A metabolic engineering target prediction method based on reference-type-high-yield-type protein concentration range comparison

Abstract

The present application relates to the field of biotechnology, and in particular to metabolic engineering strategy modification, and discloses a metabolic engineering target point prediction method based on reference type-high yield type protein concentration range comparison. The method uses optimal thermodynamic bottleneck and optimal enzyme thermal efficiency constraint, and through range comparison analysis based on enzyme concentration on the growth strain in reference state and the production model in overexpression state, finally obtains the reaction or gene which needs to be overexpressed or knocked out when producing products. The method significantly improves the accuracy of target point prediction, and is particularly suitable for efficient production of important metabolic products such as amino acids.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of metabolic engineering, and specifically relates to a metabolic engineering target prediction method based on comparison of reference-type and high-yield-type protein concentration ranges. BACKGROUND

[0002] In metabolic engineering, designing effective targets and strategies is a key step to improve the yield of target metabolites. Traditional target prediction methods, such as OptForce MUST , identify possible modification targets by comparing the metabolic flux changes of wild-type and overexpression models. However, these methods rely on quantitative models, mainly focusing on the flux regulation at the reaction level in metabolic pathways, while ignoring the influence of enzyme catalytic efficiency, enzyme consumption cost, and thermodynamic limitations. The limitations of this method often lead to a lack of accuracy and practical operability in predicting enzyme regulation strategies, and may fail to identify the optimal enzyme regulation targets or effectively optimize metabolic pathways (Ranganathan et al., 2010, "OptForce: An Optimization Procedure for Identifying All Genetic Manipulations Leading to Targeted Overproductions", PLoS Computational Biology, 6, e1000744; Choi et al., 2010, "In silico identification of gene amplification targets for improvement of lycopene production in Escherichia coli", Applied and Environmental Microbiology, 76, 3097-3105).

[0003] To solve these problems, some new methods have emerged in recent years, such as the enzyme-thermo constrained model (ecGEM), which integrates enzyme kinetic parameters and thermodynamic limitations into a whole-genome metabolic model, allowing more accurate simulation of metabolic activities within cells. These improved models have shown some success in certain experimental applications, such as improving the production of hematin in Saccharomyces cerevisiae. SUMMARY

[0004] To this end, the present application develops a target prediction method using enzyme-thermo constrained model (referred to as ET-OptForce MUST), where enzyme kinetics and thermodynamic constraints are introduced and integrated into the genome-scale metabolic model, directly targeting the regulatory strategies of enzymes. This method can more accurately predict the regulatory needs of enzymes by aggregating the enzyme concentration ranges of all reactions catalyzed by the same enzyme.

[0005] With these improvements, ET-OptForce MUST Significant accuracy improvements are shown in the prediction of multiple metabolic products. In the test of the metabolic model of Corynebacterium glutamicum, ET-OptForce MUST More effective targets can be predicted. These results show that the target prediction method combined with enzyme-thermal constraints has great potential in improving the effectiveness of metabolic engineering design. This innovative algorithm significantly improves the accuracy and feasibility of metabolic target prediction, providing a more reliable design tool for future metabolic engineering applications.

[0006] In the process of metabolic engineering strategy design and construction, the present application significantly improves the accuracy of metabolic engineering strategies by introducing the concept of enzyme thermal constraints and minimum total enzyme concentration. Specifically, during the strategy construction process, thermodynamic constraints and enzyme catalytic efficiency are considered to ensure that metabolic reactions are energetically feasible. In addition, by optimizing the use of enzymes, the constraint of minimum total enzyme concentration is added to ensure that the consumption of enzymes is minimized while achieving the target product yield. This method not only reduces the unreasonable phenomena in metabolic reactions, but also effectively improves the feasibility and accuracy of metabolic engineering strategies, thereby increasing the yield of target metabolites.

[0007] The present application provides a metabolic engineering target prediction method based on reference-type-high-yield-type protein concentration range comparison, comprising the following steps:

[0008] First step: First, under the condition of thermodynamic constraints (when B is a non-negative number, B is the minimum thermodynamic driving force of all reactions), the optimal growth rate in the cell is determined by solving a set of equations. The equation set includes steady-state mass balance constraints, reaction flux upper and lower limit constraints, thermodynamic driving force constraints, enzyme distribution constraints, and enzyme concentration and catalytic rate relationships;

[0009] Second step: On the basis of fixing the optimal growth rate, the optimal thermodynamic minimum driving force in the reference type is further solved. This is achieved by solving the equation set again, which includes all the constraints mentioned earlier.

[0010] Third step: After fixing the optimal thermodynamic driving force obtained above, the maximum growth rate under the reference type condition is calculated. On this basis, the minimum total enzyme concentration required to achieve the maximum growth rate is further determined.

[0011] Step 4: After fixing the above conditions, the maximum and minimum values of each enzyme in the reference type state are solved to determine the concentration range thereof.

[0012] Step 5: The product production rate of the overexpression type is calculated and the production rate is constrained, and the maximum product production rate, the minimum total enzyme concentration and the enzyme concentration range under the overexpression type condition are determined by using the same method as the reference type. In the overexpression type, the normal growth of the cell is ensured while the product is generated.

[0013] Step 6: By comparing the enzyme concentration ranges under the reference type and the overexpression type conditions, the key enzyme target points that need to be up-regulated or down-regulated are identified; the up-regulation target point for the enzyme is determined according to the maximum value of the enzyme concentration of the enzyme in the reference type state being less than the minimum value of the enzyme concentration of the enzyme in the overexpression type state, and the down-regulation target point for the enzyme is determined according to the minimum value of the enzyme concentration of the enzyme in the reference type state being greater than the maximum value of the enzyme concentration of the enzyme in the overexpression type state.

[0014] The enzyme heat constraint algorithm used in the first step and the second step is as follows:

[0015] Maximize v biomass

[0016] Subject to

[0017]

[0018] Wherein, S represents the measurement matrix of the model, v represents the flux value of each reaction in the metabolic network, equations (1) (2) describe the steady-state material balance constraint, LB and UB are the upper limit of the reaction flux and the lower limit of the reaction, respectively, and equation (3) represents the thermodynamic driving force of the reaction J T in the set is also equal to the negative of the Gibbs free energy, wherein S i,j represents the transpose of the jth reaction vector, g0 j is the standard Gibbs free energy of reaction j, R is the gas constant (8.3145 J / mol / K), T is the default temperature (298 K), and x i,j is the logarithmic concentration of metabolite i in reaction j. Equations (4) and (5) represent the thermodynamic constraints imposed on the pathway participating in the reaction, wherein B is the minimum value of the thermodynamic driving force of all reactions in the set J T , K is a constant value, and a large enough number is used to ensure that the reactions not participating in the pathway can not escape the thermodynamic constraint; since the thermodynamic constraint should only apply to the reactions participating in the pathway, it is necessary to distinguish the participating and non-participating reactions by using integer variables (binary variables), if a certain reaction does not participate, z j = 0, and v j = 0. Equation (6) e0 p(mmol / gDW) represents the sum of enzyme concentrations of enzyme-catalyzed reactions, e j (mmol / gDW) represents the enzyme cost allocated to reaction j; where j belongs to the set of reactions catalyzed by enzyme p; equation (7) where Kcat j (1 / h) represents the enzyme catalytic constant of reaction j; equation (7) defines that the maximum flux of reaction j is determined by the enzyme catalytic constant of reaction j and the enzyme concentration allocated to reaction j; equation (8) where MW p (g / mmol) is the molecular mass of enzyme p, Epool represents the mass fraction of enzymes in dry cells (g protein / g cell dry weight) considered in the calculation; the target value of this optimization is v biomass,max ;

[0019] Subsequently, solve the maximum thermodynamic driving force B1 under the constraints, the constraints of the algorithm are:

[0020] Maximum B1

[0021] Subject to constraints (1) (2) (3) (4) (5) (6) (7) (8)

[0022] Solve the minimum total enzyme concentration totalE under the constraints, assign the target value of this step to totalE1_min The constraints used by the algorithm are:

[0023] Minimum totalE

[0024] Subject to constraints (1) to (8)

[0025]

[0026] v biomass = v biomass_max (10)

[0027] The method of the present application is constructed by using a protein-centered algorithm, which overcomes many limitations in traditional metabolic engineering modification strategies. In the classical enzyme constraint model, modeling is usually reaction-centered, that is, each enzyme corresponds to multiple independent reactions, which may lead to contradictions in metabolic modification strategies when dealing with different reactions catalyzed by the same enzyme. For example, the flux change in different reactions may lead to inconsistency, causing confusion in target selection and optimization. By adding different reactions catalyzed by the same enzyme together, the present application successfully avoids this contradiction, ensuring the consistency and consistency of the reaction strategy in the metabolic network.

[0028] Further, the present invention introduces enzyme thermal constraints, integrating thermodynamic constraints and enzyme kinetic parameters into genome-scale metabolic models. This innovation significantly improves the feasibility of metabolic engineering strategies. Enzyme thermal constraints ensure that reactions proceed in an energetically feasible direction, avoiding the problem of determining the direction of metabolic fluxes across zero points, which is a major challenge in traditional models. In this way, the present invention not only improves the accuracy of predicting cellular metabolic behavior, but also reduces the risk of potential experimental failures.

[0029] Compared with the prior art, the method of the present invention is more comprehensive and meticulous in the design of metabolic engineering strategies. Traditional metabolic network models usually rely on metrology methods, which cannot fully consider the influence of enzyme catalytic activity, enzyme cost and thermodynamic constraints. The method of the present invention provides a more realistic and practical strategy design tool by considering these factors comprehensively. This method not only improves the accuracy of prediction, but also effectively reduces the workload and cost of large-scale strain construction, making the implementation of metabolic engineering more economical and efficient. Through this innovation, the present invention opens up a new path for the research and application of metabolic engineering, and promotes the further development of industrial microorganism modification technology. DETAILED DESCRIPTION

[0030] The specific embodiments of the present invention are described in detail below, but do not constitute a limitation on the present invention.

[0031] Example 1:

[0032] The present invention is a metabolic engineering target prediction method based on reference-type-high-yield-type protein concentration range comparison, comprising the following steps:

[0033] First step: First, under the condition of thermodynamics (when B value is a non-negative number, B value is the minimum thermodynamic driving force of all reactions), the optimal growth rate in the cell is determined by solving a set of equations. The equation set includes steady-state mass balance constraints, upper and lower limits of reaction flux constraints, thermodynamic driving force constraints, enzyme distribution constraints, and relationships between enzyme concentration and catalytic rate;

[0034] Second step: On the basis of fixing the optimal growth rate, the optimal thermodynamic minimum driving force in the reference type is further solved. This is achieved by solving the equation set again, which includes all the constraints mentioned above.

[0035] Third step: After fixing the optimal thermodynamic driving force obtained above, the maximum growth rate under the condition of the reference type is calculated. On this basis, the minimum total enzyme concentration required to achieve the maximum growth rate is further determined.

[0036] Fourth step: After fixing the above conditions, the maximum and minimum concentration ranges of each enzyme under the reference type state are solved to determine its concentration range.

[0037] Step 5: Calculate the product production rate of overexpression type and set constraints on production rate, using the same method as the reference type, determine the maximum product production rate, the minimum total enzyme concentration and the enzyme concentration range under the condition of overexpression. In the overexpression type, ensure the product generation while maintaining the minimum growth rate of the cell.

[0038] Step 6: By comparing the enzyme concentration range under the condition of reference type and overexpression type, identify the key enzyme target that needs to be up-regulated or down-regulated; determine the up-regulation target for the enzyme based on the maximum value of the enzyme concentration of the enzyme in the reference type state is less than the minimum value of the enzyme concentration of the enzyme in the overexpression type state, determine the down-regulation target for the enzyme based on the minimum value of the enzyme concentration of the enzyme in the reference type state is greater than the maximum value of the enzyme concentration of the enzyme in the overexpression type state.

[0039] More specifically, the algorithm is as follows:

[0040] 1. Enzyme concentration distribution under wild type

[0041] Solving the enzyme concentration distribution under wild type is divided into 5 steps, corresponding to the first step in actual example 1, the best growth rate when B value is 0 under thermodynamic state is solved out, the best growth rate in solving model can be determined by solving the following equation group:

[0042] Maximize v biomass

[0043] Subject to

[0044]

[0045] Where S represents the measurement matrix of the model, v represents the flux value of each reaction in the metabolic network, equations (1) (2) describe the steady-state material balance constraint, LB and UB are the upper and lower bounds of the reaction flux, respectively, equation (3) represents the thermodynamic driving force of reaction J T in the set is also equal to the opposite number of Gibbs free energy, where s i,j represents the transpose of the jth reaction vector, g0 j is the standard Gibbs free energy of reaction j, R is the gas constant (8.3145 J / mol / K), T is the default temperature (298 K), x i,j is the logarithmic concentration of metabolite i in reaction j. Equations (4) and (5) represent the thermodynamic constraints imposed on the pathways involved in the reaction, where B represents J TThe minimum value of the thermodynamic driving force in all reactions within the set, which is a non-negative number, K is a constant value, and a sufficiently large value is used to ensure that the reactions not involved in the pathway can escape the thermodynamic constraint; since the thermodynamic constraint should only apply to the reactions involved in the pathway, it is necessary to distinguish between the involved and non-involved reactions by using integer variables (binary variables), if a certain reaction is not involved, z j = 0, and v j = 0. Equation (6) e0 p (mmol / gDW) represents the sum of the enzyme concentrations of multiple enzyme-catalyzed reactions, e j (mmol / gDW) represents the enzyme cost of reaction j; where j belongs to the set of reactions catalyzed by enzyme p; Equation (7) where Kcat j (1 / h) represents the enzyme catalytic constant of reaction j; Equation (7) defines the maximum flux of reaction j, which is determined by the enzyme catalytic constant of reaction j and the enzyme concentration allocated to reaction j; Equation (8) where MW j (g / mmol) is the molecular mass of enzyme j, and Epool represents the mass fraction of enzymes in dry cells (g protein / g cell dry weight) considered in the calculation. Therefore, under such constraints, the optimal growth rate v biomass ,max .

[0046] Corresponding to the second step in Example 1, the optimal growth rate of the cell is fixed to obtain the optimal thermodynamic minimum driving force B1 of the wild type, and the solution of B1 is determined by solving the following equation set:

[0047] Maximum B1

[0048] Subject to constraints (1) (2) (3) (4) (5) (6) (7) (8).

[0049] The task of the third step is to fix the optimal thermodynamic driving force B1 obtained by solving, and to correspond to the third step in Example 1 to obtain the maximum growth rate of the cell, and the final maximum growth of the cell under the wild type state is obtained by solving the constraints in the first step, since the total enzyme concentration in the cell is not utilized when the maximum production is reached in the cell, we need to calculate the minimum total enzyme concentration totalE required to reach the maximum growth under the wild type state, and the target value of this step is assigned to totalE1_min, and the solution of totalE is determined by solving the following equation set:

[0050] Minimum totalE

[0051] Subject to constraints (1) to (8)

[0052]

[0053] v biomass = v biomass_max (10)

[0054] After the minimum total enzyme concentration totalE1_min is determined by the above equation set, finally, the optimal thermodynamic minimum driving force B1, the maximum growth rate of the cell v0 biomass and the minimum total enzyme concentration totalE1_min are fixed to solve the distribution range of each enzyme in the wild type state, and the maximum and minimum values of each enzyme concentration are solved to determine their ranges, which are determined by solving the following equations:

[0055] Minimum / Maximum e0 k

[0056] subject to constraints (1) to (10)

[0057] totalE = totalE1_min (11).

[0058] 2. The enzyme concentration distribution of overexpression type

[0059] Solving the enzyme concentration distribution in the wild type state is similar to solving the enzyme concentration distribution in the wild type state. Corresponding to the fifth step in Example 1, the first step is to solve the maximum production rate when the B value is 0 in the thermodynamic state. The maximum production rate in the model can be determined by solving the following equation set:

[0060] Maximum v1product

[0061] subject to constraints (1) to (8)

[0062]

[0063] In order to make the cell grow normally, v0 biomass_max is multiplied by a factor f bio (0.1), where the optimal growth rate of the cell is v biomass,max , so under such constraints, the maximum production rate of the product v1 product is obtained when the thermodynamic minimum driving force is the minimum value, that is, 0. Next, the obtained maximum production rate is fixed to solve the optimal thermodynamic minimum driving force B2 in the overexpression state. The solution of B2 is determined by solving the following equation set:

[0064] Maximum B2

[0065] subject to constraints (1) (2) (3) (4) (5) (6) (7) (8).

[0066] The next task is to fix the optimal thermodynamic driving force B2 obtained by solving, to solve the maximum production rate of the product, and the final maximum production rate of the product in the overexpression state is obtained by solving the constraint condition in the fourth step. Since the total enzyme concentration in the cell is not utilized at the maximum production rate of the product, we need to calculate the minimum total enzyme concentration totalE2 required to reach the maximum production rate of the product in the overexpression state, and assign the target value of this step to totalE2_min. The solution of totalE2 is determined by solving the following equation set:

[0067] Min totalE2

[0068] Subject to constraints (1) to (8) and (12)

[0069]

[0070] After determining the minimum total enzyme concentration totalE2_min by the above equation set, finally, fix the optimal thermodynamic minimum driving force B2, the maximum production rate of the product v1 product and the minimum total enzyme concentration totalE2_min to solve the distribution range of each enzyme in the overexpression state, respectively, to solve the maximum and minimum values of each enzyme to determine their range, which is determined by solving the following equation:

[0071] Min / Max e0 k

[0072] Subject to constraints (1) to (8), (12) and (13)

[0073] totalE = totalE2_min (14).

[0074] Finally, by comparing the enzyme concentration distribution of each enzyme in the wild type state and the overexpression state obtained by solving, the maximum value of the enzyme concentration of the enzyme in the reference type state is less than the minimum value of the enzyme concentration of the enzyme in the overexpression state. As the basis for determining the up-regulation target point for the enzyme, the minimum value of the enzyme concentration of the enzyme in the reference type state is greater than the maximum value of the enzyme concentration of the enzyme in the overexpression state. As the basis for determining the down-regulation target point for the enzyme; find the target points that need to be up-regulated or down-regulated and compare and analyze them with the target points that need to be regulated for the product in experiments. Corresponding to the sixth step in the actual example.

[0075] Application example:

[0076] Apply the algorithm (ET-OptForce Must) The specific operation for predicting the production of lysine by Corynebacterium glutamicum is inputting Corynebacterium glutamicum strain, lysine product and glucose substrate, and obtaining the adjusted metabolic strategy with maximum yield through the calculation process of the application. Table 1 is ET-OptForce Must The target points that have been experimentally verified in the strategy predicted by the algorithm for the production of lysine by Corynebacterium glutamicum, wherein the experimentally verified target points are found by referring to the published experimental literature related to the production of lysine by Corynebacterium glutamicum to find effective modification targets.

[0077] Table 1 ET-OptForce Must Correctly modified target points for the production of lysine predicted by the algorithm

[0078]

[0079] More effective target points are found through the metabolic engineering strategy algorithm of the application.

Claims

1. A method for predicting metabolic engineering targets based on a comparison of reference-high-yield protein concentration ranges, comprising the following steps: Step 1: Under thermodynamic constraints, i.e., the minimum thermodynamic driving force B for all reactions is a predetermined non-negative number, the optimal growth rate in the cell is determined by solving a set of equations. This set of equations includes steady-state mass balance constraints, upper and lower limits of reaction flux constraints, thermodynamic driving force constraints, enzyme distribution constraints, and the relationship between enzyme concentration and catalytic rate. The second step is to further solve for the optimal thermodynamic minimum driving force in the reference model, based on the fixed optimal growth rate. This is achieved by solving the system of equations again, which includes all the previous constraints. Step 3: After fixing the optimal thermodynamic minimum driving force obtained above, calculate the maximum growth rate under reference conditions; based on this, further determine the minimum total enzyme concentration required to achieve the maximum growth rate; Step 4: After fixing the optimal thermodynamic minimum driving force, maximum growth rate and minimum total enzyme concentration, solve for the maximum and minimum values ​​of each enzyme under the reference state to determine its concentration range; Step 5: Calculate the production rate of the overexpressed product and set constraints on the production rate. Using the same method as the reference, determine the maximum product production rate, minimum total enzyme concentration, and enzyme concentration range under the overexpression conditions. In the overexpression, ensure that the minimum specific growth rate of cells is maintained while the product is generated. Step 6: By comparing the enzyme concentration ranges under reference and overexpression conditions, identify key enzyme targets that need to be upregulated or downregulated; determine upregulation targets based on the maximum enzyme concentration in the reference state being less than the minimum enzyme concentration in the overexpression state, and determine downregulation targets based on the minimum enzyme concentration in the reference state being greater than the maximum enzyme concentration in the overexpression state. in, The protein-centric enzyme thermal constraint algorithm used in steps one and two is as follows: Where S represents the metric matrix of the model, v represents the flux value of each reaction in the metabolic network, equations (1) and (2) describe the steady-state material balance constraints, LB and UB are the upper and lower bounds of the reaction flux, respectively, and equation (3) represents the reaction J in the set. T The thermodynamic driving force is also equal to the negative of the Gibbs free energy, g0 j Here, R is the standard Gibbs free energy of reaction j, R is the gas constant (8.3145 J / mol / K), T is the default temperature (298 K), and x is the standard Gibbs free energy of reaction j. i,j It is the logarithmic concentration of metabolite i in reaction j; Equations (4) and (5) represent applying thermodynamic constraints to the pathways involved in the reaction, where B is J. T The minimum thermodynamic driving force among all reactions within the set, where K is a constant, is used to ensure that reactions not on the path can escape thermodynamic constraints. Since thermodynamic constraints should only apply to reactions participating in the path, a binary variable is needed to distinguish between participating and non-participating reactions. If a reaction does not participate, then z... j =0, and v j =0; In equation (6), e0 p This represents the sum of enzyme concentrations distributed across multiple reactions catalyzed by an enzyme, expressed in mmol / g DW; e j This represents the enzyme cost allocated to reaction j, in units of mmol / gDW; where j belongs to the set of reactions catalyzed by enzyme p. Equation (7) where Kcat j The enzyme catalytic constant of reaction j is expressed in units of 1 / h; Equation (7) defines that the maximum flux of reaction j is determined by the enzyme catalytic constant of reaction j and the enzyme concentration allocated to reaction j; in Equation (8), MW p is the molecular weight of enzyme p, expressed in g / mmol; Epool represents the mass fraction of the enzyme considered in the calculation within the stem cells, expressed in g protein / g cell dry weight; the target value for this optimization is v. biomass,max .

2. The method for predicting metabolic engineering targets based on a comparison of reference-high-yield protein concentration ranges as described in claim 1, characterized in that, The third step also includes solving for the maximum thermodynamic driving force B1 under constraints; the constraints of the algorithm are: Maximum value B1 Make it subject to the constraints of (1)(2)(3)(4)(5)(6)(7)(8).

3. The method for predicting metabolic engineering targets based on a comparison of reference-high-yield protein concentration ranges as described in claim 2, characterized in that, The third step also includes solving for the minimum total enzyme concentration totalE under constraints. The objective value of this step is assigned to the constraints of the algorithm used in totalE1_min. Minimum value totalE Make it subject to constraints (1) to (8). v biomass =v biomass_max (10)。 4. The method for predicting metabolic engineering targets based on a comparison of reference-high-yield protein concentration ranges as described in claim 3, characterized in that, The fourth step is to calculate the maximum and minimum values ​​of each enzyme under the reference state to determine its concentration range. The specific process is as follows: Minimum / Maximum value e0 k Make it subject to constraints (1) to (10). totalE = totalE1_min (11).

5. The method for predicting metabolic engineering targets based on a comparison of reference-high-yield protein concentration ranges as described in claim 2, characterized in that, The fifth step, determining the maximum product production rate, minimum total enzyme concentration, and enzyme concentration range under overexpression conditions, involves the following steps: Maximum value v1 product Make it subject to constraints (1) to (8). Minimum value totalE Make them subject to constraints (1) through (8) and (12). openE=∑ p∈P E0 p MW p (13) Minimum / Maximum value e0 k Make them subject to constraints (1) through (8), (12) and (13). totalE=totalE2_min (14) f bio The value is 0.1, and totalE2_min is the minimum total enzyme concentration.

6. A system for predicting protein-centric range-based targets using enzyme-thermal constraints, characterized in that, It includes the following modules: a data acquisition module, used to input the required data into the system: The data processing module is used to perform the calculation steps as described in any one of claims 1 to 5; The results output module is used to output the prediction results.

7. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being configured to perform the method of any one of claims 1 to 5 or to perform the system of claim 6.

8. A bioinformatics tool system based on the system described in claim 6, comprising: a. User interface that allows users to input relevant information; b. The system as described in claim 6 performs the prediction; d. Results display module, used to show the prediction results to users.

9. The bioinformatics tool system as described in claim 8, characterized in that, Also includes: e. Report generator, used to create results.

Images