Michael Kuiper

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 AlphaGenome’s 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 AlphaGenome’s 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).

Summary: PConPy is an open-source Python module for generating protein contact maps, distance maps and hydrogen bond plots. These maps can be generated in a number of publication-quality vector and raster image formats. Contact maps can be annotated with secondary structure and hydrogen bond assignments. PConPy offers a more flexible choice of contact definition parameters than existing toolkits, most notably a greater choice of inter-residue distance metrics. PConPy can be used as a stand-alone application or imported into existing source code. A web-interface to PConPy is also available for use. Availability: The PConPy web-interface and source code can be accessed from its website at http://www.csse.unimelb.edu.au/~hohkhkh1/pconpy/. Contact:hohkhkh1@csse.unimelb.edu.au Supplementary information:Supplementary data are available at Bioinformatics online.