Search

EP-4738373-A1 - DRUG EFFICACY PREDICITNG PROGRAM, METHOD FOR PREDICTING DRUG EFFICACY, AND DRUG EFFICACY PREDICTING DEVICE

EP4738373A1EP 4738373 A1EP4738373 A1EP 4738373A1EP-4738373-A1

Abstract

A drug efficacy predicting program for causing a computer to execute a process including: predicting, by using a first machine learning model, a difference in drug efficacy between one or more of two data combinations under a same experimental system, each of the two data combinations including at least one common item among items of a drug and a cell line; and predicting, by using a second machine learning model, one or more drug efficacy of each of two or more data using the predicted difference.

Inventors

  • MURAKAMI, KATSUHIKO

Assignees

  • FUJITSU LIMITED

Dates

Publication Date
20260506
Application Date
20251031

Claims (9)

  1. A drug efficacy predicting program for causing a computer (10) to execute a process comprising: predicting, by using a first machine learning model (4), a difference in drug efficacy between one or more of two data combinations under a same experimental system, each of the two data combinations including at least one common item among items of a drug and a cell line; and predicting, by using a second machine learning model (7), one or more drug efficacies of two or more data using the predicted difference.
  2. The drug efficacy predicting program according to claim 1, wherein the first machine learning model (4) is trained, using feature vectors of each of the two data combinations as an explanatory variable and using a difference in measured value of the drug efficacy between the two data combinations as a response variable.
  3. The drug efficacy predicting program according to claim 2, wherein the second machine learning model (7) is trained, using the difference in the measured value of the drug efficacy and the feature vectors of each of the two or more data combinations as explanatory variables and using the measured value of the drug efficacy as a response variable.
  4. A computer-implemented method for predicting drug efficacy comprising: predicting, by using a first machine learning model (4), a difference in drug efficacy between one or more of two data combinations under a same experimental system, each of the two data combinations including at least one common item among items of a drug and a cell line; and predicting, by using a second machine learning model (7), one or more drug efficacies of two or more data using the predicted difference.
  5. The computer-implemented method according to claim 4, wherein the first machine learning model (4) is trained, using feature vectors of each of the two data combinations as an explanatory variable, and using a difference in measured value of drug efficacy between the two data combinations as a response variable.
  6. The computer-implemented method according to claim 5, wherein the second machine learning model (7) is trained, using the difference in the measured value of the drug efficacy and the feature vectors of each of the two or more data combinations as explanatory variables and using the measured value of the drug efficacy as a response variable.
  7. A drug efficacy predicting device comprising a controller configured to: predict, by using a first machine learning model (4), a difference in drug efficacy between one or more of two data combinations under a same experimental system, each of the two data combinations including at least one common item among items of a drug and a cell line; and predict, by using a second machine learning model (7), one or more drug efficacies of two or more data using the predicted difference.
  8. The drug efficacy predicting device according to claim 7, wherein the first machine learning model (4) is trained, using feature vectors of each of the two data combinations as an explanatory variable, and using a difference in measured value of drug efficacy between the two data combinations as a response variable.
  9. The drug efficacy predicting device according to claim 8 wherein the second machine learning model (7) is trained, using the difference in the measured value of the drug efficacy and the feature vectors of each of the two or more data combinations as explanatory variables and using the measured value of the drug efficacy as a response variable.

Description

[Technical Field] The embodiments discussed herein are related to a drug efficacy predicting program, a method for predicting drug efficacy, and a drug efficacy predicting device. [Background Art] For example, the field of genome drug discovery has demanded an efficiently search for which compounds (new drug candidates) are likely to be effective to which type of cancer. As a numeric value representing a degree of drug efficacy of a drug to a certain cell line, IC50 value has been used. For example, in drug discovery for a particular cancer type, an IC50 has been used to select drug candidates (compounds). An IC50 is used as a numeric value representing drug efficacy. Since it is very difficult to measure IC50s under all conditions, features were learned from measured data (a set of IC50 values and features) and the IC50 under an unknown condition was inferred. In addition, a study has been known which applies deep learning (DL) to predict drug efficacy. For example, data of different experimental systems using, for example, different solvents are not considered to be directly comparable because it is difficult to adjust their values. Accordingly, drug efficacy needs to be examined for each individual experimental system. Specifically, a particular experimental system is fixed as a condition, and a machine learning model is prepared for each individual experimental system. Using the machine learning model, drug efficacy is inferred. As an example of features (explanatory variables), expression level (over 10,000 variables) of genes is used for a certain cell line. In addition, the chemical structure of a drug is used as a feature. The prediction of the drug efficacy is treated as a regression problem, using numeric IC50 values as target values in the training data. [Prior Art Reference] [Non-Patent Document] [Patent Document 1] Japanese Laid-open Patent Publication No. 2021-144619[Patent Document 2] Japanese Laid-open Patent Publication No. 2021-39565[Patent Document 3] US Patent Application Publication No. 2011/0173144[Patent Document 4] Japanese Laid-open Patent Publication No.2019-125045[Patent Document 5] US Patent Application Publication No. 2020/0175380 [Summary of Invention] [Problems to be Solved by Invention] However, since such a conventional method for predicting drug efficacy is unable to directly compare drug efficacy (IC50s) of the different experimental systems, data of the different experimental systems cannot be collectively learned in the same machine learning model. Accordingly, the conventional method makes use only part of the data for prediction of drug efficacy and therefore has difficulty in accurately predicting the drug efficacy. Normally, the same experimental system is used in the same project, but different experimental systems are used between different projects. Since it has not been normally assumed that data are compared across projects, the experimental systems are selected on a case-by-case basis and therefore different projects use respective different experimental systems. Ideally, if the above main conditions are the same, it is expected that IC50s representing drug efficacy are approximately the same under different experimental systems. However, the actual IC50 values considerably deviate from one another, so that it has been considered that the IC50 values of different experimental systems are not directly compared. Therefore, it has been difficult to collectively treat the IC50 values of different experimental systems. Accordingly, it is desirable to accurately predict drug efficacy. [Means to Solve the Problem] According to an aspect of the embodiments, a drug efficacy predicting program causes a computer to execute a process including: predicting, using a first machine learning model, a difference in drug efficacy between one or more of two data combinations under a same experimental system, wherein input explanatory variables are jointly formed by feature vectors of the two data combinations, each of the two data combination including at least one common item among items of a drug and a cell line; and predicting, by using a second machine learning model, one or more drug efficacies of two or more data using the predicted difference. [Effect of Invention] Prediction of drug efficacy can be performed accurately. [Brief Description of Drawings] The invention is described, by way of example only, with reference to the following drawings, in which: FIG. 1 is a diagram illustrating an example of a functional configuration of a drug efficacy predicting device according to one embodiment;FIG. 2 is a block diagram illustrating an example of a hardware (HW) configuration of a computer that achieves the functions of the drug efficacy predicting device according to the embodiment;FIG. 3 is a diagram illustrating a first data set of the drug efficacy predicting device according to the embodiment;FIG. 4 is a diagram illustrating a second data set of the drug efficacy predictin