Redefining druggable targets with artificial intelligence

Karen Akinsanya; Mohammed AlQuraishi; Ann Boija; John Chodera; Anna Cichońska; Marzyeh Ghassemi; Martha Head; Wengong Jin; Warren A. Kibbe; Nevan Krogan; Michael V. LeVine; John Moult; Lynda Stuart; Georgia Tourassi; James Zou; Regina Barzilay; Olivier Elemento

doi:10.1038/s41587-025-02770-1

Redefining druggable targets with artificial intelligence

Karen Akinsanya
, Mohammed AlQuraishi
, Ann Boija
, John Chodera
, Anna Cichońska
, Marzyeh Ghassemi
, Martha Head
, Wengong Jin
, Warren A. Kibbe
, Nevan Krogan
, Michael V. LeVine
, John Moult
, Lynda Stuart
, Georgia Tourassi
, James Zou
, Regina Barzilay
, Olivier Elemento

Research output: Contribution to journal › Comment/debate

1 Scopus citations

Abstract

A vast landscape of ‘undruggable’ cancer targets remains beyond the reach of conventional therapeutic agents. Recent advances in artificial intelligence (AI), however, are challenging this paradigm. Synthesizing insights from a Cancer Moonshot workshop, we argue that systemically addressing the undruggable target space with AI requires a new conceptual framework. We highlight the failure of current target taxonomies and the need for benchmarking datasets, and re-evaluate clinical validation for novel AI-driven modalities.

Original language	English
Pages (from-to)	1416-1418
Number of pages	3
Journal	Nature Biotechnology
Volume	43
Issue number	9
DOIs	https://doi.org/10.1038/s41587-025-02770-1
State	Published - Sep 2025
Externally published	Yes

Access to Document

10.1038/s41587-025-02770-1

Cite this

@article{6cd0025820d241f59e695cdc39e93ba2,

title = "Redefining druggable targets with artificial intelligence",

abstract = "A vast landscape of {\textquoteleft}undruggable{\textquoteright} cancer targets remains beyond the reach of conventional therapeutic agents. Recent advances in artificial intelligence (AI), however, are challenging this paradigm. Synthesizing insights from a Cancer Moonshot workshop, we argue that systemically addressing the undruggable target space with AI requires a new conceptual framework. We highlight the failure of current target taxonomies and the need for benchmarking datasets, and re-evaluate clinical validation for novel AI-driven modalities.",

author = "Karen Akinsanya and Mohammed AlQuraishi and Ann Boija and John Chodera and Anna Cicho{\'n}ska and Marzyeh Ghassemi and Martha Head and Wengong Jin and Kibbe, \{Warren A.\} and Nevan Krogan and LeVine, \{Michael V.\} and John Moult and Lynda Stuart and Georgia Tourassi and James Zou and Regina Barzilay and Olivier Elemento",

note = "Publisher Copyright: {\textcopyright} Springer Nature America, Inc. 2025.",

year = "2025",

month = sep,

doi = "10.1038/s41587-025-02770-1",

language = "English",

volume = "43",

pages = "1416--1418",

journal = "Nature Biotechnology",

issn = "1087-0156",

publisher = "Nature Research",

number = "9",

}

TY - JOUR

T1 - Redefining druggable targets with artificial intelligence

AU - Akinsanya, Karen

AU - AlQuraishi, Mohammed

AU - Boija, Ann

AU - Chodera, John

AU - Cichońska, Anna

AU - Ghassemi, Marzyeh

AU - Head, Martha

AU - Jin, Wengong

AU - Kibbe, Warren A.

AU - Krogan, Nevan

AU - LeVine, Michael V.

AU - Moult, John

AU - Stuart, Lynda

AU - Tourassi, Georgia

AU - Zou, James

AU - Barzilay, Regina

AU - Elemento, Olivier

PY - 2025/9

Y1 - 2025/9

N2 - A vast landscape of ‘undruggable’ cancer targets remains beyond the reach of conventional therapeutic agents. Recent advances in artificial intelligence (AI), however, are challenging this paradigm. Synthesizing insights from a Cancer Moonshot workshop, we argue that systemically addressing the undruggable target space with AI requires a new conceptual framework. We highlight the failure of current target taxonomies and the need for benchmarking datasets, and re-evaluate clinical validation for novel AI-driven modalities.

AB - A vast landscape of ‘undruggable’ cancer targets remains beyond the reach of conventional therapeutic agents. Recent advances in artificial intelligence (AI), however, are challenging this paradigm. Synthesizing insights from a Cancer Moonshot workshop, we argue that systemically addressing the undruggable target space with AI requires a new conceptual framework. We highlight the failure of current target taxonomies and the need for benchmarking datasets, and re-evaluate clinical validation for novel AI-driven modalities.

UR - https://www.scopus.com/pages/publications/105013800469

U2 - 10.1038/s41587-025-02770-1

DO - 10.1038/s41587-025-02770-1

M3 - Comment/debate

C2 - 40830262

AN - SCOPUS:105013800469

SN - 1087-0156

VL - 43

SP - 1416

EP - 1418

JO - Nature Biotechnology

JF - Nature Biotechnology

IS - 9

ER -

Redefining druggable targets with artificial intelligence

Abstract

Access to Document

Fingerprint

Cite this