Background/Objectives: Congenital Myasthenic Syndromes (CMS) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagno-sis and treatment initiation. Recent protein structure prediction softwares, AlphaFold2/ColabFold, have revolutionised structural biology; such predictions have also been leveraged in AlphaM-issense which predicts ClinVar variant pathogenicity with 90% accuracy. Few reports, however, have tested these tools on rigorously-characterised clinical data. We therefore assessed ColabFold and AlphaMissense as diagnostic aids for CMS, using variants of the CHRN genes that encode the nicotinic acetylcholine receptor (nAChR). Methods: Utilising a dataset of 61 clinically-validated CHRN variants, (1) we evaluated the pos-sibility of a ColabFold metric (either predicted structural disruption, prediction confidence, and prediction quality), that distinguishes variant pathogenicity. (2) We assessed AlphaMissenses’ ability to differentiate variant pathogenicity. (3) We compared AlphaMissense to existing patho-genicity prediction programmes, AlamutVP and EVE. Results: Analysing variant effects on ColabFold CHRN structure prediction, prediction confi-dence, and prediction quality, doesn’t yield any pathogenicity-indicative metric. However, Al-phaMissense predicts variant pathogenicity with 63.93% accuracy on our dataset – a much greater proportion than AlamutVP (27.87%) and EVE (28.33%). Conclusions: Emerging in silico tools can revolutionise genetic disease diagnosis – however, im-provement, refinement, and clinical validation is imperative prior to practical acquisition.

Pre-mRNA splicing is an essential process orchestrated by the spliceosome, a dynamic complex assembled stepwise on pre-mRNA. We have previously identified that USH1G protein SANS regulates pre-mRNA splicing by mediating the intra-nuclear transfer of the spliceosomal U4/U6.U5 tri-snRNP complex. During this process, SANS interacts with the U4/U6 and U5 snRNP-specific proteins PRPF31 and PRPF6 and regulates splicing, which is disturbed by variants of USH1G/SANS causative for human Usher syndrome (USH) the most common form of hereditary deaf-blindness.Here, we aimed to gain further insight into the molecular interaction of the splicing molecules PRPF31 and PRPF6 to the CENTn domain of SANS using fluorescence resonance energy transfer assays in cells and in silico deep learning-based protein structure predictions. This demonstrates that SANS directly binds via two distinct conserved regions of its CENTn to the two PRPFs. In addition, we provide evidence that these interactions occur sequentially and a conformational change of an intrinsically disordered region to a short α-helix of SANS CENTn2 is triggered by binding of PRPF6. Furthermore, we found that pathogenic variants of USH1G/SANS perturb the binding of SANS to both PRPFs implying a significance for the USH1G pathophysiology.

Kaposi’s sarcoma-associated herpesvirus (KSHV) is the etiologic agent of Kaposi’s sarcoma, primary effusion lymphoma (PEL) and multicentric Castleman’s disease. During KSHV lytic infection, lytic-related genes, categorized as immediate-early, early, and late genes, are expressed in a temporal manner. The transcription of late genes requires the virus-specific pre-initiation complex (vPIC), which consists of viral transcription factors. However, the characterization of the protein-protein interactions of the vPIC factors has not been completely elucidated. KSHV ORF18 is one of the vPIC factors, and its interaction with other viral factors has not been sufficiently revealed. Here, we analyzed the interaction between ORF18 and another vPIC factor, ORF30, in living cells using the bimolecular fluorescence complementation (BiFC) assay. We identified four amino-acid residues (Leu29, Gln36, His41 and Trp170) on ORF18 that were responsible for its interaction with ORF30. The artificial intelligence (AI) system AlphaFold2 predicted that identified four residues are exposed to the surface of ORF18 and located in proximity to each other in the surface of ORF18. Thus, AI-predicted model supports the importance of four residues for binding of ORF18 to ORF30. Our results indicated that wet experiments in combination with AI may enhance the structural characterization of vPIC protein-protein interactions.