Developing an AI CD Toolkit to Characterise G-Quadruplex and Triplex DNA Architectures

Apply and key information

Summary

Motivation

G-quadruplexes (G4s) are non-canonical structures formed by guanine-rich nucleic acids, increasingly implicated in transcriptional control, replication dynamics and genome stability at telomeres and oncogene promoters, and are actively explored as targets in cancer and antiviral drug discovery.

G-triplexes and G-hairpins are thought to act as intermediates or alternative folds on these G4 pathways, but their CD signatures, stability ranges and structural diversity remain poorly defined, making it difficult to recognise when experimental spectra report “full” G4s versus shortened stems, triplex or hairpin states.

Circular dichroism (CD) is the workhorse method for probing these systems, yet interpretation still relies on qualitative “parallel vs antiparallel” rules.

TD-DFT calculations on known structures can generate CD-like outputs, creating a timely opportunity to combine simulated and experimental CD with machine learning to derive more quantitative, structurally informed CD analysis of guanine-rich folds.

Underlying Aim

To develop a physics-guided AI method and open tool that integrates TD-DFT/ECD simulations with experimental CD spectra from PDB-resolved structures to classify guanine-rich folds as G-quadruplex, G-triplex or G-hairpin, and to predict key structural descriptors relevant to ligand binding (topology group, syn/anti content, loop type/length, stem truncation) with calibrated uncertainty, including states such as abridged G4s and triplex intermediates.

Methodology

CD spectroscopy; SRCD; PDB mining and curation of G4/G-triplex/G-hairpin structures; generation of atomistic models; TD-DFT/ECD calculations; exciton-based spectral modelling; spectral preprocessing and feature extraction; supervised and semi-supervised ML (e.g. ensembles, CNN/transformers); uncertainty quantification; Python package and GUI/web app development; benchmarking on ligand-binding and mutational datasets.

Impact

The project will deliver a validated “spectrum-to-structure” workflow and user-friendly software for rapid, information-rich analysis of guanine-rich DNA folds from a single CD/ECD experiment.

This will (i) enable high-throughput screening of sequence variants, solution conditions and cation regimes; (ii) provide quantitative fingerprints for triplex and hairpin intermediates on G4 folding landscapes; and (iii) furnish structural descriptors directly linked to ligand binding pockets and terminal capping motifs.

In drug discovery, the tool will support prioritisation and mechanistic characterisation of G4-, triplex- and hairpin-targeting compounds, and optimisation of ligands that selectively stabilise or destabilise specific folds, thereby reducing dependence on labour-intensive structural biology in early hit-to-lead campaigns.

Skills required of the applicant

Good degree in chemistry, biochemistry, physics, pharmaceutical sciences or related discipline; interest in nucleic acids and spectroscopy; interest in developing experience of Python programming and basic statistics or machine learning; enthusiasm to learn TD-DFT/ECD and work with high-performance computing; careful data management and scientific writing skills.

AccessNI clearance required

Please note, the successful candidate will be required to obtain AccessNI clearance prior to registration due to the nature of the project.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

Sound understanding of subject area as evidenced by a comprehensive research proposal
A comprehensive and articulate personal statement

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

First Class Honours (1st) Degree
Completion of Masters at a level equivalent to commendation or distinction at Ulster
Practice-based research experience and/or dissemination
Experience using research methods or other approaches relevant to the subject domain
Work experience relevant to the proposed project
Publications record appropriate to career stage
Experience of presentation of research findings

Equal Opportunities

The University is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.

Appointment will be made on merit.