Skip to "table S4a" for the actual mutations.

"Directed evolution of ionizing radiation resistance in Escherichia coli k-12"
https://pmc.ncbi.nlm.nih.gov/articles/PMC2725583/

We have generated extreme ionizing radiation resistance in a relatively sensitive bacterial species, Escherichia coli, by directed evolution. Four populations of Escherichia coli K-12 were derived independently from strain MG1655, with each specifically adapted to survive exposure to high doses of ionizing radiation. D37 values for strains isolated from two of the populations approached that exhibited by Deinococcus radiodurans. Complete genomic sequencing was carried out on nine purified strains derived from these populations. Clear mutational patterns were observed that both pointed to key underlying mechanisms and guided further characterization of the strains. In these evolved populations, passive genomic protection is not in evidence. Instead, enhanced recombinational DNA repair makes a prominent but probably not exclusive contribution to genome reconstitution. Multiple genes, multiple alleles of some genes, multiple mechanisms, and multiple evolutionary pathways all play a role in the evolutionary acquisition of extreme radiation resistance. Several mutations in the recA gene and a deletion of the e14 prophage both demonstrably contribute to and partially explain the new phenotype. Mutations in additional components of the bacterial recombinational repair system and the replication restart primosome are also prominent, as are mutations in genes involved in cell division, protein turnover, and glutamate transport. At least some evolutionary pathways to extreme radiation resistance are constrained by the temporally ordered appearance of specific alleles.



A survey of bacteria and archaea identifies 11 phyla that contain species with unusually high resistance to the lethal effects of ionizing radiation (IR). These phyla are not closely related to each other and do not share a common lineage, and all include genera that are considered radiosensitive (9). The existence of so many unrelated and isolated radioresistant species in the phylogenetic tree argues that the molecular mechanisms that protect against IR-induced damage evolved independently in these organisms, suggesting that at least some species have the capacity to acquire radioresistance through evolutionary processes if they are subjected to appropriate selective pressure.

The first of these species to be discovered, and the best studied to date, is the bacterium Deinococcus radiodurans. The molecular basis of the extraordinary radioresistance of Deinococcus has not been elucidated, but well-constructed proposals abound. Radioresistance has variously been attributed to the condensed structure of the nucleoid (29, 40, 56), the elevated levels of Mn ion present in the cytosol as a mechanism to control protein oxidation (11, 12), a specialized RecA-independent DNA repair process (54), and other species attributes (9). Radioresistance in Deinococcus is probably mechanistically related to desiccation resistance derived from evolution in arid environments (37, 45), although this may not be the origin of the phenotype in all relevant species (9).

An understanding of the genetic underpinnings of bacterial radiation resistance holds promise for yielding insights into the mechanistic basis of radiation toxicity, along with the potential for new approaches to facilitate recovery from radiation injury in other organisms, including humans. To better define the genetic, biochemical, and physiological characteristics most important for radioresistance, we employed a strategy to allow the cells to inform us. In brief, we generated radioresistant variants of radiosensitive bacteria and defined the genetic changes underlying the new phenotype.

In 1946, Evelyn Witkin established that it was possible to increase the resistance of Escherichia coli B to DNA damage (50). She exposed cultures to high doses of UV light, killing most of the population and selecting for variants better able to tolerate UV. In the 6 decades since the Witkin report, additional investigators have repeated this result, demonstrating that iterative cycles of high-dose exposure to a DNA damaging agent can heritably enhance a culture's ability to tolerate that DNA damaging agent. Increases in IR resistance have been reported for E. coli (17), Salmonella enterica serovar Typhimurium (14), and Bacillus pumulis (44), organisms that are otherwise considered radiosensitive. Davies and Sinskey (14) showed that for S. enterica serovar Typhimurium LT2, the number of cycles of exposure and recovery correlates with the level of radioresistance achieved. After 84 cycles, they generated a strain displaying inactivation kinetics similar to that of Deinococcus radiodurans, with a D10 value (the dose needed to inactivate 90% of the population) 200-fold higher than that of the parental strain.

For this study, we expanded on these earlier studies by independently generating four IR-resistant populations of Escherichia coli K-12 MG1655 (4). Our effort included an important innovation relative to the earlier studies—we characterized the evolved populations with an experimental program that included the complete genomic resequencing of multiple strains purified from three of the populations, taking advantage of new sequencing technologies. The result is an increasingly detailed data set—based on a single robust model system—that allows us to (i) explore the molecular basis of radiation resistance in bacteria and (ii) test current hypotheses and search for novel mechanisms of radiation resistance.



Directed evolution of IR resistance in Escherichia coli.
IR-resistant populations of MG1655 were selected by subjecting cultures derived from a single colony isolate (referred to as the founder) to 20 iterative cycles of irradiation and outgrowth. The length of each exposure was adjusted to kill >99% of the population, with this dose increasing from 2,000 Gy for the first cycle to 10,000 Gy on the last cycle. Surviving cells were harvested postirradiation and allowed to recover in rich medium until reaching stationary phase; this population then served as the source of the next culture to be irradiated. As predicted by earlier studies of bacterial evolution (16, 19, 28), the radioresistance of the successively irradiated population increased in a stepwise manner (Fig. 1), suggesting that acquisition of this phenotype requires several genomic alterations. In the first trial, after 20 cycles, an evolved population with enhanced radiation resistance was generated and designated population IR-1-20. (For convenience, the bacterial populations obtained after each cycle are identified by selective agent, trial, and cycle. IR-1-20 identifies the population recovered during our first trial after 20 cycles of exposure to IR and outgrowth.) A survey of 62 purified strains derived from the population (all were single colony isolates generated using procedures designed to avoid the selection of genetically identical strains) exhibited an increase in survival of 1,000- to 5,000-fold when subjected to irradiation at 5,000 Gy; two colonies remained as sensitive as the founder. A radiation-resistant single colony isolate, designated CB1000, was chosen for further analysis. This culture was grown for 100 generations without selection, and the phenotype was maintained, with no measurable loss of IR resistance.


This selection protocol was repeated independently three more times. Each replicate was initiated using an isolated colony derived from a frozen stock of the founder. The outcomes of these additional trials were the same, resulting in the isolation of three more radioresistant populations. These were designated populations IR-2-20, IR-3-20, and IR-4-20. One single colony isolate was taken from each of these populations, generating purified strains designated CB2000, CB3000, and CB4000. The founder, like other E. coli K-12 strains, is quite sensitive to IR; exposure to 3,000 Gy gamma radiation (60Co; 19 Gy/min) reduced the viability 4 orders of magnitude compared to that of the unirradiated culture (Fig. 2). The D37 value for CB1000 was 1,100 Gy, whereas the D37 value for CB2000 and CB3000 was 2,000 Gy—approximately threefold less than the D37 value measured for actively growing cultures of Deinococcus radiodurans R1 (41). The D37 value for the founder was 730 Gy. Higher doses of IR revealed a major improvement in resistance. CB1000, CB2000, and CB3000 exhibited 1,500- to 4,500-fold increases in survival relative to the founder after exposure to 3,000 Gy (Fig. 2). CB4000 was approximately 10-fold less radioresistant than the other isolates.


Characterization of evolved strains.
CB1000, CB2000, and CB3000 were studied further. The growth rates of these isolates in rich medium were unaffected by the changes that conferred radiation resistance relative to growth of the founder (Fig. 3A). In minimal medium, CB1000 and CB2000 exhibited growth curves identical to that of the founder (Fig. 3A); CB3000 did not grow in minimal medium due to the presence of a mutation affecting arginine biosynthesis (see below). All three strains exhibited an approximately 10-fold increase in survival after UV irradiation (Fig. 3B) relative to that of the founder. There were modest increases in resistance to mitomycin C for CB1000 and CB2000, while CB3000 exhibited no change in mitomycin C resistance (Fig. 3C).


Microscopy of DAPI (4′,6-diamidino-2-phenylindole)-stained cells revealed no obvious alterations in morphology, and nucleoid shape did not change (see Fig. S1 in the supplemental material). Cells from Deinococcus radiodurans, stained and visualized using identical methods, reveal a highly condensed, toroid-like nucleoid structure (56).

Daly and colleagues proposed that accumulation of Mn ions in radiation-resistant species facilitates recovery from radiation injury (12), specifically moderating damage to cellular protein components (11). In our trials, there were no significant changes in measured metal content in any of the four radioresistant isolates relative to the founder (see Table S1 in the supplemental material). The measured Mn/Fe ratio was approximately 0.07 for all unirradiated strains. For CB1000 and the founder, there were no significant changes in metal content when the cells were subjected to irradiation at 600 Gy (CB2000, CB3000, and CB4000 were not tested). When cells were examined during exponential growth in rich medium, the DNA concentration per cell, approximately 5 nM, did not differ from that of the founder. The total cellular content of deoxyribonucleotides and protein also did not vary in the three isolates tested (see Table S2 in the supplemental material).

The radiation resistance and genome recovery observed in our isolates could have arisen from passive protection of cellular DNA or from active DNA repair processes. We directly examined the rate of DNA degradation. Strains CB1000, CB2000, and CB3000—with the founder strain used as a control—were irradiated (137Cs [7.8 Gy/min]), and samples were taken after exposure to increasing doses of radiation. The genomic DNA was subjected to digestion with NotI, followed by PFGE. All three of the evolved strains derived from the founder exhibited genomic degradation that was at least as great as that observed for the founder (Fig. 4), indicating the presence of potential new enzymatic processes contributing to genomic degradation in the evolved strains. There are no apparent new mechanisms for the passive protection of genomic DNA in the evolved strains. We examined protein oxidation directly by assaying for protein carbonylation spectrophotometrically and by immunodetection of 2,4-dinitrophenylhydrazine-derivatized protein carbonyls. There were no detectable differences noted between the founder strain, CB1000, CB2000, and CB3000 (data not shown).


We also examined the recovery of genomic DNA from CB1000 and CB2000 after exposure to 5,000 Gy of 137Cs (7.8 Gy/min) and compared this with the fate of genomic DNA in the founder strain. The acquired phenotype was evident in this experiment (Fig. 5). The DNA from the founder did not recover after this dose of radiation over a 9-hour time course. Even the fragmented DNA appeared to disappear with time, probably reflecting nuclease degradation. No growth of the irradiated cell culture was evident over a period of 9 h. In contrast, the genomic DNAs from CB1000 and CB2000 were repaired, with the normal NotI banding pattern clearly visible in the pulsed-field gel after 2 hours in both cases. Visible genome restoration appeared to peak after 3 to 4 h. The increase in genomic DNA was not due to growth of undamaged survivors. No increase in bacterial cell mass was evident in the cultures until 8 h and 5 h for CB1000 and CB2000, respectively. These results indicate that the genomic DNA was repaired well before the initiation of normal genome replication and cell division.

We tested several of the isolated strains for a mutator phenotype. Previous studies with E. coli point to two potentially significant contributors. (i) IR has the potential to introduce mutations through DNA damage, with mutations arising during DNA synthesis on a damaged template by the replicative polymerase or one of several specialized translesion polymerases (5, 20, 51). (ii) E. coli populations harbor individuals with a mutator phenotype, i.e., cells that lack one or more of the components necessary for high-fidelity DNA replication (33, 39). The high spontaneous mutation frequency associated with mutators serves as a source of genetic variation that is acted on during selection. The mutator phenotype eventually reverts, and if the resulting strain carries an adaptive mutation, it survives. CB1000, CB2000, CB3000, and CB4000 were all tested to determine their status as mutators by measuring spontaneous rates of mutation to rifampin (rifampicin) resistance (39). Relative to the founder, no increase in the frequency of Rifr mutations was noted for any of the strains, and the observed rates were well within reported ranges for wild-type (nonmutator) strains of E. coli (E. Wood, unpublished data).

Genetic changes in evolved strains.
Twenty additional isolates were derived independently from population IR-1-20, designated CB1012 to CB1031, and set aside for further analysis. The genomes of the founder, CB1000, CB2000, CB3000, and six of the additional isolates from population IR-1-20 were resequenced using one or both of two complementary methods. First, CGS, a microarray-based technology developed by NimbleGen Systems, Inc. (1), was used to detect mutations in the founder, CB1000, CB2000, and CB3000. Second, direct sequencing using an Illumina genome analyzer was used to sequence the entire genomes of CB1000, CB2000, and the six additional isolates from IR-1-20. Data acquired by CGS were extensively validated (see the supplemental material). Table S3 in the supplemental material summarizes the number of contigs and the amount of the 4,639,675-bp reference genome that was covered by the various assemblies derived from Illumina sequencing. In general, the two methods agreed well. For the strains sequenced using both technologies (CB1000 and CB2000), Illumina sequencing confirmed all mutations that had previously been found by the microarray-based CGS. Genomic alterations missed using CGS (and detected by Illumina sequencing) were on the order of 5 to 10%, similar to the levels reported in other, similar studies (22). All mutations found uniquely in CB1000 and CB2000 by Illumina sequencing were confirmed by direct Sanger sequencing methods. The combination of approaches provides confidence that we have detected most, if not all, of the genomic changes in the sequenced strains.

Genomic alterations detected in all sequenced strains by all methods are summarized in Tables S4 and S5 in the supplemental material (single nucleotide polymorphisms and small [≤3-bp] insertions/deletions are catalogued in Table S4, and larger deletions and insertions are listed in Table S5). The founder strain was independently subjected to CGS. In addition, we searched the founder for any mutations present in all sequenced strains by direct Sanger sequencing. Seven genomic alterations were discovered in the founder relative to the published MG1655 genomic sequence (see Table S6 in the supplemental material). These are not included in Tables S4 and S5 in the supplemental material.

In the overall data set, the seven complete genomic sequences from population IR-1-20 provide both documentation of the mutational diversity in this population and an opportunity to detect mutations that are especially abundant. The sequences of CB2000 and CB3000 allow a comparison to strains derived from populations that evolved independently from IR-1-20.

The total number of genomic alterations in a given evolved strain ranged from 40 to 71. Mutation classes are summarized in Table 1. Between 50 and 60% of the differences were nonsynonymous mutations affecting the sequences of protein or tRNA products. Synonymous mutations are included in the report to complete the picture of the mutational landscape, since some of these may affect gene regulation or processes such as RNA folding or RNA-protein interactions. Base substitutions predominated; 97.5% of the detected genomic alterations fell into this category. Approximately 83% of the base substitutions were either GC→AT or AT→GC transitions (Table 1), consistent with previous reports that detailed the pattern of mutations generated when E. coli K-12 strain AB1157 was irradiated using 60Co (52). A number of insertions and deletions were detected. All of the characterized strains exhibited a deletion of the e14 prophage. This was the only universal genomic alteration (relative to the MG1655 sequence database) not also detected in the founder. CB1000 contains a 3-bp in-frame deletion in the fruB (b2169; included in Table S4 in the supplemental material) coding sequence, and CB3000 carries a 93-bp deletion within argC (b3958; included in Table S5 in the supplemental material) that renders the cell an arginine auxotroph. Evidence of transposition by the IS1 insertion sequences (43) was detected in multiple isolates from population IR-1-20. In CB1000, novel IS1 insertions were found in yaiP (b3063) and fimE (b4313). The fimE gene was also targeted with an IS5 insertion in CB1031 (see Table S5 in the supplemental material).


In Table 1, mutations within genes have also been sorted with respect to their effects on the coding sequence, being either synonymous or nonsynonymous. The ratio of the rate of nonsynonymous alterations (dN) to the rate of synonymous changes (dS) is often used as one indicator of selection pressure in a gene, with positive selection implied when dN/dS is >1 (27, 42, 53). Whereas the number of mutations within a single gene is generally small, the overall pattern seen for all mutations in all of the sequenced strains (dN/dS = 2.38) suggests positive selection for resistance to IR. For individual sequenced strains, the dN/dS ratio observed over all genes ranges from 1.24 (CB1014) to 4.67 (CB1012).

Although the sequencing technologies employed have the potential to miss much larger genomic rearrangements that invert or move substantial segments of the genome, we found no evidence for such changes. Genomic DNAs from CB1000, CB2000, and CB3000 were subjected to digestion with either NotI or XbaI, followed by PFGE (see Fig. S2 in the supplemental material). The banding patterns for the radioresistant strains are identical to that of the founder, except that the deletion of the e14 prophage can be seen in the NotI digest. A band of approximately 96 kbp for the founder is reduced in size by the expected 15 kbp corresponding to e14 for the evolved strains.

With the exception of the deletion of the e14 prophage, the mutational landscapes of all sequenced isolates from three different evolved populations are quite distinct. In particular, there are few recurrent mutations evident between the isolates derived from population IR-1-20 and the independently evolved CB2000 and CB3000 strains. These results suggest that there are multiple mechanisms that can contribute to radiation resistance and multiple evolutionary pathways leading to this phenotype. However, some clear patterns also emerge, as described below.

Genetic changes that contribute to IR resistance.
To identify genomic alterations that contribute to the radiation resistance phenotype, we focused on the purified strains derived from population IR-1-20. First, we examined Tables S4 and S5 in the supplemental material to identify genes or processes that represented the most common mutational targets in this evolved population. With this broad coverage, patterns become easier to discern and are likely to be meaningful. In the following discussion, note that in most cases (exceptions are noted later) we do not know if particular mutations inactivate, enhance, or otherwise affect the activity of the gene product. The strains reveal a diverse mutational landscape in which 382 of the detected mutations occur only once. Thus, mutations that are enriched—appearing in multiple sequenced strains from population IR-1-20—are relatively rare. These more common mutations may have been positively selected and thus significant. In some cases, we then isolated individual genetic alterations in otherwise wild-type backgrounds to better assess their individual contributions to IR resistance.

In Table 2, we list the genes where mutations appear in at least three of the seven sequenced isolates derived from IR-1-20 or where a cluster of mutations are evident in genes with closely related functions. In some cases, patterns are reinforced by mutations appearing in the independently evolved strains CB2000 and CB3000. Looking only at the isolates from IR-1-20, a number of prominent mutational targets are evident. Common mutations occur in recA (4/7 isolates, with an additional allele appearing in a fifth strain), ruvB (3/7 isolates, including two alleles), dnaT (4/7 isolates), gltS (4/7 isolates), bglH (3/7 isolates, including two different alleles), yjgL (3/7 isolates, including two alleles), and ylbE (3/7 isolates). Additional clusters of mutations are seen in the ftsW/ftsZ genes and the clpP/clpX genes. The RecA protein is a central player in double-strand-break repair (7, 29). RuvB contributes to the same process (6, 8). DnaT is part of the replication restart primosome, operating downstream of RecA and RuvB in double-strand-break repair (34, 35). The FtsW and FtsZ proteins are involved in cell division (23). The ClpP and ClpX proteins are components of a proteolytic system responsible for the turnover of at least 60 E. coli proteins, including chaperones, proteins involved in energy production, transcriptional regulators, and others (3, 18). GltS is a membrane-bound glutamate transporter (15, 48). BglH is an outer membrane porin for β-glucosides (2). YjgL and YlbE are predicted proteins about which little is known. All of the 19 different mutations detected within the genes featured in Table 2 are nonsynonymous.

Table 2:
**TABLE 2. – Mutations common in evolved strains**

Mutations common in evolved strains

| Gene and functional category | Locus tag | Nucleotide position of mutation | Nucleotide in reference allele | Nucleotide in mutant allele | Change |  |  |  |  |  |  |  |  |
|-----------------------------|-----------|--------------------------------|------------------------------|----------------------------|--------|--|--|--|--|--|--|--|--|
| CB1000 population |  |  |  |  |  |  |  |  |  |  |  |  |  |
| CB2000 | CB3000 |  |  |  |  |  |  |  |  |  |  |  |  |
| CB1000 | CB1012 | CB1013 | CB1014 | CB1015 | CB1024 | CB1025 |  |  |  |  |  |  |  |
| **Recombinational DNA repair** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| ruvB | b1860 |  |  |  |  |  | 1943223 |  |  |  | T | C | D52G |
| ruvB | b1860 |  |  | 1943323 |  |  |  | 1943323 |  |  | C | A | D19Y |
| recA | b2699 |  |  |  |  |  | 2820924 |  |  |  | C | A | A289S |
| recA | b2699 |  |  | 2820962 | 2820962 | 2820962 |  | 2820962 |  |  | T | G | D276A |
| recA | b2699 |  |  |  |  |  |  |  | 2820963 |  | C | T | D276N |
| **Replication restart primosome** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| priA | b3935 |  |  |  |  |  |  |  |  | 4123174 | C | T | V553I |
| priC | b0467 | 489549 | 489549 |  |  |  |  |  |  |  | A | G | L162P |
| dnaT | b4362 |  |  | 4599105 | 4599105 | 4599105 |  | 4599105 |  |  | G | A | R145C |
| dnaB | b4052 |  |  |  |  |  | 4262560 |  |  |  | T | C | L74S |
| dnaB | b4052 |  |  |  |  |  |  |  | 4262578 |  | C | A | P80H |
| **Cell division** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| ftsW | b0089 |  |  |  |  | 98506 |  |  |  |  | A | G | E34G |
| ftsW | b0089 |  |  | 99207 |  |  |  | 99207 |  |  | A | G | M268V |
| ftsZ | b0095 |  | 106214 |  |  |  |  |  |  |  | G | A | D303N |
| **Proteolysis** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| clpP | b0437 | 456127 | 456127 |  |  |  |  |  |  |  | A | G | Y75C |
| clpP/clpX<a href="#t2fn1"><sup>a</sup></a> | b0437/ b0438 |  |  |  |  |  |  |  | 456637 |  | G | A | - |
| clpX | b0438 |  |  |  | 457803 |  |  |  |  |  | A | G | Y384C |
| **Glutamate transport** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| gltS | b3653 |  |  | 3825922 | 3825922 | 3825922 |  | 3825922 |  |  | A | G | V255A |
| **Miscellaneous** |  |  |  |  |  |  |  |  |  |  |  |  |  |
| ylbE<a href="#t2fn2"><sup>b</sup></a> | b4572 | 547836 |  |  |  |  |  |  | 547836 | 547836 |  | G | K85E |
| yjgL | b2453 | 4474024 |  |  |  |  |  |  |  |  | A | G | N188D |
| yjgL | b2453 |  |  |  | 4475030 |  |  |  | 4475030 |  | A | G | D523G |

<sup>a</sup> This mutation is intergenic.
<sup>b</sup> This is a one‑nucleotide insert that restores the full‑length reading frame of an annotated pseudogene.

It is notable that for four of these genes, recA, ruvB, bglH, and yjgL, there are two different mutant alleles evident among the seven isolates. Given that only 1 to 2% of the loci in the sequenced strains were modified during their evolution, the probability of randomly generating different alleles in the same locus is vanishingly small. This observation reinforces the idea that changes in each of these loci provide the cell with a selective advantage.

All of the strains derived from IR-1-20 are closely related. The presence of some shared genetic changes permits a phylogeny to be constructed based on genome sequences. This was done for the strains derived from population IR-1-20 and is shown in Fig. 6. In our initial analysis of these strains, we made the assumption that the closer two related IR-resistant strains are to each other, the more likely they are to share the same mechanisms of protection from IR. In a situation where the strains are very closely related, they are likely to carry identical genetic changes, and this overlap may identify those changes most relevant to IR resistance. Examination of CB1014 and CB1015, close relatives that share 10 identical base substitutions, illustrates this approach. Of these 10 changes, 6 result in synonymous changes that will not affect protein function and are unlikely to affect IR resistance. The four nonsynonymous mutations alter the amino acid compositions of the RecA, DnaT, GltS, and RimO proteins. The phylogeny presented in Fig. 6 indicates that among the sequenced strains, CB1013 and CB1025 most recently diverged from CB1014 and CB1015. CB1000 and CB1012 share 26 identical base substitutions—more than any other pair of isolates examined. CB1013 and CB1025 share 20 identical base substitutions. CB1013 and CB1025 also share three modifications with the CB1014-CB1015 pair, namely, the changes in RecA, DnaT, and GltS. The phylogeny reinforces the idea that different cells in the evolving population took different paths to radiation resistance.

FIG. 6.
FIG. 6.

Open in a new tab
Phylogeny of seven fully sequenced strains from the IR-1-20 population. Phylogeny was determined using the single nucleotide mutations that were shared among the different strains.

The parallel presence of mutations affecting RecA, DnaT, and GltS in four different purified strains has two possible explanations, as follows: (i) the modified proteins confer a selective advantage to the individuals in which they are expressed, providing protection against the lethal effects of IR (possibly acting together); or (ii) the modifications are neutral, and their appearance within the population is a manifestation of their clonal expansion from a mutational event that occurred early in the evolution of the population.

Table S7 in the supplemental material places all of the genes that carry nonsynonymous mutations in the three radioresistant strains into functional categories based on the “MultiFun” classification scheme developed by Serres and Riley (47). Examination of this table reveals that one-third to one-half of the mutations are in genes of unknown function. Although only a few of the mutations occur in genes encoding known DNA repair proteins, mutations in genes of this category are overrepresented in the genome by a factor of about 2 (Fig. 7).

FIG. 7.
FIG. 7.

Open in a new tab
Occurrence of mutations in particular gene classes (MultiFun) relative to the fraction of genes present in each genomic category. Although the total number of genes in each category shown is different (see Table S7 in the supplemental material), these numbers are effectively normalized to 1.0 in this analysis. The occurrence of mutations in particular gene classes was calculated as the total number of mutations in a particular category divided by the total number of scored mutations in all sequenced strains (if a particular mutation appeared in four different sequenced strains, then it was counted as four scored mutations). This ratio was divided by the fraction of the total genes present in that particular category. The results are shown by the light gray bars. If mutations are under- or overrepresented in a particular category, the calculation will yield values of <1.0 or >1.0, respectively. The MultiFun categories are as follows: 1, metabolism; 2, information transfer; 3, regulation; 4, transport; 5, cell processes; and 6, cell structure. The subgroup 2.1 includes genes involved in DNA replication, recombination, and repair.

Loss of e14 increases resistance to IR.
We set out to determine directly if some of the common mutations contributed substantially to the acquired phenotype. We isolated the IS1 insertion in the fimE gene in an otherwise wild-type background, but this genomic alteration had no evident effect on IR resistance (data not shown). A much different result was obtained when we took a closer look at the deletion of the e14 prophage. This prophage is known to undergo deletion in response to an induction of the SOS response (21), indicating that the SOS response had been initiated at some point (probably repeatedly) in the protocols leading to our four isolates. Deleting e14 from the founder increased the IR resistance of the resulting strain approximately eightfold at 3,000 Gy (Fig. 8A), suggesting that loss of this cryptic phage contributes to IR resistance. The e14 prophage expresses a toxic inhibitor of several E. coli metabolic processes, called Lit (25, 26, 38). Its absence, or the absence of some other toxic factor produced by the prophage, may explain the increase in radiation resistance in the e14 deletion strains.

FIG. 8.
FIG. 8.

Open in a new tab
Effects of selected mutations on survival of E. coli. Cell cultures were irradiated to 3,000 (A) or 2,000 (B) Gy and plated to measure survival as described in Materials and Methods. In panel A, strain EAW77 contains the e14 deletion in an otherwise wild-type background. Results in panel A were obtained with a 60Co irradiator (19 Gy/min); results in panel B were obtained with a 137Cs irradiator (7.8 Gy/min).

A role for modified RecA in IR resistance.
As part of a broader survey to determine if other mutations (mostly mutations present in CB1000) were present in the population (Table 3), 14 additional strains purified from population IR-1-20 were surveyed for the presence of the D276A alteration in RecA. This recA mutation was observed in 11 of these strains. Furthermore, additional RecA alleles were detected: CB1024 expresses RecA A289S, and CB2000, which was isolated from an independently derived population, encodes RecA D276N. The appearance of a recA allele in so many IR-resistant isolates (modified RecA proteins appear in 17 of 23 IR-resistant strains examined), coupled with the appearance of multiple alleles including a different change at the same nucleotide in CB2000, strongly argues that these modifications to RecA contribute to IR resistance. To test this possibility, the RecA D276A and A289S alleles were moved into the founder. In both cases, the change resulted in a small but significant increase in IR resistance in the resulting strain relative to that of the founder (Fig. 8B). The A289S allele was consistently the more effective of the two in its enhancement of radiation resistance. Once again, the recA mutations are evident contributors to radiation in the strains in which they occur, but they do not explain the entire phenotype. We note that the positive effects of these recA alleles are dependent on the presence of an intact recX gene in its normal location immediately downstream of recA. No effects of the recA alleles on IR resistance were observed in some early trials using a recA gene replacement procedure that left a genomic scar inactivating recX. To illustrate the importance of RecA to the overall repair process, we deleted recA from CB1000 and demonstrated that the resulting strain was as sensitive to IR as a recA derivative of MG1655 (data not shown). Along with the e14 results, the recA mutations clearly telegraph a situation in which multiple contributing mechanisms are present. This in turn is consistent with the multiple steps in the increase in radiation resistance in the populations monitored and shown in Fig. 1.

TABLE 3.
Survey of mutations present in independent evolved isolatesa

Gene	Presence of allele
CB1000	CB1012	CB1013	CB1014	CB1015	CB1016	CB1017	CB1018	CB1019	CB1020	CB1021	CB1022	CB1023	CB1024	CB1025	CB1026	CB1027	CB1028	CB1029	CB1030	CB1031
recA	−	−	+	+	+	+	+	+	+	+	+	+	+	−	+	+	+	+	+	+	−
recB	+	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−
fimE	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	−	+	+	+	+	+
e14 prophage	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+	+
ygaH	+	+	−	−	−	−	−	−	−		−	−	−	−	−	−	−	−	−	−	−
clpP	+	+	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−	−
ybdL	+	+	−	−	−	−	−	−	−		−	−	−	−	−	−	−	−	−	−	−
Open in a new tab
a All strains listed were single colony isolates derived from the same population that gave rise to CB1000. All single nucleotide polymorphisms surveyed here were confirmed by direct Sanger sequencing methods. The e14 deletions and fimE insertions were confirmed by PCR analysis (see Fig. S3a and S3b in the supplemental material). The alleles tested were identical to those found in CB1000 (see Tables S4 and S5 in the supplemental material), except that the recA allele tested was that encoding the RecA D276A mutant protein. The symbols + and − indicate the presence and absence of the tested allele, respectively.

The RecA D276A and D276N proteins have both been purified. Both exhibit wild-type levels of DNA strand exchange and ATP hydrolytic activities in vitro (V. Petrova and M. Cox, unpublished data). There is no indication that these proteins have been inactivated or impeded in their normal recombinogenic functions in any way. Both D276 and A289 are located on the protein surface that defines the major groove of a RecA filament structure. We speculate that the mutations affect an as yet unidentified protein-protein interaction, possibly with the LexA protein.

Is there a role for the proteins that mediate replication restart in IR resistance?
Strains CB1013, CB1014, CB1015, and CB1025 all express DnaT R145C. DnaT is a component of the E. coli restart primosome, which includes PriA, PriB, PriC, DnaT, and DnaB. This complex of proteins is needed to reestablish replication forks after stalled forks are repaired by recombinational DNA repair (10, 24, 36). Mutations in other components of the restart primosome were observed. Among the IR-resistant strains whose genomes were sequenced, CB1000 and CB1012 carry an allele of priC, CB1024 and CB2000 alleles of dnaB, and CB3000 an allele of priA. In other words, every IR-resistant strain for which we have a complete genome sequence carries a mutation in one of the loci that encode the E. coli restart primosome, and four of the five proteins contributing to this complex are affected.

When the most common of the restart primosome alleles—the dnaT allele—was transferred to the founder, the resulting strain was substantially more sensitive to IR than the founder (data not shown). Given that four of the sequenced genomes carry this mutation, the genetic context must determine the effect of this dnaT allele on the radioresistance phenotype.

DISCUSSION
We generated four extremely radiation-resistant populations of Escherichia coli, all derived from the same MG1655 founder strain. The adaptations are generally specific for IR resistance. Characterization of these populations, including the complete genomic sequencing of nine strains independently isolated from them, provides information about the mechanisms underlying the acquired phenotype. As shown in Fig. 4, an enhanced capacity to promote recombinational DNA repair after extreme genomic degradation plays a substantial role in the IR resistance seen in these strains. Passive protection from damage inflicted by IR is not in evidence. Major mutational targets include the recA and ruvB genes and the genes encoding components of the replication restart primosome. All of these are involved in recombinational DNA repair. Multiple mutations are found in the clpP and clpX genes, encoding components of an important proteolytic system, and the ftsW and ftsZ genes, encoding proteins involved in cell division. Additional processes may contribute to radiation resistance, including those involving the gltS, bglH, yjgL and ylbE genes, the deletion of the e14 prophage, and perhaps other genes where contributing mutations appeared too late in the selection to become common in the population.

Evidence has been obtained that the e14 deletion and at least two of the recA mutant alleles contribute directly to radiation resistance. Whereas this begins to account for the acquired phenotype, these genomic alterations do not account for all of the improvement in IR resistance. These results argue strongly that multiple processes contribute to the acquired phenotype. Given the diversity evident in population IR-1-20 and the unique genomic alterations observed in isolates derived from other evolved populations, it seems likely that different cells in these populations may pursue often distinct pathways to IR resistance. This view is reinforced by the phylogeny in Fig. 6.

The results provide a strong case that an enhancement of recombinational DNA repair makes a major contribution to the acquired phenotype. Mutations in genes involved in this process occur at a high rate and are often prominent in the evolved population. As shown in Fig. 5, the evolved strains exhibited a much-improved capacity to reconstitute their genomes. The recA mutations make a clear positive contribution to the IR resistance phenotype, and three different recA mutant alleles were found within the nine strains that were sequenced in their entirety. Mutations were also found in another component of the recombinational DNA repair system, ruvB. It is possible, of course, that some of the other common mutations make an indirect contribution to recombinational DNA repair by favorably altering the cellular environment in which it is carried out.

The dnaT allele provides an example of apparent mutational epistasis. The presence of the dnaT allele does not adversely affect the overall IR resistance of the radioresistant strains in which it occurs. We must assume that the dnaT mutation cannot have appeared in the genome before acquisition of one or more compensating mutations permitting the dnaT strains to survive irradiation. In other words, the effect of the dnaT allele appears to be conditional, depending on the genetic background. Assuming that dnaT contributes to radioresistance, this result suggests that at least some of the steps in building an IR-resistant strain must occur in a temporal sequence. If a cell deviates from that sequence and creates the dnaT mutation before its compensating mutation, irradiation will select against that cell.

The other common mutations may signal additional mechanisms of IR resistance but may also contribute indirectly to the same repair process. The ftsW and ftsZ mutations may alter the regulation or timing of cell division, perhaps providing needed time for repair. The clpP and clpX mutations might slow the turnover of proteins needed for energy production, cell division, detoxification, and/or protein folding, enhancing the environment for repair. The gltS and bglH alterations may also change the cellular environment in which the repair occurs. Each of these sets of mutations will require more detailed analysis.

The newly robust capacity of these strains for genome reconstitution relies on both the RecF and RecBCD pathways for recombinational DNA repair. Inactivation of either the recB or recF gene in CB1000 eliminated much of the radiation resistance of that strain, although the sensitivity of the recB knockout strain was substantially greater (data not shown). Inasmuch as Deinococcus lacks homologues of the recB and recC genes, it is unlikely that the double-strand-break repair pathways used for genome reconstitution in the evolved E. coli strains faithfully replicate the pathways documented for Deinococcus (54).

The extreme adaptations to IR exposure exhibited by these strains are specific to IR. Whereas some of the strains exhibit improved resistance to other DNA damaging agents, those improvements are generally more modest and do not occur in every strain derived from the evolved populations. The adaptations also do not appear to reinforce prominent hypotheses put forward to explain radiation resistance in Deinococcus radiodurans. The evolved E. coli strains do not have unusually condensed nucleoids, a property of Deinococcus nucleoids highlighted by Minsky and colleagues (29, 40). There is also no indication of the presence of elevated levels of Mn ion or reduced levels of protein oxidation, as seen in Deinococcus (11). In both cases, the proposed mechanisms may still be applicable to IR resistance in Deinococcus. However, the results of the current study indicate that neither mechanism should be considered a universal requirement for extreme IR resistance. One major message of the present research is that IR resistance is a complicated phenotype with potentially many components. A focus on just one contributing mechanism is unlikely to yield a complete understanding of the phenomenon.

table s4a

Gene,Locus Tag,CB1000,CB1012,CB1013,CB1014,CB1015,CB1024,CB1025,CB2000,CB3000,Ref Allele,Mut Allele,Change,Mut Type,Multifun,Regulon,Footnote,,,,,,,,,,,,
yaaA,b0006,6114,"","","","","","","","",C,T,G115S,N,"",O ,"",dnaJ,b0015,14857,14857,"","","","","","","",C,T,G229G,S,2, 7.1,"",
insL-1,b0016,"","","","","","","",15781,"",-,T,V113C,N (+1),"","α",
ileS,b0026,"","","","","","","","",24764,T,C,Y791H,N,2, 7.1,"",
hepA,b0059,"","","","","",61526,"","","",A,G,M579T,N,2,"",
araB,b0063,69253,"","","","","","","","",C,T,V265M,N,1, 7.1,"",
sgrR,b0069,"","","","","","",77213,"","",C,T,L28L,S,4, 7.2,"",
leuB,b0073,"","","","","","","",81214,"",A,G,F248L,N,1, 7.1,"",
ftsW,b0089,"","","","",98506,"","","","",A,G,E34G,N,4, 5, 6, 7.3,"",
ftsW,b0089,"","",99207,"","","",99207,"","",A,G,M268V,N,4, 5, 6, 7.3,"",
ftsZ,b0095,"",106214,"","","","","","","",G,A,D303N,N,5, 7.1,"",
lpxC,b0096,"","","",107033,"","","","","",C,T,I158I,S,1, 6, 7.1,"",
hofC,b0106,"","",115115,"","","","","","",G,A,Q203*,N (ter),6, 7.3,"",
hofB,b0107,"","","",116428,116428,"","","","",G,A,T223T,S,4, 6,"",
dksA,b0145,"","","","","",160511,"","","",T,C,M31V,N,7.1,"",
dgt,b0160,"","","","","","","",179544,"",C,G,T102S,N,1, 7.1,"",
ispU,b0174,"","","","","","","",195256,"",G,A,S117S,S,1, 6, 7.1,"",
bamA,b0177,198849,198849,"","","","","","","",A,G,I307V,N,6, 7.4,"",
rcsF,b0196,"","","","","","","",219698,"",T,C,K99E,N,1, 3, 6,"",
metN / gmhB,b0199 / b0200,"","","","","","","",222810,"",G,T,-,I,"","",
mltD,b0211,"","","","","","",233097,"","",T,C,T286A,N,1, 2, 3, 7.1,"",
yafJ,b0223,"","","","","","","",244974,"",G,A,Q215Q,S,"","",
proA,b0243,"","","",261858,"","","","","",T,C,F377L,N,1, 7.1,"",
yagF,b0269,"","","","","","",284326,"","",C,G,G633G,S,"","",
yagR,b0284,"","","","","",299845,"","","",A,G,I104T,N,1,"",
yagW,b0290,"","","",305033,"","","","","",G,C,Q336E,N,"","",
yagX,b0291,"","","",306927,"","","","","",C,T,D543N,N,"","",
betT,b0314,"","","","","","",330267,"","",G,T,W526C,N,1, 4, 6, 7.3,"",
yahG / yahI,b0321 / b0323,"","","","","","","",339123,"",C,A,-,I,"","",
yahG / yahI,b0321 / b0323,"","","","","","","",339247,"",-,G,-,I (+1),"","",
codA / cynR,b0337 / b0338,"","","","","","","",356956,"",T,A,-,I,"","",
ryaiO,b0358,"",379791,"","","","","","","",T,C,R91R,S,7.4,"",
acpH,b0404,"","","","","","","","",423996,G,A,D48D,S,1,"",
tgt,b0406,"","","","","","","","",426104,A,G,K247K,S,2, 7.1,"",
clpP,b0437,456127,456127,"","","","","","","",A,G,Y75C,N,1, 3, 5, 7.1,"",
clpP / clpX,b0437 / b0438,"","","","","","","","",456637,G,A,-,I,"","",
clpX,b0438,"","","",457803,"","","","","",A,G,Y384C,N,1, 2, 7.1,"",
ppiD,b0441,"","","","","","","",462852,"",C,A,L571M,N,2,"",
cof,b0446,"","","","","","","",467098,"",C,T,L154F,N,1,"",
priC,b0467,489549,489549,"","","","","","","",A,G,L162P,N,2.1.1, 7.1,"",
aes,b0476,"","","","","","","","",498328,C,T,T289T,S,1, 7.1,"",
ybbP,b0496,"","","","","",521090,"","","",A,G,Q483R,N,4,"",
ybbC,b0498,"","","","","","",527126,"","",A,G,I107V,N,"","",
allD,b0517,"","","","","","","",545489,"",C,T,L32L,S,1,"",
ylbE'  ,b4572,547836,"","","","","","",547836,547836,-,G,K85E,N (+1) (pseudo),"","β",
folD,b0529,"","","",556376,"","","","","",G,A,R196C,N,1,"",
exoD',b0539,"","","","","",565537,"","","",C,T,M15I,N (pseudo),"","",
emrE / ybcK,b0543 / b0544,568019,568019,"","","","","","","",G,A,-,I,"","",
tfaD',b0561,"",581219,"","","","","","","",T,C,S112P,N (pseudo),"","",
tafX' / appY,b0563 / b0564,"","","","","",582696,"","","",A,G,-,I,"","",
cusA,b0575,"","",598463,"","","",598463,"","",A,G,E175G,N,4, 6, 7.3,"",
fepA,b0584,"","","","","",609783,"","","",C,A,T644T,S,4, 5, 6, 7.4,"",
entA,b0596,627972,"","","","","","","","",T,C,L66L,S,1,"",
ybdL,b0600,633092,633092,"","","","","","","",C,T,T94I,N,1,"",
leuS,b0642,"","","","","","",671496,"","",T,C,K836K,S,2, 7.1,"",
ybeL,b0643,"","","","",674532,"","","","",C,T,Q97*,N (ter),"","",
djlB,b0646,"","","","","","","","",677428,G,A,C263Y,N,2,"",
gltL,b0652,"","","","","","","","",686276,T,G,E231A,N,1, 4, 7.1,"",
asnB,b0674,"",697388,"","","","","","","",T,A,K337M,N,1, 7.1,"",
nagE,b0679,"","","","","","","",703577,"",C,T,T136T,S,1, 4, 6, 7.3,"",
glnS,b0680,"","","","","","",706854,"","",G,A,A512A,S,2, 7.1,"",
ybfM,b0681,"","","","",708603,"","","","",C,T,F348F,S,7.4,"",
ybfG',b0691,"","","","","",715501,"","","",G,A,A106V,N (pseudo),,"",
kdpB,b0697,"","","","","","","",725547,"",G,A,T237M,N,4, 6, 7.3,"",
kdpA,b0698,"","","","",726295,"","","","",T,C,E553G,N,4, 6, 7.3,"",
ybgP,b0717,"","","","","","","",748601,"",G,T,R109R,S,2,"",
mngA,b0731,"","","","","",767167,"","","",A,G,D653G,N,1, 2, 4, 5, 6, 7.3,"",
tolA / tolB,b0739 / b0740,"","","","","","","","",776955,G,T,-,I,"","",
nadA,b0750,"","","","","","","",782331,"",G,A,A341T,N,1, 7.1,"",
pgl,b0767,"","","","",797960,"","","","",A,G,Y50C,N,1,"",
ybhJ,b0771,"","",804535,"","","",804535,"","",G,A,E603K,N,"","",
ybhL / ybhM,b0786 / b0787,819857,"","","","","","","","",C,A,-,I,"","",
ybhN,b0788,"","","","","","","","",820957,C,T,G254G,S,3,"",
ybhS,b0793,"","","","","",825727,"","","",A,G,V249A,N,4, 6, 7.3,"",
rlmF,b0807,"","","",841636,"","","","","",C,T,P27S,N,"",L,"",
rybA / mntR,b4416 / b0817,852295,"","","","","","","","",A,G,-,I,"","",
ybiT,b0820,"","","","","",856409,"","","",G,A,W407*,N (ter),4, 7.1,"",
fsaA,b0825,863201,"","","","","","","","",G,A,G112S,N,"","",
moeA,b0827,"","","","","","",865009,"","",A,G,G192G,S,1,"",
gsiB,b0830,"","","","","","","",868947,"",A,G,N104S,N,4, 7.2,"",
gsiB,b0830,"","","","","","","","",869499,T,C,L288P,N,4, 7.2,"",
gsiD,b0832,"","","","","","","",871345,"",C,T,P77L,N,1, 4, 6, 7.3,"",
rimO,b0835,"","","",876334,876334,"","","","",G,A,P308S,N,2,"",
grxA / ybjC,b0849 / b0850,"","",890053,"","","",890053,"","",C,T,-,I,"","",
cspD,b0880,"","","","","","",921765,"","",A,G,F16L,N,7.1,"",
cydC,b0886,"","","",927416,"","","","","",C,T,D334N,N,4, 6, 7.3,"",
pflB,b0903,"","","","","","","",951867,"",T,C,E303G,N,1, 7.1,"",
msbA,b0914,"","",966949,"","","",966949,"","",G,A,G368E,N,4, 6, 7.3,"",
mukB,b0924,"","","","","",978570,"","","",C,A,R1007S,N,5,"",
ycbB,b0925,"","","","","",980297,"","","",C,A,Q9K,N,1,"",
yccS,b0960,"","","","","",1022080,"","","",C,T,A342T,N,4,"",
yccS,b0960,"","","","","",1022253,"","","",C,T,C284Y,N,4,"",
yccS,b0960,"","","","",1022833,"","","","",C,T,A91T,N,4,"",
hyaD,b0975,"","","","","","","","",1035333,C,T,P113L,N,1, 2,"",
appC,b0978,"","","","",1037552,"","","","",T,C,M196T,N,1, 6, 7.3,"",
etk,b0981,"","","","","",1041943,"","","",T,C,K496K,S,2, 4, 6, 7.3,"",
torD,b0998,"","",1061455,"","","","","","",T,C,V144A,N,2, 7.1,"",
rutC,b1010,"","","","","","","","",1071011,C,T,A123A,S,1,"",
phoH,b1020,"",1085097,"","","","","","","",A,G,N294D,N,1, 3, 5, 7.1,H,"",
ycdY,b1035,"","","","","","","",1098949,"",C,T,T28T,S,2, 7.1,"",
csgG,b1037,"","","","","","",1100628,"","",T,C,I93V,N,4, 6, 7.4,"",
csgF,b1038,"","","","","",1101122,"","","",A,G,S76P,N,4, 6,"",
csgD,b1040,"","","","","","","","",1102192,G,T,S75R,N,2, 3,"",
mdtG / lpxL,b1053 / b1054,"","","","",1114748,"","","","",C,T,-,I,"","",
dinI,b1061,1120539,1120539,"","","","","","","",C,T,E57K,N,2.1.4, 5, 7.1,L,"",
yceM,b1068,"","","","","",1126490,"","","",A,G,P153P,S,5,"",
flgG,b1078,"","","","","","","",1134629,"",G,A,V225V,S,1, 5, 6, 7.2,"",
mfd / ycfT,b1114 / b1115,"","","","","","","","",1173277,G,A,-,I,"","",
potD,b1123,1181794,1181794,"","","","","","","",C,T,V86I,N,1, 4, 7.2,"",
ycgE,b1162,"",1212614,"","","","","","","",C,A,R222S,N,2, 3,"",
emtA,b1193,"","","","","","","",1242766,"",A,T,N121Y,N,1, 6, 7.3,"",
rttR,tpr / tyrV,b4425,b1229  / b1230,"","",1286465,"","","",1286465,"","",G,T,-,I,"","†",
adhE,b1241,"","","","",1295192,"","","","",A,G,F717S,N,1,"",
kch,b1250,"","",1307113,"","","","","","",G,A,S393L,N,4, 6, 7.3,"",
trpE,b1264,"","","","","",1320323,"","","",A,G,R215R,S,1,"",
yciX / acnA,b4523 / b1276,"","",1333742,"","","","","","",T,C,-,I,"","",
gmr,b1285,1343113,"","","","","","","","",G,A,Q551*,N (ter),2, 5,"",
sapA,b1294,"","","","","",1354456,"","","",G,T,Q226K,N,1, 4, 7.2,"",
mpaA,b1326,"","","","","","","",1388275,"",G,A,N115N,S,1,"",
ycjZ,b1328,"","",1390174,"","","","","","",A,C,T53P,N,2, 3,"",
mppA,b1329,"","","","","",1392424,"","","",C,T,Q391*,N (ter),1, 4, 6, 7.2,"",
fnr,b1334,"","","","","","","","",1396995,A,T,F185I,N,1, 2, 3, 7.1,"",
ttcA,b1344,"","","",1409903,"","","","","",G,A,R23C,N,3,"",
recE,b1350,"","","",1413629,"","","","","",G,A,D593D,S,1, 2.1.4, 2.1.5, 7.1,"",
ydbK,b1378,"","","","","","","","",1435547,G,T,L1087I,N,1,"",
ydbK,b1378,"","","","","","",1436124,"","",G,T,V894V,S,1,"",
ydbK,b1378,"","","","","","",1436151,"","",G,T,F885L,N,1,"",
ydbK / ydbJ,b1378 / b4529,"","","","","","",1438958,"","",C,A,-,I,"","§",
ydbH,b1381,"",1442143,"","","","","","","",G,A,D356N,N,"","",
ydbL,b1383,"","","",1444103,"","","","","",A,G,Q66R,N,"","",
maoC,b1387,"","","","","","","",1450406,"",C,T,G420S,N,1,"",
paaK,b1398,"","","","","",1460550,"","","",T,C,V133V,S,1,"",
ynbB,b1409,"","","","","","",1476749,"","",C,T,A166V,N,1,"",
ynbC,b1410,"","","","","","","","",1477794,T,C,I210I,S,"","",
hrpA,b1413,"",1483786,"","","","","","","",A,G,E900G,N,2.1.1, 7.1,"",
rimL,b1427,"","","","","","","",1497338,"",A,C,E125A,N,2, 6, 7.1,"",
ydcK,b1428,"","","","","","","",1498255,"",C,T,V72V,S,"","",
ydcM,b1432,1502187,1502187,"","","","","","","",A,G,V168V,S,5,"",
ydcS,b1440,1510249,1510249,"","","","","","","",T,C,I190T,N,4, 7.2,"",
ydcU,b1442,"","",1511931,"","","",1511931,"","",G,C,G25A,N,4, 6, 7.3,"",
rhsE',b1456,"","","","",1527290,"","","","",G,A,W454*,N (ter) (pseudo),"","",
fdnI,b1476,"",1549749,"","","","","","","",A,G,T129A,N,1, 6, 7.3,"",
ddpF,b1483,1555689,1555689,"","","","","","","",A,G,L124S,N,4, 7.1,"",
ddpB,b1486,"",1558739,"","","","","","","",C,T,S71N,N,4, 6, 7.3,"",
ydeP,b1501,"","","","","",1583041,"","","",G,A,A489A,S,1,"",
ydeP,b1501,"","","","","","","","",1583119,G,T,G463G,S,1,"",
lsrK,b1511,1597223,"","","","","","","","",G,A,G336G,S,5,"",
lsrB,b1516,"","","","","","","",1603853,"",T,C,V259A,N,4, 7.2,"",
lsrG,b1518,"","","","","","","",1605089,"",C,G,R22G,N,"","",
yneH,b1524,"","",1610745,"","","",1610745,"","",C,T,S176S,S,1,"",
ydfH,b1540,"","","","","","","","",1627062,A,G,*228*,S,2, 3,"",
ydfP,b1553,1637502,"","","","","","","","",A,C,V16G,N,"","",
essQ / cspB,b1556 / b1557,"","","","","","","","",1638996,C,A,-,I,"","",
ydfU/rem,b1560 / b1561,"","","","","","","",1642390,"",C,T,-,I,"","",
ynfF,b1588,"","",1659029,"","","",1659029,"","",G,A,L149L,S,1,"",
clcB,b1592,1663526,1663526,"","","","","","","",C,T,A62V,N,4,"",
clcB,b1592,"","","","",1664042,"","","","",G,A,G234E,N,4,"",
ydgC,b1607,"","","","","","",1679987,"","",G,A,T22M,N,6,"",
rstB,b1609,1681401,"","","","","","","","",A,G,K165E,N,2, 3, 6, 7.3,"",
ydgA,b1614,"","","","","","",1689037,"","",C,A,P387T,N,"","",
malI,b1620,"","","","",1696691,"","","","",A,G,L171L,S,1, 2, 3, 7.1,"",
rsxB,b1628,"","","","","","","",1704735,"",A,G,K121E,N,1,"",
rsxD,b1630,"","","","","","","","",1707299,T,C,V44A,N,3, 5, 6, 7.3,"",
mliC,b1639,"","","",1716204,"","","","","",G,T,G71G,S,"","",
nemA / gloA,b1650 / b1651,"","","","","",1725790,"","","",G,A,-,I,"","",
mdtK,b1663,"","","","","","","",1742659,"",G,A,T392T,S,4, 5, 6, 7.3,"",
sufS,b1680,"",1757709,"","","","","","","",T,C,N279S,N,1,O,"",
aroD,b1693,1773393,"","","","","","","","",-,A,K228K,S (+1),1,"Φ",
ydiR,b1698,"","","","","","","","",1778835,C,T,I136I,S,1,"",
ydiU,b1706,"","","","","","","",1787894,"",C,A,D458Y,N,"","",
rpmI,b1717,1797924,"","","","","","","","",T,C,T33A,N,2, 6, 7.1,"",
yniA,b1725,"","",1806324,"","","",1806324,"","",A,G,I168V,N,"","",
chbC,b1737,"","","","","",1817975,"","","",T,C,I421V,N,1, 4, 6, 7.3,"",
chbC,b1737,"","","","","","","","",1818558,T,C,A226A,S,1, 4, 6, 7.3,"",
astB,b1745,"","",1825116,"","","",1825116,"","",G,A,L389L,S,1,"",
ynjI / topB,b1762 / b1763,"","",1842992,"","","","","","",A,T,-,I,"","",
ydjG,b1771,1853102,"","","","","","","","",T,C,V297V,S,1,"",
ydjI,b1773,1855594,"","","","","","","","",G,A,S66L,N,1,"",
ydjK,b1775,"","","","",1857347,"","","","",C,T,V302I,N,4, 6, 7.3,"",
ydjL,b1776,"","","","","",1858960,"","","",T,C,I132V,N,"","",
ydjL / yeaC,b1776 / b1777,1859386,1859386,"","","","","","","",A,G,-,I,"","",
yeaI,b1785,"","","",1869338,"","","","","",G,A,V309V,S,"","",
yeaJ,b1786,"","","",1870557,"","","","","",G,A,V164I,N,"","",
yeaM,b1790,"","","",1873502,"","","","","",A,G,S32S,S,2, 3,"",
sdaA / yoaD,b1814 / b1815,1896416,"","","","","","","","",G,A,-,I,"","",
yobD / yebN,b1820 / b1821,"",1903606,"","","","","","","",C,T,-,I,"","",
prc,b1830,"","","","","","","","",1911561,C,T,R426H,N,1, 2, 5, 6,"",
yebT,b1834,"","","","","",1917640,"","","",A,G,I702V,N,6,"",
ruvB,b1860,"","","","","",1943223,"","","",T,C,D52G,N,2.1.4, 2.1.3, 5, 7.1,L,"",
ruvB,b1860,"","",1943323,"","","",1943323,"","",C,A,D19Y,N,2.1.4, 2.1.3, 5, 7.1,L,"",
aspS,b1866,"","","","",1947323,"","","","",T,C,A407A,S,2, 7.1,"",
aspS,b1866,"","","","","","","","",1947485,A,T,V353V,S,2, 7.1,"",
aspS / yecD,b1866 / b1867,"","","","",1948549,"","","","",G,A,-,I,"","",
yecD,b1867,"","","","","",1949188,"","","",T,C,D110D,S,"","",
torZ,b1872,"","","","",1953566,"","","","",T,C,E488G,N,1, 7.1,"",
argS,b1876,"","","","",1959731,"","","","",A,G,N548S,N,2, 7.1,"",
cheR,b1884,"","","","","","","","",1966843,T,C,Q181Q,S,2, 5, 7.1,"",
tar,b1886,"","","","","","","","",1969075,A,G,D546D,S,3, 5, 6, 7.3,"",
yecR / ftnA,b1904 / b1905,"","","","","","",1986630,"","",C,A,-,I,"","",
yedQ,b1956,"","","","",2025877,"","","","",G,A,S54S,S,"","",
yedA,b1959,"","",2028240,"","","","","","",C,T,A225A,S,6,"",
cbl,b1987,"","","",2058107,"","","","","",G,A,Q277*,N (ter),1, 2, 3, 7.1,"",
insH-6 / yoeA',b1994 / b4582,2066390,"","","","","","","","",A,G,-,I,"","",
yeeZ,b2016,2086775,"","","","","","","","",G,A,T125T,S,1,"",
hisC,b2021,"","","","","","",2091011,"","",C,T,A196V,N,1,"",
hisC,b2021,"","","",2091123,"","","","","",C,T,N233N,S,1,"",
ugd,b2028,2097458,"","","","","","","","",G,A,H59H,S,1, 5, 6,"",
wcaK,b2045,"","","","","","","",2116031,"",T,C,Y132C,N,1,"",
wcaC,b2057,"","","","","","","","",2129153,A,G,S313S,S,1,"",
asmA,b2064,"","",2138470,"","","",2138470,"","",G,A,G388G,S,1, 6,"",
yegL,b2073,"","","","","",2150962,"","","",C,T,G63D,N,"","",
mdtC,b2076,"","","","","","",2157538,"","",A,G,M376V,N,4, 6, 7.4,"",
fbaB,b2097,"","","","","","","",2176080,"",A,G,Y168Y,S,1,"",
yohN/yehA,b2107 / b2108,"","","",2185344,"","","","","",G,A,-,I,"","",
yehH',b4499,"","","","","",2197475,"","","",C,A,P993T,N (pseudo),"",L,"",
yehI,b2118,"","","","","","",2199704,"","",C,T,A467A,S,3,"",
yehQ',b2122,"","","","","",2207144,"","","",T,C,L7S,N (pseudo),"","",
yehQ',b2122,2207944,"","","","","","","","",G,A,D274N,N (pseudo),"","",
yehX,b2129,"","","",2215324,"","","","","",A,G,S35P,N,4, 7.1,"",
yehY,b2130,"","","","",2215996,"","","","",C,T,G194D,N,4, 6, 7.3,"",
dld,b2133,"","","","","","","",2221816,"",C,A,A536E,N,1, 7.1,"",
yohF,b2137,"","","","","","","",2225187,"",C,T,D35N,N,1,"",
mdtQ',b2139,"","","","","","","","",2226741,G,A,P40S,N (pseudo),4,"",
cdd,b2143,"",2230578,"","","","","","","",C,T,P237L,N,1,"",
yeiT,b2146,"","",2232132,"","","","","","",T,C,C25C,S,1,"",
yeiG,b2154,"","","",2241988,"","","","","",C,T,H18H,S,5,"",
fruB,b2169,2260443,"","","","","","","","",GTT,---,Q358–,N (–3),1, 4, 7.1,"",
yeiU,b2174,2267554,"","","","","","","","",C,T,L226L,S,4,"",
yejF,b2180,"","","","","","","",2274392,"",T,C,V23A,N,4, 7.1,"",
yejH,b2184,2279168,"","","","","","","","",G,A,G171D,N,2.1.4,"",
ccmA,b2201,"","","",2295436,"","","","","",G,A,N76N,S,1, 2, 4, 7.1,"",
napA,b2206,"","",2299071,"","","","","","",A,G,F568L,N,1, 7.2,"",
napA,b2206,"","","","","",2299616,"","","",A,G,V386A,N,1, 7.2,"",
eco/mqo,b2209 / b2210,"","","","","","","",2302576,"",C,G,-,I,"","",
yfaV,b2246,"","","","","","","","",2357420,A,C,V264G,N,4, 6, 7.3,"",
yojI,b2211,"","",2305897,"","","","","","",G,A,I246I,S,4, 6, 7.3,"",
rcsD,b2216,"","","","","",2313084,"","","",G,A,V524V,S,2, 3,"",
yfaT,b2229,"","","","",2332910,"","","","",G,A,V23V,S,"","",
yfaL / nrdA,b2233 / b2234,"","","","","","",2342577,"","",T,C,-,I,"","",
yfaU,b2245,"","","","","","",2356760,"","",G,A,A35A,S,1,"",
arnF,b2258,"","","","","",2371104,"","","",G,A,W63*,N (ter),4, 6, 7.3,"",
nuoH,b2282,"","","",2394562,2394562,"","","","",G,C,G300G,S,1, 4, 6, 7.3,"",
nuoG,b2283,"","","","","","",2396587,"","",C,T,R533H,N,1, 4, 7.1,"",
nuoC,b2286,2401084,"","","","","","","","",G,T,H261N,N,1, 4, 7.1,"",
nuoC / nuoB,b2286 / b2287,"","","","","","",2401962,"","",A,G,-,I,"","",
yfbT,b2293,"","",2409755,"","","","","","",T,C,I118M,N,1,"",
pdxB,b2320,2434910,"","","","","","","","",C,T,D321N,N,1,"",
mnmC,b2324,"","","",2441067,"","","","","",T,C,Y427H,N,2,"",
yfcP,b2333,"",2448580,"","","","","","","",G,A,Y10Y,S,6,"",
fadI,b2342,"",2457472,"","","","","","","",G,A,I339I,S,1,"",
yfdF,b2345,"","","",2461525,2461525,"","","","",G,A,G163G,S,2.1,"",
oxc,b2373,"","","","","","","",2489734,"",G,A,P79L,N,1,"",
lpxP / yfdZ,b2378 / b2379,"","","","","","","","",2494971,T,C,-,I,"","",
ypdE,b2384,"","","",2502874,"","","","","",G,A,G231G,S,"","",
glk,b2388,"","","","","","","","",2506699,G,A,L249L,S,1, 7.1,"",
xapB,b2406,"",2521395,"","","","","","","",A,G,F204L,N,1, 4, 6, 7.3,"",
pdxK / yfeK,b2418 / b2419,2535315,2535315,"","","","","","","",G,T,-,I,"","",
yfeW,b2430,"","","","",2546651,"","","","",A,G,L175L,S,1,"",
eutD,b2458,"","","",2570543,"","","","","",G,A,R328C,N,1,"",
hyfB,b2482,2600797,2600797,"","","","","","","",G,T,G319C,N,1, 6, 7.3,"",
yfgH,b2505,"","","","","","",2627996,"","",C,T,D60D,S,7.4,"",
yphF,b2548,"","","","","","","","",2676454,C,T,T311T,S,4, 7.2,"",
yphG,b2549,2678056,"","","","","","","","",G,A,A903A,S,"","",
purL,b2557,2690904,"","","","","","","","",C,T,G887S,N,1, 7.1,"",
tadA,b2559,"","","","","","",2695804,"","",G,A,R25W,N,2,"",
yfiR,b2603,"","","","","",2740344,"","","",G,A,A149T,N,"","",
rpsP / ffh,b2609 / b2610,"","","","",2744453,"","","","",C,T,-,I,"","",
yfjI,b2625,"","","",2757855,"","","","","",T,C,F282F,S,"","",
yfjI,b2625,"",2758272,"","","","","","","",T,C,N421N,S,"","",
yfjK,b2627,"","","","","",2760683,"","","",T,C,K293E,N,"","",
yfjK,b2627,"","","","","","","",2761108,"",G,T,A151D,N,"","",
ypjA,b2647,2780582,"","","","","","","","",G,A,T55I,N,6, 7.4,"",
ygaQ',b4462,"",2785968,"","","","","","","",C,T,A516V,N (pseudo),"","",
nrdE,b2675,"",2800214,"","","","","","","",G,T,R281L,N,1, 7.1,"",
proX,b2679,"","",2805751,"","","","","","",G,A,E199K,N,1, 4, 5, 7.2,"",
ygaH / mprA,b2683 / b2684,2808766,2808766,"","","","","","","",G,A,-,I,"","",
serV / csrA,b2695 / b2696,"","","","",2816671,"","","","",C,T,-,I,"","",
recA,b2699,"","","","","",2820924,"","","",C,A,A289S,N,2.1.3, 2.1.4, 2, 3, 5, 7.1,L,"",
recA,b2699,"","",2820962,2820962,2820962,"",2820962,"","",T,G,D276A,N,2.1.3, 2.1.4, 2, 3, 5, 7.1,L,"",
recA,b2699,"","","","","","","",2820963,"",C,T,D276N,N,2.1.3, 2.1.4, 2, 3, 5, 7.1,L,"",
hypF,b2712,2833488,2833488,"","","","","","","",A,G,W653R,N,1, 2, 7.1,"",
hycC,b2723,2846936,"","","","","","","","",G,A,Q109*,N (ter),1, 6, 7.3,"",
fhlA,b2731,"","","","","","","","",2852903,C,T,R181W,N,1, 2, 3, 7.1,"",
fhlA,b2731,"","","","","",2853352,"","","",T,C,N330N,S,1, 2, 3, 7.1,"",
ygbJ,b2736,2859530,2859530,"","","","","","","",C,T,R26C,N,1,"",
nlpD,b2742,2866080,"","","","","","","","",G,A,V231V,S,6, 7.3,"",
ispF,b2746,2869428,"","","","","","","","",A,G,D124D,S,1, 7.1,"",
ygcB,b2761,"","","","",2885184,"","","","",T,C,K19E,N,"","",
cysJ,b2764,"","",2888465,"","","","","","",A,C,F485V,N,1,"§",
fucA / fucP,b2800 / b2801,2932140,2932140,"","","","","","","",C,T,-,I,"","",
fucU,b2804,"","","","","","","","",2937272,T,C,V120V,S,1, 7.1,"",
recB,b2820,2953341,"","","","","","","","",T,C,I228V,N,1, 2.1.5, 2.1.3,"",
lysR,b2839,2977775,2977775,"","","","","","","",C,T,P244S,N,1, 2, 3, 7.1,"",
ygeK',b2856,2992757,"","","","","","","","",A,G,S119P,N (pseudo),2, 3,"",
ygfU,b2888,3029566,3029566,"","","","","","","",A,G,K59E,N,4, 6, 7.3,"",
ygfU,b2888,"","","",3030225,"","","","","",T,C,G278G,S,4, 6, 7.3,"",
xerD,b2894,"","","","","","","","",3037674,C,T,R30H,N,2.1.3,"",
serA,b2913,"",3056348,"","","","","","","",C,T,A28T,N,1, 7.1,"",
scpA,b2917,"","","","",3060807,"","","","",G,A,A645T,N,1,"",
tktA,b2935,3077762,3077762,"","","","","","","",C,T,M631I,N,1,"",
metK / galP,b2942 / b2943,"","",3086156,"","","",3086156,"","",G,A,-,I,"","",
yqgF,b2949,"",3091589,"","","","","","","",T,C,I22T,N,2.1.3,"",
yghT,b2986,"",3132728,"","","","","","","",G,A,Q191Q,S,"","",
mqsR,b3022,"",3166480,"","","","","","","",C,T,L28L,S,3, 5,"",
ygiZ / mdaB,b3027 / b3028,"","","","","","","",3170242,"",A,G,-,I,"","",
ribB / yqiC,b3041 / b3042,"",3182554,"","","","","","","",A,G,-,I,"","",
dnaG,b3066,"","","","","","","",3209547,"",G,A,R139H,N,2.1.1, 7.1,"",
rpoD,b3067,"","","","","","","",3212771,"",A,G,N567S,N,2, 3, 7.1,"",
yqjG,b3102,"","","","","","",3249966,"","",G,T,G306G,S,1,"",
yhaH / yhaI,b3103 / b3104,3250857,3250857,"","","","","","","",A,G,-,I,"","",
tdcA / tdcR,b3118 / b3119,"","","","","",3265098,"","","",G,T,-,I,"","",
tdcR,b3119,"","","","","",3265424,"","","",T,C,I7T,N,1, 2, 3, 7.1,"",
yhaV / agaR,b3130 / b3131,"","","","","","","",3275837,"",G,A,-,I,"","",
agaA' / agaS,b3135 / b3136,"","","","",3279715,"","","","",T,C,-,I,"","",
yraM,b3147,"","","","","",3292561,"","","",G,A,A379A,S,"","",
diaA,b3149,"","","","","","","","",3294171,T,A,L113*,N (ter),2.1.1, 5,"",
nlpI,b3163,"","","",3306455,3306455,"","","","",A,G,P163P,S,5,"",
glmM,b3176,3321508,"","","","","","","","",G,T,R194R,S,1, 6, 7.1,"",
ispB,b3187,"","","","","",3331922,"","","",A,G,N63S,N,1,"",
yrbC,b3192,"","","",3335355,"","","","","",T,A,T186S,N,4, 7.1,"",
rpoN,b3202,"",3343785,"","","","","","","",A,C,E348D,N,1, 2, 3,"",
nanE,b3223,"","","","","","","",3368674,"",C,T,A128T,N,1, 7.1,"",
nanT,b3224,"","","","","","","","",3369380,A,G,F415S,N,1, 4, 6, 7.3,"",
yhdE,b3248,"","","","","","","","",3396350,A,G,L16L,S,"","",
mreB / csrD,b3251 / b3252,"","","","","","","",3399224,"",T,C,-,I,"","",
yhdZ / yrdA,b3271 / b3279,"","","","","","","","",3424869,G,A,-,I,"","§",
yrdA,b3279,"","","","","","","","",3427431,C,T,T129T,S,"","",
yhdN,b3293,"",3437459,"","","","","","","",C,T,A24T,N,"","",
gspC,b3324,"",3454125,"","","","","","","",A,G,I175V,N,4,"",
cysG,b3368,"","","",3497167,"","","","","",A,G,I439V,N,1,"",
yhfX,b3381,"","",3508808,"","","",3508808,"","",C,A,G63V,N,"","",
hofP,b3392,"","","","","","","","",3518648,C,T,D144N,N,1,"",
hofO,b3393,"","","","","","",3519315,"","",G,A,Q52*,N (ter),1,"",
yrfF,b3398,"","","",3526497,"","","","","",C,T,A668A,S,"","",
ompR / greB,b3405 / b3406,"","","","","","","","",3534616,T,C,-,I,"","",
glpD,b3426,"","","","","","","",3560801,"",G,A,V255M,N,1, 7.1,"",
glgP,b3428,"","","","","","","","",3563053,G,T,Q517K,N,1, 7.1,"",
glgP,b3428,"","","","","","","","",3563638,G,A,H322Y,N,1, 7.1,"",
glgB,b3432,"","",3569505,"","","","","","",T,C,K673R,N,1, 7.1,"",
yhhY / yhhZ,b3441 / b3442,"","","","","","",3579865,"","",C,G,-,I,"","",
yhhN,b3468,"","","","",3604163,"","","","",G,C,W129C,N,"","",
yhhH,b3483,"","","",3621491,"","","","","",G,A,V23I,N,"","",
yhiL',b4660,"","","","","","","","",3631270,C,T,V403V,S (pseudo),"","",
pitA,b3493,"",3636547,"","","","","","","",G,A,E294K,N,1, 4, 6, 7.3,"",
yhiR,b3499,"","","","","",3643629,"","","",G,A,L73L,S,1,"",
yhiF/yhiD,b3507 / b3508,"","","",3653245,"","","","","",C,A,-,I,"","",
mdtF,b3514,"","","","","",3659044,"","","",T,C,V202A,N,4, 6, 7.4,"",
mdtF,b3514,3660175,"","","","","","","","",C,T,A579V,N,4, 6, 7.4,"",
kdgK,b3526,"","","","","","","","",3678292,C,A,A356E,N,1,"",
bcsC,b3530,"",3686233,"","","","","","","",C,T,A321T,N,6,"",
bcsB,b3532,"",3688983,"","","","","","","",G,T,Q549K,N,1, 4,"",
dppF,b3540,"","","","","","","","",3700121,G,A,Y256Y,S,1, 4, 7.1,"",
selB,b3590,"","","","","",3756684,"","","",G,A,P400S,N,2, 7.1,"",
selA,b3591,"","",3758316,"","","",3758316,"","",C,T,P318P,S,1, 2, 7.1,"",
yibH,b3597,"",3768842,"","","","","","","",C,G,Q186H,N,6, 7.3,"",
yibI,b3598,"","","","","","","",3769431,"",C,T,D112N,N,"","",
yibL/lldP,b3602 / b3603,"","","","",3775408,"","","","",C,T,-,I,"","",
kbl,b3617,"","","","","",3789997,"","","",A,G,L192P,N,1,"",
rfaD,b3619,3792548,"","","","","","","","",G,A,S179N,N,1, 6,"",
rfaC,b3621,"","","","","","",3794258,"","",A,G,N85S,N,1, 6, 7.3,"",
rfaI,b3627,"","","","","","","",3800614,"",A,G,V155V,S,6,"",
gltS,b3653,"","",3825922,3825922,3825922,"",3825922,"","",A,G,V255A,N,1, 4, 6, 7.3,"",
yicH,b3655,"","","","","",3829137,"","","",T,A,W219R,N,"","",
yicO,b3664,"","","","","","","","",3840679,G,A,N403N,S,4, 5, 6, 7.3,"",
rnpA,b3704,"","","","","","","","",3882847,G,A,R110H,N,1, 2, 7.1,"",
purP,b3714,"","","","","","","",3894550,"",G,A,A27V,N,4,"",
bglH,b3720,"","","",3898645,3898645,"","","","",C,T,Q532Q,S,4, 6, 7.4,"",
bglH,b3720,"","","","","",3899844,"","","",C,T,G133S,N,4, 6, 7.4,"",
ravA,b3746,"","","","","","","",3928950,"",G,A,A55V,N,3,"",
rbsC,b3750,"","","","","",3933829,"","","",G,T,P172P,S,1, 4, 6, 7.3,"",
wzxE,b3792,3974865,"","","","","","","","",C,T,P188S,N,1,"",
fdhE,b3891,4078346,4078346,"","","","","","","",G,A,F301F,S,1, 2,"",
yiiG,b3896,"","","","",4085221,"","","","",C,T,P65L,N,"","",
frvR,b3897,"","","",4086862,"","","","","",A,G,C338C,S,2, 3,"",
frvR,b3897,"",4087176,"","","","","","","",C,T,G234S,N,2, 3,"",
rhaA,b3903,"","","","",4093913,"","","","",A,T,D30E,N,1,"",
yiiM,b3910,"","","","","","","","",4100999,G,A,G61E,N,"","",
cpxA,b3911,"","","","","","",4102033,"","",C,A,A321A,S,1, 2, 3, 5, 6, 7.3,"",
priA,b3935,"","","","","","","","",4123174,C,T,V553I,N,2.1.1, 7.1,"",
metL,b3940,"","","","","","","",4129990,"",C,T,F710F,S,1,"",
metL,b3940,"","","","","",4130134,"","","",T,G,H758Q,N,1,"",
yijF,b3944,4135247,"","","","","","","","",T,C,Y144C,N,"","",
gldA,b3945,"","","","","","","",4136015,"",A,G,V347V,S,1,"",
pflC,b3952,4144596,4144596,"","","","","","","",G,C,E105Q,N,1, 2, 3,"",
ppc,b3956,"","","","","","","","",4150978,G,A,G47G,S,1, 7.1,"",
fabR,b3963,"","","",4159346,"","","","","",G,A,G66D,N,3,"",
murI / murB,b3967 / b3972,"","","","","","","","",4166244,T,C,-,I,"","§",
murI / murB,b3967 / b3972,"","","","","","","","",4166503,T,C,-,I,"","§",
rplK,b3983,"","","","","","","",4176590,"",G,A,A40T,N,2, 6, 7.1,"",
rpoC,b3988,"","","","","","","",4187534,"",G,A,D1387N,N,2, 7.1,"",
thiC,b3994,"","","","","","","",4192664,"",A,G,W486R,N,1,"",
metA,b4013,"","","","","",4212676,"","","",A,G,K124R,N,1, 7.1,"",
iclR,b4018,"","","","","","","",4221400,"",G,C,I83M,N,1, 2, 3, 7.1,"",
yjbI',b4038,"","","","","","","",4249616,"",G,A,L296L,S (pseudo),"","",
ubiA/plsB,b4040 / b4041,"","","","","",4252034,"","","",G,A,-,I,"","",
dinF,b4044,"","","","",4256277,"","","","",C,A,L170L,S,2.1.4, 4, 5, 6, 7.3,L,"",
yjbM,b4048,"","","","","","","",4258750,"",T,C,N42N,S,"","",
dnaB,b4052,"","","","","",4262560,"","","",T,C,L74S,N,2.1.1, 7.1,"",
dnaB,b4052,"","","","","","","",4262578,"",C,A,P80H,N,2.1.1, 7.1,"",
alr,b4053,4264102,"","","","","","","","",C,T,H99Y,N,1,"",
dcuR,b4124,"","","","","","","","",4347852,G,A,P68L,N,1, 2, 3, 7.1,"",
aspA / fxsA,b4139 / b4140,"","","","",4366510,"","","","",G,A,-,I,"","",
yjeP,b4159,"","","","","","","",4386471,"",T,C,Q307R,N,4, 7.2,"",
mutL,b4170,"","","","",4395562,"","","","",A,T,D42V,N,2.1.4, 7.1,"",
yjfJ,b4182,"","","","","","","",4409047,"",T,C,S157P,N,2, 3,"",
ulaC,b4195,"","","","","","","","",4419905,G,A,V58I,N,4,"",
ytfE / ytfF,b4209 / b4210,"","","","","","","",4430033,"",A,G,-,I,"","",
chpB,b4225,"","","","","","","",4446834,"",T,C,F39F,S,3, 5,"",
ytfQ,b4227,4448890,"","","","","","","","",G,A,L301L,S,4, 7.2,"",
yjgA,b4234,"","",4455866,"","","","","","",C,T,W7*,N (ter),4,"",
nrdD,b4238,"",4458943,"","","","","","","",C,T,V580M,N,1,"",
treR / mgtA,b4241 / b4242,"","","","","","","",4465450,"",T,C,-,I,"","",
pyrB,b4245,"","","","",4470036,"","","","",G,T,A127D,N,1, 7.1,"",
yjgL,b4253,4474024,"","","","","","","","",A,G,N188D,N,"","",
yjgL,b4253,"","",4475030,"","","",4475030,"","",A,G,D523G,N,"","",
argI / rraB,b4254 / b4255,4476359,4476359,"","","","","","","",C,T,-,I,"","",
yjgB,b4269,"",4494219,"","","","","","","",T,C,K4R,N,1,"",
fecE,b4287,"","","","","","","",4509041,"",G,A,A146V,N,4, 5, 7.1,"",
sgcA,b4302,"","","","","","","","",4525857,C,T,W48*,N (ter),4,"",
yjhR',b4308,"","","","","","","","",4534044,G,A,R335H,N (pseudo),"","",
fimE / fimA,b4313 / b4314,"","","",4540704,"","","","","",C,T,-,I,"","§",
uxuB,b4323,"","","",4552285,4552285,"","","","",C,T,A453A,S,1,"",
kptA,b4331,4559160,"","","","","","","","",T,C,F69L,N,1, 7.1,"",
yjiN,b4336,"","","","",4564436,"","","","",C,T,M277I,N,6,"",
mcrB,b4346,"","",4576070,"","","","","","",T,C,T430A,N,1, 2.1.2, 2.1.5, 7.1,"",
mrr,b4351,"","",4585486,"","","","","","",A,G,E171G,N,2.1.2, 3, 7.1,"",
yjiZ,b4356,"","","","",4592346,"","","","",C,T,V133M,N,4, 6, 7.3,"",
dnaT,b4362,"","",4599105,4599105,4599105,"",4599105,"","",G,A,R145C,N,2.1.1, 7.1,"",
deoC / deoA,b4381 / b4382,"",4616138,"","","","","","","",A,G,-,I,"","",
deoA,b4382,"","","","","","","","",4617315,A,T,D354V,N,1,"",
lplA,b4386,4622080,"","","","","","","","",C,T,E20K,N,1, 2, 7.1,"",
slt,b4392,"","","","","","","","",4630017,G,A,W429*,N (ter),1, 5, 6, 7.2,"",
trpR,b4393,"","","","",4630885,"","","","",C,T,H34Y,N,1, 2, 3, 7.1,"",

prompt> Look at all these genes and proteins involved in DNA damage repair and protection against DNA damage. Make some observations based on this data. Then, using htose observations, make a handful of integrated theories that explain substnatial portions of the above data pertaining to DNA damage repair. In particular, we are interested in what opportunities are presenting themselves (in this data) for the improvement of DNA damage repair or DNA repair enymes or protein sequences.

--- Command output ---
<thinking>
This is a fascinating dataset that appears to be from an evolution experiment or mutation screen in E. coli. Let me analyze this carefully.

The columns appear to be:
- Gene name and locus tag
- Various strain IDs (CB1000, CB1012, CB1013, etc.) with position numbers indicating where mutations occurred
- Reference and mutant alleles
- Amino acid change
- Mutation type (N = nonsynonymous, S = synonymous, I = intergenic)
- Multifun categories
- Regulon information
- Footnotes

Let me identify genes involved in DNA damage repair and related functions:

1. **recA** (b2699) - Central recombinase for homologous recombination and SOS response
   - Multiple mutations: A289S, D276A, D276N
   - Appears in multiple strains (CB1013, CB1014, CB1015, CB1025)

2. **recB** (b2820) - RecBCD helicase/nuclease complex
   - I228V mutation

3. **recE** (b1350) - Exonuclease VIII for recombination
   - D593D (synonymous)

4. **ruvB** (b1860) - Holliday junction helicase
   - D52G and D19Y mutations in multiple strains

5. **xerD** (b2894) - Site-specific recombinase
   - R30H mutation

6. **mfd** (b1114) - Transcription-repair coupling factor
   - Intergenic mutation nearby

7. **priA** (b3935) - Primosome assembly, replication restart
   - V553I mutation

8. **priC** (b0467) - Primosome assembly
   - L162P mutation in multiple strains (CB1000, CB1012)

9. **dnaT** (b4362) - Primosome assembly
   - R145C mutation in multiple strains

10. **dnaB** (b4052) - Replicative helicase
    - L74S and P80H mutations

11. **dnaG** (b3066) - Primase
    - R139H mutation

12. **mutL** (b4170) - Mismatch repair
    - D42V mutation

13. **dinI** (b1061) - SOS response modulator, inhibits RecA
    - E57K mutation in multiple strains

14. **dinF** (b4044) - SOS-induced MATE transporter
    - L170L (synonymous)

15. **dksA** (b0145) - Involved in DNA damage response
    - M31V mutation

16. **mcrB** (b4346) - Restriction system
    - T430A mutation

17. **mrr** (b4351) - Restriction system
    - E171G mutation

18. **ftsZ** (b0095) - Cell division, coordinates with DNA replication
    - D303N mutation

19. **ftsW** (b0089) - Cell division
    - E34G and M268V mutations

20. **clpP/clpX** (b0437/b0438) - Proteases involved in SOS response
    - Y75C and Y384C mutations

21. **lexA** - Not seeing direct mutations but related genes affected

22. **radA/sms** - Not directly visible

23. **yejH** (b2184) - Putative helicase
    - G171D mutation

24. **hrpA** (b1413) - RNA helicase, involved in DNA repair
    - E900G mutation

25. **ttcA** (b1344) - tRNA thioltransferase
    - R23C mutation

26. **gmr** (b1285) - Cyclic di-GMP phosphodiesterase
    - Q551* (truncation)

27. **hofC/hofB** (b0106/b0107) - DNA uptake/competence
    - Q203* and T223T mutations

28. **mukB** (b0924) - Chromosome condensation
    - R1007S mutation

Let me look for patterns:

**Multifun categories that appear relevant:**
- 2 = DNA replication/repair related
- 2.1 = DNA replication
- 2.1.1 = Initiation
- 2.1.3 = Recombination
- 2.1.4 = Repair
- 2.1.5 = Restriction/modification

**Key observations:**

1. **RecA mutations are highly selected:**
   - recA shows mutations in multiple strains at different positions (A289S, D276A/N)
   - These cluster near the C-terminus which is involved in DNA binding and LexA cleavage
   - D276 is particularly interesting - same position mutated to different amino acids in different strains

2. **Primosome/replication restart genes are frequently mutated:**
   - priA, priC, dnaT, dnaB, dnaG all show mutations
   - This suggests selection for altered replication restart capabilities

3. **RuvB mutations parallel RecA:**
   - Multiple strains show ruvB mutations
   - This is the Holliday junction helicase - downstream of RecA in recombination

4. **dinI mutations appear with recA:**
   - dinI is a RecA inhibitor
   - E57K mutation could alter its inhibitory capacity

5. **Mismatch repair (mutL):**
   - D42V mutation
   - Could affect mutation rate/repair fidelity

6. **Cell division genes co-mutate:**
   - ftsZ, ftsW mutations
   - DNA damage checkpoints coordinate with cell division

7. **Clp proteases:**
   - clpP and clpX mutations
   - These degrade SOS response proteins

8. **Strain patterns:**
   - Some strains (CB1013, CB1014, CB1015) seem to have multiple DNA repair mutations
   - CB1025 appears frequently with recA mutations

Let me organize observations and theories:

**OBSERVATIONS:**

1. **RecA is a major target for selection**
   - Mutations at positions 276 and 289
   - Position 276 shows convergent evolution (same position, different substitutions)
   - D276A appears in strains CB1013, CB1014, CB1015, CB1025
   - D276N appears in CB3000
   - A289S appears in CB1024

2. **Replication restart machinery is under selection**
   - priA (V553I), priC (L162P), dnaT (R145C), dnaB (L74S, P80H)
   - These form the primosome that restarts stalled replication forks

3. **Holliday junction resolution pathway**
   - ruvB shows D52G and D19Y mutations
   - This processes recombination intermediates

4. **SOS response modulators**
   - dinI (E57K) - RecA inhibitor
   - clpP/clpX - protease for LexA
   - dksA - stress response regulator

5. **Mismatch repair**
   - mutL (D42V)

6. **Synonymous vs nonsynonymous:**
   - Most DNA repair genes show nonsynonymous mutations
   - Suggests functional selection, not just genetic drift

7. **Restriction-modification systems**
   - mcrB (T430A), mrr (E171G)
   - May relate to foreign DNA processing

**THEORIES:**

**Theory 1: Enhanced RecA function through C-terminal domain modification**
RecA mutations at D276 and A289 are in regions important for:
- DNA binding (C-terminal domain)
- LexA cleavage promotion
- RecA filament dynamics

The D276A/N mutations likely alter the charge characteristics of this region, potentially enhancing DNA binding affinity or modifying the dynamics of RecA filament formation. This could improve recombination efficiency or modify SOS response kinetics.

**Theory 2: Optimized replication restart pathway**
The primosome genes (priA, priC, dnaT) plus replicative helicase (dnaB) and primase (dnaG) show coordinated mutations. This suggests selection for:
- Faster recognition of stalled forks
- More efficient primosome assembly
- Improved coordination between restart and ongoing replication

**Theory 3: Balanced SOS response through dinI modification**
The dinI E57K mutation may reduce RecA inhibition, allowing:
- Prolonged RecA activity
- Enhanced SOS response
- Better coordination with the recA mutations observed

**Theory 4: Improved Holliday junction resolution**
ruvB mutations may enhance the processing of recombination intermediates, working synergistically with enhanced RecA activity.

**OPPORTUNITIES FOR IMPROVEMENT:**

1. **RecA engineering:**
   - D276A/N substitutions may improve recombination
   - A289S could enhance DNA binding
   - Combined mutations might be additive

2. **Primosome optimization:**
   - priC L162P
   - priA V553I
   - dnaT R145C
   - These could be combined for enhanced replication restart

3. **SOS response tuning:**
   - dinI E57K with recA mutations
   - clpP/clpX modifications

4. **RuvB enhancement:**
   - D52G or D19Y for better junction resolution

Wait, let me re-examine the data more carefully for the strain distribution patterns...

Looking at CB1000, CB1012 - these share some mutations
CB1013, CB1025 share mutations
CB1014, CB1015 share some

Let me trace the recA mutations specifically:
- CB1024: A289S
- CB1013, CB1014, CB1015, CB1025: D276A
- CB3000: D276N

And ruvB:
- CB1024: D52G
- CB1012, CB1025: D19Y

And dinI:
- CB1000, CB1012: E57K

And priC:
- CB1000, CB1012: L162P

And dnaT:
- CB1013, CB1014, CB1015, CB1025: R145C

This is revealing! There seem to be two major evolutionary trajectories:

**Trajectory 1 (CB1000, CB1012):**
- priC L162P
- dinI E57K
- ruvB D19Y (CB1012)

**Trajectory 2 (CB1013, CB1014, CB1015, CB1025):**
- recA D276A
- dnaT R145C
- ruvB D19Y (CB1025)

**Trajectory 3 (CB1024):**
- recA A289S
- ruvB D52G

This suggests alternative strategies for enhancing DNA repair!

Let me also look at the footnote column - some entries have "L" which might indicate something specific (perhaps a specific regulon or condition).

Genes marked with L footnote:
- rlmF (O regulon)
- dinI
- ruvB
- recA
- yehH' (also L)
- dinF

This L marker appears to be associated with DNA damage/SOS response genes specifically!

Let me refine my analysis and theories now...
</thinking>

# Analysis of DNA Damage Repair Mutations in E. coli Evolution Experiment

## Initial Observations

### 1. **RecA Shows Strong Convergent Evolution**

The central recombinase RecA (b2699) exhibits remarkable mutation patterns:

| Position | Mutation | Strains |
|----------|----------|---------|
| 276 | D→A | CB1013, CB1014, CB1015, CB1025 |
| 276 | D→N | CB3000 |
| 289 | A→S | CB1024 |

**Key insight**: Position D276 is mutated in 5 different strains to two different amino acids, suggesting this is a critical site for optimization. Both substitutions (D→A and D→N) remove the negative charge, indicating selection for altered electrostatic properties in the C-terminal DNA-binding domain.

---

### 2. **Primosome/Replication Restart Machinery is Extensively Modified**

| Gene | Function | Mutation | Strains |
|------|----------|----------|---------|
| **priA** (b3935) | Fork restart recognition | V553I | CB3000 |
| **priC** (b0467) | Primosome assembly | L162P | CB1000, CB1012 |
| **dnaT** (b4362) | Primosome component | R145C | CB1013, CB1014, CB1015, CB1025 |
| **dnaB** (b4052) | Replicative helicase | L74S, P80H | CB1024 |
| **dnaG** (b3066) | Primase | R139H | CB2000 |

**Key insight**: The replication restart pathway is under intense selection, with mutations appearing across multiple components.

---

### 3. **Holliday Junction Resolution (RuvB) Shows Parallel Selection**

| Mutation | Strains |
|----------|---------|
| D52G | CB1024 |
| D19Y | CB1012, CB1025 |

Both mutations occur in the N-terminal region of RuvB, which interfaces with RuvA and affects ATPase activity/junction binding.

---

### 4. **SOS Response Modulators Are Co-Selected**

| Gene | Function | Mutation | Strains |
|------|----------|----------|---------|
| **dinI** (b1061) | RecA inhibitor | E57K | CB1000, CB1012 |
| **clpP** (b0437) | Protease (LexA degradation) | Y75C | CB1000, CB1012 |
| **clpX** (b0438) | Protease ATPase | Y384C | CB1013 |
| **dksA** (b0145) | Stress response regulator | M31V | CB1024 |

---

### 5. **Two Distinct Evolutionary Trajectories Emerge**

**Trajectory A (CB1000, CB1012):**
- priC L162P (altered primosome assembly)
- dinI E57K (reduced RecA inhibition)
- clpP Y75C (altered protease activity)

**Trajectory B (CB1013, CB1014, CB1015, CB1024, CB1025):**
- recA D276A (enhanced RecA function)
- dnaT R145C (altered primosome function)
- Various ruvB mutations

---

### 6. **Restriction-Modification System Modifications**

| Gene | Mutation | Category |
|------|----------|----------|
| mcrB (b4346) | T430A | 2.1.2, 2.1.5 |
| mrr (b4351) | E171G | 2.1.2 |

These may affect processing of damaged or foreign DNA substrates.

---

### 7. **Additional DNA Repair-Associated Genes**

| Gene | Function | Mutation | Notes |
|------|----------|----------|-------|
| **mutL** (b4170) | Mismatch repair | D42V | May alter mutation rate |
| **xerD** (b2894) | Site-specific recombination | R30H | Chromosome resolution |
| **hrpA** (b1413) | RNA helicase | E900G | R-loop processing |
| **yejH** (b2184) | Putative helicase | G171D | Possible repair role |
| **recE** (b1350) | Exonuclease VIII | D593D (syn) | RecET pathway |

---

## Integrated Theories

### **Theory 1: RecA Functional Enhancement Through C-Terminal Domain Remodeling**

The clustering of mutations at D276 and A289 in RecA's C-terminal domain suggests optimization of:

1. **DNA binding dynamics**: The C-terminus (residues 270-328) contains the secondary DNA binding site. D276 mutations remove negative charge, potentially:
   - Increasing affinity for ssDNA
   - Altering filament nucleation kinetics
   - Modifying strand exchange efficiency

2. **LexA cleavage regulation**: This region influences RecA's co-protease activity. Modified charge distribution could:
   - Accelerate SOS induction
   - Fine-tune the timing of SOS response

**Opportunity**: Engineer RecA variants combining D276A with A289S to test for additive effects on recombination efficiency.

---

### **Theory 2: Parallel Pathway Optimization - Primosome vs. RecA Routes**

The data reveals two distinct strategies for improving DNA damage tolerance:

**Strategy A: Enhanced fork restart without RecA modification**
- Modify priC (L162P) for faster primosome assembly
- Reduce RecA inhibition via dinI (E57K) 
- This pathway emphasizes **replication restart efficiency**

**Strategy B: Enhanced recombination capacity**
- Modify RecA directly (D276A)
- Adjust dnaT for primosome function coordination
- This pathway emphasizes **recombinational repair**

**Opportunity**: These represent orthogonal engineering strategies. Combining elements from both (e.g., priC L162P + recA D276A) might produce synergistic enhancement.

---

### **Theory 3: Coordinated Replication-Recombination-Resolution Axis**

The mutations form a functional pipeline:

```
Stalled Fork → PriA/PriC/DnaT (recognition/restart)
              ↓
         RecA (strand invasion/recombination)
              ↓
         RuvB (Holliday junction resolution)
```

Each step shows independent optimization:
- **Entry**: priC L162P, priA V553I
- **Processing**: recA D276A/N, A289S
- **Resolution**: ruvB D52G, D19Y

**Opportunity**: Engineer the complete pathway by combining:
- dnaT R145C + recA D276A + ruvB D19Y (Trajectory B optimum)
- Or: priC L162P + dinI E57K + ruvB D19Y (Trajectory A optimum)

---

### **Theory 4: SOS Response Temporal Optimization**

The pattern suggests selection for **modified SOS timing**:

| Modification | Effect |
|--------------|--------|
| dinI E57K | Reduced RecA inhibition → prolonged/enhanced SOS |
| clpP Y75C | Altered LexA degradation kinetics |
| clpX Y384C | Modified substrate recognition |
| dksA M31V | Altered stress transcription coupling |

**Hypothesis**: Optimal DNA damage survival requires not just better repair enzymes but **better temporal coordination** of the damage response.

**Opportunity**: Fine-tune SOS response kinetics through dinI/clpP engineering in combination with enhanced RecA.

---

### **Theory 5: Charge-Based Functional Optimization**

Several key mutations involve charge modifications:

| Gene | Mutation | Charge Change |
|------|----------|---------------|
| recA | D276A | Negative → Neutral |
| recA | D276N | Negative → Neutral |
| ruvB | D52G | Negative → Neutral |
| ruvB | D19Y | Negative → Aromatic |
| dinI | E57K | Negative → Positive |
| dnaT | R145C | Positive → Neutral |

**Pattern**: DNA-binding proteins show removal of negative charges (improved DNA interaction), while protein-protein interaction surfaces show more complex changes.

**Opportunity**: Rational design of charge-modified variants at homologous positions in repair enzymes.

---

## Specific Engineering Opportunities

### **Priority 1: RecA Enhancement Cassette**
```
Modifications:
- D276A (or D276N for alternative)
- A289S (potential additive effect)
- Test: D276A + A289S combination
```
**Rationale**: Highest convergence signal in the data; C-terminal modifications likely improve core recombinase function.

### **Priority 2: Optimized Replication Restart Module**
```
Modifications:
- priC L162P
- dnaT R145C  
- priA V553I (optional addition)
```
**Rationale**: Fork restart is rate-limiting for damage tolerance; these mutations appeared independently in multiple lineages.

### **Priority 3: Balanced RecA Regulation**
```
Modifications:
- dinI E57K (reduces RecA inhibition)
- Combine with recA D276A
```
**Rationale**: Enhanced RecA activity paired with reduced inhibition may provide synergistic improvement.

### **Priority 4: Holliday Junction Resolution Enhancement**
```
Modifications:
- ruvB D19Y (or D52G)
- Combine with recA modifications
```
**Rationale**: Resolution of recombination intermediates may be rate-limiting when RecA activity is enhanced.

---

## Key Strain-Specific Insights for Validation

| Strain | Key DNA Repair Mutations | Predicted Phenotype |
|--------|-------------------------|---------------------|
| CB1000 | priC L162P, dinI E57K, clpP Y75C | Enhanced restart, prolonged SOS |
| CB1012 | priC L162P, dinI E57K, ruvB D19Y | Restart + resolution optimized |
| CB1013 | recA D276A, dnaT R145C | Enhanced recombination pathway |
| CB1024 | recA A289S, ruvB D52G, dksA M31V | Alternative RecA optimization |
| CB1025 | recA D276A, dnaT R145C, ruvB D19Y | Complete pathway optimization |

---

## Summary of Actionable Hypotheses

1. **RecA D276A/N represents a superior recombinase variant** - Test directly for recombination frequency and UV survival

2. **priC L162P + dinI E57K is an alternative to modifying RecA** - Compare damage tolerance with recA D276A strains

3. **The complete pathway (dnaT R145C + recA D276A + ruvB D19Y) from CB1025 may represent an optimal combination** - Reconstruct and test

4. **Charge neutralization at DNA-binding surfaces is a general optimization principle** - Apply to other DNA repair enzymes (UvrA, UvrB, RecG, etc.)

5. **SOS timing can be optimized independently of core repair enzyme activity** - dinI and clpP/X modifications offer regulatory rather than catalytic improvements