Skip to menu Skip to content Skip to footer
Professor David Ascher
Professor

David Ascher

Email: 
Phone: 
+61 7 336 53991

Overview

Background

Prof David Ascher is an NHMRC Investigator Leadership Fellow and Deputy Associate Dean (Research Partnerships) in the Faculty of Science at The University of Queensland. He also serves as Deputy Director of the Australian Centre for Ecogenomics and Head of Computational Biology & Clinical Informatics at the Baker Heart and Diabetes Institute. Internationally, he sits on scientific advisory boards for A*STAR (Singapore), Fiocruz (Brazil) and the Tuscany University Network (Italy), and has been recognised with major honours including the Royal Society of Chemistry Horizon Prize.

A global leader in computational biology and personalised medicine, Prof Ascher develops advanced AI- and structure-based approaches to understand how genetic variation alters protein structure, function, and clinical outcomes. His group has built one of the world’s most widely used platforms for interpreting coding variants—over 90 computational tools, accessed more than 9.5 million times per year from 120+ countries. These tools underpin clinical diagnostics, guide drug development pipelines, and support international public-health responses to antimicrobial resistance and emerging infectious diseases.

His research has led to new molecular insights across infectious disease, rare disease, oncology and cardiometabolic health, and has been translated directly into practice—informing WHO policy, enabling early resistance detection in tuberculosis and leprosy, stratifying patients with hereditary cancers, and supporting vaccine design with partners including Pfizer. Many of his methods are embedded in globally used resources such as Ensembl VEP, PDBe, and the EMBL-EBI KnowledgeBase.

Prof Ascher has a longstanding commitment to interdisciplinary leadership and capability-building across UQ. As Director (Strategy) of the Biotechnology Programs and later as Deputy Associate Dean (Research Partnerships), he has driven initiatives to transform UQ’s biotechnology education, grow industry-embedded training, expand international partnerships, and diversify research income. He has led the development of UQ’s biotechnology–industry placement ecosystem, initiated new professional development programs adopted across multiple Faculties and Institutes, and established major collaborations with government, industry and global research organisations.

He has published more than 250 peer-reviewed papers (over half as senior author: FWCI 2.7), secured more than $30M in competitive research funding, and supervised over 60 HDR students who now hold leadership positions in academia, industry and government. His work appears in leading journals including Nature, Nature Genetics, Science, PNAS and Nature Microbiology, and is cited in over 100 policy documents and 40 patents.

Prof Ascher holds degrees in Biotechnology, Biochemistry, Structural Biology and Law. His research career has spanned Adelaide, Melbourne, Cambridge and Brisbane. After his PhD with Professor Michael Parker, he worked with Sir Tom Blundell at the University of Cambridge, where he led programs in structure-guided drug discovery and protein–protein interaction targeting. He established his independent laboratory at Cambridge and then at the University of Melbourne/Bio21 Institute, before moving to the Baker Institute in 2019 and joining UQ in 2021.

Availability

Professor David Ascher is:
Available for supervision
Media expert

Research impacts

My research develops artificial intelligence and protein-structure tools that help clinicians, public-health agencies and industry understand how genetic changes affect disease, drug resistance and treatment outcomes. These tools are now used globally to guide healthcare decisions, improve patient outcomes and accelerate the development of safer, more effective medicines.

Clinical and Public Health Impact

  • Faster detection of antimicrobial resistance: My methods enable early identification of drug-resistant tuberculosis and leprosy directly from genome sequencing, improving treatment decisions for patients in Australia, Europe, Brazil and high-burden regions worldwide.

  • Improved diagnosis and counselling for rare disease and cancer: Structural analyses developed by my group are used by clinical teams at Addenbrooke’s Hospital (UK) and the Brazilian Ministry of Health to determine the molecular cause of disease and support personalised patient management.

  • Enhanced clinical trial design and patient stratification: Our tools have guided stratification in trials for Mendelian disorders and cardiometabolic disease, ensuring patients receive the most appropriate therapies.

Industry and Economic Impact

  • Accelerating drug and biologics development: Our platform is embedded in discovery pipelines across biotechnology and pharmaceutical companies, including Pfizer, GSK, Astex and others, supporting the design of next-generation vaccines, antibiotics and therapeutics.

  • Predicting drug toxicity and improving safety: pkCSM—one of our AI platforms—has been licensed internationally and is used to reduce costly late-stage failures in drug development.

Policy and Global Health Impact

  • Our work has shaped World Health Organization guidance on genomic surveillance and pandemic preparedness and is cited in over 100 policy documents, helping global agencies make evidence-based decisions about vaccines, emerging variants and antimicrobial resistance.

Open Knowledge and Research Infrastructure

  • We develop freely accessible tools used by researchers in more than 120 countries (>9.5 million uses per year).

  • Our methods are integrated into major international resources, including:

    • PDBe (European Protein Data Bank) for analysing molecular interactions

    • Ensembl’s Variant Effect Predictor (VEP) for interpreting human genetic variation

    • LSHTM’s TB-Profiler for global TB resistance surveillance

  • These resources support thousands of laboratories, from academic groups to diagnostic services and health agencies.

Works

Search Professor David Ascher’s works on UQ eSpace

192 works between 2008 and 2025

1 - 20 of 192 works

2025

Journal Article

Haploinsufficient variants in SMAD5 are associated with isolated congenital heart disease

Alankarage, Dimuthu, Leshchynska, Iryna, Portelli, Stephanie, Sipka, Alena, Blue, Gillian M., O'Reilly, Victoria, Das, Debjani, Rath, Emma M., Enriquez, Annabelle, Troup, Michael, Fine, Miriam, Poplawski, Nicola, Verlee, Maxim, Humphreys, David T., Harvey, Richard P., Chapman, Gavin, Kirk, Edwin P., Winlaw, David S., Callewaert, Bert, Chung, Wendy K., Ascher, David, Giannoulatou, Eleni and Dunwoodie, Sally L. (2025). Haploinsufficient variants in SMAD5 are associated with isolated congenital heart disease. Human Genetics and Genomics Advances, 6 (4) 100478, 100478. doi: 10.1016/j.xhgg.2025.100478

Haploinsufficient variants in SMAD5 are associated with isolated congenital heart disease

2025

Journal Article

Assessing the predicted impact of single amino acid substitutions in MAPK proteins for CAGI6 challenges

Turina, Paola, Petrosino, Maria, Enriquez Sandoval, Carlos A., Novak, Leonore, Pasquo, Alessandra, Alexov, Emil, Alladin, Muttaqi Ahmad, Ascher, David B., Babbi, Giulia, Bakolitsa, Constantina, Casadio, Rita, Cheng, Jianlin, Fariselli, Piero, Folkman, Lukas, Kamandula, Akash, Katsonis, Panagiotis, Li, Minghui, Li, Dong, Lichtarge, Olivier, Mahmud, Sajid, Martelli, Pier Luigi, Pal, Debnath, Panday, Shailesh Kumar, Pires, Douglas E. V., Portelli, Stephanie, Pucci, Fabrizio, Rodrigues, Carlos H. M., Rooman, Marianne, Savojardo, Castrense ... Capriotti, Emidio (2025). Assessing the predicted impact of single amino acid substitutions in MAPK proteins for CAGI6 challenges. Human Genetics, 144 (2-3) 245403, 265-280. doi: 10.1007/s00439-024-02724-8

Assessing the predicted impact of single amino acid substitutions in MAPK proteins for CAGI6 challenges

2025

Journal Article

Proximity proteomics reveals a mechanism of fatty acid transfer at lipid droplet-mitochondria- endoplasmic reticulum contact sites

Bezawork-Geleta, Ayenachew, Devereux, Camille J., Keenan, Stacey N., Lou, Jieqiong, Cho, Ellie, Nie, Shuai, De Souza, David P., Narayana, Vinod K., Siddall, Nicole A., Rodrigues, Carlos H. M., Portelli, Stephanie, Zheng, Tenghao, Nim, Hieu T., Ramialison, Mirana, Hime, Gary R., Dodd, Garron T., Hinde, Elizabeth, Ascher, David B., Stroud, David A. and Watt, Matthew J. (2025). Proximity proteomics reveals a mechanism of fatty acid transfer at lipid droplet-mitochondria- endoplasmic reticulum contact sites. Nature Communications, 16 (1) 2135, 2135. doi: 10.1038/s41467-025-57405-5

Proximity proteomics reveals a mechanism of fatty acid transfer at lipid droplet-mitochondria- endoplasmic reticulum contact sites

2025

Journal Article

Drug resistance-associated mutations in Plasmodium UBP-1 disrupt its essential deubiquitinating activity

Smith, Cameron J., Eavis, Heledd, Briggs, Carla, Henrici, Ryan, Karpiyevich, Maryia, Ansbro, Megan R., Hoshizaki, Johanna, van der Heden van Noort, Gerbrand J., Ascher, David B., Sutherland, Colin J., Lee, Marcus C.S. and Artavanis-Tsakonas, Katerina (2025). Drug resistance-associated mutations in Plasmodium UBP-1 disrupt its essential deubiquitinating activity. Journal of Biological Chemistry, 301 (3) 108266, 108266. doi: 10.1016/j.jbc.2025.108266

Drug resistance-associated mutations in Plasmodium UBP-1 disrupt its essential deubiquitinating activity

2025

Journal Article

Definition and validation of prognostic phenotypes in moderate aortic stenosis

Sen, Jonathan, Wahi, Sudhir, Vollbon, William, Prior, Marcus, de Sá, Alex G.C., Ascher, David B., Huynh, Quan and Marwick, Thomas H. (2025). Definition and validation of prognostic phenotypes in moderate aortic stenosis. JACC: Cardiovascular Imaging, 18 (2), 133-149. doi: 10.1016/j.jcmg.2024.06.013

Definition and validation of prognostic phenotypes in moderate aortic stenosis

2025

Journal Article

Exploring the effects of missense mutations on protein thermodynamics through structure-based approaches: findings from the CAGI6 challenges

Rodrigues, Carlos H. M., Portelli, Stephanie and Ascher, David B. (2025). Exploring the effects of missense mutations on protein thermodynamics through structure-based approaches: findings from the CAGI6 challenges. Human Genetics, 144 (2-3) e0217169, 327-335. doi: 10.1007/s00439-023-02623-4

Exploring the effects of missense mutations on protein thermodynamics through structure-based approaches: findings from the CAGI6 challenges

2025

Journal Article

Assessing the predicted impact of single amino acid substitutions in calmodulin for CAGI6 challenges

Turina, Paola, Dal Cortivo, Giuditta, Enriquez Sandoval, Carlos A., Alexov, Emil, Ascher, David B., Babbi, Giulia, Bakolitsa, Constantina, Casadio, Rita, Fariselli, Piero, Folkman, Lukas, Kamandula, Akash, Katsonis, Panagiotis, Li, Dong, Lichtarge, Olivier, Martelli, Pier Luigi, Panday, Shailesh Kumar, Pires, Douglas E. V., Portelli, Stephanie, Pucci, Fabrizio, Rodrigues, Carlos H. M., Rooman, Marianne, Savojardo, Castrense, Schwersensky, Martin, Shen, Yang, Strokach, Alexey V., Sun, Yuanfei, Woo, Junwoo, Radivojac, Predrag, Brenner, Steven E. ... Capriotti, Emidio (2025). Assessing the predicted impact of single amino acid substitutions in calmodulin for CAGI6 challenges. Human Genetics, 144 (2-3) 620793, 113-125. doi: 10.1007/s00439-024-02720-y

Assessing the predicted impact of single amino acid substitutions in calmodulin for CAGI6 challenges

2024

Journal Article

Use of the energy waveform electrocardiogram to detect subclinical left ventricular dysfunction in patients with type 2 diabetes mellitus

Soh, Cheng Hwee, de Sá, Alex G. C., Potter, Elizabeth, Halabi, Amera, Ascher, David B. and Marwick, Thomas H. (2024). Use of the energy waveform electrocardiogram to detect subclinical left ventricular dysfunction in patients with type 2 diabetes mellitus. Cardiovascular Diabetology, 23 (1) 91, 91. doi: 10.1186/s12933-024-02141-1

Use of the energy waveform electrocardiogram to detect subclinical left ventricular dysfunction in patients with type 2 diabetes mellitus

2024

Journal Article

Insights into the structure of NLR family member X1: Paving the way for innovative drug discovery

Jewell, Shannon, Nguyen, Thanh Binh, Ascher, David B. and Robertson, Avril A.B. (2024). Insights into the structure of NLR family member X1: Paving the way for innovative drug discovery. Computational and Structural Biotechnology Journal, 23, 3506-3513. doi: 10.1016/j.csbj.2024.09.013

Insights into the structure of NLR family member X1: Paving the way for innovative drug discovery

2024

Journal Article

piscesCSM: prediction of anticancer synergistic drug combinations

AlJarf, Raghad, Rodrigues, Carlos H. M., Myung, Yoochan, Pires, Douglas E. V. and Ascher, David B. (2024). piscesCSM: prediction of anticancer synergistic drug combinations. Journal of Cheminformatics, 16 (1) 81, 81. doi: 10.1186/s13321-024-00859-4

piscesCSM: prediction of anticancer synergistic drug combinations

2024

Conference Publication

Identification and functional characterisation of ACTN1 variants in individuals with a distinct clinical subtype of frontonasal dysplasia without platelet disorder

Tan, Tiong Yang, Houweling, Peter, Huang, Shengping, Nguyen, Thanh-Binh, Yap, Patrick, van Dooren, Marieke, Mathijssen, Irene, Delatycki, Martin, Clucas, Luisa, North, Kathryn, Ascher, David, Bell, Katrina and Cox, Timothy C. (2024). Identification and functional characterisation of ACTN1 variants in individuals with a distinct clinical subtype of frontonasal dysplasia without platelet disorder. 57th European Society of Human Genetics (ESHG) Conference, Berlin, Germany, 1-4 June 2024. London, United Kingdom: Nature Publishing Group.

Identification and functional characterisation of ACTN1 variants in individuals with a distinct clinical subtype of frontonasal dysplasia without platelet disorder

2024

Journal Article

Discriminating Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and comorbid conditions using metabolomics in UK biobank

Huang, Katherine, de Sá, Alex G. C., Thomas, Natalie, Phair, Robert D., Gooley, Paul R., Ascher, David B. and Armstrong, Christopher W. (2024). Discriminating Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and comorbid conditions using metabolomics in UK biobank. Communications Medicine, 4 (1) 248, 1-14. doi: 10.1038/s43856-024-00669-7

Discriminating Myalgic Encephalomyelitis/Chronic Fatigue Syndrome and comorbid conditions using metabolomics in UK biobank

2024

Conference Publication

Delineating the phenotypic spectrum of NSF-related disorders

Arkush, L., Coleman, J., Nguyen, T. B., Mulhern, S., Scott, D. Armstrong, Kaliakatsos, M., Lofquist, S., Lieffering, N., Ascher, D., Ben Zeev, B., Hildebrand, M., Scheffer, I. E., Sadleir, L., Gordon, S., Stephenson, S. E., McTague, A. and Howell, K. B. (2024). Delineating the phenotypic spectrum of NSF-related disorders. 15th European Epilepsy Congress, Rome, Italy, 7-11 September 2024. Hoboken, NJ, United States: Wiley-Blackwell Publishing. doi: 10.1111/epi.18151

Delineating the phenotypic spectrum of NSF-related disorders

2024

Journal Article

Rifaximin prophylaxis causes resistance to the last-resort antibiotic daptomycin

Turner, Adrianna M., Li, Lucy, Monk, Ian R., Lee, Jean Y. H., Ingle, Danielle J., Portelli, Stephanie, Sherry, Norelle L., Isles, Nicole, Seemann, Torsten, Sharkey, Liam K., Walsh, Calum J., Reid, Gavin E., Nie, Shuai, Eijkelkamp, Bart A., Holmes, Natasha E., Collis, Brennan, Vogrin, Sara, Hiergeist, Andreas, Weber, Daniela, Gessner, Andre, Holler, Ernst, Ascher, David B., Duchene, Sebastian, Scott, Nichollas E., Stinear, Timothy P., Kwong, Jason C., Gorrie, Claire L., Howden, Benjamin P. and Carter, Glen P. (2024). Rifaximin prophylaxis causes resistance to the last-resort antibiotic daptomycin. Nature, 635 (8040), 969-977. doi: 10.1038/s41586-024-08095-4

Rifaximin prophylaxis causes resistance to the last-resort antibiotic daptomycin

2024

Journal Article

AlzDiscovery: A computational tool to identify Alzheimer's disease‐causing missense mutations using protein structure information

Pan, Qisheng, Parra, Georgina Becerra, Myung, Yoochan, Portelli, Stephanie, Nguyen, Thanh Binh and Ascher, David B. (2024). AlzDiscovery: A computational tool to identify Alzheimer's disease‐causing missense mutations using protein structure information. Protein Science, 33 (10) e5147, e5147. doi: 10.1002/pro.5147

AlzDiscovery: A computational tool to identify Alzheimer's disease‐causing missense mutations using protein structure information

2024

Journal Article

A new method for network bioinformatics identifies novel drug targets for mucinous ovarian carcinoma

Craig, Olivia, Lee, Samuel, Pilcher, Courtney, Saoud, Rita, Abdirahman, Suad, Salazar, Carolina, Williams, Nathan, Ascher, David B., Vary, Robert, Luu, Jennii, Cowley, Karla J., Ramm, Susanne, Li, Mark Xiang, Thio, Niko, Li, Jason, Semple, Tim, Simpson, Kaylene J., Gorringe, Kylie L. and Holien, Jessica K. (2024). A new method for network bioinformatics identifies novel drug targets for mucinous ovarian carcinoma. NAR Genomics and Bioinformatics, 6 (3) lqae096, lqae096. doi: 10.1093/nargab/lqae096

A new method for network bioinformatics identifies novel drug targets for mucinous ovarian carcinoma

2024

Journal Article

EFG‐CS: Predicting chemical shifts from amino acid sequences with protein structure prediction using machine learning and deep learning models

Gu, Xiaotong, Myung, Yoochan, Rodrigues, Carlos H. M. and Ascher, David B. (2024). EFG‐CS: Predicting chemical shifts from amino acid sequences with protein structure prediction using machine learning and deep learning models. Protein Science, 33 (8) e5096, e5096. doi: 10.1002/pro.5096

EFG‐CS: Predicting chemical shifts from amino acid sequences with protein structure prediction using machine learning and deep learning models

2024

Journal Article

MTR3D‐AF2: Expanding the coverage of spatially derived missense tolerance scores across the human proteome using AlphaFold2

Kovacs, Aaron S., Portelli, Stephanie, Silk, Michael, Rodrigues, Carlos H. M. and Ascher, David B. (2024). MTR3D‐AF2: Expanding the coverage of spatially derived missense tolerance scores across the human proteome using AlphaFold2. Protein Science, 33 (8) e5112, e5112. doi: 10.1002/pro.5112

MTR3D‐AF2: Expanding the coverage of spatially derived missense tolerance scores across the human proteome using AlphaFold2

2024

Conference Publication

Towards evolutionary-based automated machine learning for small molecule pharmacokinetic prediction

de Sá, Alex G. C. and Ascher, David B. (2024). Towards evolutionary-based automated machine learning for small molecule pharmacokinetic prediction. GECCO '24 Companion, Melbourne, VIC, Australia, 14-18 July 2024. New York, NY, United States: ACM. doi: 10.1145/3638530.3664166

Towards evolutionary-based automated machine learning for small molecule pharmacokinetic prediction

2024

Journal Article

Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction

Myung, Yoochan, de Sá, Alex G. C. and Ascher, David B. (2024). Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction. Nucleic Acids Research, 52 (W1), W469-W475. doi: 10.1093/nar/gkae254

Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction

Funding

Current funding

  • 2026 - 2030
    Using protein structure to combat antimicrobial resistance
    NHMRC Investigator Grants
    Open grant
  • 2025 - 2027
    Resolving bottlenecks in natural product biomanufacturing (ARC Linkage Project administered by QUT)
    Queensland University of Technology
    Open grant
  • 2024 - 2027
    Broad-spectrum antibody therapy for Japanese Encephalitis serocomplex viruses
    Cumming Global Centre for Pandemic Therapeutics Foundation Grants
    Open grant
  • 2024 - 2027
    Improving genetic diagnosis of autoimmune and autoinflammatory disease through an integrated multi-omics approach (MRFF 2022 GHFM - administered by ANU)
    The Australian National University
    Open grant
  • 2021 - 2025
    Using protein structure to combat antimicrobial resistance
    NHMRC Investigator Grants
    Open grant

Past funding

  • 2024
    Development of Molecular Property Prediction Models for Exploring Alternative Chemicals
    Korea Research Institute of Chemical Technology
    Open grant
  • 2023 - 2024
    A comprehensive approach to the genetic, molecular and functional impact of rare titin missense variants in cardiomyopathy (Australian Functional Genomics Network grant administered by MCRI)
    Murdoch Childrens Research Institute
    Open grant

Supervision

Availability

Professor David Ascher is:
Available for supervision

Looking for a supervisor? Read our advice on how to choose a supervisor.

Available projects

  • Treating the Person, Not the Disease: AI-Driven Precision Medicine

    Patients with the same diagnosis can have dramatically different outcomes, driven by subtle—but crucial—genomic differences. This project develops state-of-the-art computational approaches to map how individual genetic variation reshapes molecular pathways, protein structure/function and cellular networks.

    What the student will investigate

    • AI and structural modelling approaches to predict the molecular consequences of patient variants

    • Network-level analysis of how mutations rewire biological systems

    • Linking molecular perturbations to patient outcomes, drug response and disease trajectories

    • Identifying personalised therapeutic opportunities and biomarkers

    • Understanding heterogeneity in large clinical and multi-omics datasets

    Impact The project will create tools that support personalised treatment strategies, guide clinical decision-making and identify disease mechanisms that cannot be detected by sequence analysis alone.

  • Discovering Sequence–Structure–Dynamics–Function Relationships at Scale

    Understanding how proteins work requires more than static structures: biological function emerges from the interplay between sequence, 3D structure, conformational dynamics, and molecular interactions. This project uncovers these relationships using modern structural biology, physics-informed AI and large-scale protein datasets.

    What the student will explore

    • Integrating AlphaFold2/ESMFold models with experimental structure and dynamics data (MD, cryo-EM, NMR)

    • Using AI to infer dynamic landscapes and allosteric networks

    • Mapping how sequence variation alters conformation and function across protein families

    • Predicting structure–dynamics–function relationships at proteome scale

    • Developing interpretable models to reveal fundamental design rules of proteins

    Impact Findings will drive new biological insights, facilitate annotation of uncharacterised proteins, and support rational engineering of molecules for biotechnology and medicine.

  • Developing Better and Safer Drugs through Computational Design

    Drug development remains slow and costly, with most failures occurring because candidate molecules lack efficacy or show unacceptable toxicity. This project uses AI-driven modelling and molecular simulation to design safer drugs earlier, and to anticipate resistance before it appears in the clinic.

    Student research opportunities

    • Predicting and optimising binding affinity using graph-based and deep learning models

    • Modelling pharmacokinetics, solubility and toxicity using next-generation multi-task AI

    • Using protein structure to identify vulnerable hotspots for resistance mutations

    • Designing “resistance-resistant” therapeutics through structure-guided strategies

    • Integrating experimental, structural and real-world data to improve predictive performance

    Impact This work reduces downstream clinical trial failures, supports pharmaceutical partners, and accelerates the development of new therapeutics for infectious disease, cancer and complex conditions.

  • Engineering Biotherapeutics Using Evolution, Structure and AI

    Evolution provides powerful blueprints for engineering new proteins and biologics. By integrating ancestral sequence reconstruction, structural modelling, laboratory evolution and AI-driven design, this project aims to create next-generation biotherapeutics with tailored stability, specificity and function.

    Student directions may include

    • Inferring evolutionary constraints to guide protein engineering

    • Designing highly stable or ultra-specific enzymes using structural insights

    • Developing biologics and peptides for applications such as toxin neutralisation, enzyme replacement or immune modulation

    • Using generative AI to create novel protein scaffolds with enhanced activity

    • Reconstructing and evolving ancestral proteins to reveal mechanisms that can be exploited for engineering

    Impact The project enables rational design of powerful new enzymes and biologics, supporting applications in medicine, biodefence, sustainable biotech and advanced therapeutics.

  • Quantum-Accelerated AI for Protein Dynamics and Variant Prediction

    Quantum computing is rapidly advancing, offering fundamentally new ways to represent and manipulate high-dimensional biological systems. This project will develop hybrid quantum-classical machine learning models to simulate protein conformational changes, binding interactions and mutation effects at unprecedented resolution.

    Research avenues:

    • Quantum kernels for molecular graphs and structural signatures

    • Variational quantum circuits for modelling protein flexibility

    • Quantum generative models for predicting mutation impacts

    • Benchmarking speed/accuracy trade-offs on real quantum hardware

    Impact: Creates a next-generation platform for structural biology and personalised variant interpretation—beyond what is feasible with classical ML.

  • Foundation Models for Biology: Building the “Biology GPT”

    Large language models trained on protein sequences, structures, cellular assays and phenotypic data offer a unified way to predict biological behaviour. This PhD will develop multimodal biological foundation models that integrate sequences, structural embeddings (e.g., AlphaFold2), small-molecule chemistry and clinical genomics.

    Research avenues:

    • Joint embedding of sequence + structure + function datasets

    • Continual learning from experimental perturbation data

    • Zero-shot prediction of variant consequences

    • Interpretable biological attention maps

    Impact: A general-purpose model that can reason across molecular levels—helping clinicians and researchers predict what mutations do, even when no experimental data exist.

  • Generative Design of Protein–Protein Interaction Modulators

    While many tools predict variant effects, far fewer generate new therapeutic hypotheses. This project will apply state-of-the-art generative AI (diffusion models, graph generative networks) to design peptides, small molecules or molecular glues that modulate protein–protein interactions.

    Research avenues:

    • Generative design conditioned on structural perturbation signatures

    • Modelling mutation-induced rewiring of interaction networks

    • Automated in silico screens for stabilisers/destabilisers

    Impact: A transformative approach enabling rapid in silico discovery of next-generation precision medicines.

  • AI for Evolutionary Forecasting of Pathogens and Antimicrobial Resistance

    Predicting future resistance mutations or viral variants is a frontier challenge. This PhD develops deep models that combine structural constraints, evolutionary trajectories and population-level genomics to forecast high-risk mutations before they appear.

    Research avenues:

    • Deep evolutionary diffusion models

    • Graph neural networks integrating protein structure + phylogeny

    • Simulation of adaptive landscapes under drug selection pressure

    • Real-time forecasting from genomic surveillance data

    Impact: Supports global pathogen surveillance, AMR management, and vaccine/drug development.

  • Digital Twins for Precision Medicine: AI Models of Individual Patients

    This project builds computational digital twins—AI models representing individual patients—by integrating their genomic, structural, biochemical and clinical data.

    Research avenues:

    • Modelling genotype → molecular phenotype → clinical outcome

    • Patient-specific simulation of drug responses

    • Identifying compensatory pathways and personalised treatment options

    • Multiscale modelling using structural signatures + clinical data

    Impact: Provides personalised treatment predictions, informing clinical decision-making and mechanistic understanding of disease.

  • Next-Generation Biophysical Simulation using Neural Differential Equations

    Traditional molecular simulations remain slow and limited in scale. This project develops AI-accelerated biophysical simulators that learn energy landscapes, dynamics and interaction networks directly from experimental and structural data.

    Research avenues:

    • Neural ODEs and neural Hamiltonian systems for protein motion

    • Predicting long-timescale dynamics from short MD trajectories

    • AI inference of allosteric networks and conformational shifts

    • Integration with cryo-EM, NMR and AlphaFold2 dynamics models

    Impact: Enables accurate simulation of biological processes previously inaccessible due to computational cost.

Supervision history

Current supervision

  • Doctor Philosophy

    Leveraging large-scale population data to improve missense variant pathogenicity prediction

    Principal Advisor

    Other advisors: Dr Stephanie Portelli

  • Doctor Philosophy

    Using Deep Learning in Cell & Gene Therapy

    Principal Advisor

    Other advisors: Dr Stephanie Portelli

  • Doctor Philosophy

    Structure-Guided Deep Learning Approaches for Protein Thermodynamics: Predicting Variant Effects on Protein Stability and Interactions

    Principal Advisor

  • Doctor Philosophy

    Deep Learning Algorithms for Polygenic Genotype-Phenotype Predictions and the development of genetics computation tools

    Principal Advisor

  • Doctor Philosophy

    Using AI to explore phosphorylation in disease

    Principal Advisor

    Other advisors: Dr Stephanie Portelli

  • Doctor Philosophy

    Rational protein engineering and inhibition

    Principal Advisor

  • Doctor Philosophy

    Using AI to guide antibody and vaccine design

    Principal Advisor

  • Doctor Philosophy

    Protein structure guided precision medicine

    Principal Advisor

    Other advisors: Professor Phil Hugenholtz, Dr Stephanie Portelli

  • Doctor Philosophy

    Improving rational antibody design using machine learning

    Principal Advisor

  • Doctor Philosophy

    Machine Learning for Protein Dynamics: Predicting Post-Translational Modifications and Mutation Effects

    Principal Advisor

  • Doctor Philosophy

    Harnessing AlphaFold and explainable AI to better characterise human missense variants and diseases

    Principal Advisor

    Other advisors: Dr Stephanie Portelli, Dr Thanh-Binh Nguyen

  • Doctor Philosophy

    Therapeutic Resolution of Inflammation in the Central Nervous System for Neuroprotection in Parkinson's Disease

    Associate Advisor

    Other advisors: Professor Avril Robertson

  • Doctor Philosophy

    Breaking the chain of inflammation through targetting NLR proteins

    Associate Advisor

    Other advisors: Professor Kate Schroder, Professor Avril Robertson

  • Doctor Philosophy

    Computational design of targeted lipid technologies

    Associate Advisor

    Other advisors: Professor Megan O'Mara

  • Doctor Philosophy

    Unravelling the Physicochemical Drivers of Biomolecular Self-Assembly though Multiscale Simulations

    Associate Advisor

    Other advisors: Dr Evelyne Deplazes, Professor Megan O'Mara

  • Doctor Philosophy

    Use of structural phylogeny and reconciliation in molecular phylogenetics

    Associate Advisor

    Other advisors: Dr Kate Bowerman, Professor Phil Hugenholtz

Completed supervision

Media

Enquiries

Contact Professor David Ascher directly for media enquiries about their areas of expertise.

Need help?

For help with finding experts, story ideas and media enquiries, contact our Media team:

communications@uq.edu.au