4 DISCUSSION

It has been demonstrated that amino acids that possess reactive functional groups (acidic, basic, sulfur-containing, hydroxyl) are more affected by pigment interferences (in the ECF procedure) and exposure to heat and light than are the alkyl and imino-substituted amino acids. Thus, in schemes for identification of proteins that are based on absolute or relative concentrations of amino acids (Keck and Peters 1969; White 1984; Pancella and Bart 1989; Halpine 1992; Grzywacz 1994; Ronca 1994), greater emphasis should be placed on those amino acids with more stable functional groups than on those with more reactive groups.

With respect to the concentrations of amino acids in acid hydrolysates, glue films tended to be more stable than egg yolk under identical conditions of heat and light exposure. This difference is due in part to the fact that glue has a high content of stable amino acids and correspondingly lower levels of easily photooxidized amino acids (such as histidine, tyrosine, and the sulfur-containing amino acids methionine and cysteine). In contrast, the chemical composition of egg yolk promotes photo-oxidation and radical-induced decomposition (Karpowicz 1981; Davies et al. 1987). Egg yolk has a much lower proportion of stable amino acids and higher concentrations of reactive amino acids (methionine and cysteine) that cause egg yolk films to be more susceptible to photo-oxidation. In addition, photo-induced oxidation of the lipid fraction of egg yolk results in the formation of peroxy, alkoxy, and lipid free radicals that can also react with egg proteins (Karpowicz 1981).

Hydrolysates of light-aged glue paint films contained higher concentrations of isoleucine than the corresponding unexposed paints. A possible explanation for this result is that clusters of bulky alkyl groups, such as isoleucine, present a steric hindrance to hydrolysis, resulting in reduced isoleucine yields from hydrolysates of fresh, unaged proteins (Pellett 1981; Pickering and Newton 1990). Aging causes denaturing and partial disruption of the protein structure (Karpowicz 1981), exposing the alkyl group clusters to the action of aqueous acid, thereby causing improved hydrolysis yields. Another explanation for the higher concentration of isoleucine in aged samples is that a species formed during aging may coelute with isoleucine. GC-MS could be used to test this hypothesis but was not employed in this study.

Regarding the estimation of protein content in test paint samples, the GC results agreed reasonably well (to within � 25%) with theoretical estimates based on elemental analysis (Bergquist 1981) and the known compositions of the paint test samples. Certain factors contributed to the success of the protein content estimates, such as minimizing the number of sample transfer steps and correction of hydrolysis yields through the use of a rabbit skin glue reference standard. In addition, the availability of an ultramicrobalance permitted micro-samples of paint to be weighed with high accuracy. These data should, however, be considered only as approximations, because many factors can have unforseen effects on the weight percent results (such as long-term aging effects, organic matrix effects, and pigment interferences).

In general, the samples from objects contained somewhat less protein than the test paints. Aging certainly is responsible for loss of amino acids in the samples from objects. Also, in removing paint samples from objects, there is always the likelihood that particles may be inadvertently extracted from other layers that contain little or no protein but that contribute to the total sample weight, such as varnish and wax relining adhesive.

Nevertheless, the estimates of protein content in paint from objects of art were much lower than the ion chromatography results reported by Keck and Peters (1969). In this article the average protein content was reported to be 45% for animal glue–based paint and 20% for egg yolk tempera paint. These data have been cited in other studies as typical protein contents for tempera paint and were used to estimate sample weights in HPLC studies (Halpine 1992). However, from an inspection of other results reported in this article, there may be adequate reason to suspect the accuracy of these data. For example, a sample of egg yolk tempera paint was found to contain 35% protein. However, unpigmented dried egg yolk contains less than 32% protein, as determined by elemental analysis (Bergquist 1981). In another example, it was reported that a sample of ground from the 14th century contained 92% protein, a percentage so high as to indicate that the ground is nearly pure glue with almost no gypsum, a composition that it is extremely unlikely. No explanation for these anomalous results was provided.