```Date: Dec 14, 2012 12:45 AM
Author: Halitsky
Subject: Re your questions  about the plots sent off-line (and the underlying<br> data posted here 12/13 at 10:33am)

You wrote:?What are the 1..36? All the other values are monotone increasing.Did they come that way, or did you sort them?The best way to see the difference between the plots is to take cols2 & 3 as x & y coordinates, then plot the points along with a linefrom (0,0) to (1,1). The S-plot is mostly below the line. the C-plotis mostly above. I'm not as struck by that difference as you seem tobe. Where did the numbers come from??Answers1.  The 1...36 are irrelevant if the data are plotted the way yousuggest ? they were just a way of giving Excel an x-axis to plotagainst.  And thanks very much for the suggestion as how to plot incases like this ? of course it never would have occurred to me to doit that way, and I was delighted to see that Excel lets you do itpretty easily (for a Microsoft-owned product, that is.)2.  Yes ? columns 2 and 3 were sorted.3.  Here?s where the numbers came from.Recall that:a) the fold x subset ?het? data which I presented for Aubuqe on L atMoSS N, set 1:   Slopes of Regressions ofAubqe on Length (L) for each      Fold x Subset |      Set 1, Method NFold x             SlopeSubset |     #      ofSet 1       of     AubqeMeth N     L?s      on La3_S_1_N     70  -0.000188c1_C_1_N    101  -0.000026a3_C_1_N     48   0.000052c1_S_1_N    101   0.000266c2_S_1_N     96   0.000421c2_C_1_N     95   0.000550b47_C_1_N    99   0.000618a1_S_1_N    101   0.001069b47_S_1_N    99   0.001079b1_S_1_N     31   0.001119b1_C_1_N     28   0.002015a1_C_1_N    101   0.002210were selected (because of their low associated ?het? p) from the foldx subset data for the regression Aubque on L computed for ALL sixcombinations of Set x MoSS.b) to get all the fold x subset Aubque on L data for all combinationsof Set x MoSS, we obviously had to first regress c on (e,u,u*e,u^2) ateach Len x Set x MoSS x Fold x Subset.Call this entire set of underlying data for c on (e,u,u*e,u^2) the?Rubq-base?, and instead of the computing the regression Aubque on Lover the entire Rubq-base, compute the regression ueSlope on (ubar,ebar) over the entire Rubq-base , where:i) ueSlope is the slope of the u*e term in c on (e,u,u*e,u^2);ii) ubar is the mean of ?u? (=u/(1+u) at each L and ebar is the meanof ?e? at each L.From each computation of ueSlope on (ubar, ebar) we have a pair ofslopes with a pair of associated probabilities, and therefore acrossall combinations of Set x MoSS x Fold x Subset, we have 72 such pairsof probabilities, or 144 probabilities in all.DISREGARDING Fold and Set, divide these 144 probabilities into fourgroups:36 at subset S, Method N36 at subset C, Method N36 at subset S, Method R36 at subset C, Method RSort each of these groups independently (lowest to highest p), andthen pair off elements of these four groups as follows:pair off the 36 from S,N with the 36 from C,N by corresponding rank(from the sort of each group)pair off the 36 from S,R with the 36 from C,R by corresponding rank(from the sort of each group)(Note (!!!!) that these pairings are DIFFFERENT (!!!) from thepairings of (S,N) with (S,R) and (C,N) with (C,R) which I presented inmy post of 12/13@12:33.)You will then have these two tables of paired p?s (and the associatedplot ?done your way?, which I?ve sent offline):SN,CN0.004293565,0.0001478680.009398,0.0002354070.019790086,0.0025762170.021645402,0.0208544860.041148681,0.0239190.056848093,0.0411209640.169920851,0.0424725960.236373,0.0597940.248019846,0.0799395240.277783068,0.0872681760.281488299,0.131259940.287886,0.174899240.299769,0.1807247630.299875026,0.1850426140.360314613,0.2077850970.370746358,0.211971450.406029587,0.2281762270.43289,0.2522421250.465398176,0.2752968780.482382234,0.3051349990.530897822,0.3093884420.559333624,0.3321122920.626424347,0.3610245140.702399,0.417803340.741387901,0.4234320220.768317356,0.4768182760.820922877,0.5421450.831159936,0.5590982890.832584062,0.5819603150.88900441,0.6196271050.893789589,0.6462651730.894253162,0.747177560.935126553,0.7575304160.977748076,0.8841190.980182674,0.9008674290.984220184,0.938430375SR,CR0.000503944,0.000119820.00118415,0.0122145730.041027523,0.0291339440.052112332,0.0489361380.054021335,0.057647610.057693811,0.058658960.068659527,0.0641823050.083710757,0.0883764060.094021303,0.1074738050.130456898,0.1476828730.21540961,0.1623924780.236780945,0.1817594330.236936513,0.2018473470.269875322,0.2104397360.294476424,0.2263053550.315561395,0.2270387840.319462902,0.2556991970.327971706,0.2888649350.463861812,0.3020351390.479255866,0.3121646680.564392402,0.3884479220.577382726,0.3974165240.579430243,0.4341826010.588970805,0.4382802240.61542756,0.5161287330.629984706,0.6141307750.698570658,0.6759622120.719544247,0.6899509010.732798731,0.7357798950.813873971,0.7783923330.883957837,0.8002078720.888276157,0.8707298220.888377668,0.9111498310.917545651,0.935123930.977990461,0.9411623490.980356048,0.986071449So, depending on one?s ?IOT reaction? to the plot I?ve sent offlinefor the two tables above, one might be willing to say that in general,CN p?s plot significantly lower than CR p?s for equivalent SN?s andSR?s.And this result, assuming you?re willing to accept it, is extremelyimportant for the following reason.It says that regardless of dicodon set 1,2,3, the (S,N) subsets?evolved/were designed? (depending on your point of view ? heh hehheh) so that mutation away from these sets to (C,N) sets does NOTchange the predictive capacities of ubar and ebar in ueSlope on (ubar,ebar) as much as the predictive capacities of ubar and ebar in ueSlopeon (ubar, ebar)are changed by the mutation of (S,R) sets to (C,R)sets.Or, to boil that statement down even further, the result says that wehave found a (relative) INVARIANT UNDER MUTATION for (S,N) sets thatdoes NOT exist for (S,R) sets.  And the existence of this invariantstrongly suggests that the (S,N) subsets of dicodon sets 1,2,3 allevolved to keep certain thermodynamic properties of protein messasgesrelatively constant despite the mutation which these messages mustperforce undergo over time.Finally, apart from this empirical interpretation of the plot I?vesent off line, I have a ?feeling? that the facts above regardingueSlope on (ubar,ebar) must be related somehow to the facts we?ve beendiscussing regarding Aubqe on L.  But if you agree, then the ball isnow in your court for the obvious reason that I have neither theknowledge nor experience nor statistical brain-power to determine ifueSlope on (ubar,ebar) and Aubqe on L are related, and if so how ...
```