Generating experimentally unrelated target molecule binding nucleic-acid polymers using machine learning

In vitro selection queries large combinatorial libraries for sequence-defined polymers with target binding and reaction catalysis activity. While the total sequence space of these libraries can extend beyond 10^22 sequences, practical considerations limit starting sequences to about 10^15 distinct molecules. Selection-induced sequence convergence and limited sequencing depth further constrain experimentally observable sequence space. To address these limitations, we integrate experimental and machine learning approaches to explore regions of sequence space unrelated to experimentally derived variants. We performed in vitro selections to discover highly side-chain-functionalized nucleic acid polymers (HFNAPs) with potent affinities for a target small molecule (daunomycin Kd=5-65 nM). We then used the selection data to train a conditional variational autoencoder (CVAE) machine learning model to generate diverse and unique HFNAP sequences with high daunomycin affinities (Kd=9-26 nM). Coupling in vitro selection with a machine learning model thus enables direct generation of active variants, demonstrating a new approach to the discovery of functional biopolymers.