Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer / V. Ravanmehr, H. Blau, L. Cappelletti, T. Fontana, L. Carmody, B. Coleman, J. George, J. Reese, M. Joachimiak, G. Bocci, P. Hansen, C. Bult, J. Rueter, E. Casiraghi, G. Valentini, C. Mungall, T.I. Oprea, P.N. Robinson. - In: NAR GENOMICS AND BIOINFORMATICS. - ISSN 2631-9268. - 3:4(2021 Dec 04), pp. lqab113.1-lqab113.13. [10.1093/nargab/lqab113]

Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer

L. Cappelletti
Software
;
E. Casiraghi
Methodology
;
G. Valentini
Methodology
;
2021

Abstract

Inhibiting protein kinases (PKs) that cause cancers has been an important topic in cancer therapy for years. So far, almost 8% of >530 PKs have been targeted by FDA-approved medications, and around 150 protein kinase inhibitors (PKIs) have been tested in clinical trials. We present an approach based on natural language processing and machine learning to investigate the relations between PKs and cancers, predicting PKs whose inhibition would be efficacious to treat a certain cancer. Our approach represents PKs and cancers as semantically meaningful 100-dimensional vectors based on word and concept neighborhoods in PubMed abstracts. We use information about phase I-IV trials in ClinicalTrials.gov to construct a training set for random forest classification. Our results with historical data show that associations between PKs and specific cancers can be predicted years in advance with good accuracy. Our tool can be used to predict the relevance of inhibiting PKs for specific cancers and to support the design of well-focused clinical trials to discover novel PKIs for cancer therapy.
word embedding; supervised learning; kinases; cancer; bioinformatics
Settore INF/01 - Informatica
Settore BIO/11 - Biologia Molecolare
Article (author)
File in questo prodotto:
File Dimensione Formato  
PubMed2Vec-kinases-cancer-NAR-published.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Publisher's version/PDF
Dimensione 1.23 MB
Formato Adobe PDF
1.23 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

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/2434/887943
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact