JP3012441B2 - Protein three-dimensional structure prediction method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for predicting the three-dimensional structure of a protein from the amino acid sequence of a protein whose structure is unknown.

[0002]

2. Description of the Related Art As a local three-dimensional structure of a protein,
There are secondary structures such as α-helix and β-sheet, and motifs such as zinc finger and leucine zipper. It is generally considered that if it becomes possible to predict the local structure of a protein with respect to the amino acid sequence of a protein whose structure is unknown, it is possible to predict the three-dimensional structure of the entire protein.

For example, the problem of protein secondary structure prediction is as follows:
This is a problem that has been solved for more than 20 years. Conventionally, each residue in the primary structure of a protein (hereinafter, the residue to be predicted is referred to as a central residue) has 3 (or 4) types. Has been treated as a matter of predicting which of the secondary structures corresponds to As a method for predicting the secondary structure of a protein according to the prior art, for example, a US magazine “Biochemistry” published in 1974 (Biochemistry)
y), Vol. 23, pp. 222-245.
u) and Fasman's dissertation "Prediction of Protein Conformation"
(Prediction of protein co
nformation) (hereinafter abbreviated as CF method), 19
US journal "Journal of Molecule Biology" published in 1978
Cultural Biology) Volume 120 97-12
"Analysis of the Accuracy and Implications of Simple Methods for Predicting the Secondary Structure of Globular Proteins" by Garnier et al.
s of the accuracy and impl
indications of simple method
for predicting the second
day structure of global
proteins) (hereinafter abbreviated as GOR method), 19
1987 US journal "Journal of Molecule Biology" (Journal of Mole
Circular Biology) Vol.
Gibrat et al., Page 43, "Father Developments of Protein Secondary Structure Prediction Yousing Information Theory: New Parameters and Conclusion of Residue"
Pairs "(Further developments
of protein secondary str
ucture prediciton using i
nformation theory: New par
meters and considation
of resin pairs) (hereinafter GGR
1988), a US magazine published in 1988, "Journal of Molecular Biology" (Journal
of Molecular Biology)
Qian et al., Predicting the Secondary Structure of Globber Proteins Using Neural Network Models, Vol. 02, pages 865-884 (Pr.
editing the secondary st
structure of global prote
insuring neural network m
odels) (hereinafter abbreviated as QS), and the 1993 American academic conference “Hawaii International Conference of System Sciences” (Hawaii).
International Conference
of System Sciences, Vol. 1, pages 659-668, written by Umizuka et al., "Protein α-Helix Region Prediction Based on Stochastic Rule Learning" (Protein α-Helix Region).
n Prediction Based-on Sto
classic Rule Learning) (hereinafter abbreviated as MY method).

[0004] In the CF method, the statistical appearance frequency of amino acids in each secondary structure is obtained from a protein structure database, and the frequency table is used to make predictions based on empirical rules. Also, the GOR method calculates the sum of the information amounts independently brought about by the residues several residues away from the secondary structure of the central residue, makes a prediction from the relative value, and calculates the GGR The method predicts the secondary structure of the central residue from the sum of the information content provided by the residue and the residues several residues away from the residue. Furthermore, QS
The method uses a three-layer feed-forward network, inputs a sequence containing eight residues before and after the central residue, and uses a neural network to determine the contribution of the central and peripheral residues to the secondary structure. Prediction is performed by extracting. The MY method calculates the probability that each amino acid is an α-helix at each residue position in the training sequence as a probability distribution, and then calculates the probability of the α-helix for each region of the test sequence.

[0005]

In the amino acid sequence of a protein, it is considered that each amino acid residue retains a dependency and forms a local three-dimensional structure or a functional site. Therefore, in order to represent and predict the local three-dimensional structure of a protein, it is considered important to express the dependence between the residues in the local three-dimensional structure. However, there has been no study on a method for automatically extracting a dependency depending on the residue position in the form of a network or a method for predicting unknown data by using the dependency as a rule. , Such a method was not established.

[0006]

Means for Solving the Problems The present invention provides a protein structure.
Steps to learn the structure of stochastic rules for predicting
In the method for predicting a protein three-dimensional structure having
The step consists of training the amino acid sequence consisting of positive and negative examples.
Entering the data and the dependencies of each amino acid
Positive and negative real-valued parameters as conditional probabilities
And the real-valued parameters
Using the information criterion provided, the residue of each of the amino acid sequences
By determining the position of other residues on which the base position depends
And constructing a probabilistic rule structure to express the dependency
Outputting the probabilistic rule.
Calculate the activity of the test data and calculate the activity
Predicts the three-dimensional structure of proteins based on
And

Further , the present invention provides a method for predicting a protein structure.
Learning the structure of stochastic rules for
In the protein three-dimensional structure prediction method, the step
Provides training data for amino acid sequences consisting of positive and negative examples.
Entering as real-valued attributes
Real-valued patterns of positive and negative examples
Calculating the parameters, and
Using a more defined information criterion, the amino acid sequence
Determine the other residue positions on which each residue position depends
Thus, the structure of the stochastic rule expressing the dependency is
Constructing and outputting the probabilistic rule.
Calculate the activity of the test data using the structure and calculate
Predict the three-dimensional structure of a protein based on the activity
And features.

[0008] The present invention also provides a method for predicting a protein structure.
Learning the structure of stochastic rules for
In the protein three-dimensional structure prediction method, the step
Provides training data for amino acid sequences consisting of positive and negative examples.
Condition of input step and dependency of each amino acid
Calculate positive and negative real-valued parameters as probabilities.
And the information defined by the real-valued parameters.
Each residue position in the amino acid sequence is determined using the
If the residue does not circulate to other dependent residue positions
Express the dependency by deciding under the restrictions
Constructing and outputting a probabilistic rule structure
And use the structure of the probabilistic rules to activate test data.
Calculate the degree of activity and calculate the protein based on the calculated activity
Is predicted.

The present invention also provides a method for predicting a protein structure.
Learning the structure of stochastic rules for
In the protein three-dimensional structure prediction method, the step
Provides training data for amino acid sequences consisting of positive and negative examples.
Entering as real-valued attributes
Real-valued patterns of positive and negative examples
Calculating the parameters, and
Using a more defined information criterion, the amino acid sequence
Dependency on other residue positions where each residue position depends
Is determined under the restriction that the
Build and output the structure of probabilistic rules expressing dependencies
Using the structure of the stochastic rule.
Calculate the activity of the strike data, and based on the calculated activity
And predicts the three-dimensional structure of the protein.
You.

[0010]

Next, the present invention will be described in detail with reference to the drawings.

FIG. 1 is a flow chart for explaining an embodiment of the protein three-dimensional structure prediction method of the present invention. In this embodiment, it is assumed that an α-helix is treated as a local three-dimensional structure of a target protein.

In step 11, the amino acid sequence of the protein whose α-helix region is known is aligned with the same family of proteins, for example, the same protein of different species, and the partial sequence corresponding to the α-helix is determined. Is extracted as a positive example of an α helix.

For example, in the case of a protein β-chain called hemoglobin, the position of the α-helix of human hemoglobin has been clarified from the results of X-ray crystal diffraction.
It is known to have a region of eight α-helices. Therefore, human hemoglobin β chain is aligned with other species, for example, chimpanzee, horse and other species of hemoglobin β chain. Extract.

In step 12, each sequence of the amino acid sequence database with known α-helix position is aligned with the partial sequence corresponding to α-helix of the protein with known α-helix position, Non-corresponding subsequences are extracted as a negative example relative to the positive example of the α helix extracted in step 10.

In the example of the hemoglobin β chain, the partial sequence corresponding to the eight α helices is, for example, PDB
Alignment is performed for several sequences in a protein structure database such as (Data Protein Bank), and in each partial sequence obtained as a result of the alignment, if the structure of the sequence is not α-helix, these are regarded as negative examples. Extract as For example, in the alignment at the time of extracting a negative example, it is conceivable that a partial sequence having homology of a certain ratio or more is regarded as a negative example. Specifically, there is a method using a partial sequence having a homology of 30% or more by alignment as a negative example.

The number of data to be extracted is, for example, α
It is conceivable that the ratio of the positive example to the negative example in each region serving as the positive example of the helix is made equal in each region. Furthermore, more specifically, it is conceivable that the same number of positive examples and negative examples is used as the ratio.

Step 13 is a step of calculating the real-valued parameters of the probabilistic rule from the positive and negative examples extracted in steps 11 and 12.

The stochastic rule here is a probability distribution that gives a probability that an α-helix corresponds to an arbitrary region of a given sequence. Each X _i (i =
1,. . . , N) are attribute value spaces, and X is their direct product, that is, X = X ₁ × X ₂ ×. . . × X
Write _n .

For example, X represents one set of 20 kinds of amino acids, or X = X ₁ × X ₂ and X ₁
May represent a range of numerical values representing hydrophobicity and X ₂ may represent a range of numerical values representing molecular weight.

For a window W of length L in the positive example of the α helix, a region S of arbitrary length L in the test sequence is W
The likelihood corresponding to the part is determined as follows. First, X _t (hereinafter, referred to as a variable) is the t-th residue position counted from the left of the sequence S, and π _t is a set of residue positions on which X _t depends in the region W (hereinafter, π _t is referred to as a variable). set of parent variables of X _t, the X _t is referred to as a child variable of π _t) to. here,

[0021]

(Equation 1)

Let the conditional probability that X _t depends on π _t be in the region W, and assume that the probability Pw (S) that the region S corresponds to the W portion can be written as follows.

[0023]

(Equation 2)

The right side of Equation 1 corresponds to a network structure by using variables as nodes and extending an arc from a parent to a child between the variables. For example, if the region S is composed of three residues, and the connection probability of each residue in the region S can be specifically written as the following expression, the following expression corresponds to the network of FIG.

[0025]

(Equation 3)

Further, each

[0027]

(Equation 4)

Is determined as follows, for example, from the given case data including the positive and negative examples.

[0029] First, in the t-th residue position, partial area not overlapping the possible range of real-valued attributes (hereinafter, referred to as cells) and finite divided, the total number of cell m _t, C _i Is the i-th cell.

[0030] If the residue of the t-th position is included in C _i of the m _t number of cells, X _t of the occurrence probability P (X _t = i)
= P _i (t). here,

[0031]

(Equation 5)

This is called a probability parameter. FIG. 4 shows an example of the structure of the finite division, in which the value is from 0 to 1.
Shows a case where a probability parameter is estimated by one attribute having a range of.

The probability parameter is estimated using the number of positive and negative data included in each cell.

[0034]

(Equation 6)

Is the number of positive cases contained in the i-th cell at the t-th position, and N _i (t) is the sum of the number of positive cases and the number of negative cases contained in the i-th cell at the t-th position. , Let the estimated value at the i-th cell at the t-th position be p _i (t). For example, a probability parameter for each cell is calculated by the Laplace estimator of the following equation.

[0036]

(Equation 7)

However, not only the Laplace estimator but also many estimators can be used. Then, similarly, X _t and [pi _t joint probability P (X _{t, π t)} can be calculated using the estimated amount. For example, [pi when the elements of _t is only variable X _s, and finite divides X _s in m _s number of partial areas not overlapping in the same manner as X _t, s-th residue of the m _s number of cells C _j
Included in

[0038]

(Equation 8)

And the probability parameters p _{i, j} (t, s)
Is estimated.

At each of the t-th and s-th positions, based on the number of data of the positive and negative examples contained in each cell,

[0041]

(Equation 9)

Is the number of positive examples included in the i, j-th cell at each position, and N _{i, j} (t, s) is the number of positive examples and the negative example included in the i, j-th cell at each position. The sum of numbers. From this, for example, a probability parameter is estimated by the following Laplace estimator.

[0043]

(Equation 10)

Finally, using these estimated probability parameters, the conditional probability of X _{t in} the presence of π _t

[0045]

[Equation 11]

Is calculated as a probability parameter. As described above, [pi elements _t is only variable X _s, t th and s-th each m _t pieces each position, and finite divided into m _s pieces, further residue cell C _i of each position , C _j ,

[0047]

(Equation 12)

And the probability parameter

[0049]

(Equation 13)

Is calculated as follows:

[0051]

[Equation 14]

In step 14, the structure of the stochastic rule is determined. That is, for each variable X _t , a set of parent variables π _t is determined using the information amount criterion, and corresponds to the first and third inventions of the present invention.

Hereinafter, the minimum description length (Mi
minimum Description Length
(MDL) An example of a network configuration method when applied to the principle (hereinafter, the MDL principle) will be described. In addition,
For the MDL principle, see the 14th edition of the American magazine "Automatica" published in 1978.
Volume 465-471, Rissane.
n), "Modeling by Shortest Data Description" (Modelingby
shortest data description
n).

According to the MDL principle, the rule that minimizes the sum of the data description length calculated from given case data and the rule description length is determined as the optimal rule. Therefore, step 1
The data description length of the probabilistic rule and the description length of the rule here are calculated from the positive examples, negative examples, and real-valued parameters obtained in 1, 12, and 13.

In the example described here, it is considered that, for each residue position, a position that is dependent on the position is determined. That is, the parent variable is determined independently for each variable.

First, attention is paid to the t-th residue position. The dependency between the variable X _t and its parent variable set π _t is determined by the conditional probability

[0057]

(Equation 15)

Is represented by Here, the number of parent variables is k,
The residue position of the parent variables and t _k from t _l in order, also, t
And the total number of cells at residue positions from t _l to t _k is m
_t, m _tl, ···, and m _tk. Further, the variable X _t
Residues i, residues X _tk from the variable X _tl, respectively j _l, · · ·, a positive number of cases that have attributes such as contained in j _k th cell

[0059]

(Equation 16)

[0060], residues of variable X _t is i, from the variable X _tl X
residues _tk are respectively j _l, · · ·, the sum N _i of the j _k-th number of positive cases that have attributes such as the cell contains a negative number of _{cases, jl, · · ·, jk} (t, t _l , ..., t
_k), the variable X residues _t is i, the residues X _tk from the variable X _tl, respectively jl, · · ·, a j _k-th conditional probability has attributes such as entering a cell probability Parameter

[0061]

[Equation 17]

It is assumed that

Then, the data description length of the probabilistic rule here is given by the following equation by taking the log likelihood of the rule negative from the probability parameter calculated in step 13.

[0064]

(Equation 18)

Further, the description length of the rule of the stochastic rule is given by the following equation.

[0066]

[Equation 19]

[0067] Therefore, with respect to the variable X _t, which corresponds to t-th residue positions, by selecting the set of parent variables minimizing the sum of (6) and (7), stochastic The structure of the rule is determined.

In step 15, the probabilistic rule constructed in step 14 is used to calculate the activity of each region of the given test data array.

Here, likelihood is used as the activity.

First, an area W having an arbitrary length L in the positive example of the training sequence is extracted. The parent variable of the variable corresponding to each residue position of W has been determined in step 14. Further, the real-valued parameter of the conditional probability representing the dependency between each variable and its parent variable is calculated in step 13.

Next, this area W is applied to a partial sequence S of an arbitrary length L of the test sequence, and the likelihood of the α helix is calculated.

For example, in the area W where L = 3, (2)
The structure of the stochastic rule such as the equation is determined, and in the region S of L = 3 of the test sequence, each residue in the region is 2,
Suppose that it has a real-valued attribute that goes into the first and third cells. Then, the likelihood that this area S is W can be calculated by the following equation.

[0073]

(Equation 20)

This operation is performed on all the sub-arrays of length L in the test array using a probabilistic rule composed of all possible length L regions in the positive example of the training array.

In step 16, for a region S of an arbitrary length L in the test sequence, a plurality of likelihoods calculated by all possible length L regions of the positive example in the training sequence are calculated. , The maximum likelihood is selected as the α-helix likelihood of the region S.

The operations in steps 15 and 16 can be summarized as follows. That is, all sets of the length L region in the positive sequence in the training sequence are A, and the likelihood P (S) of the α helix with respect to the partial sequence S having the length L of the test sequence is calculated by the following equation.

[0077]

(Equation 21)

By repeating this operation for each area of the test array, the likelihood of the α helix is calculated for each area of the test array.

Here, if there are a plurality of α-helix regions, the same likelihood calculation is performed for each α-helix region, and the maximum likelihood is selected as the optimum value over the entire α-helix region.

Further, in each region where the likelihood in the test sequence is given, the maximum likelihood is set as the optimum value of each residue in the region. The average of the obtained likelihood of the region containing the residue is used as the optimum value of each residue, and the like, and the likelihood change for the entire test amino acid sequence is output.

The learning and predicting method in FIG.
The present invention can be applied to feature extraction and prediction of local regions such as secondary structures and motifs other than the α-helix. FIG. 2 is a flowchart illustrating an embodiment of the protein three-dimensional structure prediction method of the present invention. In the present embodiment, it is assumed that an α-helix is used as a target secondary structure.

In step 21, the same processing as in step 11 in FIG. 1 is performed to extract a positive example required for α-helix region prediction.

In step 22, the same processing as in step 12 in FIG. 1 is performed to extract a negative example necessary for α-helix region prediction.

In step 23, the same processing as in step 13 in FIG. 1 is performed, and the real-valued parameters of the probabilistic rule are estimated from the positive and negative examples extracted in steps 21 and 22.

Step 24 is a step in which the construction of the probabilistic rule is restricted, and a consistent probabilistic rule is constructed as a joint probability distribution of all variables in the local structure region. Included in the invention. The restriction here is a restriction in which the direction of the arc is non-circular so that the probability distribution does not conflict when the probabilistic rule is represented by a network structure as shown in FIG. For example, FIG. 3 is an example of a non-circulating network. In this figure, if the arc extending from X ₁ to X ₃ is extended from X ₃ to X ₁ , the network becomes a cyclic network, and so on. We do not allow the creation of a simple network.

As a method of adding a restriction, for example, a method in which each variable is ordered and only variables having a small order can be used as a parent variable, or a case where a dependency is formed such that an arc is circulated. Only, a method of preventing the dependency from being established can be considered.

In step 25, the same processing as in step 15 in FIG. 1 is performed, and using a stochastic rule whose structure has been optimized using step 24, the activity of each region of the test amino acid sequence data is determined. Calculate the degree.

In step 26, the same processing as in step 16 of FIG. 1 is performed, and a change in the activity for the entire array is output from the plurality of activities determined in step 25.

The learning and prediction method in FIG.
The present invention can be applied to feature extraction and prediction of local regions such as secondary structures and motifs other than the α-helix.

[0090]

According to the present invention, from the amino acid sequence information of a protein having a known three-dimensional structure, the local three-dimensional structure of a protein whose local three-dimensional structure is unknown can be predicted with higher accuracy than the prior art. For example, the MY method, which is one of the conventional methods, does not consider the dependency between the residue positions in the local region at all. However, due to the configuration of the probabilistic rule reflecting the dependency between the residue positions, The feature extraction and prediction of the local region with higher accuracy can be performed. In addition, the optimization based on the information criterion makes it possible to theoretically optimize the structure of the stochastic rule.

[Brief description of the drawings]

FIG. 1 is a flow chart showing one embodiment of the protein three-dimensional structure prediction method of the present invention.

FIG. 2 is a flowchart showing an embodiment of the protein three-dimensional structure prediction method of the present invention.

FIG. 3 is a schematic diagram showing a dependency relationship between variables of a stochastic rule used in the present invention.

FIG. 4 is a schematic diagram showing a specific example of finite division performed at each residue position in the present invention.

[Explanation of symbols]

 11 Extraction of positive examples 12 Extraction of negative examples 13 Estimation of real-valued parameters 14 Determination of the structure of probabilistic rules 15 Calculation of activity for test sequences 16 Calculation of predicted values for test sequences 21 Extraction of positive examples 22 Extraction of negative examples 23 Real-valued parameter estimation 24 Probability Determining the structure of a statistical rule 25 Calculating activity for a test sequence 26 Calculating a predicted value for a test sequence

Continuation of the front page (56) References Proceedings of the IPSJ National Convention, 45th, 1-343-344, Mamizuka, Yamazaki "Helix region prediction of proteins using stochastic rules" (Hei 4 −10−11) (58) Fields investigated (Int.Cl. ⁷ , DB name) G06F 15/20 G06F 15/40 530

Claims (4)

(57) [Claims] 1. A stochastic rule for predicting a protein structure.
In protein tertiary structure prediction method having a step of learning the structure of law, the step includes a step of inputting <br/> training data of the amino acid sequence consisting of positive cases and negative cases, the dependency of each amino acid conditions attached as a probability, real value parameters of the positive examples and negative examples
Calculating the data position and using the information criterion defined by the real-valued parameters to determine other residue positions on which each residue position of the amino acid sequence is dependent. by, and a step of outputting to build the structure of probabilistic rules that express the dependency, the activity of the test data using the structure of the probabilistic rule
Calculates and calculates the 3D of the protein based on the calculated activity
A method for predicting a protein three-dimensional structure, comprising predicting a structure. 2. A stochastic rule for predicting a protein structure.
In protein tertiary structure prediction method having a step of learning the structure of law, the step includes a step of inputting <br/> training data of the amino acid sequence consisting of positive cases and negative cases as a real numeric attributes, each
Amino acid of dependency as a conditional probability, positive examples and negative
Calculating an example real-valued parameter;
Using the information criterion defined by the parameters, determine the residue positions on which each residue position of the amino acid sequence depends, thereby constructing a probabilistic rule structure expressing the dependency relationship. and a step of and outputs, the activity of the test data using the structure of the probabilistic rule
Calculates and calculates the 3D of the protein based on the calculated activity
A method for predicting a protein three-dimensional structure, comprising predicting a structure. 3. A stochastic rule for predicting a protein structure.
Three-dimensional structure with the step of learning the rule structure
In the structure prediction method, the step comprises the steps of:
Input training data and the dependence of each amino acid
Real-valued parameters for positive and negative examples
Calculating the data and the real-valued parameters
Using a defined information criterion, each of the amino acid sequences
The other residue positions on which the
By making decisions under the restriction of not circulating,
Construct and output the structure of probabilistic rules expressing existence relationships
And determining the activity of the test data using the structure of the stochastic rule.
Calculates and calculates the 3D of the protein based on the calculated activity
Protein three-dimensional structure prediction characterized by predicting the structure
Measurement method. 4. A stochastic rule for predicting a protein structure.
Three-dimensional structure with the step of learning the rule structure
In the structure prediction method, the step comprises the steps of:
Inputting training data as real-valued attributes;
Positive and negative amino acid dependencies as conditional probabilities
Calculating an example real-valued parameter;
Using the information criterion defined by the parameter,
Other residue positions at which each residue position in the amino acid sequence is dependent
Location under the restriction that dependencies do not cycle.
Form the structure of the probabilistic rule expressing the dependency.
And outputting the test data using the structure of the stochastic rule.
Calculates and calculates the 3D of the protein based on the calculated activity
Protein three-dimensional structure prediction characterized by predicting the structure
Measurement method.