Integrated machine learning and multimodal data fusion for patho-phenotypic feature recognition in iPSC models of dilated cardiomyopathy

Integration of multiple data sources presents a challenge for accurate prediction of molecular patho-phenotypic features in automated analysis of data from human model systems. Here, we applied a machine learning-based data integration to distinguish patho-phenotypic features at the subcellular level for dilated cardiomyopathy (DCM). We employed a human induced pluripotent stem cell-derived cardiomyocyte (iPSC-CM) model of a DCM mutation in the sarcomere protein troponin T (TnT), TnT-R141W, compared to isogenic healthy (WT) control iPSC-CMs. We established a multimodal data fusion (MDF)-based analysis to integrate source datasets for Ca2+ transients, force measurements, and contractility recordings. Data were acquired for three additional layer types, single cells, cell monolayers, and 3D spheroid iPSC-CM models. For data analysis, numerical conversion as well as fusion of data from Ca2+ transients, force measurements, and contractility recordings, a non-negative blind deconvolution (NNBD)-based method was applied. Using an XGBoost algorithm, we found a high prediction accuracy for fused single cell, monolayer, and 3D spheroid iPSC-CM models (≥92 ± 0.08 %), as well as for fused Ca2+ transient, beating force, and contractility models (>96 ± 0.04 %). Integrating MDF and XGBoost provides a highly effective analysis tool for prediction of patho-phenotypic features in complex human disease models such as DCM iPSC-CMs.

Synthesis and evaluation of novel S-benzyl- and S-alkylphthalimide- oxadiazole -benzenesulfonamide hybrids as inhibitors of dengue virus protease

Direct acting antiviral drugs (DAADs) are becoming therapeutics of choice for the treatment of viral infections. Successful development of anti HIV and HCV drugs by targeting the viral proteases has provided impetus for discovering newer DAADs. Dengue virus (DENV) protease, which is composed of two nonstructural proteins, NS2B and NS3pro, can be likewise exploited for discovering new anti-dengue therapeutics. In this study, we have linked together two pharmaceutically interesting motifs, namely 1,3,4-oxadiazole and benzenesulfonamide in two alternative series to develop novel S-benzylated and S-alkylphthalimidated hybrids. For the first series of hybrids, 4-aminobenzoic acid (1) was reacted with substituted benzenesulfonyl chlorides via its amino group, whereas the carboxylic acid side was elaborated to sulfonamido-1,3,4-oxadiazole-2-thiols (6a/b) in three steps. At this stage, the intermediates 6a/b were bifurcated to either S-alkylphthalimidated (8a-j) or S-benzylated (9a-c) hybrids by reacting with corresponding halides. For the alternative series of hybrids, the carboxylic acid group of probenecid (10) was similarly elaborated to sulfonamido-1,3,4-oxadiazole-2-thiols (13), and diverged to S-alkylphthalimidated (14a-f) and S-benzylated hybrids (15a-e). Bioactivity assays demonstrated that 8g and 8h are the most potent inhibitors among the synthesized analogs, exhibiting the IC50 values of 13.9 μM and 15.1 μM, respectively. Computational assessment predicted the binding of the inhibitors at an allosteric site developed in the open conformation of DENV2 NS2B/NS3pro. Taken together these findings point out that the synthesized hybrid inhibitors possess a great potential for further antiviral drug development.