Skip to content

Search

AI succeeds in diagnosing rare diseases

Timo Lassmann BSc (Hons) MSc PhD Feilman Fellow; Head, Precision Health Research and Head, Translational Intelligence timo.lassmann@thekids.org.au

Mesothelioma location influences the tumour microenvironment and immune checkpoint therapy response in preclinical models

Mesothelioma is a cancer derived from mesothelial cells, most commonly arising from the pleura or the peritoneum. Immune checkpoint therapy (ICT) has shown survival benefit for pleural mesothelioma, but little is known about the response in peritoneal mesothelioma. Most preclinical mesothelioma models involve subcutaneous cancer cell implantation, which lacks the relevant tumour microenvironment of peritoneal mesothelioma and does not resemble the clinical presentation.

A precision medicine approach to interpret a GATA4 genetic variant in a paediatric patient with congenital heart disease

Patients with congenital heart disease (CHD) are identified in 1% of live births. Improved surgical intervention means many patients now survive to adulthood, the corollary of which is increased mortality in the over-65-year-old congenital heart disease population. In the clinic, genetic sequencing increasingly identifies novel genetic variants in genes related to CHD.

Functional characterization of the MED12 p.Arg1138Trp variant in females: implications for neural development and disease mechanism

Seven female individuals with multiple congenital anomalies, developmental delay and/or intellectual disability have been found to have a genetic variant of uncertain significance in the mediator complex subunit 12 gene. The functional consequence of this genetic variant in disease is undetermined, and insight into disease mechanism is required.

Single-cell data combined with phenotypes improves variant interpretation

Whole genome sequencing offers significant potential to improve the diagnosis and treatment of rare diseases by enabling the identification of thousands of rare, potentially pathogenic variants. Existing variant prioritisation tools can be complemented by approaches that incorporate phenotype specificity and provide contextual biological information, such as tissue or cell-type specificity. 

A corpus of GA4GH phenopackets: Case-level phenotyping for genomic diagnostics and discovery

The Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema was released in 2022 and approved by ISO as a standard for sharing clinical and genomic information about an individual, including phenotypic descriptions, numerical measurements, genetic information, diagnoses, and treatments. A phenopacket can be used as an input file for software that supports phenotype-driven genomic diagnostics and for algorithms that facilitate patient classification and stratification for identifying new diseases and treatments.

An evaluation of GPT models for phenotype concept recognition

Clinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field.

Pushing the boundaries of rare disease diagnostics with the help of the first Undiagnosed Hackathon

Timo Lassmann BSc (Hons) MSc PhD Feilman Fellow; Head, Precision Health Research and Head, Translational Intelligence timo.lassmann@thekids.org.au

Coupling of response biomarkers between tumor and peripheral blood in patients undergoing chemoimmunotherapy

Platinum-based chemotherapy in combination with anti-PD-L1 antibodies has shown promising results in mesothelioma. However, the immunological mechanisms underlying its efficacy are not well understood and there are no predictive biomarkers to guide treatment decisions.

Autism risk associated with parental age and with increasing difference in age between the parents

Increases in ASD was not only limited to advancing paternal or maternal age alone but also to differences parental age including younger or older similarly age