KR20200066904A - A three dimensional image generation appratus of amino acid residues in protein context and thereof method - Google Patents

Abstract

The present invention relates to an apparatus for generating three dimensional images of surrounding environment of amino acid residues of proteins and a method thereof. According to the present invention, the apparatus comprises: a protein data input unit for receiving structure data of a protein; a group formation unit calculating the distance between atoms included in each residue constituting a protein using the inputted protein structure data, and forming a group of residues using the calculated distance value; a spatial coordinate display unit for displaying, on three dimensional spatial coordinates, atoms of C_α, N and C that are basic constituent of each residue and included in the formed group; and a three dimensional image conversion unit for displaying, on the three dimensional spatial coordinates, all atoms that constitute the group. As such, according to the present invention, a three dimensional image representing amino acid residues of a protein and surrounding environment thereof can be used as data for data analysis and artificial intelligence model learning, and therefore the present invention provides an effect of proving the three dimensional image as a raw material for pioneering a new possibility of artificial intelligence convergence.

Description

A three dimensional image generation appratus of amino acid residues in protein context and the method thereof

The present invention relates to a device and a method for generating a three-dimensional image of an environment surrounding an amino acid residue of a protein, and more specifically, an amino acid residue of a protein that generates an amino acid residue of a protein and its surrounding environment as three-dimensional image data. It relates to a device and a method for generating a three-dimensional image of the surrounding environment.

The pharmaceutical bio industry is paying high attention to artificial intelligence convergence in order to reduce the cost of new drug research and development and lower the failure rate in clinical trials, and big data analysis through artificial intelligence will bring innovation in all stages of drug development and the development process. Expect.

In order to train artificial intelligence models, chemical and biological big data is required. Representative big data includes PDB (Protein Data Bank). PDB is a protein database operated by the Brookhaven National Laboratory in the United States, which collects information about tertiary structures of macromolecules in vivo that have been found in experiments. Thus, the PDB provides information on atomic coordinates, bibliographic citations, primary and secondary structure information, crystallographic structures, and the like.

Recently, the pharmaceutical bio industry is producing various feature data due to the increasing need for artificial intelligence convergence, and image data applicable to convolutional neural networks emerging in artificial intelligence fields such as deep learning. The need for is increasing.

The background technology of the present invention is disclosed in Korean Patent Publication No. 10-2001-0020443 (published on March 15, 2001).

An object of the present invention is to provide an apparatus and a method for generating an amino acid residue surrounding a protein as a three-dimensional image and a method for generating an amino acid residue surrounding a protein as three-dimensional image data. .

, N, C의 원자를 3차원의 공간 좌표에 표시하는 공간좌표 표시부, 그리고 상기 3차원 공간 좌표에 상기 그룹을 형성하는 모든 원자들을 표시하는 3차원 이미지 변환부를 포함한다. According to an embodiment of the present invention for achieving such a technical problem, in a device for generating a three-dimensional image of the environment around the amino acid residue of a protein, the protein data input unit for receiving the structural data for the protein, the input protein structural data Using the calculated distance between atoms contained in each residue constituting the protein, and using the calculated distance value to form a group for the residue group forming unit, included in the formed group, the basic configuration of each residue Being

, A spatial coordinate display unit displaying atoms of N and C in three-dimensional spatial coordinates, and a three-dimensional image conversion unit displaying all atoms forming the group in the three-dimensional spatial coordinates.

The group forming unit decomposes for each residue using the received protein structure data, calculates a distance between all atoms included in the decomposed residue, and pre-sets a specific atom included in the corresponding residue. Information about all atoms located within a radius with a cutoff value can be obtained and grouped.

All atoms to be grouped may include atoms included in the corresponding residue having the center point and atoms of other residues located within the set radius.

, N, C의 원자에 대한 정보를 획득하는 원자 정보 획득모듈, 그리고 상기 백본에서 획득한

, N, C의 원자가 이루는 평면이 3차원의 공간좌표의 XY축의 평면과 평행이 되도록 위치시키고, 상기 XY축과 평행하게 위치한

, N, C의 원자 중에서

을 원점에 위치시킨 다음, 상기

을 중심으로 N과 C를 좌표변환 및 회전처리를 이용하여 정규화하는 공간좌표 표준화 모듈을 포함할 수 있다. The spatial coordinate display unit distinguishes whether the grouped residue is glycine (GLY), is located in the protein backbone, and has all residues identically.

, N, C atomic information acquisition module for obtaining information about the atom, and obtained from the backbone

, N, C atoms are placed in a plane parallel to the plane of the XY axis of the three-dimensional spatial coordinates, located parallel to the XY axis

Among the atoms of, N, C

To the origin, then

A spatial coordinate standardization module that normalizes N and C using coordinate transformation and rotation processing may be included.

의 좌표가 XY축의 원점에 위치하도록 좌표를 이동시키고, 상기

을 원점에 위치시킨 상태에서 N의 좌표를 XY축의 평면에 사영시킨 다음, XY축의 평면에 위치한 N의 좌표에 대한

벡터와 Y축의 사이에 형성된 사잇각을 이용하여 N의 좌표가 YZ축의 평면에 닿도록 Z축을 회전시키며, 상기 회전된 N의 좌표에 대한

벡터와 Y축의 사이에 형성된 사잇각을 이용하여 N의 좌표가 XY축의 평면에 닿도록 X축을 회전시키고, 그리고 상기 C의 좌표를 XZ축의 평면에 사영시킨 다음,

벡터와 X축의 사이에 형성된 사잇각을 이용하여 C의 좌표가 XY축의 평면에 닿도록 Y축을 회전시킴으로써, 상기

, N, C의 원자가 XY축의 평면상에 평행하게 위치시킬 수 있다. The spatial coordinate standardization module, among the three atoms

Move the coordinates so that their coordinates are located at the origin of the XY axis, and

After projecting the coordinates of N on the plane of the XY axis while positioning at the origin, the coordinates of N on the plane of the XY axis

The Z-axis is rotated so that the coordinates of N contact the plane of the YZ axis by using the angle of incidence formed between the vector and the Y-axis.

The X-axis is rotated so that the coordinates of N touch the plane of the XY-axis using the angle formed between the vector and the Y-axis, and the coordinates of C are projected onto the plane of the XZ-axis,

By rotating the Y-axis so that the coordinates of C touch the plane of the XY-axis by using the angle of incidence formed between the vector and the X-axis,

, N, C atoms can be positioned parallel to the plane of the XY axis.

의 좌표를 원점에 위치시킨 상태에서

벡터는 y축과 평행하고, C의 좌표는

와 N의 좌표보다 큰 위치값을 가질 수 있다. The spatial coordinate standardization module, the

With the coordinates of

The vector is parallel to the y-axis, and the coordinates of C are

It may have a position value greater than the coordinates of and N.

, N, C의 좌표를 잔기의

가 원점이 되는 좌표에 이동하여 위치시킨 다음, 상기

를 중심으로 상기

와의 거리가 컷오프(cutoff)값보다 작은 모든 원자의 좌표를 표시할 수 있다. The three-dimensional image conversion unit, normalized on the plane of the XY axis

, N, C coordinates of the residue

Is moved to the origin coordinate and positioned, and then

Centered on the above

You can display the coordinates of all atoms whose distance from and is less than the cutoff value.

, N, C의 좌표의

를 중심으로 상기

와의 거리가 컷오프(cutoff)값보다 작은 모든 원자의 좌표를 표시할 수 있다. The 3D image conversion unit, when the grouped residue is glycine (GLY), normalized on the plane of the XY axis

, N, C coordinates

Centered on the above

You can display the coordinates of all atoms whose distance from and is less than the cutoff value.

, N, C의 원자를 3차원의 공간 좌표로 정규화하는 단계, 그리고 상기 3차원 공간 좌표에 상기 그룹을 형성하는 모든 원자들을 표시하여 이미지화하는 단계를 포함한다. In addition, according to an embodiment of the present invention, in a method for generating a 3D image of an environment surrounding an amino acid residue of a protein using a 3D image generating apparatus, receiving structural data for a protein, and using the input protein structural data By calculating the distance between the atoms contained in each residue constituting the protein, forming a group for the residue using the calculated distance value, included in the formed group, the basic configuration of each residue

, Normalizing the atoms of N and C to three-dimensional spatial coordinates, and displaying and displaying all the atoms forming the group in the three-dimensional spatial coordinates.

As described above, according to the present invention, a three-dimensional image representing an amino acid residue of a protein and its surrounding environment can be generated and used as data for learning data analysis and artificial intelligence models, thereby opening new possibilities for artificial intelligence fusion. It has an effect that can be provided.

In addition, according to the present invention, when performing 3D image generation, since it includes a normalization process to the same position line, it is possible to effectively identify the type of residue and contact with other residues, and through hydrogen removal and channel increase, etc. The effect that can be extended to a desired shape can be achieved.

1 is a configuration diagram showing a three-dimensional image generating apparatus according to an embodiment of the present invention.
FIG. 2 is a configuration diagram schematically showing the spatial coordinate display unit illustrated in FIG. 1.
3 is a flowchart schematically showing a 3D image generating method using a 3D image generating apparatus according to an embodiment of the present invention.
4 is an exemplary view showing a state in which proteins are decomposed by residues in step S320 shown in FIG. 3.
FIG. 5 is a flowchart for schematically explaining step S330 illustrated in FIG. 3.
6 is a flowchart for schematically explaining step S340 illustrated in FIG. 3.
FIG. 7 is an exemplary view schematically showing a method of positioning N in the plane of the YZ axis in step S344 illustrated in FIG. 6.
FIG. 8 is an exemplary view schematically showing a method of normalizing by placing N on a plane of the XY axis in step S345 illustrated in FIG. 6.
FIG. 9 is an exemplary view schematically showing a method of normalizing by placing a C atom in the plane of the XY axis in step S346 illustrated in FIG. 6.
10 is an exemplary view showing a state in which all elements grouped in step S350 shown in FIG. 3 are displayed on a 3D coordinate space.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this process, the thickness of the lines or the size of components shown in the drawings may be exaggerated for clarity and convenience.

In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to a user or operator's intention or practice. Therefore, the definition of these terms should be made based on the contents throughout the specification.

Hereinafter, a 3D image generating apparatus according to an embodiment of the present invention will be described with reference to FIGS. 1 and 2.

1 is a configuration diagram showing a three-dimensional image generating apparatus according to an embodiment of the present invention.

As shown in FIG. 1, the 3D image generating apparatus 100 according to an embodiment of the present invention includes a protein data input unit 110, a group forming unit 120, a spatial coordinate display unit 130 and a 3D image conversion unit ( 140).

First, the protein data input unit 110 receives structural data for a protein. At this time, the protein structure data is in the form of a pdb file, and includes information on coordinates in three-dimensional rectangular coordinates with respect to amino acids contained in the protein.

The group forming unit 120 decomposes for each residue using the input protein structure data, and calculates a distance value between atoms contained in the residue. Then, the group forming unit 120 forms a group of all atoms located within a predetermined radius from the atom that is the center of the residue using the distance value.

Incidentally, proteins contain dozens to thousands of amino acids, or residues, and residues are composed of multiple atoms. Therefore, the group forming unit 120 decomposes for each residue, and calculates a distance value between atoms constituting the residue using the atomic coordinates included in the protein structure data. Then, the group forming unit 120 forms a group for all atoms located within a predetermined radius from a central point or central atom located inside the residue. That is, the group formed by the group forming unit 120 may also include elements of residues and other residues located in the vicinity.

, N, C의 원자를 3차원의 공간 좌표상에 표시 표시하며, 백본에 포함된

, N, C의 원자에 대한 정규화를 수행한다. The spatial coordinate display unit 130 corresponds to a backbone of a residue among grouped atoms

Atoms of N, C are displayed and displayed on three-dimensional spatial coordinates, and are included in the backbone.

, N, and C for normalization.

, N, C의 원자를 중심으로 그룹형성부(120)에서 그룹화한 모든 원자들을 3차원 공간좌표에 표시한다. The 3D image conversion unit 140

, All atoms grouped in the group forming unit 120 around the atoms of N and C are displayed in a 3D spatial coordinate.

FIG. 2 is a configuration diagram schematically showing the spatial coordinate display unit illustrated in FIG. 1.

As shown in FIG. 2, the spatial coordinate display unit 130 includes an atomic information acquisition module 131 and a spatial coordinate standardization module 132.

, N, C의 원자에 대한 정보를 획득한다. First, the atomic information acquisition module 131 is located in the protein backbone and all residues have the same

Obtain information about the atoms of, N, C.

, N, C의 원자가 이루는 평면이 3차원의 공간좌표의 XY축의 평면과 평행이 되도록 위치시킨다. 그 다음, 공간좌표 표준화 모듈(132)은 XY축과 평행하게 위치한

, N, C의 원자를 순서대로 좌표변환 및 회전 처리하여,

, N, C의 원자를 XY평면의 동일한 위치선상에 정규화시킨다. In addition, the spatial coordinate standardization module 132 uses information obtained from the backbone.

The planes formed by the atoms of,, N, and C are positioned to be parallel to the plane of the XY axis of the three-dimensional spatial coordinate. Next, the spatial coordinate standardization module 132 is located parallel to the XY axis

, N, C atoms in order of coordinate transformation and rotation processing,

, N, and C atoms are normalized on the same position line of the XY plane.

Hereinafter, a method for generating a 3D image using a 3D image generating apparatus according to an embodiment of the present invention will be described in more detail with reference to FIGS. 3 and 10.

3 is a flowchart schematically showing a 3D image generating method using a 3D image generating apparatus according to an embodiment of the present invention.

As shown in FIG. 3, first, the protein data input unit 110 receives structural data for proteins from an external server (S310).

In other words, the protein data input unit 110 receives protein data including information about atomic coordinates from a PDB (Protein Data Bank). At this time, the Protein Data Bank (PDB) provides protein data in a PDB file format.

Then, the group forming unit 120 decomposes the protein for each residue by using the structural information included in the received protein structural data (S320).

4 is an exemplary view showing a state in which proteins are decomposed by residues in step S320 shown in FIG.

, N, C를 중심으로 잔기를 분해한다.As shown in Figure 4, the group forming unit 120 corresponds to the backbone of the protein, which is the basic structure of the residue

Decomposes residues around N, C.

)와 질소(N) 및 탄소(C)를 중심으로 수소(H), 산소(O) 또는 다른 사이드 체인을 포함한다. 따라서, 그룹형성부(120)는 아미노산 즉, 잔기마다 기본 원자로 포함되는 알파탄소(

)와 질소(N) 및 탄소(C)를 중심으로 단백질을 잔기별로 분해한다. First, when the amino acid is described, the amino acid refers to a molecule having a specific structure in which an amine group (-NH2) having basic properties and a carboxyl group (-COOH) having acidic properties coexist. The amine group and carboxyl group are bonded to the same carbon atom, and this carbon is called alpha carbon. Amino acids are alpha carbons that form the backbone (

) And nitrogen (N) and carbon (C), and hydrogen (H), oxygen (O), or other side chains. Therefore, the group forming unit 120 is an amino acid, that is, an alpha carbon contained as a basic atom for each residue (

) And nitrogen (N) and carbon (C), the protein is broken down into residues.

After the residue decomposition is completed, the group forming unit 120 calculates a distance value between a plurality of atoms included in the decomposed residue, and uses the calculated distance value to include atoms included within a certain distance based on the center point of the residue. Group them (S330).

Hereinafter, a method of forming a group for residues will be described in more detail with reference to FIG. 5.

FIG. 5 is a flowchart for schematically explaining step S330 illustrated in FIG. 3.

As shown in FIG. 5, first, the group forming unit 120 calculates a distance value between atoms contained in the decomposed residue (S331). That is, the group forming unit 120 calculates the distance value between the atoms using the circular coordinates included in the input protein structure data.

와 다른 원자간의 거리를 산출하고, 글라이신이 아닌 경우에는

와 다른 원자간의 거리를 산출한다. In other words, the group forming unit 120 determines whether the residue is glycine (GLY) or not. Therefore, if the group forming unit 120 is glycine

Calculates the distance between and other atoms, and if not glycine

Calculates the distance between and other atoms.

Then, the group forming unit 120 calculates the distance between the atoms using Equation 1 below.

또는

원자의 좌표이고, {(x',y',z'), (x",y",z")...}는 주변 원자의 좌표이다. Where (x,y,z) is

or

The coordinates of the atom, {(x',y',z'), (x",y",z")...} are the coordinates of the surrounding atoms.

Then, the group forming unit 120 sets a cutoff value using the calculated distance value (S332). The cutoff value is a value for a radius applied when grouping residues, and the group forming unit 120 limits the radius required for grouping residues to 10 mm 2. As described above, the reason for limiting the distance to the radius from the center point to 10 이다 is that the average value for the distance of the previously calculated atoms is calculated as 3.63 Å, and the maximum value is calculated as 6.10 Å. As described above, the group forming unit 120 can not only group all the atoms included in the decomposed residue by setting the cutoff value to 10 kV, but also obtain contact information between the corresponding residue and surrounding residues.

When the setting for the cutoff value is completed as in step S332, the group forming unit 120 obtains information about the atom centered in the residue in order to group all the atoms located within 10 km of radius (S333).

를 중심점으로 설정하고, 그 외의 잔기일 경우에는 원소 중에서

를 중심점으로 설정한다. That is, the group forming unit 120 sets the atom that is the center in the residue as the center point. Here, the group forming unit 120 is among the elements of the residue when the residue is glycine (GLY)

Set as the center point, and for other residues, among the elements

Set as the center point.

Then, the group forming unit 120 groups all atoms located within a radius of 10 km from the obtained center point (S334). In this case, the generated group includes atoms of the corresponding residue at the center point and other residues located within a predetermined radius.

, N, C 원자를 3차원의 공간 좌표에 표시한다(S340). After the group is completed for each of the decomposed residues as in step S334, the spatial coordinate display unit 130 is included in the grouped residues and corresponds to the backbone of the protein.

, N, C atoms are displayed in three-dimensional spatial coordinates (S340).

Hereinafter, step S340 will be described in more detail with reference to FIGS. 6 to 9.

6 is a flowchart for schematically explaining step S340 illustrated in FIG. 3.

, N, C원자에 대한 정보를 획득한다(S341). 부연하면, 원자 정보 획득모듈(131)은 단백질 백본(backbone)에 위치하며 모든 잔기가 동일하게 가지고 있는

, N, C의 원자에 대한 정보를 획득한다. 여기서,

, N, C의 원자에 대한 정보는 원자 좌표 및 원자간의 거리에 정보를 포함한다. As illustrated in FIG. 6, the spatial coordinate display unit 130 has all the residues identically.

, N, C to obtain information about the atom (S341). In other words, the atomic information acquisition module 131 is located in the protein backbone and all residues have the same

Obtain information about the atoms of, N, C. here,

The information on the atoms of, N, C includes information on atomic coordinates and distances between atoms.

, N, C원자를 3차원 공간좌표의 XY축의 평면과 평행이 되도록 위치시킨다(S342). 이를 다시 설명하면, 공간좌표 표준화 모듈(132)은

, N, C원자 중에서

를 3차원 공간좌표의 원점과 동일한 위치선상에 위치시킨다. 그 후, 공간좌표 표준화 모듈(132)은

, N, C원자를 3차원 공간좌표의 XY축의 평면과 평행하도록 위치시킨다. Then, the spatial coordinate standardization module 132 is acquired

, N, C atoms are positioned to be parallel to the plane of the XY axis of the 3D spatial coordinates (S342). In other words, the spatial coordinate standardization module 132

, N, C atoms

Is placed on the same position line as the origin of the 3D spatial coordinate. Then, the spatial coordinate standardization module 132

, N and C atoms are placed parallel to the plane of the XY axis of the 3D spatial coordinate.

, N, C원자와 XY축의 평면이 평행한 상태에서, 공간좌표 표준화 모듈(132)은

원자를 XY축의 원점에 위치시킨다(S343).like this

, N, C atom and the XY axis in parallel, the spatial coordinate standardization module 132

The atom is positioned at the origin of the XY axis (S343).

을 원점에 위치시킨 상태에서 N을 XY축의 평면에 사영시키고, Z축을 중심으로 회전시켜 N을 YZ축의 평면에 위치시킨다(S344). And, the spatial coordinate standardization module 132

In the state where is located at the origin, N is projected onto the plane of the XY axis, and rotated around the Z axis to locate N on the plane of the YZ axis (S344).

Hereinafter, step S344 will be described in more detail with reference to FIG. 7.

7 is an exemplary view schematically showing a method of positioning N in the plane of the YZ axis in step S344 illustrated in FIG. 6.

벡터와 Y축의 사이에 형성된 사잇각을 추출한다.As shown in FIG. 7, the spatial coordinate standardization module 132 projects N to the plane of the XY axis, and then projects the coordinates of N located in the plane of the XY axis.

The angle between the vector and the Y axis is extracted.

벡터와 Y축의 사이에 형성된 사잇각을 산출한다. At this time, the spatial coordinate standardization module 132 uses the following Equation 2 for N coordinates.

Calculate the angle between the vector and the Y axis.

는 양의 Y축 벡터값으로서 (0, 1, 0)의 좌표값으로 나타내고,

는 N을 XY평면에 사영 시켰을 때의 벡터값으로 (

,

, 0)의 좌표값으로 나타낸다. here,

Is a positive Y-axis vector value represented by (0, 1, 0) coordinate values,

Is the vector value when N is projected on the XY plane (

,

, 0).

의 값은

이 되고, |

||

| 는 1 ×

의 값을 통해 산출된다. therefore,

The value of

Become, |

||

| 1 ×

Is calculated through the value of

Then, the spatial coordinate standardization module 132 rotates the Z-axis around the Z-axis so that N touches the YZ-axis plane.

와 동일 선상에 위치하도록 이동시켜 정규화한다(S345). Next, the spatial coordinate standardization module 132 locates N located in the plane of the YZ axis and located in the plane of the XY axis.

It is normalized by moving to be on the same line as (S345).

Hereinafter, step S345 will be described in more detail with reference to FIG. 8.

FIG. 8 is an exemplary view schematically showing a method of normalizing by placing N on a plane of the XY axis in step S345 illustrated in FIG. 6.

벡터와 Y축의 사이에 형성된 사잇각을 추출한다. 8, the spatial coordinate standardization module 132 is for the coordinates of N located in the plane of the YZ axis

The angle between the vector and the Y axis is extracted.

벡터와 Y축의 사이에 형성된 사잇각을 산출한다. At this time, the spatial coordinate standardization module 132 uses the following Equation 3 for N coordinates.

Calculate the angle between the vector and the Y axis.

는 양의 Y축 벡터값으로서 (0, 1, 0)의 좌표값으로 나타내고,

는 N좌표의 벡터값으로 (0,

,

)의 좌표값으로 나타낸다. here,

Is a positive Y-axis vector value represented by (0, 1, 0) coordinate values,

Is the vector of N coordinates (0,

,

).

의 값은

이 되고, |

||

| 는 1 ×

의 값을 통해 산출된다. therefore,

The value of

Become, |

||

| 1 ×

Is calculated through the value of

Next, the spatial coordinate standardization module 132 rotates the X-axis around the X-axis so that the N contacts the plane of the XY-axis.

와 N를 정규화 한 다음, 공간좌표 표준화 모듈(132)은 C원자를 XZ축의 평면에 사영시킨 후, 좌표변환 및 회전처리를 이용하여 C원자를 정규화시킨다(S346). As above,

After normalizing and N, the spatial coordinate normalization module 132 projects the C atom onto the plane of the XZ axis, and then normalizes the C atom using coordinate transformation and rotation processing (S346).

Hereinafter, step S346 will be described in more detail with reference to FIG. 9.

FIG. 9 is an exemplary view schematically showing a method of normalizing by placing a C atom in the plane of the XY axis in step S346 illustrated in FIG. 6.

벡터와 X축의 사이에 형성된 사잇각을 추출한다. As shown in FIG. 9, in the state in which the C atom is positioned parallel to the plane of the XY axis, the spatial coordinate standardization module 132 projects the C atom onto the plane of the XZ axis. The spatial coordinate standardization module 132 uses coordinates of C atoms projected on the plane of the XZ axis

Between the vector and the X-axis, the angle of incidence formed is extracted.

벡터와 X축의 사이에 형성된 사잇각을 산출한다. At this time, the spatial coordinate standardization module 132 uses Equation 4 below.

Calculate the angle between the vector and the X axis.

는 양의 x축 벡터값으로서 (1, 0, 0)의 좌표값으로 나타내고,

는 C좌표를 XZ평면에 사영시켰을 때의 벡터값으로 (

, 0,

)의 좌표값으로 나타낸다. here,

Is a positive x-axis vector value represented by (1, 0, 0) coordinate values,

Is the vector value when projecting the C coordinate onto the XZ plane (

, 0,

).

의 값은

이 되고, |

||

| 의 값은 1 ×

을 통해 산출된다. therefore,

The value of

Become, |

||

| The value of 1 ×

Is calculated through

와 N와 동일한 위치 선상에 위치하되, C의 좌표는

와 N의 좌표보다 큰 위치값을 가진다. Then, the spatial coordinate standardization module 132 rotates the Y axis by a four angle so that the coordinates of C touch the plane of the XY axis. Then, atom C is

And N on the same position line, but the coordinates of C are

It has a position value greater than the coordinates of and N.

, N, C원자를 XY축의 평면상에 정규화 시킨 다음, 3차원 이미지 변환부(140)는

, N, C원자의 주변에 위치하며 그룹형성부(120)을 통해 그룹화되었던 모든 원자들을 3차원 공간좌표상에 표시하여 이미지화시킨다(S350).As in step S340,

After normalizing the N, C atoms on the plane of the XY axis, the 3D image conversion unit 140

, N and C atoms are located around the atoms and grouped through the group forming unit 120 to display images on the 3D spatial coordinates (S350).

, N, C의 좌표를 잔기의

가 원점이 되도록 좌표를 이동하여 위치시킨 다음,

를 중심으로

와의 거리가 컷오프 값보다 작은 모든 원자의 좌표를 표시한다. The 3D image conversion unit 140 is normalized on the plane of the XY axis

, N, C coordinates of the residue

Move the position so that is the origin, and then

Centered on

Displays the coordinates of all atoms whose distance is less than the cutoff value.

대신에

를 중심으로

와의 거리가 컷오프 값보다 작은 모든 원자의 좌표를 표시한다.On the other hand, when the residue to be imaged is glycine,

Instead of

Centered on

Displays the coordinates of all atoms whose distance is less than the cutoff value.

10 is an exemplary view showing a state in which all elements grouped in step S350 shown in FIG. 3 are displayed on a 3D coordinate space.

또는

를 중심으로

, N, C의 좌표를 위치시키고, 그룹화된 모든 원자들을

, N, C의 주변에 위치하며 3차원 이미지를 생성한다. 3D image conversion unit 140, as shown in Figure 10, of the residue

or

Centered on

Position the coordinates of,, N, C, and all the grouped atoms

It is located around, N, C and creates a 3D image.

As described above, according to an embodiment of the present invention, by generating a three-dimensional image representing the amino acid residues of a protein and its surroundings, data analysis and artificial intelligence models can be used as data to learn, so new possibilities for artificial intelligence fusion It has the effect that can be provided as a raw material to open.

In addition, according to an embodiment of the present invention, when performing 3D image generation, since it includes a normalization process on the same position line, it is possible to effectively identify the type of residue and contact with other residues, and remove hydrogen and increase channels. It is possible to promote an effect that can be expanded to a desired shape through the like.

The present invention has been described with reference to the embodiment shown in the drawings, but this is only exemplary, and those skilled in the art to which the art belongs understand that various modifications and other equivalent embodiments are possible therefrom. will be. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the claims below.

100: 3D image generating device
110: protein data input unit
120: group forming unit
130: spatial coordinate display unit
131: Atomic information acquisition module
132: spatial coordinate standardization module
140: 3D image conversion unit

Claims (16)

In the device for generating a three-dimensional image of the environment surrounding the amino acid residues of the protein,
Protein data input unit that receives the structural data for the protein,
Group forming unit for calculating the distance between atoms contained in each residue constituting the protein using the input protein structure data, and forming a group for the residue using the calculated distance value,
It is included in the formed group, and is the basic structure of each residue

Spatial coordinate display unit that displays atoms of, N, and C in three-dimensional spatial coordinates, and
And a 3D image conversion unit displaying all atoms forming the group in the 3D spatial coordinates. According to claim 1,
The group forming unit,
Decomposition is performed for each residue using the received protein structure data, a distance between all atoms included in the decomposed residue is calculated, and a preset cutoff value is centered around a specific atom included in the corresponding residue. 3D image generating apparatus for acquiring and grouping information about all atoms located within a radius having a. According to claim 2,
All atoms grouped above,
A device for generating a 3D image including an atom contained in a corresponding residue having the center point and an atom of other surrounding residues located within the set radius. According to claim 1,
The spatial coordinate display unit,
Located in the protein backbone and all residues have the same

Atomic information acquisition module to obtain information on atoms of, N, C, and
Obtained from the above backbone

, N, C atoms are placed in a plane parallel to the plane of the XY axis of the three-dimensional spatial coordinates, located parallel to the XY axis

Among the atoms of, N, C

To the origin, then

A 3D image generating apparatus including a spatial coordinate standardization module that normalizes N and C by using coordinate transformation and rotation processing. The method of claim 4,
The spatial coordinate standardization module,
Among the three atoms

Move the coordinates so that their coordinates are at the origin of the XY axis,
remind

After projecting the coordinates of N on the plane of the XY axis while positioning at the origin, the coordinates of N on the plane of the XY axis

Rotate the Z-axis so that the coordinates of N touch the plane of the YZ-axis by using the angle formed between the vector and the Y-axis,
For the coordinates of the rotated N

Rotate the X-axis so that the coordinates of N touch the plane of the XY-axis using the angle formed between the vector and the Y-axis, and
After projecting the coordinates of C onto the plane of the XZ axis,

By rotating the Y-axis so that the coordinates of C touch the plane of the XY-axis by using the angle of incidence formed between the vector and the X-axis,

, N, C atoms are located in parallel on the plane of the XY axis. The method of claim 4,
The spatial coordinate standardization module,
remind

With the coordinates of

The vector is parallel to the y-axis, and the coordinates of C are

3D image generating apparatus having a position value greater than the coordinates of and N. According to claim 1,
The 3D image conversion unit,
Normalized on the plane of the XY axis

, N, C coordinates of the residue

Is moved to the origin coordinate and positioned, and then

Centered on the above

A 3D image generating device that displays the coordinates of all atoms whose distance to and from is less than the cutoff value. According to claim 1,
The 3D image conversion unit,
When the grouped residue is glycine (GLY), normalized on the plane of the XY axis

, N, C coordinates

Centered on the above

A 3D image generating device that displays the coordinates of all atoms whose distance to and from is less than the cutoff value. In the method of generating a three-dimensional image of the surrounding environment of amino acid residues of proteins using a three-dimensional image generating device,
Receiving structural data for a protein,
Computing the distance between atoms contained in each residue constituting the protein using the input protein structure data, and forming a group for the residue using the calculated distance value,
It is included in the formed group, and is the basic structure of each residue

, Normalizing the atoms of N, C to three-dimensional spatial coordinates, and
And displaying all the atoms forming the group in the 3D spatial coordinates and imaging the 3D image. The method of claim 9,
Forming a group for the residue,
Decomposing the protein for each residue using the received protein data, and calculating a distance value between atoms included in the decomposed residue,
Setting a cutoff value using the calculated distance value,
Obtaining a central atom among a plurality of atoms included in the residue, and
Comparing the distance value between the calculated atoms and the cutoff (cutoff) value, grouping all the atoms located within a radius with the set cutoff (cutoff) value, and obtaining information about the atoms in the formed group 3D image generation method comprising a. The method of claim 10,
All atoms grouped above,
A method for generating a 3D image including an atom contained in a corresponding residue having the center point and an atom of other residues located within the set radius The method of claim 9,
The step of normalizing to the three-dimensional spatial coordinates,
Located in the protein backbone and all residues have the same

Obtaining information about atoms of, N, C,
Obtained above

, Positioning the plane formed by the atoms of N and C to be parallel to the plane of the XY axis of the three-dimensional spatial coordinate, and
Located parallel to the XY axis

Among the atoms of, N, C

To the origin, then

A method of generating a 3D image, comprising normalizing spatial coordinates using coordinate transformation and rotation processing of N and C as a center. The method of claim 12,
Normalizing the spatial coordinates,
Among the three atoms

Moving the coordinates so that their coordinates are located at the origin of the XY axis,
remind

After projecting the coordinates of N on the plane of the XY axis while positioning at the origin, the coordinates of N on the plane of the XY axis

Rotating the Z-axis so that the coordinates of N touch the plane of the YZ-axis using the angle of incidence formed between the vector and the Y-axis,
For the coordinates of the rotated N

Rotating the X-axis so that the coordinates of N touch the plane of the XY-axis by using the sway angle formed between the vector and the Y-axis, and
After projecting the coordinates of C onto the plane of the XZ axis,

A method of generating a three-dimensional image, comprising rotating the Y-axis so that the coordinates of C contact the plane of the XY-axis using the angle of incidence formed between the vector and the X-axis. The method of claim 12,
Normalizing the spatial coordinates,
remind

With the coordinates of

The vector is parallel to the y-axis, and the coordinates of C are

A method of generating a 3D image positioned larger than the coordinates of and N. The method of claim 9,
The imaging step,
Normalized on the plane of the XY axis

, N, C coordinates of the residue

Is moved to the origin coordinate and positioned, and then

Centered on the above

A method of generating a 3D image that displays the coordinates of all atoms whose distance to and is less than the cutoff value. The method of claim 9,
The imaging step,
When the grouped residue is glycine (GLY),
Normalized on the plane of the XY axis

, N, C coordinates

Centered on the above

A method of generating a 3D image that displays the coordinates of all atoms whose distance to and is less than the cutoff value.

Images