 781 39 6224 -703 3372 -3 aq ALBU_BOVIN 5 254 -458 65 6 545 -53 3373 -3 aq INS_BOVIN 6 1026 -1783 318 9 2053 -300 3374 -3 aq PRIO_BOVIN
a <- affinity(T=c(0, 200))
energy.args: pressure is Psat energy.args: variable 1 is T at 128 values from 273.15 to 473.15 K affinity: loading buffer species subcrt: 14 species at 128 values of T and P (wet) subcrt: 18 species at 128 values of T and P (wet) buffer: ( GSH-GSSG ) for activity of H2 (active), CO2 (conserved)
# set line colors according to oxidation state of carbon ZC <- ZC(species()$ispecies) col <- rep("red", length(prot)) col[ZC > 0] <- "blue" e <- equilibrate(a, normalize=TRUE)
balance: coefficients are protein length equilibrate: balancing coefficients are 104 124 58 583 51 217 equilibrate: logarithm of total protein length is 0.0557604646877348 equilibrate: using 'normalize' for molar formulas
d <- diagram(e, col=col, legend.x=NA) title(main="Bovine proteins, GSH/GSSG redox buffer")

Image protein4

 


next up previous
Next: [2] ionize.aa Up: CHNOSZ examples Previous: [1] iprotein