ABSTRACT
Fusion oncoproteins, a class of chimeric proteins arising from chromosomal translocations, drive and sustain various cancers, particularly those impacting children. Unfortunately, due to their intrinsically disordered nature, large size, and lack of well-defined, druggable pockets, they have been historically challenging to target therapeutically: neither small molecule-based methods nor structure-based approaches for binder design are strong options for this class of molecules. Recently, protein language models (pLMs) have demonstrated success at representing protein sequences with information-rich embeddings, enabling downstream design applications from sequence alone. However, no current pLM has been trained on fusion oncoprotein sequences and thus may not produce optimal representations for these proteins. In this work, we introduce FusOn-pLM, a novel pLM that fine-tunes the state-of-the-art ESM-2 model on fusion oncoprotein sequences. We specifically introduce a novel masked language modeling (MLM) strategy, employing a binding-site probability predictor to focus masking on key amino acid residues, thereby generating more optimal fusion oncoprotein-aware embeddings. Our model improves performance on both fusion oncoprotein-specific benchmarks and disorder prediction tasks in comparison to baseline ESM-2 representations, as well as manually-constructed biophysical embeddings, motivating downstream usage of FusOn-pLM embeddings for therapeutic design tasks targeting these fusions. We have made our model publicly available to the community at https://huggingface.co/ChatterjeeLab/FusOn-pLM.
ABSTRACT
Heterozygous carriers of the glucocerebrosidase 1 (GBA) L444P Gaucher mutation have an increased risk of developing Parkinson's disease (PD). The GBA mutations result in elevated alpha synuclein (aSyn) levels. Heterozygous mice carrying one allele with the L444P mutation knocked-into the mouse gene show increased aSyn levels and are more sensitive to motor deficits following exposure to the neurotoxin (1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine) MPTP than wild-type mice. Paraquat (PQ), a herbicide, increases PD risk in most studies. Its effects on the brain involve alterations in the gut microbiome. Exposure to dextran sulfate sodium (DSS), a mouse model of colitis, can be used to determine whether gut microbiome alterations are sufficient to induce PD-relevant phenotypes. We rederived the A53T-L444P and A53T mouse lines to assess whether PQ, PQ in combination with radiation exposure (IR), and DSS have differential effects in A53T and A53T-L444P mice and whether these effects are associated with alterations in the gut microbiome. PQ and PQ + IR have differential effects in A53T and A53T-L444P mice. In contrast, effects of DSS are only seen in A53T-L444P mice. Exposure and genotype modulate the relationship between the gut microbiome and behavioral performance. The gut microbiome may be an important mediator of how environmental exposures or genetic mutations yield behavioral and cognitive impacts.
