Transforming cancer drug discovery with Big Data and AI

Workman, Paul; Antolín, Albert A.; Al‐Lazikani, Bissan

doi:10.1080/17460441.2019.1637414

Cited by 26 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although a large number of cancer cell lines were used in their study, the authors along with other researchers pointed out that more further studies were needed to construct a complete map. Workman along with other researchers also stated that cooperation among countries was crucial to a complete cancer dependency map ( 7 ). In this study it was also concluded that the best way to predict this dependence was to study gene activity patterns instead of focusing on whether a single gene was defective, which surprised us remarkably ( 8 ).…”

Section: Introductionmentioning

confidence: 99%

Derivation and Validation of a Prognostic Model for Cancer Dependency Genes Based on CRISPR-Cas9 in Gastric Adenocarcinoma

Zhou

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

As a CRISPR-Cas9-based tool to help scientists to investigate gene functions, Cancer Dependency Map genes (CDMs) include an enormous series of loss-of-function screens based on genome-scale RNAi. These genes participate in regulating survival and growth of tumor cells, which suggests their potential as novel therapeutic targets for malignant tumors. By far, studies on the roles of CDMs in gastric adenocarcinoma (GA) are scarce and only a small fraction of CDMs have been investigated. In the present study, datasets of the differentially expressed genes (DEGs) were extracted from the TCGA-based (The Cancer Genome Atlas) GEPIA database, from which differentially expressed CDMs were determined. Functions and prognostic significance of these verified CDMs were evaluated using a series of bioinformatics methods. In all, 246 differentially expressed CDMs were determined, with 147 upregulated and 99 downregulated. Ten CDMs (ALG8, ATRIP, CCT6A, CFDP1, CINP, MED18, METTL1, ORC1, TANGO6, and PWP2) were identified to be prognosis-related and subsequently a prognosis model based on these ten CDMs was constructed. In comparison with that of patients with low risk in TCGA training, testing and GSE84437 cohort, overall survival (OS) of patients with high risk was significantly worse. It was then subsequently demonstrated that for this prognostic model, area under the ROC (receiver operating characteristic) curve was 0.771 and 0.697 for TCGA training and testing cohort respectively, justifying its reliability in predicting survival of GA patients. With the ten identified CDMs, we then constructed a nomogram to generate a clinically practical model. The regulatory networks and functions of the ten CDMs were then explored, the results of which demonstrated that as the gene significantly associated with survival of GA patients and Hazard ratio (HR), PWP2 promoted in-vitro invasion and migration of GA cell lines through the EMT signaling pathway. Therefore, in conclusion, the present study might help understand the prognostic significance and molecular functions of CDMs in GA.

show abstract

Section: Introductionmentioning

confidence: 99%

Derivation and Validation of a Prognostic Model for Cancer Dependency Genes Based on CRISPR-Cas9 in Gastric Adenocarcinoma

Zhou

et al. 2021

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Overall, the sensitivity and precision between these three computational methods was significantly different, despite their sharing of the same underlying principles. We have previously argued that the lack of data completeness, and the strong biases toward certain kinases, could contribute to explain the low precision of in silico prediction of polypharmacology (Antolin et al, 2020;Mestres et al, 2008;Workman et al, 2019). In this particular example, CLARITY's integration of several methods appears to be advantageous.…”

Section: In Vitro Kinome Activity Profiling Uncovers Differential Polypharmacology Between Ganetespib and Luminespibmentioning

confidence: 99%

Evolution of kinase polypharmacology across HSP90 drug discovery

Antolín

Clarke

Collins

et al. 2021

Cell Chemical Biology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Author Manuscript Published OnlineFirst on September 22, 2021; DOI: 10.1158/2159-8290.CD-20-1201 scientific data available to researchers is to use artificial intelligence (AI) methods, which are only recently being harnessed for cancer drug discovery (20).…”

Section: Introductionmentioning

confidence: 99%

Repurposing Vandetanib plus Everolimus for the Treatment ofACVR1-Mutant Diffuse Intrinsic Pontine Glioma

Carvalho

Richardson²,

Olaciregui

et al. 2021

Cancer Discovery

View full text Add to dashboard Cite

Somatic mutations in ACVR1 are found in a quarter of children with diffuse intrinsic pontine glioma (DIPG), however there are no ACVR1 inhibitors licensed for the disease. Using an Artificial Intelligence-based platform to search for approved compounds for ACVR1-mutant DIPG, the combination of vandetanib and everolimus was identified as a possible therapeutic approach. Vandetanib, an inhibitor of VEGFR/RET/EGFR, was found to target ACVR1 (Kd=150nM) and reduce DIPG cell viability in vitro, but has limited ability to cross the bloodbrain-barrier. In addition to mTOR, everolimus inhibits ABCG2 (BCRP) and ABCB1 (P-gp) transporters, and was synergistic in DIPG cells when combined with vandetanib in vitro. This combination is well-tolerated in vivo, and significantly extended survival and reduced tumor burden in an orthotopic ACVR1-mutant patient-derived DIPG xenograft model. Four patients with ACVR1-mutant DIPG were treated with vandetanib plus mTOR inhibitor, informing the dosing and toxicity profile of this combination for future clinical studies. STATEMENT OF SIGNIFICANCE25% patients with the incurable brainstem tumour DIPG harbour somatic activating mutations in ACVR1, however there are no approved drugs targeting the receptor. Using Artificial Intelligence, we identify and validate the novel combination of vandetanib and everolimus in these children based upon both signalling and pharmacokinetic synergies, experimentally and clinically.Research.

show abstract

Transforming cancer drug discovery with Big Data and AI

Cited by 26 publications

References 44 publications

Derivation and Validation of a Prognostic Model for Cancer Dependency Genes Based on CRISPR-Cas9 in Gastric Adenocarcinoma

Derivation and Validation of a Prognostic Model for Cancer Dependency Genes Based on CRISPR-Cas9 in Gastric Adenocarcinoma

Evolution of kinase polypharmacology across HSP90 drug discovery

Repurposing Vandetanib plus Everolimus for the Treatment ofACVR1-Mutant Diffuse Intrinsic Pontine Glioma

Contact Info

Product

Resources

About