In microscopy-based drug screens, fluorescent markers carry critical information on how compounds affect different biological processes. However, practical considerations may hinder the use of certain fluorescent markers. Here, we present a deep learning method for overcoming this limitation. We accurately generated predicted fluorescent signals from other related markers, and validated this new machine learning (ML) method on two biologically distinct datasets. We used the ML method to improve the selection of potentially efficacious therapeutic compounds for Alzheimer’s disease (AD) from high-content high-throughput screening (HCS). The ML method identified novel compounds that effectively blocked tau aggregation, which would have been missed by traditional screening approaches unguided by ML. The ML method also improved triaging efficiency of compound rankings over a current in-house screening approach. We reproduced this ML method on a biologically independent cancer-based dataset, demonstrating its generalizability. The approach is disease-agnostic, and applicable across fluorescence microscopy datasets.