High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on‑demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high‑quality X‑ray crystal structures, or manual cherry‑picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug‑like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small‑molecule drug discovery.

null, n., Wallach, I., Bernard, D., Nguyen, K., Ho, G., Morrison, A., et al. (2024). AI is a viable alternative to high throughput screening: a 318-target study. SCIENTIFIC REPORTS, 14(1), 1-16 [10.1038/s41598-024-54655-z].

AI is a viable alternative to high throughput screening: a 318-target study

Porcelli, Anna Maria;Lama, Eleonora;Gasparre, Giuseppe;Iommarini, Luisa;De Luise, Monica;
2024

Abstract

High throughput screening (HTS) is routinely used to identify bioactive small molecules. This requires physical compounds, which limits coverage of accessible chemical space. Computational approaches combined with vast on‑demand chemical libraries can access far greater chemical space, provided that the predictive accuracy is sufficient to identify useful molecules. Through the largest and most diverse virtual HTS campaign reported to date, comprising 318 individual projects, we demonstrate that our AtomNet® convolutional neural network successfully finds novel hits across every major therapeutic area and protein class. We address historical limitations of computational screening by demonstrating success for target proteins without known binders, high‑quality X‑ray crystal structures, or manual cherry‑picking of compounds. We show that the molecules selected by the AtomNet® model are novel drug‑like scaffolds rather than minor modifications to known bioactive compounds. Our empirical results suggest that computational methods can substantially replace HTS as the first step of small‑molecule drug discovery.
2024
null, n., Wallach, I., Bernard, D., Nguyen, K., Ho, G., Morrison, A., et al. (2024). AI is a viable alternative to high throughput screening: a 318-target study. SCIENTIFIC REPORTS, 14(1), 1-16 [10.1038/s41598-024-54655-z].
null, null; Wallach, Izhar; Bernard, Denzil; Nguyen, Kong; Ho, Gregory; Morrison, Adrian; Stecula, Adrian; Rosnik, Andreana; O’Sullivan, Ann Marie; Da...espandi
File in questo prodotto:
File Dimensione Formato  
s41598-024-54655-z.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 1.58 MB
Formato Adobe PDF
1.58 MB Adobe PDF Visualizza/Apri
41598_2024_54655_MOESM1_ESM.zip

accesso aperto

Tipo: File Supplementare
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 24.95 MB
Formato Zip File
24.95 MB Zip File Visualizza/Apri
41598_2024_54655_MOESM2_ESM.pdf

accesso aperto

Tipo: File Supplementare
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 10.55 MB
Formato Adobe PDF
10.55 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/966963
Citazioni
  • ???jsp.display-item.citation.pmc??? 5
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 17
social impact