Discovery of photoactive anti-cancer platinum(II) complexes: synthesis, screening and machine learning approaches

A prevailing issue with current anti-cancer therapeutics is non-specific drug toxicity leading to a range of negative side effects. One way to avoid these off-target effects is through the use of pro-drugs: drugs which are non-toxic until activated by a trigger such as an enzyme, change in pH or light. However, the development of new drugs is a highly laborious process, which takes many years and costs millions of pounds. Recent advances in drug discovery have been accelerated by the use of data driven and machine learning approaches. This thesis presents a case study applying such approaches to the discovery of photoactive complexes as anti-cancer therapeutics. Within this thesis 22 new platinum(II) salphen complexes were synthesised during the development of a high throughput (HT) synthesis and screening pipeline. Platinum(II) salphen complexes were selected for their unique photophysical properties and known binding affinity to alternate DNA secondary structures highly enriched in cancer cells. To determine the potential drug-like properties of the complexes, photoactivity, DNA binding, DNA damage, and cellular activity were screened. As a result, two lead candidates were identified which had good DNA binding affinity and selectivity, cell permeability, and localisation within the nucleus. These complexes were shown to be non-toxic within cancer cells until irradiated, at which point they exhibited IC50 values of 0.29 µM and 2.57 µM. Alongside the experimental work, computational calculations were performed on a larger library of 263 platinum(II) salphen complexes for the application of machine learning (ML) prediction tasks. The objectives of these ML models were to better understand structure activity relationships (SAR) and predict photophysical properties of unseen platinum(II) salphen complexes. Overall, this work has combined data driven experimental and computational approaches for the synthesis, screening and ML analysis of platinum(II) salphen complexes as potential novel photoactive anti-cancer therapeutics.

Institutions

Publication Details

Journal
Imperial College Research Computing Service Data Repository
Published
2025-03-21
DOI
https://doi.org/10.25560/120268
Primary Topic
Cloud Computing and Resource Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Discovery of photoactive anti-cancer platinum(II) complexes: synthesis, screening and machine learning approaches

Imperial College Research Computing Service Data Repository
Cloud Computing and Resource Management
article

Discovery of photoactive anti-cancer platinum(II) complexes: synthesis, screening and machine learning approaches

article en

Abstract

A prevailing issue with current anti-cancer therapeutics is non-specific drug toxicity leading to a range of negative side effects. One way to avoid these off-target effects is through the use of pro-drugs: drugs which are non-toxic until activated by a trigger such as an enzyme, change in pH or light. However, the development of new drugs is a highly laborious process, which takes many years and costs millions of pounds. Recent advances in drug discovery have been accelerated by the use of data driven and machine learning approaches. This thesis presents a case study applying such approaches to the discovery of photoactive complexes as anti-cancer therapeutics. Within this thesis 22 new platinum(II) salphen complexes were synthesised during the development of a high throughput (HT) synthesis and screening pipeline. Platinum(II) salphen complexes were selected for their unique photophysical properties and known binding affinity to alternate DNA secondary structures highly enriched in cancer cells. To determine the potential drug-like properties of the complexes, photoactivity, DNA binding, DNA damage, and cellular activity were screened. As a result, two lead candidates were identified which had good DNA binding affinity and selectivity, cell permeability, and localisation within the nucleus. These complexes were shown to be non-toxic within cancer cells until irradiated, at which point they exhibited IC50 values of 0.29 µM and 2.57 µM. Alongside the experimental work, computational calculations were performed on a larger library of 263 platinum(II) salphen complexes for the application of machine learning (ML) prediction tasks. The objectives of these ML models were to better understand structure activity relationships (SAR) and predict photophysical properties of unseen platinum(II) salphen complexes. Overall, this work has combined data driven experimental and computational approaches for the synthesis, screening and ML analysis of platinum(II) salphen complexes as potential novel photoactive anti-cancer therapeutics.

Imperial College Research Computing Service Data Repository
Imperial College London (GB)
Good health and well-being
Openalex Percentile: Top 39%
Cloud Computing and Resource Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.