Biology subjects

Ramarao-Milne, P.

Publications and source records attributed to Ramarao-Milne, P..

3 recordsLinked to original sources

bioRxiv2026

Evaluating the cross-species transferability and scaling of sequence-to-function predictions in AlphaGenome

Deep learning models that predict molecular phenotypes directly from DNA sequence offer a powerful framework for interpreting genomic variation. Recently, AlphaGenome was introduced as a deep sequence-to-function architecture capable of predicting observations that historically required experiments. While the model has shown high accuracy, it was primarily evaluated on human variants scored against a reference genome. Here, we test performance on mouse data, the other species AlphaGenome was trained on although with fivefold fewer features than human (1,128 versus 5,930). We demonstrate that AlphaGenomes predictive performance varies considerably depending on the functional task. Specifically, predicted quantitative expression effects are directionally weak and compressed roughly 100-fold relative to empirical benchmarks across both reconstructed-haplotype and single-variant regimes. In contrast, canonical splice-site disruptions are recognized with near-identical accuracy in mouse and human (AUC 0.96 versus 0.98), displaying no cross-species divergence in predicted effect magnitude. We developed a scoring-approach for AI-agents to autonomously assess AlphaGenome prediction confidence and accurately differentiate between AlphaGenomes robust sequence-level recognition across species and its current limitations when interpreting un-fine-mapped regulatory variants. This demonstrates how GenAI innovations that are still under development can safely be harnessed by wrapping a responsible AI layer around the call to intercept flawed results, thereby adhering to international standards, such as the Australian Voluntary AI Safety Standard (VAISS).

bioinformatics↗

bioRxiv2025

Machine Learning-Driven Discovery of Synergistic Protein Interactions Identifies ATL3 as a Putative Biomarker for Cancer Drug Response

BackgroundResistance to targeted molecular therapies--both primary and acquired--remains a major obstacle to effective cancer treatment. Despite extensive research, the molecular determinants of treatment resistance are still incompletely understood, underscoring the need to identify robust resistance drivers to improve therapeutic outcomes. Recently, the ProCan and Wellcome Sanger Institute released the worlds largest pan-cancer proteomic dataset to date, comprising 949 cancer cell lines treated with 625 anti-cancer agents. Despite progress in identifying single protein markers, scalable methods for detecting synergistic protein interactions driving drug susceptibility remain limited. Machine learning models such as random forests may offer a robust framework for capturing non-linear protein interactions across diverse cancer types. ResultsOur study presents synerOmics, a scalable framework for identifying putative synergistic protein interactions by leveraging parent-child co-occurrences in random forest regression trees to reduce the interaction search space. We validated our approach using simulated data and two independent cancer proteomic datasets, identifying both pan-cancer and breast cancer-specific markers associated with drug susceptibility. Synergistic interactions that consistently replicated across datasets were enriched for endoplasmic reticulum stress pathways. Notably, shared targets included established sensitivity markers for tyrosine kinase inhibitors (TKIs) and revealed a resistance-associated network centred on ATL3, which demonstrated both prognostic and predictive relevance. ConclusionsApplying synerOmics to the largest cancer cell line proteomic dataset to date, we identified ATL3 as a strong candidate biomarker for lapatinib resistance in breast cancer, with superior predictive performance compared to the current gold standard sensitivity biomarker, ERBB2. HighlightsO_LIWe present a machine learning framework for drug response biomarker discovery, leveraging the largest proteomic cancer cell line dataset, ProCan-DepMapSanger C_LIO_LIATL3 is proposed as a candidate predictive biomarker for lapatinib resistance in breast cancer C_LIO_LIElevated expression of a novel resistance-conferring subcluster centered on ATL3 is associated with poor prognosis across 11 TCGA cancer types C_LIO_LIBaseline drug resistance may be broadly driven by stress pathways, with ER stress and protein ATL3 implicated in ER-phagy in response to TKIs. C_LI

cancer biology↗

bioRxiv2021

Genomic analysis of patient-derived xenograft models reveals intra-tumor heterogeneity in endometrial cancer and can predict tumor growth inhibition with talazoparib

BackgroundEndometrial cancer (EC) is a major gynecological cancer with increasing incidence. It comprised of four molecular subtypes with differing etiology, prognoses, and response to chemotherapy. In the future, clinical trials testing new single agents or combination therapies will be targeted to the molecular subtype most likely to respond. Pre-clinical models that faithfully represent the molecular subtypes of EC are urgently needed, we sought to develop and characterize a panel of novel EC patient-derived xenograft (PDX) models. MethodsHere, we report whole exome or whole genome sequencing of 11 PDX models and the matched primary tumor. Analysis of multiple PDX lineages and passages was performed to study tumor heterogeneity across lineages and/or passages. Based on recent reports of frequent defects in the homologous recombination (HR) pathway in EC, we assessed mutational signatures and HR deficiency scores and correlated these with in vivo responses to the PARP inhibitor (PARPi) talazoparib in six PDXs representing the different molecular subtypes of EC. ResultsPDX models were successfully generated from all four molecular subtypes of EC and uterine carcinosarcomas, and they recapitulated morphology and the molecular landscape of primary tumors without major genomic drift. We also observed a wide range of inter-tumor and intra-tumor heterogeneity, well captured by different PDX lineages, which could lead to different treatment responses. An in vivo response to talazoparib was detected in two p53mut models consistent with stable disease, however both lacked the HR deficiency genomic signature. ConclusionsEC PDX models represent the four molecular subtypes of disease and can capture intra-tumoral heterogeneity of the original primary tumor. PDXs of the p53mut molecular subtype showed sensitivity to PARPi, however, deeper and more durable responses will likely require combination of PARPi with other agents.

genomics↗