Expanding antiviral treatment options against SARS-CoV-2 remains crucial as the virus evolves rapidly and drug resistant strains have emerged. Broad spectrum host-directed antivirals (HDA) are promising therapeutic options, however the robust identification of relevant host factors by CRISPR/Cas9 or RNA interference screens remains challenging due to low consistency in the resulting hits. To address this issue, we employed machine learning based on experimental data from knockout screens and a drug screen. As gold standard, we assembled perturbed genes reducing virus replication or protecting the host cells. The machines based their predictions on features describing cellular localization, protein domains, annotated gene sets from Gene Ontology, gene and protein sequences, and experimental data from proteomics, phospho-proteomics, protein interaction and transcriptomic profiles of SARS-CoV-2 infected cells. The models reached a remarkable performance with a balanced accuracy of 0.82 (knockout based classifier) and 0.71 (drugs screen based classifier), suggesting patterns of intrinsic data consistency. The predicted host dependency factors were enriched in sets of genes particularly coding for development, morphogenesis, and neural related processes. Focusing on development and morphogenesis-associated gene sets, we found β-catenin to be central and selected PRI-724, a canonical β-catenin/CBP disruptor, as a potential HDA. PRI-724 limited infection with SARS-CoV-2 variants, SARS-CoV-1, MERS-CoV and IAV in different cell line models. We detected a concentration-dependent reduction in CPE development, viral RNA replication, and infectious virus production in SARS-CoV-2 and SARS-CoV-1-infected cells. Independent of virus infection, PRI-724 treatment caused cell cycle deregulation which substantiates its potential as a broad spectrum antiviral. Our proposed machine learning concept may support focusing and accelerating the discovery of host dependency factors and the design of antiviral therapies.