Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery

Ravi Salgia; Mohit Kumar Jolly; Prakash Kulkarni; Govindan Rangarajan; Maria Jose Peláez; Shreya Goel; Vittorio Cristini; Zhihui Wang; Prashant Dogra

doi:10.1093/med/9780192867636.003.0034

Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery

Ravi Salgia, Mohit Kumar Jolly, Prakash Kulkarni, Govindan Rangarajan, Maria Jose Peláez, Shreya Goel, Vittorio Cristini, Zhihui Wang, Prashant Dogra

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

The physicochemical properties of nanoparticles (NPs), designed for tumour-targeted drug delivery, play a key role in governing the systemic pharmacokinetics, safety, and tumour delivery efficiency of NPs. It is critical to understand the structure–activity relationship (SAR) of NPs to optimize their in vivo behaviour for improved cancer nanomedicine outcomes. Due to the complex and multiscale nature of the NP-mediated drug delivery process, it is challenging to investigate the SAR of NPs solely through experimental means. Integration with mathematical modelling and machine learning allows to explore the multidimensional parameter space of NP design with greater efficiency. In this chapter, we discuss the challenges associated with tumour-targeted delivery of NPs and explore the key modelling methods employed to study NP SAR, pertinent to their systemic pharmacokinetics, safety, and tumour delivery efficiency.

Original language	Undefined/Unknown
Title of host publication	Cancer Systems Biology: Translational Mathematical Oncology
Publisher	Oxford University Press
Chapter	34
Pages	347-356
ISBN (Print)	9780192867636
DOIs	https://doi.org/10.1093/med/9780192867636.003.0034
State	Published - Sep 1 2025

Divisions

Medical Oncology

Access to Document

10.1093/med/9780192867636.003.0034

https://doi.org/10.1093/med/9780192867636.003.0034

Cite this

Salgia, R., Jolly, M. K., Kulkarni, P., Rangarajan, G., Peláez, M. J., Goel, S., Cristini, V., Wang, Z., & Dogra, P. (2025). Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery. In Cancer Systems Biology: Translational Mathematical Oncology (pp. 347-356). Oxford University Press. https://doi.org/10.1093/med/9780192867636.003.0034

Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery. / Salgia, Ravi; Jolly, Mohit Kumar; Kulkarni, Prakash et al.
Cancer Systems Biology: Translational Mathematical Oncology. Oxford University Press, 2025. p. 347-356.

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Salgia, R, Jolly, MK, Kulkarni, P, Rangarajan, G, Peláez, MJ, Goel, S, Cristini, V , Wang, Z & Dogra, P 2025, Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery. in Cancer Systems Biology: Translational Mathematical Oncology. Oxford University Press, pp. 347-356. https://doi.org/10.1093/med/9780192867636.003.0034

@inbook{5b61b7db450b411a8e64a961fa4d2ce5,

title = "Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery",

abstract = "The physicochemical properties of nanoparticles (NPs), designed for tumour-targeted drug delivery, play a key role in governing the systemic pharmacokinetics, safety, and tumour delivery efficiency of NPs. It is critical to understand the structure–activity relationship (SAR) of NPs to optimize their in vivo behaviour for improved cancer nanomedicine outcomes. Due to the complex and multiscale nature of the NP-mediated drug delivery process, it is challenging to investigate the SAR of NPs solely through experimental means. Integration with mathematical modelling and machine learning allows to explore the multidimensional parameter space of NP design with greater efficiency. In this chapter, we discuss the challenges associated with tumour-targeted delivery of NPs and explore the key modelling methods employed to study NP SAR, pertinent to their systemic pharmacokinetics, safety, and tumour delivery efficiency.",

author = "Ravi Salgia and Jolly, \{Mohit Kumar\} and Prakash Kulkarni and Govindan Rangarajan and Pel{\'a}ez, \{Maria Jose\} and Shreya Goel and Vittorio Cristini and Zhihui Wang and Prashant Dogra",

year = "2025",

month = sep,

day = "1",

doi = "10.1093/med/9780192867636.003.0034",

language = "Undefined/Unknown",

isbn = "9780192867636",

pages = "347--356",

booktitle = "Cancer Systems Biology: Translational Mathematical Oncology",

publisher = "Oxford University Press",

address = "United Kingdom",

}

TY - CHAP

T1 - Mechanistic modelling and machine learning to establish structure–activity relationship of nanomaterials for improved tumour delivery

AU - Salgia, Ravi

AU - Jolly, Mohit Kumar

AU - Kulkarni, Prakash

AU - Rangarajan, Govindan

AU - Peláez, Maria Jose

AU - Goel, Shreya

AU - Cristini, Vittorio

AU - Wang, Zhihui

AU - Dogra, Prashant

PY - 2025/9/1

Y1 - 2025/9/1

N2 - The physicochemical properties of nanoparticles (NPs), designed for tumour-targeted drug delivery, play a key role in governing the systemic pharmacokinetics, safety, and tumour delivery efficiency of NPs. It is critical to understand the structure–activity relationship (SAR) of NPs to optimize their in vivo behaviour for improved cancer nanomedicine outcomes. Due to the complex and multiscale nature of the NP-mediated drug delivery process, it is challenging to investigate the SAR of NPs solely through experimental means. Integration with mathematical modelling and machine learning allows to explore the multidimensional parameter space of NP design with greater efficiency. In this chapter, we discuss the challenges associated with tumour-targeted delivery of NPs and explore the key modelling methods employed to study NP SAR, pertinent to their systemic pharmacokinetics, safety, and tumour delivery efficiency.

AB - The physicochemical properties of nanoparticles (NPs), designed for tumour-targeted drug delivery, play a key role in governing the systemic pharmacokinetics, safety, and tumour delivery efficiency of NPs. It is critical to understand the structure–activity relationship (SAR) of NPs to optimize their in vivo behaviour for improved cancer nanomedicine outcomes. Due to the complex and multiscale nature of the NP-mediated drug delivery process, it is challenging to investigate the SAR of NPs solely through experimental means. Integration with mathematical modelling and machine learning allows to explore the multidimensional parameter space of NP design with greater efficiency. In this chapter, we discuss the challenges associated with tumour-targeted delivery of NPs and explore the key modelling methods employed to study NP SAR, pertinent to their systemic pharmacokinetics, safety, and tumour delivery efficiency.

U2 - 10.1093/med/9780192867636.003.0034

DO - 10.1093/med/9780192867636.003.0034

M3 - Chapter

SN - 9780192867636

SP - 347

EP - 356

BT - Cancer Systems Biology: Translational Mathematical Oncology

PB - Oxford University Press

ER -