{
  "abstract": "Small-molecule drug discovery requires navigating enormous chemical space to identify candidates that are simultaneously potent, selective, synthetically accessible, and acceptable across pharmacokinetic and safety profiles; modern generative AI extends a long computational medicinal chemistry lineage that began with QSAR, pharmacophore modeling, and early structure-based de novo design. This survey focuses primarily on developments from 2017 to 2025, with the literature updated through 31 January 2026. Using a medicinal-chemistry lens, it first establishes the shared machinery of the field: molecular representations such as SMILES, SELFIES, graphs, fingerprints, three-dimensional coordinates, voxels, and latent vectors; commonly used datasets and benchmarks; and graph neural network encoders, including message-passing, directional, and equivariant architectures. We compare five principal generative mechanisms—autoregressive models, variational autoencoders, generative adversarial networks, normalizing flows, and diffusion models—together with reinforcement learning as a major goal-directed optimization framework. Across these approaches, we show that current methods offer complementary rather than interchangeable trade-offs, and we highlight recurring challenges, including validity versus synthesizability, limited prospective experimental validation, mode collapse and diversity loss, stereochemical and physical realism in three-dimensional design, computational cost, data scarcity, and the emerging convergence toward scaffold-conditioned generation, hybrid architectures, developability-aware optimization, and molecular foundation models.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Medicinal Chemistry, Faculty of Pharmacy",
    "Tehran University of Medical Sciences",
    "Faculty IV–Electrical Engineering and Computer Science",
    "Technische Universität Berlin",
    "Department of Mathematical Sciences",
    "Sharif University of Technology",
    "Department of Management, Science and Technology",
    "Amirkabir University of Technology (Tehran Polytechnic)",
    "Department of Computer Engineering",
    "Department of Electrical Engineering",
    "Department of Computer Science",
    "Missouri University of Science and Technology",
    "Department of Medicinal Chemistry, School of Pharmacy",
    "Mashhad University of Medical Sciences",
    "School of Electrical and Computer Engineering",
    "University College of Engineering, University of Tehran",
    "Department of Occupational Health Engineering, School of Health",
    "Semnan University of Medical Sciences",
    "Electronics Research Institute",
    "The Alan Turing Institute",
    "Computer Science, School of Physical and Digital Sciences, Faculty of Science and Engineering",
    "University of Hull"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 20,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Houman Kazemzadeh",
      "orcid": "0000-0002-3491-0892"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Kiarash Mokhtari"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Seyed Reza Tavakoli"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Nazanin Mirzaei"
    },
    {
      "affs": [
        6,
        7
      ],
      "name": "Ali Reza Keivanimehr"
    },
    {
      "affs": [
        8,
        5
      ],
      "name": "Shayan Majidifar"
    },
    {
      "affs": [
        9,
        5
      ],
      "name": "Ali Behrad"
    },
    {
      "affs": [
        10,
        11
      ],
      "name": "Farbod Davoodi"
    },
    {
      "affs": [
        12,
        13
      ],
      "name": "Sina Khosravi"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Behdad Alikhani"
    },
    {
      "affs": [
        8,
        5
      ],
      "name": "Ali Sabzi"
    },
    {
      "affs": [
        8,
        5
      ],
      "name": "Parham Abed Azad"
    },
    {
      "affs": [
        14,
        15
      ],
      "name": "Arshia Abolghasemi"
    },
    {
      "affs": [
        16,
        17
      ],
      "name": "Afshin Cheraghzade"
    },
    {
      "affs": [
        18,
        5
      ],
      "name": "Siavash Ahmadi"
    },
    {
      "affs": [
        9,
        5
      ],
      "name": "Babak Khalaj"
    },
    {
      "affs": [
        8,
        5
      ],
      "name": "Mohammad Hossein Rohban"
    },
    {
      "affs": [
        19
      ],
      "name": "Gholamali Aminian"
    },
    {
      "name": "Ali Baheri"
    },
    {
      "affs": [
        20,
        21
      ],
      "name": "Koorosh Aslansefat",
      "orcid": "0000-0001-9318-8177"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3s1sqmd488xbs.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008163/v1",
  "fulltext_url": null,
  "id": "3s1sqmd488xbs",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008163/v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204961973",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008163/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/3s1sqmd488xbs.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008163",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008163/v3"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "From Computational Chemistry to Generative Models: A Survey of AI-Driven Small-Molecule Drug Discovery",
  "title_text": "From Computational Chemistry to Generative Models: A Survey of AI-Driven Small-Molecule Drug Discovery",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:19Z",
  "url": "https://research.draconitic.com/paper/3s1sqmd488xbs",
  "venue": "ChemRxiv",
  "versions": []
}