Method of predicting chromatographic elution order of compounds

Patent metadata

Field	Value
Publication number	US-2020394513-A1
Application number	US-202016740243-A
Country	US
Kind code	A1
Filing date	Jan 10, 2020
Priority date	Jun 13, 2019
Publication date	Dec 17, 2020
Grant date	—

Abstract

Disclosed is a method for predicting an elution order of compounds in a mixture. The method includes (a) building a quantitative structure-retention relationship (QSRR) model and (b) predicting a chromatographic elution order of the compounds in the mixture on the basis of the QSRR model using mathematical programming. The mathematical programming is a non-linear programming technique in which a predicted elution order of the compounds is used as a constraint or a multi-objective optimization (MOO) in which a retention time prediction error and an elution order prediction error are used as objective functions. With the use of the method of the present disclosure, it is possible to optimize separation of complex mixtures in reversed-phase chromatography by enabling identification of accurate positions of individual compounds that provides higher certainty in identifying a given compound, e.g., during an “omics” analysis (proteomics, metabolomics, etc.).

First claim

What is claimed is:

1 . A method of predicting a chromatographic elution order of compounds in a mixture, the method comprising:
(a) modeling a quantitative structure-retention relationship (QSRR) model; and (b) predicting a chromatographic elution order of the compounds in the mixture from the QSRR model using mathematical programming, wherein the mathematical programming is (i) a non-linear programming technique using a predicted elution order of the compounds as a constraint or (ii) a multi-objective optimization (MOO) technique using a retention time prediction error and an elution order prediction error as objective functions.

2 . The method according to claim 1 , wherein the QSRR model obtained through the (a) modeling is a linear model represented by the following formula:
t R,j =a 1 x j,1 +a 2 x j,2 + . . . +a n x j,n where t R,j are retention times of respective compounds j sorted in ascending order, x j,i (i=1, . . . , n) are molecular descriptors of respective compounds j, and a i (i=1, . . . , n) are regression coefficients.

3 . The method according to claim 1 , wherein the QSRR model obtained through the (a) modeling is a non-linear model obtained by using artificial neural networks (ANN).

4 . The method according to claim 1 , wherein on the (b) predicting, the chromatographic elution order of the compounds in the mixture is predicted by applying the following non-linear programming I under the following inequality constraints II:

min

a
_



{

∑

j
=
1

m





(

t

R
,
j

-

a
1



x

j
,
1

-

a
2



x

j
,
2

-

a
3



x

j
,
3

)

2

+

∑

j
=
1

m



α
j

}

(
I
)

a
1



(

x

j
,
1

-

x

j
+
1

,
1

)

+

a
2



(

x

j
,
2

-

x

j
+
1

,
2

)

+

a

Assignees

• Nat Univ Pukyong Ind Univ Coop Found
• Medical Univ Of Gdansk

Inventors

• Liu Jay
• Zuvela Petar
• Baczek Tomasz
• Alipuly Alham

Classifications

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G16C20/70

  Machine learning, data mining or chemometrics · CPC title

• G16C20/30 Primary

  Prediction of properties of chemical compounds, compositions or mixtures · CPC title

• G06N3/004

  Artificial life, i.e. computing arrangements simulating life · CPC title