Identification of binding sites in protein structures

Abstract

In one aspect, a method is provided for identifying a residue in a particular conformation of a protein molecule that is capable of forming a stable bond between a compound and the protein molecule. The method can include identifying one or more residues from the conformation of the protein molecule to include in a perturbation set, the one or more residues exhibiting a protection factor that satisfies one or more thresholds. One or more residues may be excluded from the perturbation set based at least on the spatial arrangement and / or orientation of the one or more residues. One or more rounds of molecular dynamics simulations may be performed, the results of which are indicative of interactions between the compound and the residues in the perturbation set. The residues in the perturbation set may be identified as forming a stable binding between the compound and the protein molecule based at least on the results of the molecular dynamics simulation.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Application No. 63 / 347,798, entitled “IDENTIFICATION OF BINDING SITES IN A PROTEINSTRUCTURE” and filed on June 1, 2022, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] The subject matter described herein generally relates to the identification of one or more binding sites in the conformation of a protein molecule. Background Art

[0004] Molecular binding is a process in which two or more molecules (e.g., proteins, ligands, etc.) can interact to form a stable molecular structure. For example, molecular binding can include chemical bonding between a portion of a first molecule and a portion of a second molecule. The portion of the first molecule that is bound to the second molecule can include multiple binding sites. For example, in the case of a protein-ligand complex, each binding site in a protein molecule can include multiple binding residues, which are residues that participate in binding to a ligand. Various real-world applications (e.g., drug discovery, etc.) may require identification of a binding site in a molecule that can bind to another molecule. For example, the identity of the binding residues in a protein molecule can be used to design a ligand that can effectively bind to a protein molecule. Summary of the invention

[0005] Systems, methods, and articles, including computer program products, for identifying binding sites in protein molecules are provided. In some exemplary embodiments, a system including at least one processor and at least one memory is provided. The at least one memory may include program code that provides operations when executed by at least one processor. The operations may include: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set includes identifying one or more residues to be included in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further includes excluding at least a first residue from the first perturbation set, the distance between the at least first residue and the second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating an interaction between the compound and the first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0006] On the other hand, a method for identifying a binding site in a protein molecule is provided. The method may include: (a) determining a first perturbation set for a first conformation of the protein molecule, determining the first perturbation set includes identifying one or more residues to include in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further includes excluding at least a first residue from the first perturbation set, the distance between the at least first residue and the second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating an interaction between the compound and the first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0007] On the other hand, a computer program product is provided, which includes a non-transitory computer-readable medium storing instructions. The instructions may cause operations that can be performed by at least one data processor. The operations may include: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set includes identifying one or more residues to be included in the first perturbation set based at least on the protection factor of at least a portion of the residues in the protein molecule, and determining the first perturbation set further includes excluding at least a first residue from the first perturbation set, and the distance between the at least first residue and the second residue in the first perturbation set fails to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating interactions between the compound and the first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0008] In some variations, one or more features disclosed herein, including the following features, can optionally be included in any feasible combination.

[0009] In some variations, the protection factor associated with each residue in the first conformation may correspond to the difference between a first energy for the residue in a bound state and a second energy for the residue in an unbound state.

[0010] In some variations, the one or more residues are identified for inclusion in the first perturbation set based at least on a protection factor for the one or more residues satisfying one or more thresholds.

[0011] In some variations, the protection factor of the one or more residues may be determined to satisfy the one or more thresholds based at least on the value of the protection factor being within a percentile of a maximum protection factor value observed for the first conformation of the protein molecule.

[0012] In some variations, a percentile may be determined based at least on a magnitude of a difference between a maximum protection factor value and a plurality of other protection factor values ​​observed for the first conformation of the protein molecule.

[0013] In some variations, the percentile may be a value between 5 and 20.

[0014] In some variations, the interaction between the compound and the first plurality of residues in the first perturbation set may include at least a portion of the first plurality of residues in the first perturbation set forming an induced fit pocket within the first conformation of the protein molecule.

[0015] In some variations, each round of molecular dynamics simulation may simulate the time evolution of a coupled protein-structure-compound comprising a compound bound to a first conformation of a protein molecule at a first plurality of residues included in a first set of perturbations.

[0016] In some variations, a coupled protein-structure-compound may be generated based on at least a first set of perturbations and structural information specifying a spatial arrangement of atoms in a first conformation of the protein molecule in an unbound state.

[0017] In some variations, determining the first perturbation set may further comprise excluding at least a third residue from the first perturbation set, the third residue requiring a threshold amount of reorientation to interact with the compound.

[0018] In some variations, the threshold number of reorientations may be satisfied by: (i) the number of atoms in the third residue that need to be reoriented to interact with the compound, (ii) the angle of reorientation that one or more atoms in the third residue need to undergo to interact with the compound, and / or (iii) the distance that the one or more atoms in the third residue need to undergo to interact with the compound.

[0019] In some variations, a first vector may be determined from a center of geometry (COG) of a first plurality of residues in a first perturbation set and an alpha-carbon of a third residue. A second vector may be determined from the alpha-carbon to one of a delta-carbon, a gamma-carbon, or a beta-carbon present in the third residue. Satisfying a threshold amount of reorientation may be determined based at least on an angle formed by the first vector and the second vector satisfying one or more thresholds.

[0020] In some variations, the third residue may be retained in the first perturbation set based at least on the fact that the third residue is a glycine.

[0021] In some variations, determining the first perturbation set can further include determining a distance between a first center of mass of the first cluster of residues and a second center of mass of the second cluster of residues, determining that the distance fails to correspond to one or more dimensions of the compound, and excluding the first residue from the first perturbation set based at least on the first residue being part of the first cluster of residues.

[0022] In some variations, determining the first set of perturbations may further comprise applying a clustering technique to the first plurality of residues to partition the first plurality of residues into at least a first cluster of residues and a second cluster of residues.

[0023] In some embodiments, clustering techniques may include one or more of k-means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), expectation-maximization (EM) clustering using a Gaussian mixture model (GMM), and agglomerative hierarchical clustering.

[0024] In some variations, determining the first perturbation set may further include determining a first number of residues in the first cluster of residues and a second number of residues in the second cluster of residues, determining a first average distance between the first centroid and the residues in the first cluster; and determining a second average distance between the second centroid and the residues in the second cluster.

[0025] In some variations, determining the first perturbation set can further include excluding the first cluster of residues from the first perturbation set based at least on determining that: (i) the second cluster includes fewer residues than the first cluster, and (ii) a distance between a first centroid of the first cluster and a second centroid of the second cluster exceeds a sum of a first average distance between the first centroid and the residues in the first cluster and a second average distance between the second centroid and the residues in the second cluster.

[0026] In some variations, the result may comprise a distance between a first geometric center of the compound and a second geometric center of a plurality of backbone nitrogen (N) atoms in a first plurality of residues in a first perturbation set.

[0027] In some variations, the result may include the distance between a first geometric center of the compound and one or more amide nitrogen atoms present in the first plurality of residues in the first perturbation set.

[0028] In some variations, the one or more rounds of molecular dynamics simulations may include a first round of molecular dynamics simulations performed at a first temperature and a second round of molecular dynamics simulations performed at a second temperature.

[0029] In some variations, the one or more rounds of molecular dynamics simulations may include a first round of molecular dynamics simulations performed for a first length of time and a second round of molecular dynamics simulations performed for a second length of time.

[0030] In some variations, the one or more rounds of molecular dynamics simulations may include a first round of molecular dynamics simulations performed on a first conformation of the protein molecule associated with a first set of perturbations and a second round of molecular dynamics simulations performed on a second conformation of the protein molecule associated with a second set of perturbations.

[0031] In some variations, each of the first conformation and the second conformation may be a three-dimensional structure having a different spatial arrangement of atoms in the protein molecule.

[0032] In some variations, a second set of perturbations for a second conformation of the protein molecule can be determined. The determination can include at least one of: (i) identifying one or more residues to include in the second set of perturbations based at least on a protection factor of at least a portion of the residues in the protein molecule, (ii) excluding at least a third residue from the second set of perturbations, the third residue having a distance from a fourth residue in the second set of perturbations failing to correspond to one or more dimensions of the compound, and (iii) excluding at least a fifth residue from the second set of perturbations, the fifth residue requiring a threshold number of reorientations to interact with the compound.

[0033] In some variations, the one or more rounds of molecular dynamics simulations may include multiple rounds of molecular dynamics simulations. Each round of molecular dynamics simulations may subject the coupled compound-protein-structure comprising the compound bound to the protein molecule at the first plurality of residues in the first perturbation set to different conditions.

[0034] In some variations, the results of the one or more rounds of molecular dynamics simulations may include one or more conditions for the dissociation of the coupled compound-protein-structure.

[0035] In some variations, the one or more conditions may include a temperature at which the coupled compound-protein-structure dissociates.

[0036] In some variations, the one or more conditions may include a length of time after which the coupled compound-protein-structure dissociates.

[0037] In some variations, the one or more rounds of molecular dynamics simulations may include a round of molecular dynamics simulations performed at a higher temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0038] In some variations, the one or more rounds of molecular dynamics simulations may include a round of molecular dynamics simulations performed at a lower temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0039] In some variations, the one or more rounds of molecular dynamics simulations may include a round of molecular dynamics simulations that is performed for a longer period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0040] In some variations, the one or more rounds of molecular dynamics simulations may include a round of molecular dynamics simulations that is performed for a shorter period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0041] In some variations, a first plurality of residues in the perturbation set can be identified as forming a stable binding at least by determining one or more metrics that quantify the binding affinity between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations, and determining the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the one or more metrics.

[0042] In some variations, determining the first perturbation set may further include determining a distance between the first residue and the second residue, and excluding the first residue from the first perturbation set in response to determining that the distance between the first residue and the second residue exceeds the one or more dimensions of the compound.

[0043] Specific implementations of the current subject matter may include, but are not limited to, methods consistent with the description provided herein and articles including tangibly embodied machine-readable media that are operable to cause one or more machines (e.g., computers, etc.) to cause operations that implement one or more of the features described. Similarly, a computer system that may include one or more processors and one or more memories coupled to the one or more processors is also described. A memory that may include a non-transitory computer-readable or machine-readable storage medium may include, encode, store, etc., one or more programs that cause one or more processors to perform one or more of the operations described herein. A computer-implemented method consistent with one or more implementations of the current subject matter may be implemented by one or more data processors present in a single computing system or multiple computing systems. Such multiple computing systems may be connected and may exchange data and / or commands or other instructions, etc., via one or more connections, including, for example, via a network (e.g., the Internet, a wireless wide area network, a local area network, a wide area network, a wired network, etc.) via a direct connection between one or more computing systems in the multiple computing systems, etc.

[0044] The details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the following description. Other features and advantages of the subject matter described herein will become apparent with reference to the description and drawings, as well as the claims. Although certain features of the subject matter disclosed herein are described for illustrative purposes related to identifying binding sites in protein molecules, it should be readily understood that such features are not intended to be limiting. The claims following this disclosure are intended to define the scope of the subject matter protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate certain aspects of the subject matter disclosed herein and, together with the description, help explain some of the principles associated with the subject matter disclosed herein. This patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with one or more color drawings will be provided by the Patent Office upon request and payment of the necessary fee. In the drawings,

[0046] Figure 1 depicts a system diagram showing an example of a protein structure analysis system 100 according to some exemplary embodiments;

[0047] Figure 2A depicts a flow chart illustrating an example of a process for identifying residues in a protein molecule that are capable of providing a stable binding between a compound and the protein molecule, according to some exemplary embodiments;

[0048] Figure 2Bdepicts a flow chart showing an example of a process for determining one or more binding conformations of a protein molecule bound to a compound, according to some exemplary embodiments;

[0049] Figure 3 depicts a flow chart illustrating an example of a process for determining a perturbation set according to some exemplary embodiments;

[0050] Figure 4 depicts an example of a graph showing protection factors for residues included in a protein molecule according to some exemplary embodiments;

[0051] Figure 5 depicts examples of residues in chemical compounds and protein molecules identified as binding sites between chemical compounds and protein molecules according to some exemplary embodiments;

[0052] Figure 6 depicts schematic diagrams showing examples of protein molecules and residue clusters identified within protein molecules according to some exemplary embodiments;

[0053] Figure 7 depicts a schematic diagram showing the displacement between the respective geometric centers of two clusters of residues within a protein molecule according to some exemplary embodiments;

[0054] Figure 8 depicts a schematic diagram illustrating the exclusion of certain residues from an initial perturbation set of a protein molecule according to some exemplary embodiments;

[0055] Fig. 9 depicts a schematic diagram showing a portion of an example of a protein molecule having at least two side chains oriented in different directions according to some exemplary embodiments;

[0056] Fig.10 depicts a schematic diagram illustrating exclusion of certain residues from a perturbation set based on the orientation of the residues according to some exemplary embodiments;

[0057] Fig.11 depicts a block diagram showing an exemplary schematic diagram of an analysis controller according to some exemplary embodiments;

[0058] Fig.12 depicts a system diagram illustrating an exemplary implementation of an analysis controller according to some exemplary embodiments;

[0059] Fig.13 depicts a system diagram illustrating an example of a process for identifying a perturbation set according to some exemplary embodiments; and

[0060] Fig.14 Depicted is a block diagram illustrating an example of a computing system in accordance with some example embodiments.

[0061] Wherever practical, like reference numbers are used to refer to the same or like items in the drawings. DETAILED DESCRIPTION

[0062] The interaction between two molecules, such as the binding between a compound (e.g., a ligand and / or) and a protein molecule, can play an important role in biological processes. Therefore, understanding the dynamics of protein-compound interactions, including identifying potential binding sites on protein molecules for binding to compounds, may be desired by various scientific efforts (e.g., drug discovery). The binding affinity between a protein molecule and a compound may depend on whether the three-dimensional structure (e.g., secondary structure, tertiary structure, etc.) of the protein molecule is complementary to the three-dimensional structure of the compound. However, due to its flexible nature, the three-dimensional structure of a protein molecule may evolve over time, especially when the protein molecule is in close proximity to and interacts with the compound. In addition, in some cases, a population of protein molecules with the same primary structure (e.g., a sequence of amino acid residues) may still exhibit different three-dimensional structures. The terms "protein conformation", "conformation" and "conformer" are used interchangeably herein to refer to a specific three-dimensional structure of a protein molecule. The same amino acid residue sequence may be associated with a conformational aggregate (CE) containing multiple conformations (conformers), each of which is defined by the spatial arrangement of atoms in the constituent amino acid residues.

[0063] Prior art techniques that are capable of identifying portions of protein molecules that are energetically favorable for binding to compounds ignore the dynamic properties of protein molecules during the binding process, including changes in the three-dimensional structure of the protein molecules that occur when the protein molecules are in close proximity to and interact with the compounds. Therefore, conventional techniques are inaccurate in cases where the structural dynamics of the protein molecules affect the binding between the protein molecules and the compounds. Other prior art techniques rely on trial and error, in which the binding energy between the compound and the protein molecule is calculated at multiple positions on a specific conformation of the protein molecule before identifying the position with the minimum binding energy. However, purely trial-and-error-based methods that consume excessive computing resources and impose a large amount of running time are too inefficient to be feasible.

[0064] The interaction between a compound and a protein molecule (e.g., during the binding process) can change the three-dimensional structure of the protein molecule. For example, the presence of the compound can cause the reorientation of one or more amino acid residues in the protein molecule, thereby affecting its three-dimensional structure. Such changes can affect the ability of at least some residues to form a stable bond between the compound and the protein molecule. For example, one or more residues in a protein molecule can be reoriented to form an induced fit pocket, in which case the residues forming the pocket will have a higher probability of forming a stable bond with the compound. However, as noted, the prior art for identifying binding sites in protein molecules ignores the dynamic properties of protein molecules, including those generated by the interaction between protein molecules and compounds.

[0065] In contrast, according to some specific implementations of the current subject matter, the analysis controller may identify a perturbation set that includes one or more residues in a particular conformation of the protein molecule that are capable of forming a stable bond with the compound. The analysis controller may iteratively identify a perturbation set for each conformation of the protein molecule in order to account for the structural changes that the protein molecule undergoes when interacting and binding with the compound. In addition, it should be understood that the perturbation set of the protein conformation does not necessarily include every residue that will interact and bind with the compound. That is, while the residues included in the perturbation set are more likely to interact with the compound to form a bond between the compound and the corresponding protein conformation, other residues in the protein molecule that are not identified as included in the perturbation set may still interact with the compound as part of the binding process.

[0066] In some exemplary embodiments, the analysis controller may generate a separate perturbation set for each conformation of the protein molecule. For example, the analysis controller may identify one or more residues in the conformation for each conformation of the protein molecule to be included in the perturbation set. In some cases, the one or more residues may be identified based on a protection factor associated with a separate residue in the protein conformation to be included in the perturbation set of the protein conformation. In addition, in some cases, the perturbation set for the protein conformation may be further updated to exclude one or more residues based on the geometric features of the residues (including, for example, the relative position, direction, etc. of the residues in a specific conformation of the protein molecule). Before performing one or more rounds of molecular dynamics (MD) simulations on the coupled protein-structure-compound, the analysis controller may determine the structural information (e.g., three-dimensional coordinates, etc.) of the coupled protein-structure-compound, which is formed by a compound bound to the conformation of the protein molecule at the residues included in the perturbation set. For example, each round of molecular dynamics simulation may include simulated movements of dissociated coupled protein-structure-compounds at different temperatures. In some cases, one round of molecular dynamics simulations can be performed at a different temperature than another round (e.g., a previous round) of molecular dynamics simulations. Alternatively and / or additionally, one round of molecular dynamics simulations can be performed at the same temperature as another round (e.g., a previous round) of molecular dynamics simulations, but for an additional period of time. The analysis controller can determine whether the residues in the perturbation focus form a stable association between the protein conformation and the compound based at least on the results of the molecular dynamics simulations.

[0067] As noted above, in some exemplary embodiments, one or more residues in a particular protein conformation may be selected to be included in a corresponding perturbation set based at least on a protection factor associated with a single residue in the protein conformation. The protection factor of a residue may indicate the ability of the residue to interact with a compound, such as the ability to bind to a compound. For example, in some cases, the protection factor of a residue may correspond to the difference between a first energy of a residue in a bound state and a second energy of a residue in an unbound state. In some cases, the protection factor of a residue may be determined based on the amide hydrogen exchange (HX) rate of the protein conformation, and the amide hydrogen exchange rate value may be determined experimentally, such as by mass spectrometry, nuclear magnetic resonance, and / or similar methods. Residues exhibiting higher protection factors have a higher a priori probability of binding to a compound than residues exhibiting lower protection factors. Therefore, if the protection factor of one or more residues in a protein molecule meets one or more thresholds, the analysis controller may identify the one or more residues to be included in the perturbation set. In doing so, the analysis controller may identify one or more residues in the conformation of a protein molecule whose probability of forming a stable bond with a compound meets one or more thresholds to be included in the perturbation set.

[0068] In some cases, the ability of two separate residues in a specific conformation of a protein molecule to bind to a compound simultaneously may depend on their spatial arrangement in the conformation of the protein molecule, such as their relative positions. For example, if the distance between a first residue and a second residue (e.g., Euclidean distance, etc.) exceeds one or more dimensions of the compound (e.g., greater than the maximum dimension associated with the compound), at least because the compound cannot bind to both the first residue and the second residue at the same time, at least one residue can be excluded from the perturbation set. Therefore, in some cases, the analysis controller can determine the perturbation set of the protein conformation at least by excluding one or more residues based on the position of the residue in the conformation of the protein molecule. For example, when determining that the compound cannot bind to both the first residue and the second residue at the same time, the analysis controller can include the first residue in the perturbation set, but not the second residue. As described in more detail below, in some cases, the analysis controller can further refine the perturbation set with the first residue at least by excluding one or more residues whose orientation prevents them from forming a stable bond with the compound. In addition, it should be understood that the perturbation set of a specific protein conformation can be reconstructed by one or more changes to its constituent residues based on the results of molecular dynamics simulation (MD). For example, after one or more rounds of molecular dynamics simulations (MD), the perturbation set can be reconstructed in the case of protein molecules and compounds dissociated before performing one or more additional rounds of molecular dynamics simulations (MD) based on the reconstructed perturbation set.

[0069] In some cases, due to the spatial arrangement of two or more clusters of residues within a particular protein conformation, the two or more clusters of residues may not be able to bind to the compound at the same time. For example, if the distance between the first cluster of residues and the second cluster of residues (e.g., Euclidean distance, etc.) exceeds one or more dimensions of the compound (e.g., greater than the maximum dimension of the compound), at least one cluster of residues can be excluded from the perturbation set because the compound cannot bind to both clusters at the same time. In some cases, the analysis controller can identify one or more clusters of residues based on the corresponding positions (e.g., three-dimensional coordinates and / or similar coordinates) of individual residues in the protein conformation. In addition, in some cases, the analysis controller can identify the one or more clusters of residues at least by applying a clustering technique, which includes, for example, k-means clustering, mean shift clustering, density-based spatial clustering with noise applications (DBSCAN), expectation maximization (EM) clustering using a Gaussian mixture model (GMM), agglomerative hierarchical clustering, and / or similar clustering. As described in more detail below, in some cases, the analysis controller can further refine the perturbation set with the first cluster of residues by at least excluding one or more residues whose orientations prevent them from forming a stable association with the compound. In addition, in some cases, if the protein molecule and the compound dissociate after one or more rounds of molecular dynamics simulation (MD), the perturbation set for the conformation of the protein molecule can be reconstructed so that one or more additional rounds of molecular dynamics simulation (MD) can be performed based on the reconstructed perturbation set.

[0070] As noted, in some exemplary embodiments, the analysis controller may determine the perturbation set by excluding one or more residues from the perturbation set at least based on the orientation of the residue in a particular conformation of the protein molecule. For example, in some cases, the analysis controller may exclude a residue at least because the orientation of the residue reduces the likelihood of binding between the residue and the compound. Excluding a residue from the perturbation set corresponds to the observation that the binding between the residue and the compound may have a higher energy threshold when the orientation of the residue relative to the compound (e.g., when the compound approaches the protein molecule) requires the residue to undergo a significant reorientation in order to bind to the compound. Therefore, in some cases, if the orientation of the residue within the protein conformation requires the residue to undergo a threshold number of reorientations in order to bind to the compound, the analysis controller may exclude the residue. In some cases, this threshold number of reorientations may be satisfied, for example, by a threshold number of atoms in the residue (e.g., a threshold number of side chain atoms and / or main chain atoms) reorientation. Alternatively, and / or additionally, the threshold number of reorientations may be satisfied by the angle and / or distance of the reorientation of one or more atoms in the residue.

[0071] In some exemplary embodiments, the analysis controller can determine the stability of the binding provided by the residues in the perturbation set, and identify the binding stability based on at least the protection factor, spatial arrangement and / or orientation of the individual residues (or residue clusters) within the corresponding conformation of the protein molecule. For example, in some cases, the stability of the binding provided by the residues in the perturbation set can be determined at least by one or more rounds of molecular dynamics simulations (MD) based on the coupled protein-structure-compound, wherein the compound is bound to the conformation of the protein molecule at the residues included in the perturbation set. The coupled protein-structure-compound can be determined by applying one or more docking algorithms to generate complex structural information of the coupled protein-structure-compound based on the perturbation set and unbound structural information of the protein conformation. In some cases, the molecular dynamics simulation can be performed based on the complex structural information of the coupled protein-structure-compound, for example, proposed in a complex coordinate file associated with the coupled protein-structure-compound.

[0072] In some exemplary embodiments, the analysis controller may perform iterative rounds of molecular dynamics simulations (MD), wherein each round of molecular dynamics simulation subjects the coupled protein-structure-compound to different conditions until, for example, the coupled protein-structure-compound dissociates. For example, in some cases, the first round of molecular dynamics simulations may be performed at a temperature different from the second round of molecular dynamics simulations, so as to simulate the time evolution of the coupled protein-structure-compound at multiple temperatures. Alternatively and / or additionally, the second round of molecular dynamics simulations may be performed at the same temperature as the first round of molecular dynamics simulations, but for an additional time period. In some cases, if the coupled protein-structure-compound does not dissociate after one or more rounds of molecular dynamics simulations at the first temperature, the analysis controller may perform one or more additional rounds of molecular dynamics simulations at a second temperature, which in some cases may be higher than the first temperature. The analysis controller may continue to perform additional molecular dynamics simulations on the coupled protein-structure complex at successively higher temperatures and / or longer time periods until the coupled protein-structure-complex dissociates. In doing so, the analysis controller can determine and / or rank the stability of the bonds formed by the residues in the perturbation set by at least determining the temperature at which the coupled protein-structure-compound dissociates and / or the duration of the coupled protein-structure-compound dissociation (e.g., the length of time that the coupled protein-structure-compound is dissociated). For example, when it is determined that the coupled protein-structure-compound dissociates at a higher temperature and / or after a longer period of time, the analysis controller can determine that the stability of the bond between the compound and the protein conformation is greater at the residues included in the perturbation set.

[0073] In some exemplary embodiments, the analysis controller may perform multiple rounds of molecular dynamics simulations (MD) on different conformations of protein molecules in order to take into account changes in the three-dimensional structure of the same protein molecule, which are observed in the same molecular population over time and due to the folding of the protein molecule. For example, in some cases, the analysis controller may perform a first round of molecular dynamics simulation on a first conformation of the protein molecule and a second round of molecular dynamics simulation on a second conformation of the protein molecule. Here, the analysis controller may receive structural information (e.g., unbound coordinate files) for each conformation of the protein molecule, which indicates, for example, the spatial arrangement of various atoms in the protein molecule (e.g., the spatial positions of individual atoms relative to each other). In addition, each conformation of the protein molecule may be associated with a different perturbation set, at least because changes in the spatial three-dimensional structure of the protein molecule may affect the corresponding changes in residues that are more likely to form a stable bond with the compound. Therefore, the analysis controller may generate a first perturbation set for the first conformation of the protein molecule and a second perturbation set for the second conformation of the protein molecule. Each of the first perturbation set and the second perturbation set may include, for example, residues identified based on the protection factor, spatial arrangement and / or direction of individual residues (or residue clusters) within the corresponding conformation of the protein molecule. The analysis controller may determine the relative binding affinity and / or ranking between the compound and the protein molecule based at least on the results of the molecular dynamics simulation (MD), as indicated by the stability of the bond between the compound and the protein molecule across multiple conformations of the protein molecule.

[0074] Figure 1 A system diagram illustrating an example of a protein structure analysis system 100 according to some exemplary embodiments is depicted. Figure 1 , the protein structure analysis system 100 may include an analysis controller 110 communicatively coupled to a client device 130 via a network 140. The network 140 may be a wired network and / or a wireless network, including, for example, a local area network (LAN), a virtual local area network (VLAN), a wide area network (WAN), a public land mobile network (PLMN), the Internet, etc. The client device 130 may be a processor-based device, including, for example, a workstation, a desktop computer, a laptop computer, a high-performance computer, a smart phone, a tablet computer, a wearable device, etc.

[0075] In some exemplary embodiments, the analysis controller 110 may identify one or more residues in a protein molecule that are capable of forming a stable bond with a compound (eg, a ligand and / or an analog). Figure 1As shown, in some cases, the analysis controller 110 may include a perturbation set engine 112 that identifies one or more residues that can form a stable bond between the corresponding conformation of the protein molecule and the compound to include in each perturbation set associated with the protein molecule. For example, in some cases, the one or more residues that can provide a stable bond with the compound can be identified based on the protection factor, spatial arrangement and / or orientation of the individual residues in the corresponding conformation of the protein molecule. In addition, in Figure 1 In the example shown, the analysis controller 110 may include a molecular dynamics simulation (MD) engine 114 that performs one or more rounds of molecular dynamics simulations.

[0076] In some cases, the molecular dynamics simulation engine 114 may perform one or more rounds of molecular dynamics simulation for each perturbation set, with each round of molecular dynamics simulation being performed at a different temperature, or in some cases, at the same temperature but for an additional period of time. For example, for a first perturbation set 113a of a first conformation 119a of a protein molecule, the molecular dynamics simulation engine 114 may perform a first round of molecular dynamics simulation 115a at a first temperature, and a second round of molecular dynamics simulation 115b at the same first temperature or a different second temperature. Figure 1 As shown, the analysis controller 110 may include an evaluation engine 118, which determines whether the residues included in the first perturbation set 113a form a stable binding between the compound and the first conformation 119a of the protein molecule based on at least the results of the first round of molecular dynamics simulation 115a and the second round of molecular dynamics simulation 115b.

[0077] As described in more detail below, where the perturbation set engine 112 generates multiple perturbation sets, including a separate perturbation set for each conformation of the protein molecule, the molecular dynamics simulation engine 114 can perform one or more rounds of molecular dynamics simulations for each perturbation set (e.g., at different temperatures, for different lengths of time, and / or the like). For example, the molecular dynamics simulation engine 114 can perform a first round of molecular dynamics simulations 115a on a first perturbation set 113a for a first conformation 119a, and a second round of molecular dynamics simulations 115b on a second perturbation set 113b for a second conformation 119b. In these cases, the evaluation engine 118 can further determine the stability of the bond between the protein molecule and the compound across multiple conformations of the protein molecule based at least on the results of the first round of molecular dynamics simulations 115a and the second round of molecular dynamics simulations 115b.

[0078] To further illustrate, Figure 2AA flow chart illustrating an example of a process 200 for identifying residues in a specific conformation of a protein molecule that are capable of forming a stable binding between a compound and the protein molecule, according to some exemplary embodiments. Figure 1 and Figure 2A , process 200 may be performed by analysis controller 110 to determine, for example, whether residues included in a perturbation set of a protein conformation form a stable binding between a protein molecule and a compound (eg, a ligand and / or an analog).

[0079] At 202, the analysis controller 110 may determine a perturbation set for the conformation of the protein molecule. In some exemplary embodiments, the analysis controller 110, such as the perturbation set engine 112, may generate a first perturbation set 113a to include one or more residues from the first conformation 119a of the protein molecule. In some cases, the perturbation set engine 112 may generate the first perturbation set 113a by at least identifying one or more residues to include in the first perturbation set 113a based at least on a protection factor, spatial arrangement, and / or orientation of individual residues in the first conformation 119a of the protein molecule. For example, in some cases, the perturbation set engine 112 may determine to include a first residue in the first perturbation set 113a based at least on a protection factor of the first residue that satisfies one or more thresholds. Figure 1 In the example shown, the protection factor of the first residue can be included in the first protection factor data 117a received from the protection factor analyzer 116 (e.g., a mass spectrometer, a nuclear magnetic resonance (NMR) device, and / or the like). In some cases, if the protection factor value of the first residue falls within a certain percentile (or quantile) of the protection factor values ​​observed in the first conformation 119a of the protein molecule, the protection factor of the first residue can meet the one or more thresholds. For example, in some cases, if the value of the protection factor of the first residue is within X% (where X can be a value between 5 and 20) of the maximum protection factor value (or maximum value log (PF)), the protection factor of the first residue can meet the one or more thresholds. In this case, if the maximum value log (PF) is 2, then if its value is greater than 1.6, the protection factor of the first residue will fall into the 20th percentile. Alternatively, if the maximum value log (PF) is 4, then if the value of the first residue is greater than 3.2, then the protection factor of the first residue will fall into the 20th percentile. It will be appreciated that the value of percentile X may be determined and in some cases adjusted based on the magnitude of the difference between the maximum protection factor value observed for the first conformation 119a of the protein molecule and other protection factor values ​​for other residues in the first conformation 119a of the protein molecule.

[0080] However, in some cases, if the perturbation engine 112 determines that the distance (e.g., Euclidean distance) between a first residue (or a first cluster of residues including the first residue) and a second residue (or a second cluster of residues including the second residue) in the first conformation 119a of the protein molecule exceeds one or more dimensions (e.g., the largest dimension) associated with the compound, the perturbation set engine 112 may then determine to exclude the first residue from the first perturbation set 113a. As will be described in more detail below, the residues in the first conformation 119a of the protein molecule may be grouped into one or more clusters, and in some cases, if, for example, the distance (e.g., Euclidean distance and / or the like) between a first centroid of the first cluster and a second centroid of the second cluster exceeds one or more dimensions of the compound, such that the compound cannot simultaneously bind to both the residues in the first cluster and the residues in the second cluster, the first cluster residues may be excluded from the first perturbation set 113a. Excluding the residue from the first cluster reflects the observation that a compound that binds to a residue in the second cluster cannot simultaneously bind to a residue in the first cluster.

[0081] In some cases, the perturbation set engine 112 can further determine the first perturbation set 113a by excluding the one or more residues from the first perturbation set 113a based at least on the orientation of the one or more residues. Fig.10 In more detail, the α-carbon (c α ), the geometric center of the perturbation set containing the residue (COG), and the β-carbon in the residue (c β ),δ-carbon(c δ ) or γ-carbon (c γ ) to determine the orientation of the residue. In some cases, a residue can be excluded from the first perturbation set 113a if the residue is required to undergo a threshold number of reorientations in order to bind to the compound. For example, in some cases, if the number of atoms in the residue that are required to undergo reorientation meets one or more thresholds, the threshold number of reorientations can be satisfied. Alternatively, and / or additionally, the threshold number of reorientations can be satisfied if the angle and / or distance of the reorientation of one or more atoms in the residue meets one or more thresholds. In some cases, a residue can be excluded from the first perturbation set 113a if the side chain of the residue is required to undergo a threshold number of reorientations in order to bind to the compound. In these cases, if the first vector (consisting of the first position of the geometric center of the perturbation set containing the residue and the α-carbon (c α ) and the second vector (defined by the α-carbon (c α ) and the β-carbon (c β ),δ-carbon(c δ ) or γ-carbon (c γ) satisfies one or more thresholds, then the threshold number of reorientations can be satisfied.

[0082] At 204, the analysis controller 110 may perform one or more rounds of molecular dynamics simulation to generate results indicating the interaction between the compound and the plurality of residues in the perturbation set. In some exemplary embodiments, the molecular dynamics simulation (MD) engine 114 may perform one or more rounds of molecular dynamics simulation (MD) based at least on, for example, the first perturbation set 113 generated at operation 202 and the structural information describing the spatial arrangement of atoms within the first conformation 119a of the protein molecule. For example, in some cases, the structural information associated with the first conformation 119a of the protein molecule may indicate the position (e.g., coordinates) of atoms in the protein molecule. In some cases, in addition to the structural information of the first conformation 119a of the protein molecule, the molecular dynamics simulation engine 114 may also receive additional information, such as the position of one or more heavy atoms (e.g., oxygen, nitrogen, carbon, and / or) in the first conformation 119a of the protein molecule, the experimental pH for defining the ionization state on the side chain of the protein molecule, the force field generated for the compound (e.g., ligand), and / or the like.

[0083] In some example embodiments, the analysis controller 110 may generate a coupled compound-protein-structure (e.g., a protein-ligand complex) based at least on the first perturbation set 113a and the structural information of the first conformation 119a of the protein molecule. For example, in some cases, the analysis controller 110 may apply a docking algorithm to generate a coupled compound-protein-structure, wherein the compound is bound to the protein molecule at the residues included in the first perturbation set. Furthermore, in some cases, the analysis controller 110 may generate complex structural information of the coupled compound-protein-structure based at least on the unbound structural information of the first perturbation set 113a and the first conformation 119a of the protein molecule. In some cases, the molecular dynamics simulation engine 114 may perform one or more rounds of molecular dynamics simulations based at least on the complex structural information of the coupled compound-protein-structure. For example, the molecular dynamics simulation engine 114 may perform a first round of molecular dynamics simulation 115a at a first temperature, and perform a second round of molecular dynamics simulation 115b at the same first temperature for an additional length of time or perform the second round of molecular dynamics simulation at a second temperature (different from the first temperature). Figure 2B , Fig.11 and Fig.12 The iterative rounds of molecular dynamics simulations (MD) are described in more detail in .

[0084] At 206, the analysis controller 110 may identify the plurality of residues in the perturbation set as forming a stable binding between the compound and the conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulation. In some exemplary embodiments, the results of the one or more rounds of molecular dynamics simulation, such as the results from the first round of molecular dynamics simulation 113a and the second round of molecular dynamics simulation 113b, may include the temperature at which the coupled compound-protein-structure dissociates and / or the duration of the coupled compound-protein-structure (e.g., the length of time the coupled compound-protein-structure remains bound). In some cases, the evaluation engine 118 may determine one or more metrics (e.g., a satisfaction score, a divergence score, etc.) that quantify the binding affinity between the compound and the first conformation 119a of the protein molecule based at least on the results of the molecular dynamics simulation. Furthermore, in some cases, the evaluation engine 118 may identify the residues in the perturbation set as forming a stable binding between the compound and the first conformation 119a of the protein molecule based at least on the one or more metrics satisfying one or more thresholds. Fig.11 and Fig.12 The analysis performed to identify the set of perturbations as forming stable binding between the compounds and specific conformations of the protein molecule is described in further detail.

[0085] Figure 2B A flow chart illustrating another example of a process 250 for determining one or more binding conformations of a protein molecule bound to a compound according to some exemplary embodiments is depicted. Figure 1 and Figure 2B , process 250 can be performed by the analysis controller 110 to determine the binding affinity between the protein molecule and the compound (e.g., a ligand and / or an analog) based on the binding stability between the compound and the multiple conformations of the protein molecule. As noted, the folding of the protein molecule may cause a change in the three-dimensional structure of the protein molecule. For example, the protein molecule may present a first conformation 119a at a first time point and a second conformation 119b at a second time point. In addition, at any time point, a population of the same protein molecule may include multiple conformations of the protein molecule, including, for example, the first conformation 119a and the second conformation 119b. Changes in the conformation of the protein molecule can change the residues in the protein molecule that are capable of forming a stable bond with the compound. Therefore, in some exemplary embodiments, the analysis controller 110 can determine a plurality of perturbation sets, each perturbation set being associated with a different conformation of the protein molecule and including one or more residues in the protein molecule that are capable of forming a stable bond with the compound, while the protein molecule presents a corresponding three-dimensional structure. As described in more detail below, process 250 may be performed to take into account the structural dynamics of a protein molecule, including the temporal evolution of its three-dimensional structure and the concomitant changes in the interactions between the protein molecule and chemical compounds.

[0086] At 252, the analysis controller 110 may determine a first perturbation set for the first conformation of the protein molecule. In some exemplary embodiments, the analysis controller 110, such as the perturbation set engine 112, may determine the first perturbation set 113a for the first conformation of the protein molecule. Figure 1 In the example shown, the perturbation set engine 112 may determine the first perturbation set 113a based on at least first protection factor data 117a associated with the first conformation 119a of the protein molecule (e.g., protection factor data received from the protection factor analyzer 116). Alternatively and / or additionally, the perturbation set engine 112 may determine the first perturbation set 113a based on the spatial arrangement and / or orientation of atoms in individual residues forming the first conformation 119a of the protein molecule.

[0087] At 254, the analysis controller 110 may determine a second perturbation set for the second conformation of the protein molecule. In some exemplary embodiments, the analysis controller 110, such as the perturbation set engine 112, may determine a second perturbation set 113b for the second conformation of the protein molecule. For example, Figure 1 In the example shown, the perturbation set engine 112 may determine the second perturbation set 113b based at least on the second protection factor data 117b associated with the second conformation 119b of the protein molecule (e.g., protection factor data received from the protection factor analyzer 116). Alternatively and / or additionally, the perturbation set engine 112 may determine the second perturbation set 113b based on the spatial arrangement and / or orientation of atoms in the individual residues that form the second conformation 119b of the protein molecule.

[0088] At 256, the analysis controller 110 may perform at least a first round of molecular dynamics simulation to generate a first result indicative of an interaction between the compound and a first plurality of residues in the first perturbation set. In some exemplary embodiments, the analysis controller 110, such as the molecular dynamics simulation engine 114, may perform one or more rounds of molecular dynamics simulation (MD) on a first coupled compound-protein-structure, such as a first round of molecular dynamics simulation 115a, corresponding to the compound bound to a first conformation 119a of a protein molecule at residues included in the first perturbation set 113a. In some cases, the molecular dynamics analysis engine 114 may perform multiple rounds of molecular dynamics simulation on the first coupled compound-protein-structure, such as at different temperatures, for different durations, etc. Multiple rounds of molecular dynamics simulation may be performed to determine, for example, a first temperature at which the first coupled compound-protein-structure dissociates and / or a first duration of the first coupled compound-protein-structure. In doing so, the analysis controller 110, eg, the evaluation engine 118, may determine whether the first conformation 119a of the protein molecule is capable of forming a stable binding with the compound at the residues included in the first perturbation set 113a.

[0089] At 258, the analysis controller 110 may perform at least a second round of molecular dynamics simulation to generate a second result indicating an interaction between the compound and a second plurality of residues in the second perturbation set. In some exemplary embodiments, the analysis controller 110, such as the molecular dynamics simulation engine 114, may perform one or more rounds of molecular dynamics simulation (MD) on a second coupled compound-protein-structure, such as a second round of molecular dynamics simulation 115b, corresponding to a compound bound to a second conformation 119b of a protein molecule at residues included in the second perturbation set 113b. For example, in some cases, the molecular dynamics analysis engine 114 may perform multiple rounds of molecular dynamics simulation on the second coupled compound-protein-structure at different temperatures, for different durations, and / or the like. Furthermore, in some cases, multiple rounds of molecular dynamics simulation may be performed to determine, for example, a second temperature at which the second coupled compound-protein-structure dissociates and / or a second duration of the second coupled compound-protein-structure. In doing so, the analysis controller 110, eg, the evaluation engine 118, may determine whether the second conformation 119b of the protein molecule is capable of forming a stable binding with the compound at the residues included in the second perturbation set 113b.

[0090] At 260, the analysis controller 110 may determine the binding affinity between the compound and the protein molecule based at least on the first result and the second result. In some exemplary embodiments, the analysis controller 110, such as the evaluation engine 118, may determine the binding affinity between the compound and multiple conformations of the protein molecule based at least on the results of the molecular dynamics simulation of different conformations of the protein molecule. As noted, the evaluation engine 118 may determine the bonding stability between the compound and the protein molecule in the first conformation 119a (e.g., at operation 256) and the bonding stability between the compound and the protein molecule in the second conformation 119b (e.g., at operation 258). Doing so may take into account the structural dynamics of the protein molecule, which includes changes in the three-dimensional structure of the protein molecule over time.

[0091] Therefore, in some cases, the evaluation engine 118 can further determine one or more metrics (e.g., satisfaction scores, score scores, and / or similar scores) that quantify the binding affinity between the compound and the protein molecule based on the bonding stability between the compound and each conformation of the protein molecule. For example, in some cases, if the compound is able to form a stable bond with a threshold number of conformations of the protein molecule, the evaluation engine 118 can determine that the binding affinity between the compound and the protein molecule meets one or more thresholds. Alternatively and / or additionally, the evaluation engine 118 can identify one or more of the first conformation 119a and the second conformation 119b as a stable docking conformation (or most stable conformation) of the protein molecule based at least on the results of the first round of molecular dynamics simulation 115a performed on the first conformation 119a and the second round of molecular dynamics simulation 115b performed on the second conformation 119b. In the case where the compound is able to form a stable bond with multiple conformations of the protein molecule, the evaluation engine 118 can determine that multiple conformations of the protein molecule are able to stably bind to the compound.

[0092] Figure 3 A flow chart illustrating an example of a process 300 for determining a perturbation set according to some exemplary embodiments is depicted. Figure 1 , Figure 2A-2B and Figure 3 , process 300 can be performed by analysis controller 110 (e.g., perturbation set engine 112) to determine a perturbation set for a specific conformation of a protein molecule. In some cases, process 300 can implement operation 202 of process 200 and operations 252 and 254 of process 250.

[0093] At 302, the analysis controller 110 may identify one or more residues to include in a perturbation set based at least on the protection factor of each residue in the conformation of the protein molecule. In some exemplary embodiments, the analysis controller 110, such as the perturbation set engine 112, may generate a perturbation set, such as the first perturbation set 113a or the second perturbation set 113b, at least by identifying one or more residues in a plurality of regions in the corresponding protein conformation that exhibit a protection factor that satisfies one or more thresholds. For example, in some cases, a perturbation set may be determined by including in the perturbation set one or more residues from the protein molecule that exhibit a protection factor above a threshold. Figure 4 An example of a protein conformation 402 and a protection factor graph 404 is shown, which depicts the value of the protection factor associated with each residue in the protein conformation 402. The protection factor graph 404 includes the value of the protection factor as a function of the residues in the protein conformation 402. As noted, in some cases, one or more residues whose protection factors meet one or more thresholds may be included in the perturbation set. In some cases, the one or more thresholds may include a minimum protection factor value, a maximum protection factor value, and / or the like. Alternatively, the one or more thresholds may include a percentage of the maximum protection factor value of the residues in the protein molecule (e.g., 70% of the maximum protection factor value). In some cases, the perturbation set engine 112 may generate a perturbation set by including a threshold number of residues in the perturbation set (e.g., a maximum number of residues, a minimum number of residues, and / or the like). It should be understood that the number of residues included in the perturbation set, including the aforementioned threshold number of residues, may be fixed or variable between molecular dynamics simulation (MD) rounds. In Figure 4 In the example shown, three residues (labeled 1, 2, and 3) in the protein conformation 402 are identified as being associated with protection factors above a threshold, and are therefore identified by the perturbation set engine 112 for inclusion in the perturbation set.

[0094] At 304, the analysis controller 110 may exclude one or more residues from the perturbation set based at least on the spatial arrangement of the residues in the perturbation set. In some exemplary embodiments, determining the perturbation set may include excluding the one or more residues from the perturbation set based on the spatial arrangement of the one or more residues in the protein conformation. For example, if the distance between the first residue and the second residue in the protein conformation exceeds one or more dimensions of the compound, the analysis controller 110 (e.g., the perturbation set engine 112) may exclude the first residue. In some cases, for example, if the Euclidean distance between the nearest two atoms on the first residue and the second residue exceeds the maximum dimension of the compound, the perturbation set engine 112 may exclude the first residue.

[0095] In some cases, if a compound bound to a protein conformation at a residue included in the perturbation set dissociates, for example, after one or more rounds of molecular dynamics simulations (MD), the perturbation set engine 112 can reconstruct the perturbation set to include the second residue but not the first residue. In some cases, the analysis controller 110 can further refine the perturbation set with the first residue (and / or the reconstructed perturbation set with the second residue) by at least excluding one or more residues, the orientation of which prevents them from forming a stable binding with the compound. In addition, in some cases, one or more subsequent rounds of molecular dynamics simulations can be performed to evaluate the stability of the binding formed by the residues in each perturbation set. In doing so, the perturbation set engine 112 can generate a perturbation set for each conformation of the protein molecule, and in some cases, the perturbation set can be reconstructed based on the results of the molecular dynamics simulation (MD).

[0096] Figure 5 An example of a compound 502 and a protein molecule 402 including three residues (labeled 1, 2, and 3) that are identified as included in the perturbation (e.g., at operation 302) is depicted. Compound 502 is characterized by lengths L1, L2, and L3 along three axes (e.g., orthogonal axes). If the lengths L1, L2, and L3 (or the maximum lengths among the lengths L1, L2, and L3) are less than, for example, the distance between residue cluster 1 and residue cluster 3 (e.g., the Euclidean distance), compound 502 may not be able to bind to residues in both residue cluster 1 and residue cluster 3 simultaneously. Similarly, if the lengths L1, L2, and L3 (or the maximum lengths among the lengths L1, L2, and L3) are less than, for example, the distance between residue clusters 2 and 3 (e.g., the Euclidean distance), compound 502 may not be able to bind to residues in both residue clusters 2 and residue clusters 3 simultaneously. These observations may indicate that a single perturbation set may not include residues in both residue cluster 1 and residue cluster 3, or residues in both residue cluster 2 and residue cluster 3. Conversely, when the distance (eg, Euclidean distance) between residue cluster 1 and residue cluster 2 is less than at least one of lengths L1, L2, or L3, each residue in residue cluster 1 and residue cluster 2 may be included in the perturbation set.

[0097] In some cases, in addition to or instead of excluding residues based on compound dimensions (in some cases with additional constants to allow for flexibility of the protein), the analysis controller 110 will instruct the perturbation set engine 112 to identify clusters of residues to include in the perturbation set and / or exclude from the perturbation set. For example, in some cases, the residues in the protein molecule can be grouped into clusters, such as by applying clustering techniques before excluding one or more residue clusters from the perturbation set. In addition to or instead of excluding individual residues from the perturbation set, the perturbation set engine 112 can identify clusters of residues to exclude from the perturbation set in order to take into account neighborhoods of neighboring residues that can and / or cannot bind to the compound due to the physical dimensions of the compound. As described in more detail below, a first cluster of residues for exclusion can be identified based on the number and position of the residues included in the cluster and the centroid of the cluster.

[0098] Examples of clustering techniques may include one or more of k-means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), expectation-maximization (EM) clustering using a Gaussian mixture model (GMM), and agglomerative hierarchical clustering. Figure 6 A depicts the residues in the protein conformation before clustering, while Figure 6 B depicts the residues in the protein conformation after clustering. Figure 6 In A, residues in the protein conformation are represented by individual spheres. Figure 6 The result of applying the clustering technique, shown in (B), includes a first cluster 612 of residues represented by spheres labeled "1" and a second cluster 614 of residues represented by spheres labeled "2". Figure 7 A schematic diagram of a first cluster 612 and a second cluster 614 is depicted. The first cluster 612 has a first characteristic position 702 and the second cluster 614 has a second characteristic position 704. The first characteristic position 702 and the second characteristic position 704 may be the centroids of the first cluster 612 and the second cluster 614, respectively. The first cluster 612 may be characterized by a first average distance d1 and the second cluster 614 may be characterized by a second average distance d2, where

[0099] and

[0100]

[0101] Where n represents the number of residues in the first cluster 612, and m represents the number of residues in the second cluster 614; |d i | is the distance between the ith residue in the first cluster 612 and the centroid 702 of the first cluster 612; and |s i| is the distance between the i-th residue in the second cluster 614 and the centroid 704 of the first cluster 612. The displacement vector R indicates the displacement of the second centroid 704 relative to the first centroid 702. The distance between the two centroids can be described as the absolute value of the displacement vector R. Based on the foregoing, if the second cluster 614 has fewer residues than the first cluster 612, and if the absolute value of the displacement vector R is greater than the sum of the first average distance d1 and the second average distance d2 (or |R|>(d1+d2)×constant), the second cluster 614 can be excluded.

[0102] In addition to excluding the second cluster 614, one or more individual residues in the first cluster 612 (e.g., residues selected for inclusion after excluding the second cluster 614) may be further excluded from the perturbation set based on the orientation of one or more residues in the first cluster 612. Figure 8 The residues in the first cluster 612 represented by the spheres marked as "3" in the perturbation set are retained, while those residues represented by the spheres marked as "1" are selected for exclusion based on the orientation of those residues. In some cases, the residues represented by the spheres marked as "1" can be excluded from the perturbation set based at least on those residues that need to undergo a threshold amount of reorientation in order to bind to the compound. If the number of atoms in the residues that need to undergo reorientation meets one or more thresholds, the threshold number of reorientations can be met. For example, some residues represented by the spheres marked as "1" may include a threshold number of atoms that need to undergo reorientation in order to interact with the compound. Alternatively and / or additionally, some residues represented by the spheres marked as "1" may include one or more atoms whose angle of reorientation and / or distance of reorientation meet one or more thresholds. In some cases, some residues represented by the spheres marked as "1" may include side chains that need to undergo a threshold amount of reorientation in order to bind to the compound. In these cases, if the first vector (the first position of the geometric center of the perturbation set containing the residue and the α-carbon (c α ) and the second vector (defined by the α-carbon (c α ) and the β-carbon (c β ),δ-carbon(c δ ) or γ-carbon (c γ ) satisfies one or more thresholds, then the threshold number of reorientations can be satisfied.

[0103] return Figure 3At 306, the analysis controller 110 may exclude the one or more residues in the perturbation set based at least on the orientation of the one or more residues in the perturbation set. In some exemplary embodiments, determining the perturbation set may further include excluding one or more residues (e.g., from the plurality of residues selected at operation 302, from a plurality of residues excluded from those identified at operation 304, and / or similar residues) based at least on the orientation of the one or more residues and / or one or more constituent atoms of the one or more residues. For example, in some cases, a residue may be excluded from the perturbation set if the orientation of the residue requires a threshold amount of change to interact with the compound. Fig.10 An exemplary calculation for identifying residues for exclusion based on their orientation and / or the orientation of their constituent atoms is shown. In some cases, if the number of atoms in the residue that are oriented away from the compound (e.g., oriented at an angle greater than a threshold angle relative to the compound) meets one or more thresholds (e.g., exceeds a certain number), then the above threshold number changes may be met. In this case, the residue may be excluded because the binding of the compound to the second residue will require additional energy in order to reorient the residue. Therefore, the residue may have a lower probability of forming a stable bond with the compound.

[0104] Fig. 9 An exemplary portion 900 of a protein conformation having multiple residues is shown. Fig. 9 As shown, some residues in the protein conformation have their side chains oriented toward the first side (side 1), while other residues in the protein conformation have their side chains oriented toward the second side (side 2). If a compound approaches the protein molecule from the first side (side 1), the possibility of interaction (or binding) between the compound and the residues whose side chains are oriented toward the second side (side 2) of the protein molecule is low. Similarly, if a compound approaches the protein molecule from the second side (side 2), the possibility of interaction (or binding) between the compound and the residues whose side chains are oriented toward the first side (side 1) is low.

[0105] Fig.10 An exemplary method for excluding or including residues based on their orientation is shown. Fig.10 An exemplary residue 1000 is shown having a single α-carbon (denoted as c) disposed at a certain position (eg, having spatial coordinates (x, y, z)). a ). Residue 1000 can be part of a perturbation set containing one or more other residues. Each residue in the perturbation set, including residue 1000, can be associated with two directional unit vectors (e.g., vectors of magnitude 1). For example, if residue 1000 is considered the i-th residue in the perturbation set, residue 1000 can be associated with an α-carbon (c ) pointing from the geometric center (COG) of the perturbation set toward residue 1000. a)'s first unit vector (in Fig.10 In the expression ), and from the α-carbon of residue 1000 (c a ) points to the δ-carbon (if the δ-carbon is present), the γ-carbon of residue 1000 (if the γ-carbon is present), or the β-carbon of residue 1000 (if the β-carbon is present). or in Fig.10 Marked as ). If residue 1000 is a glycine without a β-carbon, residue 1000 can be included in the perturbation set without undergoing any orientation-based exclusion. Otherwise, if residue 1000 is not a glycine, residue 1000 can remain in the perturbation set if the following constraints are met:

[0106] where 0≤θ≤π (e.g., ).

[0107] In some cases, residue 1000 may not have a second unit vector b i (or Fig.10 In ) (e.g., such as in the case for glycine), in which case residue 1000 can also remain in the perturbation set without undergoing orientation-based exclusion.

[0108] In some cases, the geometric center of the perturbation set as a whole (COG) can be defined by the spatial coordinates (e.g., three-dimensional coordinates (x, y, z)) of the backbone nitrogen atom (N) of each residue included in the perturbation set. It should be understood that the geometric center of the perturbation set (COG) can be defined for each frame of a molecular dynamics simulation (MD) trajectory t. Therefore, the geometric center of the perturbation set for a frame in a molecular dynamics simulation (MD) trajectory t is can be determined based on the following equation, where represents the vector r from the origin of the reference frame to the main-chain nitrogen atom of the i-th residue in the perturbation set i , and N is the number of residues in the perturbation set.

[0109]

[0110] Fig.11 An exemplary schematic diagram of the analysis controller 110 is shown, which includes a perturbation set engine 112 and a molecular dynamics simulation engine 114 as well as a first database 1104 and a second database 1108. The molecular dynamics simulation engine 114 may receive from the first database 1104 a first conformation 119a of a protein molecule and at least first structural information of a first perturbation set 113a associated with the first conformation 119a generated by the perturbation set engine 112.

[0111] The first database 1104 (also referred to as an unbound protein structure database) may include structural information (e.g., unbound coordinate files) of multiple conformations (or conformers) of protein molecules. The structural information of the protein conformation may indicate, for example, the shape of the protein conformation, including indicating the shape of the protein conformation by specifying the spatial arrangement of the constituent atoms. As described in more detail below, each conformation of the protein molecule may be generated by a protein structure information generation algorithm (e.g., an accelerated molecular dynamics algorithm and / or a similar algorithm) that simulates the time evolution of the protein molecule (e.g., the dynamics of the protein) and captures the structural configuration of the protein molecule at various time instances during the particular trajectory (e.g., the spatial arrangement of individual residues and / or constituent atoms). The structural configuration of each individual protein conformation and the corresponding perturbation set are provided as input to a molecular dynamics simulation (MD) engine 114.

[0112] The perturbation set engine 112 can receive first structural information of the first conformation 119a (e.g., from the first database 1104) and generate a first perturbation set 113a. As noted, the perturbation set engine 112 can generate a first perturbation set 113a based at least on the protection factor, spatial arrangement, and / or orientation of the residues in the first conformation 119a of the protein molecule (e.g., by performing Figure 3 The process 300 shown in FIG. 1 is used to identify one or more residues in the first conformation 119a of the protein molecule to be included in the first perturbation set 113a. In the case where the perturbation set engine 112 generates the first perturbation set 113a by excluding one or more clusters of residues in the first conformation 119a of the protein molecule, the analysis controller 110 may further include a clustering engine that divides the residues in the protein molecule into one or more clusters. The molecular dynamics simulation engine 114 may perform one or more molecular dynamics simulations based on the first conformation 119a of the protein molecule and the first structural information of the first perturbation set 113a, and the evaluation engine 118 may determine whether the residues in the first perturbation set 113a are capable of forming a stable binding between the compound and the protein molecule based at least on the results of the molecular dynamics simulation.

[0113] Fig.12 2 shows an exemplary implementation of the analysis controller 110 according to some exemplary embodiments. Fig.12As shown, in some cases, the molecular dynamics simulation engine 114 may include a guided docking system that may receive a first perturbation set 113a (e.g., from the perturbation set engine 112) and a first conformation 119a of a protein molecule in an unbound state (e.g., from the first database 1104). The guided docking system may generate a complex coordinate file that includes structural information of a coupled protein-structure-compound, in this case, a compound (e.g., a ligand) that is bound to the first conformation 119a of the protein molecule. For example, in some cases, a complex coordinate file may be generated by clustering individual frames of a molecular dynamics simulation (MD) based on the positions of atoms in the residues included in the first perturbation set 113a and selecting one or more clusters (e.g., the densest cluster and / or similar clusters) based on the number of atoms contained therein.

[0114] It should be understood that other conformations of protein molecules in the first database 1104 (e.g., an unbound protein structure database), such as the second conformation 119a of the same protein molecule, can be provided as input to the guided docking system before undergoing guided docking to generate one or more corresponding complex coordinate files. Since a single protein molecule can present multiple conformations, a single protein molecule can be associated with multiple unbound coordinate files and complex coordinate files (e.g., one complex coordinate file for each unbound coordinate file).

[0115] In some cases, the unbound coordinate file can specify a specific conformation of the protein molecule, such as the shape of the first conformation 119a, by specifying at least the position and orientation of each atom in the protein molecule. The guided docking system can generate a complex coordinate file by reducing (e.g., minimizing) an energy function associated with the compound bound to the first conformation 119a of the protein molecule, while the distance from the residues in the first perturbation set 113a can be used for a scoring function (e.g., Rosetta Dock, HADDOCK, Autodock, and / or similar functions). The resulting complex coordinate file can specify the position of each atom in the coupled protein-structure-compound (including, for example, atoms in the first conformation 119a of the protein molecule and atoms in the compound).

[0116] The molecular dynamics simulation engine 114 may include a temperature search system that can receive a complex coordinate file (e.g., including structural information of coupled compound-protein-structures) from a guided docking system and simulate the time evolution of the corresponding coupled protein-structure. The temperature search system can simultaneously receive multiple complex coordinate files, each of which includes structural information of compounds bound to different conformations of protein molecules. In some cases, the temperature search system can, for example, perform multiple rounds of molecular dynamics simulation (MD) at different temperatures and for different coupled compound-protein-structures (e.g., complexes formed by compounds bound to different conformations of the same protein molecule) to determine the temperature at which a threshold number of coupled compound-protein-structures dissociate.

[0117] The time evolution of multiple coupled protein-structure-compounds (e.g., generated for different conformations of the protein molecule) can be simulated at a first temperature (e.g., 375 Kelvin). This can result in multiple simulations (or trajectories) for each coupled protein-structure-compound. For example, three simulations or trajectories can be simulated for each coupled compound-protein-structure at a first temperature, wherein each simulation (or trajectory) is performed for a first predetermined time period (e.g., 100 nanoseconds). If no trajectory results in the dissociation of the coupled compound-protein-structure, one or more additional rounds of molecular dynamics simulations can be performed, wherein each simulation (or trajectory) is performed for a second predetermined time period that is longer than the first predetermined time period (e.g., 1 microsecond) and / or is performed at a second temperature that is higher than the first temperature (25 Kelvin higher than the first temperature).

[0118] Alternatively, if each molecular dynamics simulation (MD) or (trajectory) calculated at a given temperature results in dissociation of a coupled compound-protein-structure, it may be performed at a second temperature that is lower than the first temperature (e.g., 25 Kelvin lower than the first temperature) and typically lasts for 100 nanoseconds.

[0119] Reference again Fig.12 , the boundary testing system can determine whether the coupled protein-structure-compound has dissociated, for example, during or at the end of a round of molecular dynamics simulation (or trajectory). The boundary testing system can calculate a distance metric indicating the distance between a first geometric center (COG) of the first perturbation set 113a and a second geometric center (COG) of the compound during the molecular dynamics simulation process. In some cases, the distance metric can correspond to the distance between the geometric center (COG) of the backbone nitrogen (N) atom in the first perturbation set 113a and the geometric center (COG) of the compound. If the value of the distance metric satisfies one or more thresholds (e.g., exceeds a threshold distance value), the coupled protein-structure-compound is considered to be dissociated.

[0120] In some cases, a complex coordinate file can be generated for each coupled compound-protein-structure, wherein the protein molecule presents different conformations. Then, each complex coordinate file can be subjected to multiple rounds of molecular dynamics simulation (or trajectory) at a temperature search system determined to be an acceptable temperature. In some cases, after (or during) the time evolution of the first temperature simulation by the temperature search system, a new complex coordinate file can include structural information associated with the coupled protein-structure-compound. If the corresponding coupled compound-protein-structure does not dissociate at the end of the molecular dynamics simulation, the corresponding complex coordinate file can be stored in the binding structure database, and can be further evaluated by the evaluation engine 118, including, for example, by calculating one or more metrics as a substitute consistent with the data between the compound and the protein molecule (e.g., seeking to maximize satisfaction scores and minimize divergence scores, and / or the like). Alternatively, the complex coordinate file associated with the coupled compound-protein-structure dissociated during and / or at the end of one or more rounds of molecular dynamics simulation can be discarded. Furthermore, in some cases, when a protein molecule dissociates from a compound, an unbound coordinate file specifying the conformation of the protein molecule may be returned to the unbound protein structure database (eg, first database 1104 ) so that the dissociated conformation of the protein molecule may undergo additional evaluation.

[0121] The satisfaction score and the divergence score can be calculated by the evaluation engine 118 and assigned to the complex coordination file of the corresponding coupled compound-protein-structure. The satisfaction score can indicate the strength of the bond between the compound and the specific conformation of the protein molecule in the corresponding compound-protein-structure. In some cases, the satisfaction score can be a function (or proportional to) of the number of hydrogen bonds and / or atomic packing density in the coupled compound-protein-structure at or around one or more residues in the protein molecule. A higher satisfaction score value may be desirable because it can indicate the consistency between the molecular dynamics simulation results and the experimental results.

[0122] If the coupled compound-protein-structure does not dissociate during or at the end of the molecular dynamics simulation, the satisfaction score of the coupled compound-protein-structure can be calculated by the following expression:

[0123]

[0124] Alternatively, if the coupled compound-protein-structure dissociates during or at the end of a molecular dynamics simulation, the satisfaction score of the coupled compound-protein-structure can be determined based on the following equation:

[0125]

[0126] In some exemplary embodiments, ΔE is an energy value determined for the trajectories of the protein molecule with and without the compound bound; N C is the number of heavy atoms within 6.5 Å of the amide nitrogen atom of the residue in the perturbation set for any particular frame (or time instance) of the molecular dynamics simulation; N H is the number of nitrogen atoms and oxygen atoms within 2.5 Å of the amide nitrogen atom of the residue in the perturbation set for any particular frame of the molecular dynamics simulation; d is the distance from the amide nitrogen of any particular residue in the perturbation set to the center of geometry (COG) of the compound (e.g., ligand) for any particular frame of the molecular dynamics simulation; variable> is the distance from the amide nitrogen of any particular residue in the perturbation set to the center of geometry (COG) of the compound (e.g., ligand) for any particular frame of the molecular dynamics simulation The average value of (e.g., averaged over the individual frames of the MD simulation).

[0127] The divergence score can be calculated by the following expression:

[0128]

[0129] in is the standard deviation of the average distance from the amide nitrogen atoms in the perturbation set (e.g., the nitrogen (N) atoms contained in the amide group) to the geometric center (COG) of the compound (e.g., ligand) on the trajectory. More generally, the distance between the amide nitrogen of the residue and the center of mass of the compound can vary during the course of a molecular dynamics simulation (e.g., from one frame to another in the corresponding trajectory). An average distance value can be calculated based on various distance values ​​(distance values ​​associated with different frames). Based on the average and the various distance values, a standard deviation value (or divergence score) can be determined. The divergence score may be high in the first few rounds of molecular dynamics simulation, but in the case where the compound binds properly in a well-formed protein conformation, the divergence score will typically decrease in subsequent rounds.

[0130] In some cases, the average distance (or divergence) between the compound and the protein molecule can be determined based on the geometric center of gravity (COG) of the atoms in the compound and the geometric center of gravity (COG) of the residues in the perturbation set, or based on the average distance (or divergence) between the geometric center of gravity (COG) of the compound and each backbone nitrogen atom in the perturbation set residues (as described below). The geometric center of gravity (COG) of the residues in the perturbation set can be determined based on the position of the backbone nitrogen (N) atoms in these residues. It should be understood that each residue in the perturbation set will have one backbone nitrogen (N) atom. For further illustration, take to represent the geometric center of the collection of atoms that form the compound, and take The average distance can correspond to d in any frame of simulation tt The individual distances d in i,t The average value of . Divergence score It can be determined based on the following equation.

[0131]

[0132] where N represents the number of residues in the perturbation set, M represents the number of frames in the trajectory, and Or the size of the variable in the units used above.

[0133] The molecular dynamics simulation engine 114 may include a determination system to determine whether to perform additional rounds of molecular dynamics simulations (MD) under, for example, different conditions. For example, if a threshold number of trajectories from different starting poses of a particular conformation of a protein molecule ends with corresponding coupled compound-protein-structure dissociation at a given temperature, then one or more additional rounds of molecular dynamics simulations from the same conformation may be performed at a lower temperature (e.g., 25K lower than the initial simulation). Similarly, if a threshold number of trajectories from a threshold portion of different starting poses of a protein conformation remain associated for a particular round, then the temperature may be increased to favor dissociation in one or more subsequent rounds of molecular dynamics simulations.

[0134] In some cases, multiple trajectories may not result in the dissociation of the coupled compound-protein-structure, while the corresponding satisfaction score is less than a threshold (e.g., less than 50, the actual score will always be relative to the size of the perturbation set, etc., and the threshold will be case-dependent) and / or the corresponding divergence score is greater than a threshold (e.g., less than 1, which is absolute and generally not case-dependent). In this case, one or more corresponding complex coordinate files can be stripped to generate additional conformations of the protein molecule for storage in the unbound protein structure database (e.g., the first database 1104). These conformations can be different from the conformations of the protein molecule provided to the molecular dynamics simulation engine 114 to perform one or more rounds (e.g., one or more previous rounds) of molecular dynamics simulation after the new perturbation set has been generated and provided to the docking algorithm. Structural information associated with these conformations of the protein molecule can be provided as input to the guided docking system of the molecular dynamics simulation engine 114. For example, the molecular dynamics simulation engine 114 can perform one or more rounds of molecular dynamics simulation for each additional conformation of the protein molecule and the corresponding perturbation set to determine whether the perturbation set can form a stable binding between the compound and the protein molecule across different conformations of the protein molecule. For example, a specific conformation of the protein molecule (e.g., corresponding structural information, such as an unbound coordinate file) and a corresponding perturbation set can be provided to a guided docking system to generate a complex coordinate file of the compound bound to the conformation of the protein molecule at the residues included in the perturbation set. If the molecular dynamics simulation engine 114 is provided with a complex coordinate file (e.g., a complex coordinate file of the protein conformation coupled to the compound), the guided docking system can be bypassed and the complex coordinate file can be provided to the temperature search system.

[0135] The determination system can determine that the plurality of regions in the first perturbation set 113a (used by the molecular dynamics simulation engine 114 for simulation) are identified as forming a stable binding between the compound and the protein molecule. For example, when one or more exit criteria are met, the determination system can determine that the complex coordinate file should be placed in the binding structure database and that no additional simulations are required for the molecule. In some cases, the exit criteria can be based on the maximum satisfaction score and the minimum divergence score of one or more trajectories. For example, if the trajectory meets the satisfaction score criteria (e.g., the satisfaction score has stabilized or stopped increasing) and the divergence score criteria (e.g., the divergence score is less than 1), the complex coordinate file will be placed in the binding structure database.

[0136] In some cases, the exit criteria can also be based on the alignment between a threshold number of structures in the binding structure database (e.g., at least three or different thresholds). For example, the atoms of the protein molecule in three (or more) complex coordinate files (e.g., associated with the first trajectory and the second trajectory, respectively) can be aligned, and the positions of the atoms of the ligand in the first new complex coordinate file can be compared with the atoms of the ligand in the second and third new complex coordinate files. For example, this can be achieved by first taking the intersection of sets formed by selecting all atoms within a predefined distance (e.g., 6 angstroms) from the ligand. The atoms in the two complex coordinate files can be aligned using the minimization of the carbon alpha root mean square distance (RMSD) of the intersection of the sets. From these coordinates, one can calculate the all-atom root mean square distance (RMSD) between the atoms in the ligand between each complex coordinate file. If this value is below a predefined threshold (e.g., 1 angstrom) of the complex coordinate files located in the binding structure database for a threshold number (e.g., three or more) of complex coordinate files, the exit criteria can be based on the alignment between the atoms in the ligand in the second and third new complex coordinate files. 2 ), then the exit criteria have been met and those coupled compound-protein-structures are placed in the results database.

[0137] In some exemplary embodiments, once the exit criteria are met, the residues in the perturbation set (e.g., the first perturbation set 113a) used in the current simulation are identified as forming a stable binding between the compound and the protein molecule. In addition, the perturbation set and structural information of the protein conformation used in the current simulation (e.g., the first perturbation set 113a, the first structural information, etc.) are stored in a second database 1108 (also referred to as a selected perturbation set database).

[0138] Fig.13An exemplary implementation of a protein structure information generation algorithm 1302 is shown, which can generate multiple conformations of protein molecules and store corresponding structure information files (e.g., unbound structure information) in a first database 1104 (e.g., an unbound protein structure database). It should be understood that unbound protein conformations and corresponding unbound structure information can be generated once (e.g., generated at the beginning of a molecular dynamics simulation) and stored in a first database 1104 (e.g., an unbound protein structure database). In some cases, the first database 1104 (e.g., an unbound protein structure database) can store multiple conformations of protein molecules corresponding to the structural evolution of protein molecules over time for a single protein molecule. As described above, multiple conformations of the same protein molecule structure can be retrieved from the first database 1104 and provided as input (e.g., simultaneously) to a guided docking system. The protein spatial structure generation algorithm 1302 can include an accelerated molecular dynamics simulator (commonly referred to as accelerated molecular dynamics simulation (MD) or metadynamics, etc.), which can receive unbound structure information of protein conformations and simulate the time evolution of the initial three-dimensional structure.

[0139] In view of the above specific implementation of the subject matter, the present application discloses the following list of examples, wherein one feature of a single example or a combination of more than one feature of the example, and optionally a combination with one or more features of one or more other examples, are other examples that also fall within the disclosure scope of the present application:

[0140] Item 1: A computer-implemented method comprising: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set comprising identifying one or more residues to include in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further comprising excluding at least a first residue from the first perturbation set, the distance between the at least first residue and a second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating an interaction between the compound and a first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0141] Item 2: A method according to item 1, wherein the protection factor associated with each residue in the first conformation corresponds to the difference between a first energy of the residue in a bound state and a second energy of the residue in an unbound state.

[0142] Item 3: A method according to any one of Items 1 to 2, further comprising: identifying the one or more residues to be included in the first perturbation set based at least on a protection factor of the one or more residues satisfying one or more thresholds.

[0143] Item 4: The method according to Item 3 further comprises: determining that the protection factor of the one or more residues satisfies the one or more thresholds based at least on the value of the protection factor being within a percentile of the maximum protection factor value observed for the first conformation of the protein molecule.

[0144] Item 5: The method according to Item 4, further comprising: determining a percentile based at least on the magnitude of the difference between the maximum protection factor value and a plurality of other protection factor values ​​observed for the first conformation of the protein molecule.

[0145] Item 6: A method according to any one of items 4 to 5, wherein the percentile is a value between 5 and 20.

[0146] Item 7: A method according to any one of Items 1 to 6, wherein the interaction between the compound and the first plurality of residues in the first perturbation set includes at least a portion of the first plurality of residues in the first perturbation set forming an induced fit pocket within the first conformation of the protein molecule.

[0147] Item 8: A method according to any one of Items 1 to 7, wherein each round of molecular dynamics simulation simulates the time evolution of a coupled protein-structure-compound, wherein the coupled protein-structure-compound includes a compound bound to a first conformation of a protein molecule at a first plurality of residues included in a first perturbation set.

[0148] Item 9: A method according to Item 8, wherein the coupled protein-structure-compound is generated based at least on a first set of perturbations and structural information specifying the spatial arrangement of atoms in a first conformation of the protein molecule in an unbound state.

[0149] Item 10: The method of any one of Items 1 to 9, wherein determining the first perturbation set further comprises excluding at least a third residue from the first perturbation set, the third residue requiring a threshold amount of reorientation to interact with the compound.

[0150] Item 11: A method according to Item 10, wherein the threshold number of reorientations is satisfied by: (i) the number of atoms in the third residue that need to be reoriented to interact with the compound, (ii) the angle of reorientation that one or more atoms in the third residue need to undergo to interact with the compound, and / or (iii) the distance that the one or more atoms in the third residue need to undergo to interact with the compound.

[0151] Item 12: A method according to any one of items 10 to 11, further comprising: determining a first vector from the geometric center (COG) of a first plurality of residues in a first perturbation set and the α-carbon of a third residue; determining a second vector from the α-carbon to one of the δ-carbon, γ-carbon or β-carbon present in the third residue; and determining a reorientation that satisfies a threshold number based at least on the angle formed by the first vector and the second vector satisfying one or more thresholds.

[0152] Item 13: The method of any one of items 10 to 12, wherein the third residue is maintained in the first perturbation set based at least on the fact that the third residue is glycine.

[0153] Item 14: A method according to any one of items 1 to 13, wherein determining the first perturbation set further includes determining a distance between a first center of mass of residues in a first cluster and a second center of mass of residues in a second cluster, determining that the distance fails to correspond to one or more dimensions of the compound, and excluding the first residue from the first perturbation set at least based on the first residue being part of the first cluster of residues.

[0154] Item 15: The method of Item 14, wherein determining the first perturbation set further comprises applying a clustering technique to the first plurality of residues to divide the first plurality of residues into at least a first cluster of residues and a second cluster of residues.

[0155] Item 16: A method according to Item 15, wherein the clustering techniques include one or more of k-means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), expectation-maximization (EM) clustering using Gaussian mixture model (GMM), and agglomerative hierarchical clustering.

[0156] Item 17: A method according to any one of Items 14 to 15, wherein determining the first perturbation set further includes determining a first number of residues in a first cluster of residues and a second number of residues in a second cluster of residues, determining a first average distance between the first centroid and the residues in the first cluster, and determining a second average distance between the second centroid and the residues in the second cluster.

[0157] Item 18: A method according to Item 17, wherein determining the first perturbation set further includes excluding the first cluster of residues from the first perturbation set based at least on the following determinations: (i) the second cluster includes fewer residues than the first cluster, and (ii) the distance between the first centroid of the first cluster and the second centroid of the second cluster exceeds the sum of a first average distance between the first centroid and the residues in the first cluster and a second average distance between the second centroid and the residues in the second cluster.

[0158] Item 19: A method according to any one of items 1 to 18, wherein the result includes the distance between a first geometric center of the compound and a second geometric center of a plurality of main chain nitrogen (N) atoms in a first plurality of residues in a first perturbation set.

[0159] Item 20: A method according to any one of items 1 to 19, wherein the result comprises the distance between a first geometric center of the compound and one or more amide nitrogen atoms present in the first plurality of residues in the first perturbation set.

[0160] Item 21: The method according to any one of Items 1 to 20, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed at a first temperature and a second round of molecular dynamics simulations performed at a second temperature.

[0161] Item 22: The method according to any one of Items 1 to 21, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed for a first time length and a second round of molecular dynamics simulations performed for a second time length.

[0162] Item 23: A method according to any one of Items 1 to 22, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed on a first conformation of the protein molecule associated with a first perturbation set and a second round of molecular dynamics simulations performed on a second conformation of the protein molecule associated with a second perturbation set.

[0163] Item 24: The method according to Item 23, wherein each of the first conformation and the second conformation comprises a three-dimensional structure having a different spatial arrangement of atoms in the protein molecule.

[0164] Item 25: A method according to any one of items 23 to 24, further comprising: determining a second perturbation set for a second conformation of the protein molecule, the determination comprising at least one of the following: (i) identifying one or more residues to include in the second perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, (ii) excluding at least a third residue from the second perturbation set, the distance between the third residue and a fourth residue in the second perturbation set failing to correspond to one or more dimensions of the compound, and (iii) excluding at least a fifth residue from the second perturbation set, the fifth residue requiring a threshold number of reorientations to interact with the compound.

[0165] Item 26: A method according to any one of Items 1 to 25, wherein the one or more rounds of molecular dynamics simulations include multiple rounds of molecular dynamics simulations, and wherein each round of molecular dynamics simulation subjects the coupled compound-protein-structure (including a compound bound to a protein molecule at a first plurality of residues in a first perturbation set) to different conditions.

[0166] Item 27: The method according to Item 26, wherein the results of the one or more rounds of molecular dynamics simulations include one or more conditions for the dissociation of the coupled compound-protein-structure.

[0167] Item 28: The method according to Item 27, wherein the one or more conditions include the temperature at which the coupled compound-protein-structure dissociates.

[0168] Item 29: The method according to any one of Items 27 to 28, wherein the one or more conditions include the length of time after which the coupled compound-protein-structure dissociates.

[0169] Item 30: A method according to any one of Items 1 to 29, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a higher temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0170] Item 31: A method according to any one of Items 1 to 30, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a lower temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0171] Item 32: A method according to any one of Items 1 to 31, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a longer period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0172] Item 33: A method according to any one of Items 1 to 32, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a shorter period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0173] Item 34: A method according to any one of Items 1 to 33, wherein a first plurality of residues in the perturbation set are identified as forming a stable binding at least by: determining one or more metrics that quantify the binding affinity between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations, and determining the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the one or more metrics.

[0174] Item 35: A method according to any one of items 1 to 34, wherein determining the first perturbation set further includes determining a distance between the first residue and the second residue, and excluding the first residue from the first perturbation set in response to determining that the distance between the first residue and the second residue exceeds the one or more dimensions of the compound.

[0175] Item 36: A system comprising: at least one data processor, and at least one memory storing instructions that, when executed by the at least one data processor, result in operations comprising: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set comprising identifying one or more residues to include in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further comprising excluding at least a first residue from the first perturbation set, the distance between the at least first residue and a second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating an interaction between the compound and a first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0176] Item 37: A system according to item 36, wherein the protection factor associated with each residue in the first conformation corresponds to the difference between a first energy of the residue in a bound state and a second energy of the residue in an unbound state.

[0177] Item 38: A system according to any one of items 36 to 37, wherein the operation further comprises: identifying the one or more residues to include in the first perturbation set based at least on a protection factor of the one or more residues satisfying one or more thresholds.

[0178] Item 39: A system according to Item 38, wherein the operation further includes: determining that the protection factor of the one or more residues satisfies the one or more thresholds based at least on the value of the protection factor being within a percentile of the maximum protection factor value observed for the first conformation of the protein molecule.

[0179] Item 40: The system of Item 39, wherein the operation further comprises: determining a percentile based at least on a magnitude of a difference between a maximum protection factor value and a plurality of other protection factor values ​​observed for the first conformation of the protein molecule.

[0180] Item 41: The system of any one of Items 39 to 40, wherein the percentile is a value between 5 and 20.

[0181] Item 42: A system according to any one of Items 36 to 41, wherein the interaction between the compound and the first plurality of residues in the first perturbation set includes at least a portion of the first plurality of residues in the first perturbation set forming an induced fit pocket within the first conformation of the protein molecule.

[0182] Item 43: A system according to any one of Items 36 to 42, wherein each round of molecular dynamics simulation simulates the time evolution of a coupled protein-structure-compound, wherein the coupled protein-structure-compound includes a compound bound to a first conformation of a protein molecule at a first plurality of residues included in a first perturbation set.

[0183] Item 44: A system according to Item 43, wherein the coupled protein-structure-compound is generated based on at least a first set of perturbations and structural information specifying the spatial arrangement of atoms in a first conformation of the protein molecule in an unbound state.

[0184] Item 45: The system of any one of Items 36 to 44, wherein determining the first perturbation set further comprises excluding at least a third residue from the first perturbation set, the third residue requiring a threshold amount of reorientation to interact with the compound.

[0185] Item 46: A system according to Item 45, wherein the threshold number of reorientations is satisfied by: (i) the number of atoms in the third residue that need to be reoriented to interact with the compound, (ii) the angle of reorientation that one or more atoms in the third residue need to undergo to interact with the compound, and / or (iii) the distance that the one or more atoms in the third residue need to undergo to interact with the compound.

[0186] Item 47: A system according to any one of items 45 to 46, further comprising: determining a first vector from the geometric center (COG) of a first plurality of residues in a first perturbation set and the α-carbon of a third residue; determining a second vector from the α carbon to one of a δ-carbon, a γ-carbon or a β-carbon present in the third residue; and determining a reorientation that satisfies a threshold number based at least on the angle formed by the first vector and the second vector satisfying one or more thresholds.

[0187] Item 48: The system of any one of items 45 to 47, wherein the third residue is maintained in the first perturbation set based at least on the fact that the third residue is glycine.

[0188] Item 49: A system according to any one of items 36 to 48, wherein determining the first perturbation set further includes determining a distance between a first center of mass of residues in the first cluster and a second center of mass of residues in the second cluster, determining that the distance fails to correspond to one or more dimensions of the compound, and excluding the first residue from the first perturbation set based at least on the fact that the first residue is part of the first cluster of residues.

[0189] Item 50: The system of Item 49, wherein determining the first set of perturbations further comprises applying a clustering technique to the first plurality of residues to divide the first plurality of residues into at least a first cluster of residues and a second cluster of residues.

[0190] Item 51: A system according to Item 50, wherein the clustering techniques include one or more of k-means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), expectation-maximization (EM) clustering using Gaussian mixture model (GMM), and agglomerative hierarchical clustering.

[0191] Item 52: A system according to any one of items 49 to 51, wherein determining the first perturbation set further includes determining a first number of residues in a first cluster of residues and a second number of residues in a second cluster of residues, determining a first average distance between the first centroid and the residues in the first cluster, and determining a second average distance between the second centroid and the residues in the second cluster.

[0192] Item 53: A system according to Item 52, wherein determining the first perturbation set further includes excluding the first cluster of residues from the first perturbation set based at least on the following determination: (i) the second cluster includes fewer residues than the first cluster, and (ii) the distance between the first centroid of the first cluster and the second centroid of the second cluster exceeds the sum of a first average distance between the first centroid and the residues in the first cluster and a second average distance between the second centroid and the residues in the second cluster.

[0193] Item 54: A system according to any one of items 36 to 53, wherein the result comprises a distance between a first geometric center of the compound and a second geometric center of a plurality of main-chain nitrogen (N) atoms in a first plurality of residues in a first perturbation set.

[0194] Item 55: A system according to any one of items 36 to 54, wherein the result comprises a distance between a first geometric center of the compound and one or more amide nitrogen atoms present in a first plurality of residues in the first perturbation set.

[0195] Item 56: The system according to any one of Items 36 to 55, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed at a first temperature and a second round of molecular dynamics simulations performed at a second temperature.

[0196] Item 57: The system according to any one of Items 36 to 56, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed for a first time length and a second round of molecular dynamics simulations performed for a second time length.

[0197] Item 58: A system according to any one of Items 36 to 57, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed on a first conformation of the protein molecule associated with a first set of perturbations and a second round of molecular dynamics simulations performed on a second conformation of the protein molecule associated with a second set of perturbations.

[0198] Item 59: The system of Item 58, wherein each of the first conformation and the second conformation comprises a three-dimensional structure having a different spatial arrangement of atoms in the protein molecule.

[0199] Item 60: A system according to any one of items 58 to 59, wherein the operation further includes: determining a second perturbation set for a second conformation of the protein molecule, the determination comprising at least one of the following: (i) identifying one or more residues to include in the second perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, (ii) excluding at least a third residue from the second perturbation set, the distance between the third residue and a fourth residue in the second perturbation set failing to correspond to one or more dimensions of the compound, and (iii) excluding at least a fifth residue from the second perturbation set, the fifth residue requiring a threshold number of reorientations to interact with the compound.

[0200] Item 61: A system according to any one of Items 36 to 60, wherein the one or more rounds of molecular dynamics simulations include multiple rounds of molecular dynamics simulations, and wherein each round of molecular dynamics simulation subjects the coupled compound-protein-structure (including a compound bound to a protein molecule at a first plurality of residues in a first perturbation set) to different conditions.

[0201] Item 62: A system according to Item 61, wherein the results of the one or more rounds of molecular dynamics simulations include one or more conditions for dissociation of the coupled compound-protein-structure.

[0202] Item 63: A system according to Item 62, wherein the one or more conditions include a temperature at which the coupled compound-protein-structure dissociates.

[0203] Item 64: The system according to any one of Items 62 to 63, wherein the one or more conditions include the length of time after which the coupled compound-protein-structure dissociates.

[0204] Item 65: A system according to any one of Items 36 to 64, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a higher temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0205] Item 66: A system according to any one of Items 36 to 65, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a lower temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0206] Item 67: A system according to any one of Items 36 to 66, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a longer period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0207] Item 68: A system according to any one of Items 36 to 67, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a shorter period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising a compound bound to a protein molecule at a first plurality of residues in a first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

[0208] Item 69: A system according to any one of items 36 to 68, wherein a first plurality of residues in the perturbation set are identified as forming a stable binding at least by: determining one or more metrics that quantify the binding affinity between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations, and determining the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the one or more metrics.

[0209] Item 70: A system according to any one of items 36 to 69, wherein determining the first perturbation set further includes determining a distance between the first residue and the second residue, and excluding the first residue from the first perturbation set in response to determining that the distance between the first residue and the second residue exceeds the one or more dimensions of the compound.

[0210] Item 71: A non-transitory computer-readable medium storing instructions that, when executed by at least one data processor, cause operations including the following: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set comprising identifying one or more residues to include in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further comprising excluding at least a first residue from the first perturbation set, the distance between the at least first residue and a second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicating an interaction between the compound and a first plurality of residues in the first perturbation set; and (c) identifying the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations.

[0211] Item 72: The non-transitory computer-readable medium of claim 71, wherein the instructions further cause operations comprising the method of any one of items 2 to 35.

[0212] Fig.14 1400 is a block diagram illustrating an example of a computing system 1400 according to some exemplary embodiments. In some exemplary embodiments, computing system 1400 may be used to implement analysis controller 110 and / or any components thereof. Fig.14 As shown, the computing system 1400 may include a processor 1410, a memory 1420, a storage device 1430, and an input / output device 1440. The processor 1410, the memory 1420, the storage device 1430, and the input / output device 1440 may be interconnected via a system bus 1450. The processor 1410 is capable of processing instructions for execution within the computing system. Such executed instructions may implement, for example, one or more components of the analysis controller 110 (e.g., a molecular dynamics simulation engine 114, a perturbation set engine 112, etc.). In some exemplary embodiments, the processor 1410 may be a single-threaded processor. Alternatively, the processor 1410 may be a multi-threaded processor. The processor 1410 is capable of processing instructions stored on the memory 1420 and / or the storage device 1430 to display graphical information for a user interface provided via the input / output device 1440.

[0213] Memory 1420 is a computer-readable medium, such as a volatile or non-volatile computer-readable medium, that stores information within computing system 1400. For example, memory 1420 may store a data structure representing a configuration object database. Storage device 1430 can provide persistent storage for computing system 1400. Storage device 1430 may be a floppy disk device, a hard disk device, an optical disk device, a tape device, a solid-state hard disk, and / or other suitable persistent storage devices. Input / output device 1440 provides input / output operations for computing system 1400. In some exemplary embodiments, input / output device 1440 includes a keyboard and / or a pointing device. In various specific implementations, input / output device 1440 includes a display unit for displaying a graphical user interface.

[0214] definition

[0215] Unless otherwise defined, all technical terms, symbols and other scientific terms or technical terms used herein are intended to have the meanings commonly understood by those skilled in the art to which the present disclosure belongs. In some cases, for the sake of clarity and / or for ease of reference, terms with commonly understood meanings are defined herein, and these definitions contained herein are not necessarily interpreted as indicating significant differences from the commonly understood meanings in the art compared to the definitions of terms commonly understood in the prior art. Many of the techniques and procedures described or referenced herein are well known to those skilled in the art and are commonly employed using conventional methods.

[0216] As used herein, the conformation of a protein molecule (or protein conformation) is the three-dimensional arrangement of residues in the amino acid residue sequence that forms a protein molecule. Residues are organic molecules including α carbons connected to amino groups, carboxyl groups, hydrogen atoms, and variable components called side chains. As used herein, coupled protein-structure-compounds are couplings or combinations between protein molecules (having a specific conformation) and compounds (e.g., ligands). In some cases, the protein molecules and compounds in the coupled protein-structure-compounds can be combined with each other (e.g., the distance between the center of mass of the compound and the center of mass of the nitrogen atom in the perturbation concentration of the protein molecule is less than a threshold distance value). In some cases, the protein molecules and compounds in the coupled protein-structure-compounds dissociate or do not combine with each other (e.g., the distance between the center of mass of the compound and the center of mass of the nitrogen atom in the perturbation concentration of the protein molecule is greater than a threshold distance value). As used herein, the structural information associated with a specific conformation of a protein molecule includes the spatial arrangement and / or orientation of atoms in each constituent amino acid residue that forms the protein molecule (e.g., the relative spatial position and orientation of atoms in the protein molecule).

[0217] The singular forms "a", "an", and "the" include plural referents unless the context clearly dictates otherwise. For example, the term "a cell" includes one or more cells, including mixtures thereof. As used herein, "A and / or B" includes all of the following alternatives: "A", "B", "A or B", and "A and B".

[0218] It should be understood that the disclosed aspects and embodiments described herein include aspects and embodiments referred to as "comprising," "consisting of," and "consisting essentially of."

[0219] As used herein, "comprising" is synonymous with "including," "containing," or "characterized by," and is inclusive or open-ended and does not exclude additional, unrecited elements or method steps. Any recitation of the term "comprising" herein, particularly in the description of the components of a composition or in the description of the steps of a method, should be understood to cover those compositions and methods consisting essentially of and consisting of the recited components or steps. As used herein, "consisting of excludes any element, step, or ingredient not specified in the claimed composition or method. As used herein, "consisting essentially of does not exclude materials or steps that do not materially affect the basic and novel characteristics of the claimed composition and method.

[0220] When providing numerical range, it will be understood by those skilled in the art that all ranges disclosed herein encompass any and all possible sub-ranges and combinations of sub-ranges thereof.Any listed range can be easily considered to fully describe and enable the same range to be decomposed into at least equal half, one-third, one-quarter, one-fifth, one-tenth, etc. As a non-limiting example, each range discussed herein can be easily decomposed into lower third, middle third, and upper third, etc. It will also be understood by those skilled in the art that all languages ​​such as "at most", "at least", "greater than", "less than", etc. include the numbers listed, and refer to the ranges that can be subsequently decomposed into sub-ranges as discussed above. As will be understood by those skilled in the art, ranges include each individual member.Therefore, for example, a group with 1 to 3 articles refers to a group with 1, 2 or 3 articles. Similarly, a group with 1 to 5 articles refers to a group with 1, 2, 3, 4 or 5 articles, etc.

[0221] Certain ranges are presented herein with numerical values ​​preceded by the term "about". The term "about" is used herein to provide literal support for the exact number that follows, as well as numbers that are close to or approximately the number that follows the term. In determining whether a number is close to or approximately to a specifically recited number, the close or approximately unrecited number may be a number that, in the context in which it is presented, provides a number that is substantially equivalent to the specifically recited number. If the degree of approximation is not otherwise clear from the context, "about" means within plus or minus 10% of the value provided, or rounded to the nearest significant figure, which includes the value provided in all cases.

[0222] Headings, such as (a), (b), (i), etc., are presented only to facilitate reading of the specification and claims. The use of headings in the specification or claims does not require that the steps or elements be performed in alphabetical or numerical order or in the order in which they are presented.

[0223] It should be understood that, for the sake of clarity, certain features of the present disclosure described in the context of independent embodiments may also be provided in combination in a single embodiment. Conversely, for the sake of brevity, various features of the present disclosure described in the context of a single embodiment may also be provided individually or in any suitable sub-combination. All combinations of embodiments belonging to the present disclosure are specifically included in the present disclosure and disclosed herein, just as each and every combination is individually and clearly disclosed. In addition, all sub-combinations of various embodiments and elements thereof are also specifically included in the present disclosure and disclosed herein, just as each and every such sub-combination is individually and clearly disclosed herein.

[0224] A non-transitory computer program product (i.e., a physically embodied computer program product) storing instructions is also described, which, when executed by one or more data processors of one or more computing systems, causes at least one data processor to perform the operations described herein. Similarly, a computer system that may include one or more data processors and a memory coupled to the one or more data processors is also described. The memory may temporarily or permanently store instructions that cause at least one processor to perform one or more of the operations described herein. In addition, the method may be implemented by one or more data processors within a single computing system or distributed between two or more computing systems. Such computing systems may be connected and may exchange data and / or commands or other instructions, etc., via one or more connections, including through a network (e.g., the Internet, a wireless wide area network, a local area network, a wide area network, a wired network, etc.) via a direct connection between one or more computing systems in the multiple computing systems, etc.

[0225] Depending on the desired configuration, the subject matter described herein may be embodied in a system, device, method, and / or article. For example, the apparatus and / or process described herein may be implemented using one or more of the following: a processor that executes program code, an application specific integrated circuit (ASIC), a digital signal processor (DSP), an embedded processor, a field programmable gate array (FPGA), and / or a combination thereof. These various implementations may include implementations in one or more computer programs that are executable and / or interpretable on a programmable system that includes at least one programmable processor (which may be dedicated or general purpose, coupled to receive data and instructions from it and to send data and instructions to it), a storage system, at least one input device, and at least one output device. These computer programs (also referred to as programs, software, software applications, applications, components, program codes, or codes) include machine instructions for programmable processors and may be implemented in high-level procedural and / or object-oriented programming languages ​​and / or in assembly / machine languages. As used herein, the term "machine-readable medium" refers to any computer program product, computer-readable medium, computer-readable storage medium, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions. Similarly, systems are also described herein that may include a processor and a memory coupled to the processor. The memory may include one or more programs that cause the processor to perform one or more of the operations described herein.

[0226] Although some variations have been described in detail above, other modifications or additions are possible. In particular, in addition to those features and / or variations set forth herein, other features and / or variations may also be provided. In addition, the above-mentioned specific implementations may be directed to various combinations and sub-combinations of the disclosed features and / or to combinations and sub-combinations of several further features disclosed above. In addition, the logical flows depicted in the drawings and / or described herein do not require the specific order or sequential order shown to achieve the desired results. Other specific implementations may be within the scope of the following claims. In addition, the specific values ​​provided above are only examples and may vary in some specific implementations.

[0227] While various aspects of the disclosure are set forth in the claims, other aspects of the disclosure include other combinations of features from the described implementations and features of the claims, and not just the combinations explicitly set forth in the claims.

Claims

1. A computer-implemented method comprising: (a) determining a first perturbation set for a first conformation of a protein molecule, determining the first perturbation set comprising identifying one or more residues to include in the first perturbation set based at least on a protection factor of at least a portion of the residues in the protein molecule, determining the first perturbation set further comprising excluding at least a first residue from the first perturbation set, the first residue having a distance from a second residue in the first perturbation set failing to correspond to one or more dimensions of the compound; (b) performing one or more rounds of molecular dynamics simulations to generate results indicative of interactions between the compound and a first plurality of residues in the first perturbation set; as well as (c) identifying, based at least on the results of the one or more rounds of molecular dynamics simulations, the first plurality of residues in the perturbation set as forming a stable binding between the compound and the first conformation of the protein molecule.

2. The method of claim 1 , wherein the protection factor associated with each residue in the first conformation corresponds to a difference between a first energy of the residue in a bound state and a second energy of the residue in an unbound state, and wherein the one or more residues are identified for inclusion in the first perturbation set based at least on the protection factor of the one or more residues satisfying one or more thresholds.

3. The method according to any one of claims 1 to 2, wherein each round of molecular dynamics simulation simulates the time evolution of a coupled protein-structure-compound, wherein the coupled protein-structure-compound includes the compound bound to the first conformation of the protein molecule at the first plurality of residues included in the first perturbation set.

4. The method of any one of claims 1 to 3, wherein determining the first set of perturbations further comprises excluding at least a third residue from the first set of perturbations, the third residue requiring a threshold number of reorientations to interact with the compound.

5. A method according to claim 4, wherein the threshold number of reorientations is satisfied by: (i) the number of atoms in the third residue that need to be reoriented to interact with the compound, (ii) the angle of reorientation that one or more atoms in the third residue need to undergo to interact with the compound, and / or (iii) the distance of reorientation that the one or more atoms in the third residue need to undergo to interact with the compound.

6. The method according to any one of claims 4 to 5, further comprising: determining a first vector from a center of geometry (COG) of the first plurality of residues and an alpha-carbon of the third residue in the first perturbation set; determining a second vector from the α-carbon to one of a δ-carbon, a γ-carbon, or a β-carbon present in the third residue; as well as Satisfying the threshold number of reorientations is determined based at least on an angle formed by the first vector and the second vector satisfying one or more thresholds.

7. The method according to any one of claims 1 to 6, wherein determining the first set of perturbations further comprises determining the distance between the first centroid of the first cluster of residues and the second centroid of the second cluster of residues, determining that the distance fails to correspond to one or more dimensions of the compound, and The first residue is excluded from the first set of perturbations based at least on the first residue being part of the first cluster of residues.

8. The method of claim 7, wherein determining the first perturbation set further comprises determining a first number of residues in the first cluster of residues and a second number of residues in the second cluster of residues, determining a first average distance between the first centroid and the residues in the first cluster, determining a second average distance between the second centroid and the residues in the second cluster, and The first cluster of residues is excluded from the first perturbation set based at least on a determination that: (i) the second cluster includes fewer residues than the first cluster, and (ii) the distance between the first centroid of the first cluster and the second centroid of the second cluster exceeds the sum of the first average distance between the first centroid and the residues in the first cluster and the second average distance between the second centroid and the residues in the second cluster.

9. The method of any one of claims 1 to 8, wherein the result comprises at least one of: (i) a first distance between a first geometric center of the compound and a second geometric center of a plurality of main-chain nitrogen (N) atoms in the first plurality of residues in the first perturbation set, and (ii) a second distance between the first geometric center of the compound and one or more amide nitrogen atoms present in the first plurality of residues in the first perturbation set.

10. The method according to any one of claims 1 to 9, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed at a first temperature and a second round of molecular dynamics simulations performed at a second temperature.

11. The method according to any one of claims 1 to 10, wherein the one or more rounds of molecular dynamics simulations comprise a first round of molecular dynamics simulations performed for a first time length and a second round of molecular dynamics simulations performed for a second time length.

12. The method according to any one of claims 1 to 11, wherein the one or more rounds of molecular dynamics simulations include a first round of molecular dynamics simulations performed on the first conformation of the protein molecule associated with the first perturbation set and a second round of molecular dynamics simulations performed on the second conformation of the protein molecule associated with a second perturbation set.

13. The method according to any one of claims 1 to 12, wherein each round of molecular dynamics simulation subjects a coupled compound-protein-structure comprising the compound bound to the protein molecule at the first plurality of residues in the first perturbation set to different conditions, wherein the results of the one or more rounds of molecular dynamics simulation include one or more conditions under which the coupled compound-protein-structure dissociates, and wherein the one or more conditions include at least one of: (i) a temperature at which the coupled compound-protein-structure dissociates, and (ii) a length of time after which the coupled compound-protein-structure dissociates.

14. The method according to any one of claims 1 to 13, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a higher temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising the compound bound to the protein molecule at the first plurality of residues in the first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

15. The method according to any one of claims 1 to 14, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations performed at a lower temperature than another round of molecular dynamics simulations in response to a coupled compound-protein-structure of the compound bound to the protein molecule at the first plurality of residues in the first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

16. The method according to any one of claims 1 to 15, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a longer period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising the compound bound to the protein molecule at the first plurality of residues in the first perturbation set failing to dissociate during or at the end of a threshold number of other rounds of molecular dynamics simulations.

17. The method according to any one of claims 1 to 16, wherein the one or more rounds of molecular dynamics simulations include a round of molecular dynamics simulations that is performed for a shorter period of time than another round of molecular dynamics simulations in response to a coupled compound-protein-structure comprising the compound bound to the protein molecule at the first plurality of residues in the first perturbation set having dissociated during or at the end of a threshold number of other rounds of molecular dynamics simulations.

18. The method of any one of claims 1 to 17, wherein the first plurality of residues in the perturbation set are identified as forming a stable association at least by: determining one or more metrics quantifying the binding affinity between the compound and the first conformation of the protein molecule based at least on the results of the one or more rounds of molecular dynamics simulations, and The first plurality of residues in the perturbation set are determined as forming the stabilizing binding between the compound and the first conformation of the protein molecule based at least on the one or more metrics.

19. A system comprising: at least one data processor; as well as At least one memory storing instructions which, when executed by said at least one data processor, result in operations including the method according to any one of claims 1 to 18.

20. A non-transitory computer-readable medium storing instructions that, when executed by at least one data processor, result in operations including the method of any one of claims 1 to 18.

Images