{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:36:44Z","timestamp":1785436604938,"version":"3.56.0"},"reference-count":56,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["#1936791"],"award-info":[{"award-number":["#1936791"]}]},{"name":"National Science Foundation","award":["#1919691"],"award-info":[{"award-number":["#1919691"]}]},{"name":"National Science Foundation","award":["#2107108"],"award-info":[{"award-number":["#2107108"]}]},{"award":["#1936791"],"award-info":[{"award-number":["#1936791"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["#1919691"],"award-info":[{"award-number":["#1919691"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["#2107108"],"award-info":[{"award-number":["#2107108"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"name":"University Research Computing Facility"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biology"],"abstract":"<jats:p>Recently, there has been great interest in AI-based approaches for de novo design of novel drug candidates. However, the generation of useful lead drug candidate compounds requires more than predicting engagement with the desired protein target. Candidate molecules must also be anchored in the real world of medicinal chemistry for their synthesis and modification as well as satisfying multiple drug development-related criteria. Here, we present Nevermore, an AI target-conditioned, database-grounded workflow for prioritizing candidate ligands from large compound libraries. Nevermore uses a geometry-aware protein\u2013ligand affinity oracle to score target-specific binding and perform sparse integer edits in count-based Morgan fingerprint space. Nevermore then retrieves the most structurally similar molecules from public chemical databases. This design enables multi-objective search over predicted affinity and absorption, distribution, metabolism, excretion, and toxicity (ADMET) proxies while keeping all candidates anchored to valid database compounds. We evaluated Nevermore\u2019s performance across three biologically distinct targets: Menin, a protein-interaction target relevant to leukemia; SARS-CoV-2 Mpro, a viral cysteine protease relevant to antiviral discovery; and epidermal growth factor receptor (EGFR), a kinase-superfamily oncology target with extensive experimentally tested compounds. Nevermore retrieved candidate sets with favorable predicted affinity\u2013property trade-offs. These results support database-grounded fingerprint steering as a practical computational strategy for lead prioritization and for generating testable molecular hypotheses, although the prioritized candidates remain predictions, requiring follow-up experimental validation.<\/jats:p>","DOI":"10.3390\/biology15120971","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T03:06:34Z","timestamp":1782875194000},"page":"971","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Nevermore: Target-Conditioned Protein\u2013Ligand Representation Learning for Multi-Objective Lead Optimization with Database-Grounded Retrieval"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9581-5883","authenticated-orcid":false,"given":"Mohammad Saleh","family":"Refahi","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0689-5044","authenticated-orcid":false,"given":"Milad","family":"Toutounchian","sequence":"additional","affiliation":[{"name":"College of Computing & Informatics, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5050-5926","authenticated-orcid":false,"given":"Bahrad A.","family":"Sokhansanj","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3862-4006","authenticated-orcid":false,"given":"Hyunwoo","family":"Yoo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9368-627X","authenticated-orcid":false,"given":"James R.","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5450-0121","authenticated-orcid":false,"given":"Hai-Feng","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1763-5750","authenticated-orcid":false,"given":"Gail L.","family":"Rosen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Passaro, S., Corso, G., Wohlwend, J., Reveiz, M., Thaler, S., Somnath, V.R., Getz, N., Portnoi, T., Roy, J., and Stark, H. (2025). Boltz-2: Towards accurate and efficient binding affinity prediction. bioRxiv.","DOI":"10.1101\/2025.06.14.659707"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"7236","DOI":"10.52202\/068431-0525","article-title":"Tankbind: Trigonometry-aware neural networks for drug-protein binding structure prediction","volume":"35","author":"Lu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/nrd4609","article-title":"An analysis of the attrition of drug candidates from four major pharmaceutical companies","volume":"14","author":"Waring","year":"2015","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41573-022-00633-x","article-title":"The evolving role of investigative toxicology in the pharmaceutical industry","volume":"22","author":"Pognan","year":"2023","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3049","DOI":"10.1016\/j.apsb.2022.02.002","article-title":"Why 90% of clinical drug development fails and how to improve it?","volume":"12","author":"Sun","year":"2022","journal-title":"Acta Pharm. Sin. B"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Aksamit, N., Hou, J., Li, Y., and Ombuki-Berman, B. (2024). Integrating transformers and many-objective optimization for drug design. BMC Bioinform., 25.","DOI":"10.1186\/s12859-024-05822-6"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"btae416","DOI":"10.1093\/bioinformatics\/btae416","article-title":"ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries","volume":"40","author":"Swanson","year":"2024","journal-title":"Bioinformatics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"bbae008","DOI":"10.1093\/bib\/bbae008","article-title":"ChemMORT: An automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization","volume":"25","author":"Yi","year":"2024","journal-title":"Brief. Bioinform."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"17304","DOI":"10.1038\/s41598-021-96812-8","article-title":"Evolutionary design of molecules based on deep learning and a genetic algorithm","volume":"11","author":"Kwon","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2910","DOI":"10.1039\/D5DD00188A","article-title":"Adaptive subspace Bayesian optimization over molecular descriptor libraries for data-efficient chemical design","volume":"4","author":"Sorourifar","year":"2025","journal-title":"Digit. Discov."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"18193","DOI":"10.1021\/acs.est.3c02198","article-title":"Count-based morgan fingerprint: A more efficient and interpretable molecular representation in developing machine learning-based predictive regression models for water contaminants\u2019 activities and properties","volume":"57","author":"Zhong","year":"2023","journal-title":"Environ. Sci. Technol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41573-023-00832-0","article-title":"Integrating QSAR modelling and deep learning in drug discovery: The emergence of deep QSAR","volume":"23","author":"Tropsha","year":"2024","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1038\/s41586-023-05812-3","article-title":"The menin inhibitor revumenib in KMT2A-rearranged or NPM1-mutant leukaemia","volume":"615","author":"Issa","year":"2023","journal-title":"Nature"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"eabo7201","DOI":"10.1126\/science.abo7201","article-title":"Open science discovery of potent noncovalent SARS-CoV-2 main protease inhibitors","volume":"382","author":"Boby","year":"2023","journal-title":"Science"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1126\/science.1099314","article-title":"EGFR mutations in lung cancer: Correlation with clinical response to gefitinib therapy","volume":"304","author":"Paez","year":"2004","journal-title":"Science"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: Deep drug\u2013target binding affinity prediction","volume":"34","author":"Ozkirimli","year":"2018","journal-title":"Bioinformatics"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lee, I., Keum, J., and Nam, H. (2019). DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences. PLoS Comput. Biol., 15.","DOI":"10.1371\/journal.pcbi.1007129"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound\u2013protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1093\/bioinformatics\/btaa880","article-title":"MolTrans: Molecular interaction transformer for drug\u2013target interaction prediction","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: Toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"9431","DOI":"10.1038\/s41467-024-53751-y","article-title":"MolE: A foundation model for molecular graphs using disentangled attention","volume":"15","author":"Nicolaou","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_23","unstructured":"Chithrananda, S., Grand, G., and Ramsundar, B. (2020). ChemBERTa: Large-scale self-supervised pretraining for molecular property prediction. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e2220778120","DOI":"10.1073\/pnas.2220778120","article-title":"Contrastive learning in protein language space predicts interactions between drugs and protein targets","volume":"120","author":"Singh","year":"2023","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_25","unstructured":"Refahi, M., Sokhansanj, B.A., Brown, J.R., and Rosen, G. (2025). Learning to Align Molecules and Proteins: A Geometry-Aware Approach to Binding Affinity. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"vbaf060","DOI":"10.1093\/bioadv\/vbaf060","article-title":"Aggregating residue-level protein language model embeddings with optimal transport","volume":"5","author":"NaderiAlizadeh","year":"2025","journal-title":"Bioinform. Adv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"eads9530","DOI":"10.1126\/science.ads9530","article-title":"Deep contrastive learning enables genome-wide virtual screening","volume":"391","author":"Jia","year":"2026","journal-title":"Science"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"Wei","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","article-title":"Molecular de-novo design through deep reinforcement learning","volume":"9","author":"Olivecrona","year":"2017","journal-title":"J. Cheminform."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"eaap7885","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2018","journal-title":"Sci. Adv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"10752","DOI":"10.1038\/s41598-019-47148-x","article-title":"Optimization of molecules via deep reinforcement learning","volume":"9","author":"Zhou","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3826","DOI":"10.1021\/acs.jcim.4c00234","article-title":"Streamlining computational fragment-based drug discovery through evolutionary optimization informed by ligand-based virtual prescreening","volume":"64","author":"Chandraghatgi","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1021\/acs.jcim.8b00839","article-title":"GuacaMol: Benchmarking models for de novo molecular design","volume":"59","author":"Brown","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_35","unstructured":"Yong, A., Tripp, A., Hosseini-Gerami, L., and Paige, B. (2025). Bayesian optimization for molecules should be pareto-aware. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Choong, J.J., Madhawa, K., and Ozawa, K. (2025). AutoLead: An LLM-Guided Bayesian Optimization Framework for Multi-Objective Lead Optimization. bioRxiv.","DOI":"10.1101\/2025.08.19.671029"},{"key":"ref_37","unstructured":"Rapin, J., and Teytaud, O. (2026, June 17). Nevergrad\u2014A Gradient-Free Optimization Platform. Available online: https:\/\/GitHub.com\/FacebookResearch\/Nevergrad."},{"key":"ref_38","first-page":"3942","article-title":"Film: Visual reasoning with a general conditioning layer","volume":"32","author":"Perez","year":"2018","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_39","unstructured":"Huang, K., Fu, T., Gao, W., Zhao, Y., Roohani, Y., Leskovec, J., Coley, C.W., Xiao, C., Sun, J., and Zitnik, M. (2021). Therapeutics data commons: Machine learning datasets and tasks for drug discovery and development. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"D945","DOI":"10.1093\/nar\/gkw1074","article-title":"The ChEMBL database in 2017","volume":"45","author":"Gaulton","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"ref_41","unstructured":"Wang, E., Schmidgall, S., Jaeger, P.F., Zhang, F., Pilgrim, R., Matias, Y., Barral, J., Fleet, D., and Azizi, S. (2025). Txgemma: Efficient and agentic llms for therapeutics. arXiv."},{"key":"ref_42","unstructured":"Lam, H.T., Sbodio, M.L., Galindo, M.M., Zayats, M., Fernandez-Diaz, R., Valls, V., Picco, G., Ramis, C.B., and Lopez, V. (2023). Otter-Knowledge: Benchmarks of multimodal knowledge graph representation learning from different sources for drug discovery. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive analysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat. Biotechnol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"D198","DOI":"10.1093\/nar\/gkl999","article-title":"BindingDB: A web-accessible database of experimentally determined protein\u2013ligand binding affinities","volume":"35","author":"Liu","year":"2007","journal-title":"Nucleic Acids Res."},{"key":"ref_45","unstructured":"Zitnik, M., Sosic, R., and Leskovec, J. (2026, June 17). BioSNAP Datasets: Stanford Biomedical Network Dataset Collection. Available online: http:\/\/snap.stanford.edu\/biodata."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.tibs.2013.05.005","article-title":"Menin: A scaffold protein that controls gene expression and cell signaling","volume":"38","author":"Matkar","year":"2013","journal-title":"Trends Biochem. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"101118","DOI":"10.1016\/j.currproblcancer.2024.101118","article-title":"Menin signaling and therapeutic targeting in breast cancer","volume":"51","author":"Liu","year":"2024","journal-title":"Curr. Probl. Cancer"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1038\/s41586-020-2223-y","article-title":"Structure of Mpro from SARS-CoV-2 and discovery of its inhibitors","volume":"582","author":"Jin","year":"2020","journal-title":"Nature"},{"key":"ref_49","unstructured":"National Center for Biotechnology Information (2025, December 28). PubChem Compound Summary for CID 132212657, Revumenib. PubChem, Available online: https:\/\/pubchem.ncbi.nlm.nih.gov\/compound\/132212657."},{"key":"ref_50","unstructured":"National Center for Biotechnology Information (2025, December 28). PubChem Compound Summary for CID 5475158, Cinanserin. PubChem, Available online: https:\/\/pubchem.ncbi.nlm.nih.gov\/compound\/5475158."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"2785","DOI":"10.1002\/jcc.21256","article-title":"AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility","volume":"30","author":"Morris","year":"2009","journal-title":"J. Comput. Chem."},{"key":"ref_52","first-page":"4","article-title":"Rdkit documentation","volume":"1","author":"Landrum","year":"2013","journal-title":"Release"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/jcc.21334","article-title":"AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading","volume":"31","author":"Trott","year":"2010","journal-title":"J. Comput. Chem."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1002\/pro.3943","article-title":"UCSF ChimeraX: Structure visualization for researchers, educators, and developers","volume":"30","author":"Pettersen","year":"2021","journal-title":"Protein Sci."},{"key":"ref_55","unstructured":"National Center for Biotechnology Information (2026, May 12). PubChem Protein Summary for Protein P00533, Epidermal Growth Factor Receptor (Human), Available online: https:\/\/pubchem.ncbi.nlm.nih.gov\/protein\/P00533."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1186\/s13321-025-01074-5","article-title":"Reverse engineering molecules from fingerprints through deterministic enumeration and generative models","volume":"17","author":"Meyer","year":"2025","journal-title":"J. Cheminform."}],"container-title":["Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-7737\/15\/12\/971\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:17:20Z","timestamp":1783052240000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-7737\/15\/12\/971"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,21]]},"references-count":56,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["biology15120971"],"URL":"https:\/\/doi.org\/10.3390\/biology15120971","relation":{},"ISSN":["2079-7737"],"issn-type":[{"value":"2079-7737","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,21]]}}}