For the purpose of our study, both proteins are described with a simplified structural model, where each amino acid is represented by one interaction center, coinciding with the atom.

The folding dynamics is simulated using the stochastic Monte Carlo (MC) approach introduced and validated in Ref. [41]. The MC evolution entails a brief relaxation from the initial fully-extended state using both local and non-local moves. After this stage, indicated with a shaded region in Fig. 2 and related ones, the MC dynamics proceeds exclusively through local moves. The moves amplitude is sufficiently small that no chain crossings occurs, as verified a posteriori. The stochastic scheme is analogous to the kink-jump dynamics [42] which, by virtue of the local character of the moves, is known to provide a physically-viable description of biopolymers' kinetics in thermal equilibrium [41], [43].

The folding simulations are carried out using two alternative energy functions. The first one promotes exclusively the formation of native contacts between pairs of amino acids. Following Refs. [44], [45], the strength of the attractive interaction between any given native amino acid pair is derived from the strength of their hydrogen bonding in the native state and is expressed in thermal units, , at the nominal Monte Carlo temperature of . The second energy function includes electrostatic and non-native pairwise interactions in addition to the native-centric potential. The relative strength of the non-native interactions is set according to the quasi-chemical potentials of Miyazawa and Jernigan (MJ) [46] that reflect the statistical propensity of amino acid pairs to be in contact in proteins' native states. Following, again, Ref.s [44], [45], the average strength of the added non-native interactions is set to one tenth of the native one. No change to the MC temperature was made using this second potential because previous studies have shown that the addition of non-native interactions modifies the effective temperature of the system by less than [47]. Consistently with this fact we have verified that the native states of both AOTCase and OTCase remain stable when evolved with the MC scheme using the second type of potential. In fact, the asymptotic value for average fraction of native contacts was %. The fact that this value is smaller than the asymptotic one, %, of the first type of potential indicates that the strength non-native interactions while weak enough to maintain stable the native state, can nevertheless compete with the native attractive interactions. The addition of the quasi-chemical interactions are therefore expected to be capable of accounting for sequence-specific non-native contact propensities in the partly-folded state. The sequence-dependent character of the non-native interaction differentiates the present approach from the early one of Wallin et al. [35] where the knot-promoting effect of non-native interactions was probed by systematically introducing attractive interactions between various pairs of segments of YibK.

For each of the two proteins and for each of the two energy functions, we generated trajectories each consisting of MC moves per amino acid (corresponding to 3000 units of MC time reported in Fig. 2 and Fig. 3), for a total of 75,000 CPU hours. The acceptance rate of the local MC moves for both proteins was nearly constant throughout the simulation and approximately equal to .

The entanglement of the structures sampled during the MC evolution was established using a combination of two unrelated knot detection schemes, which are described in the Materials and Methods. This choice was made to maximize the robustness of the criterion used to establish the knotted state of an open chain - which is mathematically properly defined only after the chain termini are joined by a segment or arc thus giving a circular chain (chain closure operation). As described in the Materials and Methods section we used many alternative closures for each chain and adopted a majority rule to single out chains that have non trivial self-entanglements. These chains can correspond to proper, fully developed knots (fully accommodated in the knotted structures) as well as improper ones (partly accommodated in the closing arcs).

In order to illustrate how the folding process differs for the two potential energy functions, we show in Fig. 2 the evolution of the gyration radius (upper panel) and the fraction of native contacts (lower panel) of the knotted AOTCase, obtained by employing these two potentials. It is seen that the effect of the non-native and electrostatic interactions results in the higher compactness of the protein globule, since the gyration radius in this case lies systematically below the one calculated with the purely native-centric model. At any given stage of the MC evolution, the fraction of established native contacts is systematically lower for non-native interactions thus indicating that the latter introduce frustration that slows down the folding dynamics. Analogous results hold for the unknotted OTCase, see top panel of Fig. 3.

The data in Fig. 3 represent how the average radius of gyration and fraction of formed native contacts evolve in the course of the folding simulations of the two transcarbamylases. It is seen that, over the duration of the simulation, the average fraction of formed native contacts grows to on average (the maximum value in all trajectories was . Overall, the probability of formation of native contacts decreases with the sequence separation of the amino acid pair, so that native -helical contacts are substantially more probable than inter-strand ones [48].

From the steady increase of the fraction of native contacts, , it is extrapolated that folding completion would occur on time-scales at least ten times larger than considered here. From the same figure it emerges that the radius of gyration gradually decreases to about 25 Å, which is larger than the native one, consistently with the less compact character of the partially folded states.

To characterize the overall propensity of the two proteins to form knots while still largely unfolded, we extracted configurations at regular intervals of the simulations and analyzed their topological state.

The knotting propensity of AOTCase, which is natively knotted, is illustrated in the upper panel of Fig. 4 which portrays the fraction of configurations that are properly or improperly knotted during a given time-window of the MC dynamics.

It is seen that when the purely native-centric potential is used, the knotting propensity is always negligible. However, when non-native interactions are added, the number of knotted configurations increases to a definite fraction of the total: at the end of the simulations, when only of the native contacts are formed, the fraction of conformations that are properly or improperly knotted is about . Notice that this value is comparable with the yield of purely native-centric coarse-grained models where pathways with a late-stage formation of knots are typically observed [36]. Within the limitations of coarse-grained approaches, the results indicate that sequence-dependent non-native interactions can produce a detectable fraction of configurations with the correct native entanglement already at early folding stages.

The analysis was repeated for the natively-unknotted OTCase and the results are shown in the lower panel of Fig. 4. The contrast with the case of the ATOCase is striking. In fact, the knotting probability is negligible not only for the purely-native case, but remains so even when non-native interactions are introduced.

The results indicate that the sequence-dependent non-native interactions – promoted by the quasi-chemical potential – increase dramatically the incidence of knots in the partially folded state of the AOTCase compared to the OTCase. Equivalently, the model calculations indicate that the two related natively-knotted and unknotted proteins have different knotting propensities already in the partially folded state, and that this difference can be ascribed to sequence-specific non-native interactions.

To further elucidate the mechanisms responsible for these differences we monitored several parameters in the course of the simulations of the two transcarbamylases. More specifically, we searched for systematic differences in the interactions that the termini of these proteins establish with other parts of the peptide chain and for preferential locations of fully-developed knots.

In this respect, it is important to point out that, in the course of the simulations for the AOTCase with non-native interactions, the process of knot formation is not irreversible. As illustrated in Fig. 5, trefoil knots can be formed and untied during each simulation. In particular, fully-developed knots can persists for up to one tenth of the duration of our simulations. Notably, only knots with the correct (i.e. native) chirality are observed.

By analysing the configurations preceding and following the knotting/unknotting events it is found that the change in topological state is typically caused by the threading of the helical C-terminus through loops formed by various protein regions.

Among the independent knotting events we identified six for which the stochastic closure returned a non-trivial topology in at least of the cases or the portion accommodating the knot had a depth of at least 20 amino acids. The analysis of the loop threading events leading to such persistent fully-developed knots showed that they involved the C terminus interacting with amino acids 55–65, 90–110, or 125–155. Only in one case it was observed the threading of the N-terminal through a loop involving segments 252–277.

Representative configurations are shown in the left panel of Fig. 6 where it is clear that the helical C-terminus of the AOTCase typically points towards the rest of the protein, and the stiffness of the helix facilitates the threading of various loop regions.

At variance with the above situation, for both potential energy functions the OTCase C-terminus is typically exposed to the solvent and pointing away from the rest of the protein, as in the example shown in the right panel of Fig. 6. The terminus also shows a lower propensity to form -helices. An analogous situation is found for the AOTCase in the presence of only native interactions.

The effect is quantitatively illustrated in Fig. 7, which portrays the average strength of the non-native interaction potential energy between the amino acids in the C-terminal -helix of the AOTCase or the OTCase and all the other residues in the chain. It is seen that the average non-native attraction is consistently stronger in the case of the knotted protein by about , which is a sizable amount considering that the average is taken over all sampled structures, irrespective of their compactness and knotted topology.

The same figure also illustrates that, if the amino acids in the C-terminal -helix of protein AOTCase are replaced by neutral hydrophilic residues (GLU, GLN, ASN), then the average non-native interaction energy becomes slightly repulsive, explaining the tendency of the -helix to point outwards. This provides an additional argument in support of the picture where the hydrophobicity character of the residues plays a role in the folding of knotted proteins [35].

Finally, in Fig. 8 we plot the average electrostatic potential energy between the -helix and the rest of the chain and show that, overall, the electrostatic interaction is about two orders of magnitude smaller than that of the quasi-chemical potential.

To further clarify the role of the C-terminal -helix in the knotting of the partially-folded states of the AOTCase, we have carried out another set of simulations on a mutant protein. The last 25 residues of the OTCase (which are involved in the C-terminal -helix) were substituted with the same number of residues that form the C-terminal -helix in the knotted AOTCase. Apart from such a substitution, all other attributes, namely the length of the chain and the native contact map, were identical to the unknotted protein. The outcome of the simulation is summarized in Fig. 9, from which we can conclude that the mutant protein forms a substantial fraction of knotted configurations in the presence of non-native interactions in its early stage of the folding.

A simplified coarse-grained protein model was used for a comparative study of early folding stages of two evolutionarily related transcarbamylase proteins: an AOTCase (PDB id 2g68) and an OTCase (PDB id 1pvv). The two proteins are well-alignable in sequence and structure and yet possess differently knotted native states: AOTCase is trefoil-knotted while OTCase is unknotted.

The role of sequence-dependent non-native interactions in promoting the correct native topology in the early folding stages was investigated by using two different energy functions in the simulations: one with a purely native-centric potential energy ( favoring only native contact interaction) and one with the additional contribution of quasi-chemical and electrostatic non-native interactions.

We found that in the absence of quasi-chemical interactions, neither protein shows an appreciable propensity to self-entangle in the early folding stages. However, once non-native interactions are introduced, the natively-knotted AOTCase does show a strongly enhanced propensity to form proper and improper knots with the correct native topology and chirality. By contrast, the knot enhancement effect is completely absent in the natively-unknotted OTCase.

Inspection of the ensemble of folding trajectories of the two proteins suggest that knotting in the partly unfolded AOTCase mostly results from the approach of the hydrophobic C-terminal -helix to other regions of the protein which are eventually threaded through. Because of the non-compact character of the partly-unfolded structures, the -helix in the C-terminal can also retract from the threaded regions, so that various events of formation/disruption of proper and improper knots can be observed in a given trajectory.

The influence of the C-terminal region on the different knotting propensity of the two carbamylases is further supported by the folding simulations for an “in silico mutant” of the OTCase obtained by replacing the C-terminal sequence with the one of the knotted AOTCase. In fact, the folding simulations based on the quasi-chemical non-native interactions yielded a portion of knotted structures similar to the natively-knotted AOTCase, from which the C terminus was taken.

We recall that, the seminal study of Wallin et al. [35], which was based on a coarse-grained model of YibK with ad hoc non-native interactions, had suggested the relevance of non-native interactions for steering the early formation of the native knotted topology (by the threading of a loop by the C-terminal). Our results, which are consistent with these conclusions, provide additional elements to the picture by taking advantage of a coarse-grained framework where the folding of two carbamylases with similar structures, and yet different knotted topology are compared on equal footing. In particular our results indicate that non-native interaction propensities that are encoded in the primary sequence, can favor or disfavor the formation of knots already at early folding stages.

The necessarily limited scope of the coarse-grained approach used here does not clarify whether additional pathways leading to a late-stage formation of knots can be present in transcarbamylases. It would be most interesting to address this standing issue in future studies within the present, or alternative comparative schemes.

We have adopted the coarse-grained model developed in Ref.s [44], [45], in which the effective degrees of freedom are the amino acid residues, represented by a spherical bead located at the position of the corresponding atom. The potential energy of the model consists of bonded and non-bonded terms. The bonded part of the of the potential consists of stretching potentials of the pseudo-bond - and pseudo-angle --, as well as potential for pseudo-torsions ---:(1)

All the values of the spring and energy constants appearing in the expressions of the bonded energy terms in Eqs. (2), (3) and (4) can be found in Ref. [45].

The non-bonded part of the potential consists of three terms, comprising native, non-native and electrostatic interactions, respectively:(5)

For pairs of residues that effectively repel each other, so that , the non-native potential energy function takes the following form:(8)

The effective Lennard-Jones interaction strength between residues and in the coarse-grained model of Kim and Hummer [45] is defined as(9)The coefficients are negative and coincide with the entries of the MJ matrix [46], while is an offset parameter. Hence, Eq. (8) defines a statistical knowledge-based potential which measures the preference of residue-residue interactions relative to residue-solvent interactions. The parameter scales the strength of the Lennard-Jones interaction compared to the physical electrostatic interactions. The two free parameters and are fitted in order to correctly reproduce the binding affinity of the broad set of experimentally well-characterized protein complexes [45]. As an illustration, the effective interaction strength between the neutral hydrophilic residues GLU and GLN is , so that effective interaction is repulsive, while for the hydrophobic residues ILE and LEU is , so that the effective interaction is attractive.

The non-native interactions in the force field of our coarse-grained model introduce frustration and make the potential energy surface quite rugged. As a consequence, even within such a simple model, molecular dynamics (MD) simulations of the folding for chains of several hundreds amino acids are very expensive. Within the simulation time intervals which were accessible to our computer resources, such MD trajectories did not allow to monitor significant changes in the chain conformations.

To cope with this problem, we have simulated MC dynamics, using an algorithm which combines different types of moves, namely:

The moves were accepted or rejected according to the standard Metropolis criterion.

MC algorithms based on local crankshaft and end moves are commonly employed in the polymer physics [41] to study dynamic properties, since it is was shown that they can mimic the intrinsic dynamics of a polymer in solution [50] at a much lower computational cost of MD simulations [52]. However, we emphasize that since our computational scheme is based on the MC evolution, we can not establish a quantitative mapping between the simulation time and physical time.

We have generated 150 independent MC trajectories for each system, starting from the same stretched coil configuration. In the early stage of the folding, these types of moves were attempted with the constant probabilities of 0.8, 0.1 and 0.1, respectively. Such an algorithm generates a rapid collapse of the chain from a fully stretched configuration to one in which the gyration radius is reduced from about 70A˚ to about 30A˚ in about MC steps per particle, that corresponds to 100 units of MC time (see Fig. 3). During such collapse, no knot was observed. At the end of this stage, the acceptance rate of the global pivot moves typically dropped below . After this happened, we switched off the pivot moves, except from those involving few residues near the the two terminal of the chain. From this point on, the conformational changes of the chain are driven by the local crank-shaft and cartesian moves with an overall acceptance of about .

When computing the fraction native contacts along the calculated MC trajectories, we adopt a criterion according to which two residues with index difference are said to be in contact if the distance of their is less than 7.5Å.

The conformations visited during the Monte Carlo dynamics were topologically classified by computing the Alexander determinants after suitable closure into a ring [17].

For robustness, two alternative closure schemes are used: the minimally-interfering closure [53] and a modified version of the stochastic one [54]. The minimally-interfering closure is used first because it is very computationally effective, in that it entails a single, optimally chosen closure. In case of positive knot detection we further validate the non-trivial entanglement by performing 100 closures where each terminus is prolonged far out of the protein along a stochastically chosen direction, and the end of the prolonged segments are closed by an arc (that does not intersect the protein). The stochastic exit directions are picked uniformly among those that are not back-turning. Specifically, they must form an angle of more than 90 with the oriented segment going from each terminus to the at a sequence distance of 10. If the majority of the stochastic closures return non-trivial Alexander determinants, than the conformation is non-trivially entangled. Such conformations can correspond to both proper, fully developed knots, and improper ones. The two can be distinguished using knot localization criteria [53], [55]: proper knots are entirely accommodated within the original protein chain, while improper ones span the exit segments. The knot type was determined using the scheme of Ref. [15], which is based on the KNOTFIND algorithm.