Method and System for Predicting Spatial and Temporal Distributions of Therapeutic Substance Carriers

• US 20150036889A1
• Filed: 08/01/2014
• Published: 02/05/2015
• Est. Priority Date: 08/02/2013
• Status: Active Grant

• Current Assignee: Crixlabs, Inc.
• Original Assignee: Crixlabs, Inc.
• Inventors: Ananda Yogendran, Shalini
• Granted Patent: US 9,153,024 B2
• Time in Patent Office: Days
• US Class Current: 382/107
• CPC Class Codes: A61B 5/4848 Monitoring or testing the effects of treatment, e.g. of medication
• CPC Class Codes: G01N 2500/00 Screening for compounds of potential therapeutic value
• CPC Class Codes: G01N 2800/52 Predicting or monitoring the response to treatment, e.g. for selection of therapy based on assay results in personalised medicine; Prognosis
• CPC Class Codes: G06T 2207/10061 from scanning electron microscope
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30104 Vascular flow; Blood flow; Perfusion
• CPC Class Codes: G06T 7/0016 involving temporal comparison
• CPC Class Codes: G16C 20/50 Molecular design, e.g. of drugs

Abstract

A method and system for predicting spatial and temporal distributions of therapeutic substance carriers within a body of a user, comprising: at a computing system, receiving an image dataset and a spectra dataset of a therapeutic substance carrier generated from at least one of an imaging model and a spectra-generating module; transforming the image dataset and the spectra dataset into a set of characteristics, wherein the set of characteristics comprises electrotopological characteristics and geometrical characteristics; generating a set of pharmacokinetic parameters and a set of pharmacodynamic parameters for the therapeutic substance carrier based upon the set of characteristics and a transformation model; and transforming the set of pharmacokinetic parameters and the set of pharmacodynamic parameters into a spatial distribution and a temporal profile of the therapeutic substance carrier, based upon a predictive model incorporating physiological parameters of the body, thereby predicting distributions of the therapeutic substance carrier within the body.

Claims

1. A method for predicting spatial and temporal distributions of therapeutic substance carriers within a body, comprising:

at a computing system, receiving an image dataset and a spectra dataset of a drug carrier;

at the computing system, transforming the image dataset and the spectra dataset into a set of characteristics, wherein the set of characteristics comprises electrotopological characteristics, connectivity characteristics, molecular characteristics, and geometrical characteristics;

generating a set of descriptors based upon the set of characteristics and a set of encoding functions;

at the computing system, transforming the set of descriptors into a set of pharmacokinetic parameters and a set of pharmacodynamic parameters for the therapeutic substance carrier based upon a transformation model;

at the computing system, transforming the set of pharmacokinetic parameters and the set of pharmacodynamic parameters into a spatial distribution and a temporal profile of the therapeutic substance carrier based upon a predictive model; and

mapping the spatial distribution and the temporal profile onto at least a portion of an organ system of the user, thereby characterizing at least one of a concentration of the therapeutic substance carrier and a concentration of a therapeutic substance carried by the drug carrier in the organ system within a time window.

2. The method of claim 1, wherein receiving the image dataset and the spectra dataset comprises receiving the electron microscopy data from an electron microscopy module and receiving spectra data from at least one of an FTIR spectroscopy module, an NMR spectroscopy module, and an MS module.

3. The method of claim 1, wherein transforming the image dataset and the spectra dataset into the set of characteristics comprises generating electrotopological characteristics derived from molecular electrotopological state values of the therapeutic substance carrier, connectivity characteristics comprising chi indices of the therapeutic substance carrier, characteristics of molecular groups of the therapeutic substance carrier, and displacement moments along an inertial axis for the therapeutic substance carrier.

4. The method of claim 3, wherein transforming the image dataset and the spectra dataset into the set of characteristics comprises at least one of improving edge fidelity of an object captured within the image dataset and estimating motion behavior of a portion of the object captured within the image dataset.

5. The method of claim 1, wherein generating the set of descriptors based upon the set of characteristics and the set of encoding functions comprises processing the set of characteristics using at least one of a 2D autocorrelation function, a 3D autocorrelation function, and a radial distribution function.

6. The method of claim 1, wherein transforming the set of descriptors into the set of pharmacokinetic parameters and the set of pharmacodynamic parameters for the therapeutic substance carrier comprises generating values of a volume of distribution of a dose of the therapeutic substance, an unbound volume of distribution of the dose, a clearance of the therapeutic substance carrier from the body, and a half-life of the therapeutic substance carrier based upon the transformation model.

7. The method of claim 1, wherein mapping the spatial distribution and the temporal profile onto at least a portion of the organ system of the user comprises generating a model of the organ system of the user divided into a set of elements, and attributing an intensity value, corresponding to the concentration of the therapeutic substance carrier, to each of the set of elements based upon the spatial distribution and the temporal profile of the drug carrier.

8. A method for predicting spatial and temporal distributions of therapeutic substance carriers within a body of a user, comprising:

at a computing system, receiving an image dataset and a spectra dataset of a therapeutic substance carrier generated from at least one of an imaging module and a spectra-generating module;

at the computing system, transforming the image dataset and the spectra dataset into a set of characteristics, wherein the set of characteristics comprises electrotopological characteristics and geometrical characteristics;

at the computing system, generating a set of pharmacokinetic parameters and a set of pharmacodynamic parameters for the therapeutic substance carrier based upon the set of characteristics and a transformation model; and

at the computing system, transforming the set of pharmacokinetic parameters and the set of pharmacodynamic parameters into a spatial distribution and a temporal profile of the therapeutic substance carrier, based upon a predictive model incorporating physiological parameters of the body, thereby predicting distributions of the therapeutic substance carrier within the body.

9. The method of claim 8, wherein receiving the image dataset and the spectra dataset comprises receiving the electron microscopy data from an electron microscopy module and receiving spectra data from at least one of an FTIR spectroscopy module, an NMR spectroscopy module, and an mass spectroscopy module.

10. The method of claim 8, wherein transforming the image dataset and the spectra dataset into a set of characteristics further comprises generating connectivity characteristics and molecular characteristics of the therapeutic substance carrier.

11. The method of claim 10, wherein transforming the image dataset and the spectra dataset into the set of characteristics comprises generating electrotopological characteristics derived from molecular electrotopological state values of the therapeutic substance carrier, connectivity characteristics comprising chi indices of the therapeutic substance carrier, characteristics of molecular groups of the therapeutic substance carrier, and displacement moments along an inertial axis for the therapeutic substance carrier.

12. The method of claim 8, wherein generating the set of pharmacokinetic parameters and the set of pharmacodynamic parameters comprises generating a set of descriptors based upon processing the set of characteristics with a set encoding functions comprising at least one of a 2D autocorrelation function, a 3D autocorrelation function, and a radial distribution function.

13. The method of claim 12, wherein generating the set of descriptors comprises generating scalar descriptors comprising at least one of molecular weight, number of hydrogen bonding acceptors, topological polar surface area, and total charge of the therapeutic substance carrier.

14. The method of claim 12, further comprising transforming the set of descriptors into the set of pharmacokinetic parameters and the set of pharmacodynamic parameters, wherein transforming comprises generating values of a volume of distribution of a dose of the therapeutic substance, an unbound volume of distribution of the dose, a clearance of the therapeutic substance carrier from the body, and a half-life of the therapeutic substance carrier based upon the transformation model.

15. The method of claim 8, wherein transforming the set of pharmacokinetic parameters and the set of pharmacodynamic parameters into the temporal profile of the therapeutic substance carrier comprises processing the set of pharmacokinetic parameters and the set of pharmacodynamic parameters with a probabilistic model that determines an amount of the therapeutic substance carrier within a time window.

16. The method of claim 8, further comprising mapping the spatial distribution and the temporal profile onto an organ system of the user and generating a rendering of the mapping, thereby characterizing at least one of a concentration of the therapeutic substance carrier and a concentration of a therapeutic substance carried by the therapeutic substance carrier in the organ system within a time window.

17. The method of claim 8, further comprising training the transformation model based upon boosting and bootstrapped aggregation using training data characterizing at least one of drug carriers, drugs, and nanoparticles.

19. A method for predicting distributions of therapeutic substance carriers within a body, comprising:

at a computing system, receiving a dataset of a therapeutic substance carrier generated from at least one of an imaging module and a spectra-generating module;

at the computing system, transforming the dataset into a set of characteristics, wherein the set of characteristics comprises at least one of electrotopological characteristics and geometrical characteristics;

at the computing system, generating a set of parameters for the therapeutic substance carrier based upon the set of characteristics and a transformation model; and

at the computing system, transforming the set of parameters into a spatial distribution and a temporal profile of the therapeutic substance carrier based upon a predictive module incorporating physiological parameters of the body, thereby predicting distributions of the therapeutic substance carrier within the body.

18. The method of claim 19, wherein mapping the spatial distribution and the temporal profile onto at least a portion of the organ system of the user comprises generating a model of the organ system of the user divided into a set of elements, and attributing an intensity value, corresponding to the concentration of the therapeutic substance carrier, to each of the set of elements based upon the spatial distribution and the temporal profile of the drug carrier.

20. The method of claim 19, wherein transforming the dataset into the set of characteristics comprises generating electrotopological characteristics derived from molecular electrotopological state values of the therapeutic substance carrier, connectivity characteristics comprising chi indices of the therapeutic substance carrier, characteristics of molecular groups of the therapeutic substance carrier, and displacement moments along an inertial axis for the therapeutic substance carrier.