{"doi":"10.1101/2025.04.22.649862","title":"Zero-shot design of drug-binding proteins via neural selection-expansion","abstract":"<jats:title>Abstract</jats:title>\n                <jats:p>\n                  Computational design of molecular recognition remains challenging despite advances in deep learning\n                  <jats:sup>1–3</jats:sup>\n                  . The design of proteins that bind to small molecules has been particularly difficult because it requires simultaneous optimization of protein sequence, protein structure, and ligand conformation\n                  <jats:sup>1–7</jats:sup>\n                  . Despite their promise, current deep-learning algorithms have struggled to navigate this landscape, precluding the zero- or few-shot design of binders. Here we show that the combination of two neural networks in an iterative design algorithm can create small-molecule binding proteins from scratch with high accuracy. To optimize a design in the joint distribution of sequence, structure, and ligand conformation, we use a pair of neural networks that were trained on reciprocal tasks. We train and use a graph neural network, LASErMPNN, to design protein sequence given protein−ligand co-structure, and we use RoseTTAFold-All Atom\n                  <jats:sup>8</jats:sup>\n                  (RFAA) to predict protein−ligand co-structure given protein sequence. We iteratively apply these two networks to design proteins that bind the drug, exatecan, a topoisomerase I inhibitor that is prone to inactivation by hydrolysis\n                  <jats:sup>9</jats:sup>\n                  . Each of four experimentally tested designs bound the drug, with the lowest dissociation constant (\n                  <jats:italic>K</jats:italic>\n                  <jats:sub>d</jats:sub>\n                  ) near 100 nM. The hit rate and highest affinity design each surpassed the current state-of-the-art method by 5- and 70-fold, respectively. We further show that LASErMPNN can improve upon its own designs in a manner resembling chain-of-thought reasoning. Without experimental input, LASErMPNN suggested two mutations that increased affinity by over two orders of magnitude (\n                  <jats:italic>K</jats:italic>\n                  <jats:sub>d</jats:sub>\n                  = 1.2 ± 0.2 nM). Designs were selective, structurally accurate, and achieved their intended purpose to protect the drug from hydrolysis. Our work describes a recipe for using neural networks to automate the design of high affinity small-molecule binding proteins, which should have wide application in the creation of novel drug-delivery vehicles, antidotes, sensors, and enzymes.\n                </jats:p>","journal":null,"year":null,"id":653519,"datarank":0.32958368660043297,"base_score":2.1972245773362196,"endowment":2.1972245773362196,"self_citation_contribution":0.32958368660043297,"citation_network_contribution":0.0,"self_endowment_contribution":0.32958368660043297,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":8,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1705184,"name":"Kaia Slaw","orcid":"0009-0000-2322-1373","position":1,"is_corresponding":false},{"id":258384,"name":"Nicholas F. Polizzi","orcid":"0000-0002-1779-8907","position":2,"is_corresponding":false},{"id":1325446,"name":"Benjamin Fry","orcid":"0000-0003-0981-9605","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Zero-shot design of drug-binding proteins via neural selection-expansion","abstract":"<jats:title>Abstract</jats:title>\n                <jats:p>\n                  Computational design of molecular recognition remains challenging despite advances in deep learning\n                  <jats:sup>1–3</jats:sup>\n                  . The design of proteins that bind to small molecules has been particularly difficult because it requires simultaneous optimization of protein sequence, protein structure, and ligand conformation\n                  <jats:sup>1–7</jats:sup>\n                  . Despite their promise, current deep-learning algorithms have struggled to navigate this landscape, precluding the zero- or few-shot design of binders. Here we show that the combination of two neural networks in an iterative design algorithm can create small-molecule binding proteins from scratch with high accuracy. To optimize a design in the joint distribution of sequence, structure, and ligand conformation, we use a pair of neural networks that were trained on reciprocal tasks. We train and use a graph neural network, LASErMPNN, to design protein sequence given protein−ligand co-structure, and we use RoseTTAFold-All Atom\n                  <jats:sup>8</jats:sup>\n                  (RFAA) to predict protein−ligand co-structure given protein sequence. We iteratively apply these two networks to design proteins that bind the drug, exatecan, a topoisomerase I inhibitor that is prone to inactivation by hydrolysis\n                  <jats:sup>9</jats:sup>\n                  . Each of four experimentally tested designs bound the drug, with the lowest dissociation constant (\n                  <jats:italic>K</jats:italic>\n                  <jats:sub>d</jats:sub>\n                  ) near 100 nM. The hit rate and highest affinity design each surpassed the current state-of-the-art method by 5- and 70-fold, respectively. We further show that LASErMPNN can improve upon its own designs in a manner resembling chain-of-thought reasoning. Without experimental input, LASErMPNN suggested two mutations that increased affinity by over two orders of magnitude (\n                  <jats:italic>K</jats:italic>\n                  <jats:sub>d</jats:sub>\n                  = 1.2 ± 0.2 nM). Designs were selective, structurally accurate, and achieved their intended purpose to protect the drug from hydrolysis. Our work describes a recipe for using neural networks to automate the design of high affinity small-molecule binding proteins, which should have wide application in the creation of novel drug-delivery vehicles, antidotes, sensors, and enzymes.\n                </jats:p>","is_dataset_classified":null,"base_score":0.0,"endowment":0.0,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":null,"pmcid":null,"openalex_id":null,"authors":[],"funders":[{"funder_name":"","grant_id":"R00GM135519","title":null},{"funder_name":"","grant_id":"Innovation Research Fund","title":null},{"funder_name":"","grant_id":"Graduate Research Fellowship Program","title":null}],"total_grants":3,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[],"oa_status":"green","license":"cc-by","oa_locations":[{"url":"https://www.biorxiv.org/content/biorxiv/early/2025/04/25/2025.04.22.649862.full.pdf","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.1101/2025.04.22.649862","host_type":"publisher"}],"fields_of_study":[],"mesh_terms":[],"keywords":[],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-10T22:20:47.119742Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}