Based on the principle of the standard DNA-MFA [24], the Molecular Force Probes of the Protein-MFA consist of two molecular bonds in series, which are attached between two surfaces. The bond to be probed is the protein complex, where both proteins are attached covalently, one to the glass slide, which acts as the lower surface and the other to one strand of a DNA duplex which acts as the reference bond. A Cy5 dye is attached to the DNA strand coupled to the protein. The complementary DNA strand is labeled with a Cy3 dye, forming a FRET pair with the Cy5, as well as with a Biotin, which enables the coupling to the upper surface, a soft PDMS stamp functionalized with Streptavidin (Fig. 1A). The PDMS stamp has a size of 1 cm ×1 cm and features 16 pillars of 1mm in height and 1.1mm in diameter. A matching 4×4 array of MFPs is assembled on a glass slide, where each spot can be functionalized independently, enabling the measurement of 16 different protein pairs and/or the variation of the reference DNA (Fig. 1A). For the preparation of the measurement, first the lower proteins are attached to the glass slide via a PEG linker, then the pre-incubated complex of upper protein and DNA reference is added. Multiple washing steps after each incubation step minimize unspecific binding. Fluorescence “Start” images of the Cy5 (red excitation) and FRET signals are recorded for each spot on the glass slide with an inverted epi-fluorescence microscope. After the stamp is lowered gradually onto the glass slide using reflection interference contrast microscopy [35], an incubation step of 10 min allows for the coupling of the Biotins to the Streptavidin on the stamp. A piezo actuator enables retraction of the stamp with constant speed, gradually building up a force acting on both complexes of the MFPs until, statistically, the weaker one unbinds. Here, the retraction speed of 1 µm/s yields a force loading rate in the range of 10⁵ pN/s [27], [36]. After the retraction of the stamp, another set of “Final” fluorescence images is taken as the ratio of remaining dyes determines the outcome of the experiment.

The Normalized Fluorescence (NF) gives the number of broken upper DNA bonds normalized to the total number of Molecular Force Probes that have been under load. To determine the NF, the “RED“ and “FRET” signals recorded of every single spot before and after the actual force assay are processed after background correction. In the analysis, the ratio of RED Final to RED Start gives the density of still intact protein bonds in comparison to the initial amount of protein bonds.

The ratio of FRET values needs to be determined as well, as a remaining FRET signal after the force assay gives the number of MFPs that have not been under load and are thus still fully assembled (see Fig. 1B). For those MFPs, the Cy5 dye giving the RED signal is still attached to the surface yielding a false positive signal. By determining the FRET ratio (Ratio_FRET  =  FRET_Final/FRET_Start), those MFPs can be subtracted.

Normalization to the Coupling Efficiency CE  = 1– Ratio_FRET yields the Normalized Fluorescence:

(Equation 1)

Thus, a NF of 0.5 in this context means that the protein and the DNA complex have the same binding strength, a NF closer to 1 indicates that the protein complex is stronger than its DNA reference and vice versa for a NF closer to 0. For the analysis, the assumption is made that all MFPs are correctly assembled in the beginning, meaning that every protein-DNA complex has the second DNA strand attached to it. This is achieved by pre-incubating the DNA in a stoichiometry of 1∶2 before coupling to the protein. If only the lower protein is present with nothing bound to it, it does not give a fluorescent signal and can thus be neglected. The RED and FRET signals cannot be compared directly by division, as the fluorescence efficiency of a Cy5 dye is different to that of a Cy3-Cy5 FRET pair. As demonstrated before by Severin et al. [24], the pixel-by-pixel method offers the advantage of canceling out inhomogeneities due to the Gaussian illumination profile or coupling density as well as surface defects. Importantly, in the actual force assay all MFPs are tested simultaneously in the moment of the retraction of the stamp while the read-out can take place subsequently without time constraints [27]. Another very substantial advantage is that the force assay is not disturbed by complex ambients [37] since only fluorescence from the lower surface is measured.

Supporting information on chemical protocols and the measurement process can be found in Materials and Methods in S1 Supplement and S1 Fig.

One of the key challenges in the integration of functional proteins in the MFA was their covalent attachment, especially to the DNA. In principle, different possibilities exist for the coupling of proteins, although differing widely in yield, experimental effort and cost as well as the applicability for attachment to DNA [38], [39]. For the experiments conducted here, as for single-molecule force spectroscopy measurements in general, the site-specific attachment is of utmost importance, as the force needed to unbind a complex depends on the pulling geometry and thus on the position of the attachment [40]. Additionally, to prevent possible mis-assembly, it is reasonable to choose two different strategies for the attachment of the two proteins. In the study presented here, we employed the ybbR-tag [41] on the GFPs' N-termini to covalently attach 5′ Coenzyme A-modified DNA. The coupling is mediated by the Phosphopantetheinyl Transferase Sfp [42], [43] and offers the advantages of very high yield (up to 90%) [44] and a negligible size (11 amino acids) of the protein modification. Further, it has been successfully employed e.g. in single-molecule force spectroscopy experiments for the coupling of different proteins in varying experiments to DNA [44], [45] and surfaces [21], [46].

The nanobodies are attached to the glass slide by coupling of the free C-terminal Cysteine to the maleimide group of a heterobifunctional PEG linker [47]. As no extra components are needed, this is a good choice, provided that the protein does not harbor any other accessible or interfering Cysteine residues.

While not needed for the readout of the actual experiment, the use of GFP in this proof-of-principle system offers the advantage of an additional intrinsic control. We observed colocalization of GFP-fluorescence with the fluorescence of the Cy3 and Cy5 dyes, which confirms the specific interaction and correct assembly of the Protein MFPs. The surface density of the Protein MFPs estimated from the Cy5 signal is, similar to previous MFA experiments, about 10⁴ MFPs per µm² [23], [27]. The results for the NF values are reproducible over numerous experiments conducted independently (see S1 Table). However, the most valid conclusions on very small differences can be drawn from data received by a single experiment since it offers exactly the same environment and treatment such as pressure of the stamp and loading rate.

As with an old-fashioned scale, the MFA has its highest sensitivity to discriminate very small differences if it is well balanced, which in our case means that the binding strengths of both complexes are very similar, so that the NF lies close to 0.5. For pure DNA-MFA experiments the strength of the reference could easily be tuned by varying length, composition and conformation of the DNA duplex, reaching from 15pN for DNA in zipper mode (by opening the DNA like a zipper from the same end) [48] to about 65pN by implementing a 40 base-pair (bp) duplex in shear mode (where the DNA is sheared by applying the force at opposing 5′ termini). Higher average forces cannot be reached with short oligonucleotides as DNA reaches a force plateau at about 65pN when sheared due to the so-called BS-transition [49], [50]. Forces in between can be achieved by varying the number of base pairs in shear mode [51]. For a random protein-protein complex, no information is given about the interaction strength a priori.

In the study presented here, the tested protein complexes between nanobodies and GFPs were stronger than a 40bp duplex in shear confirmation, resulting in very high NF-values (see S1 Table). To determine small differences in binding strength, higher sensitivity at NF-values closer to 0.5 is highly desirable, which can be obtained by increasing the strength of the reference. To demonstrate the flexibility and robustness of the Protein-MFA, two different methods to enhance the mechanical stability of the DNA reference are presented here.

The stability of the DNA duplex can be altered intrinsically by nucleobase modification, methylation of the 5′ position in cytosines [52], [53] being a prominent example. Studied primarily in duplex formation with RNA for antisense gene inhibition [54], the modification of the 5′ position of pyrimidines with a propynyl group [55] results in an even higher increase in melting temperature than achieved by 5′ methylation [55]-[57]. The propynyl group is planar with respect to the heterocycle and extends into the major groove. It is thus expected to stabilize the duplex due to increased base-stacking and a smaller unfavorable entropy change [55], [57], [58]. In the experiments presented here, a 40bp DNA duplex is employed as a reference, where in the biotinylated strand 13 cytidines and 9 thymines are replaced by their corresponding propynyl bases. In comparison to this intrinsic stabilization, the stability can also be altered extrinsically by the addition of a DNA binding ligand. As has been shown in previous studies with the MFA [23], [59], sequence-specific binding of pyrrole-imidazole hairpin polyamides [60], [61] to the minor groove of the DNA helix enhances the stability of the duplex depending on the modification and concentration of the polyamide. For the experiment presented here, three hairpin polyamides with different affinities for the same DNA sequence have been employed. Polyamides P1 (K_D  = 105pM), (R)-P2 (here P2; K_D  = 44pM) and (R)-P3 (here P3; K_D  = 1442pM) described in Ho et al. [23] have been used in a concentration of 1 µM, approximately 1000 times higher than the saturation concentration, to ensure an excess of available ligand (see S2 Fig. for the DNA sequences as well as the chemical structures of the propynyl bases and the polyamides). P2 displays higher affinity than the sequence-specific binding P1, as it was modified with an amine substituent to introduce chiral selectivity. P3's lower affinity, despite also being chiral, results from a single base-pair mismatch [23].

Fig. 2A depicts the three different reference types used to identify the window of high sensitivity of the assay: unmodified 40 bp double-stranded DNA, intrinsically stabilized DNA using propynyl bases, and extrinsically stabilized DNA through the binding of sequence-specific polyamide ligands. Representative data for the different references testing Enhancer and Modified Enhancer against sfGFP are depicted in Fig. 2B with standard deviation. The original values can be found in S2 Table. Small differences in the size of the error bars can be attributed to measurement error. For all three types of reference, the outcome of the experiment – namely the relative higher NF values for the Modified Enhancer in comparison to Enhancer – stays the same, but the absolute NF values change depending on the reference. This was to be expected since the reference does not influence the nanobody-GFP complex itself so that the relative ranking of the stability of the complexes stays preserved. Whereas the incorporation of propynyl bases into a 40 bp DNA duplex reduces the NF values about 10%, employing a 20 bp DNA reference with added polyamide ligand leads to larger drops in NF depending on the polyamide. Notably, the closer the mean of the NF values for one reference is to 0.5, the larger the difference between the data points for Enhancer and Modified Enhancer becomes. This is consistent with the higher sensitivity of a well-balanced MFP.

The stronger binding of the Modified Enhancer can be attributed to its more positive charge (pI ≈9.89) when compared to the original Enhancer (pI ≈7.85), as sfGFP is slightly negatively charged (pI ≈6.4) under the given buffer conditions (pH 7.4). This ranking holds also true for the other GFP variants wtGFP (pI  = 6.17) and eGFP (pI  = 6.04), as can be seen in S1 Table. The incorporation of propynyl bases into the 40 bp DNA duplex obviously tunes the molecular balance closer to neutral, but with NF values of approximately 0.8 the result is still not entirely satisfying. Not much is known at present about the molecular mechanisms of the stabilization of the DNA duplex by the propynyl bases. The apolar methyl group is assumed to be buried in the core of the DNA double strand and by means of this contributes to the hybridization energy via hydrophobic interaction. Since the increase in stability of the reference depends on number and position of included propynyl bases [62], they represent a versatile tool for fine-tuning the reference bond. Whether this modification of the local interactions results in a change of the potential width or only deepens the potential well is not known yet and will be in the focus of future AFM-based single-molecule force spectroscopy studies.

In comparison to the intrinsic stabilization by propynyl bases, the addition of a polyamide has a much stronger impact on the NF, depending on the chosen polyamide. As expected, the lower the K_D, the higher the stabilization of the DNA reference and thus the lower the NF. While P3 already has a bigger effect on the NF than the incorporation of propynyl-bases, P1 tunes the MFA closest to neutral. In fact the addition of the polyamide P2 tunes the balance towards the other side resulting in an NF between 0.2 and 0.4. This enables to probe even stronger protein bonds than that of nanobody-GFP complexes. The polyamides used for the given study are known to bind into the minor groove of the DNA, thereby enhancing its mechanical stability, as has been found also for other DNA binding molecules [63], [64]. As shown in Ho et al. [23], such polyamides can be designed to modulate the stability of a DNA helix in a wide range. Following this principle, other DNA binding molecules might be candidates to change the DNA reference stability extrinsically as well.

Summarizing, DNA offers the possibility to introduce a very broad range of references with different mechanical and thermal stability, ranging from low forces of about 15 pN with DNA in zipper mode over shear mode DNA in various lengths to enhanced stability via intrinsic or extrinsic modification of the DNA. The dynamic range of the mechanical stability of DNA-based references can be extended even further towards higher stabilities by the use of DNA binding proteins such as EcoRI and p53 [27]. Protein-MFA is thus applicable for many different protein pairs of varying bond strength.

Fig. 3A depicts the result of one representative example measurement, where the binding between the nanobody Enhancer and the three different variants of GFP, namely enhanced GFP, wild type GFP, and superfolder GFP are compared. As shown in the ribbon model structure for wild type GFP [30], all GFP constructs are attached at their N-termini to the DNA reference while Enhancer is coupled to the glass slide via its C-terminus. For this measurement, the 20 bp DNA stabilized with polyamide P1 was used as a reference. P1 was chosen as its use could tune the NF in the measurement shown in Fig. 2B closest to neutral. All data points are derived from one contact process with a single stamp ensuring exactly the same conditions and thus minimizing measurement error. As the reference DNA is the same for all protein pairs, comparing the resulting NF values provides information about the differences in the binding strengths of the protein-protein interactions. Displaying the bulk readout of the extensive number of parallelized single-molecule measurements, sample histograms of protein spots with MFPs of all three GFPs are shown in Fig. 3B. In order to evaluate the outcome of the MFA experiment, the Normalized Fluorescence NF is calculated by dividing the fluorescence images according to equation 1. The most-likely NF is then determined by Gaussian fitting of the resulting count histogram.

While the NF values for the Enhancer-eGFP (0.255±0.023) and Enhancer-wtGFP (0.253±0.018) interaction are the same within experimental error, they both lie distinctively lower than the value for the Enhancer-sfGFP (0.353±0.018) construct. This corresponds to a higher ratio of resulting intact Enhancer-sfGFP complexes than Enhancer-eGFP or wtGFP complexes after force application, implying that for this specific pulling geometry the Enhancer-sfGFP interaction is stronger.

From the crystal structure of wtGFP binding Enhancer (PDB 3K1K), Kirchhofer et al. [30] determined 9 amino acids that form 13 direct contacts and 3 amino acids forming hydrophobic interactions. The alignment of the amino acid sequences of all three GFP variants (see S3 Fig.) shows that all interacting amino acids of wtGFP are conserved for eGFP, which is in good agreement with the similar binding strength observed in Fig. 3A. The difference in binding strength of sfGFP to Enhancer could result from the mutation of two of the amino acids which form direct contacts to Enhancer and all three amino acids responsible for the hydrophobic interaction. Notably, in force spectroscopy experiments the pulling geometry may have a significant impact on the unbinding force [40].

With the proof-of-principle system of nanobodies binding to GFPs, we successfully demonstrated the implementation of the Molecular Force Assay in parallelized measurements of protein-protein interactions. The reference strength of the DNA duplex can be adjusted as required both intrinsically through modification of the bases or extrinsically by binding of a ligand to ensure high sensitivity of the assay for the investigated interaction. In addition, the assay has a multiplexing capacity for different protein pairs and provides the high sensitivity and versatility of a fluorescence readout. With a moderate experimental effort, high statistics can be achieved in a single experiment with easy and very fast analysis. The parallel format of the assay also offers the advantage of testing the proteins only once, allowing the measurement of proteins that lose their original conformation upon application of force. With the current set-up, protein interactions that dissociate in the time span of the experiment can not be investigated. A solution would be an alternative set-up of the MFA such as presented in [65], where the upper part of the MFP is attached to the stamp. Also, at the moment only a limited number of protein-pairs can be tested simultaneously and to obtain absolute values the binding strength of the reference has to be known. Additional miniaturization and parallelization will further emphasize the main advantage of the Protein-MFA, namely the high sensitivity due to the comparative approach of the assay. It has already been shown [27], that the results for DNA-MFA do not change when the diameter of the MFP spot is reduced from 1 mm in our current standard set-up to approximately 20 µm. In Otten et al. [26] the MFA system was integrated into a microfluidic chip, enabling the measurement of 640 spots of MFPs simultaneously. The next goal will be to combine the parallelization and miniaturization with the expression and direct covalent attachment of the lower protein in a microfluidic chip, as demonstrated recently [21], to turn the Protein-MFA into a high-throughput method. Such a set-up would allow the additional measurement of standardized protein pairs with known rupture force in the same stamping process, which could provide a very robust way to gain even more accurate information about the absolute values of the rupture forces. Creating a “toolbox” of references will render the Protein-MFA applicable to measure an extensive number of protein pairs and a fast way to determine and compare binding strengths.