02937nas a2200613 4500008004100000022001400041245012600055210006900181260001500250300001500265490000700280520120500287653001801492653001101510653001301521653001101534653002101545653000901566653001401575653002001589653001301609653001501622653001801637100001301655700002401668700001201692700001701704700001601721700001701737700001601754700001601770700001201786700001401798700001601812700001501828700002101843700002101864700002201885700001501907700002301922700002101945700002101966700001601987700001602003700002102019700002502040700001902065700001702084700001402101700001802115700002602133710003102159856013302190 2020 eng d a2405-472000aCommunity Assessment of the Predictability of Cancer Protein and Phosphoprotein Levels from Genomics and Transcriptomics.0 aCommunity Assessment of the Predictability of Cancer Protein and c2020 08 26 a186-195.e90 v113 a
Cancer is driven by genomic alterations, but the processes causing this disease are largely performed by proteins. However, proteins are harder and more expensive to measure than genes and transcripts. To catalyze developments of methods to infer protein levels from other omics measurements, we leveraged crowdsourcing via the NCI-CPTAC DREAM proteogenomic challenge. We asked for methods to predict protein and phosphorylation levels from genomic and transcriptomic data in cancer patients. The best performance was achieved by an ensemble of models, including as predictors transcript level of the corresponding genes, interaction between genes, conservation across tumor types, and phosphosite proximity for phosphorylation prediction. Proteins from metabolic pathways and complexes were the best and worst predicted, respectively. The performance of even the best-performing model was modest, suggesting that many proteins are strongly regulated through translational control and degradation. Our results set a reference for the limitations of computational inference in proteogenomics. A record of this paper's transparent peer review process is included in the Supplemental Information.
10aCrowdsourcing10aFemale10aGenomics10aHumans10aMachine Learning10aMale10aNeoplasms10aPhosphoproteins10aProteins10aProteomics10aTranscriptome1 aYang, Mi1 aPetralia, Francesca1 aLi, Zhi1 aLi, Hongyang1 aMa, Weiping1 aSong, Xiaoyu1 aKim, Sunkyu1 aLee, Heewon1 aYu, Han1 aLee, Bora1 aBae, Seohui1 aHeo, Eunji1 aKaczmarczyk, Jan1 aStępniak, Piotr1 aWarchoł, Michał1 aYu, Thomas1 aCalinawan, Anna, P1 aBoutros, Paul, C1 aPayne, Samuel, H1 aReva, Boris1 aBoja, Emily1 aRodriguez, Henry1 aStolovitzky, Gustavo1 aGuan, Yuanfang1 aKang, Jaewoo1 aWang, Pei1 aFenyö, David1 aSaez-Rodriguez, Julio1 aNCI-CPTAC-DREAM Consortium uhttps://www.clinbioinfosspa.es/content/community-assessment-predictability-cancer-protein-and-phosphoprotein-levels-genomics-and03269nas a2200685 4500008004100000022001400041245011800055210006900173260001500242300000900257490000700266520115400273653001901427653005101446653001701497653002201514653002101536653002601557653002201583653002001605653003001625653001901655653001301674653001101687653003101698653001301729653001401742653002101756653003501777653004101812653002201853100002301875700001701898700001901915700001801934700002301952700001901975700001501994700001702009700001602026700002002042700001602062700002402078700001902102700001802121700002402139700001802163700002502181700001702206700001902223700002302242700002702265700002002292700002502312700002002337700002102357700002602378710005702404856012202461 2019 eng d a2041-172300aCommunity assessment to advance computational prediction of cancer drug combinations in a pharmacogenomic screen.0 aCommunity assessment to advance computational prediction of canc c2019 06 17 a26740 v103 aThe effectiveness of most cancer targeted therapies is short-lived. Tumors often develop resistance that might be overcome with drug combinations. However, the number of possible combinations is vast, necessitating data-driven approaches to find optimal patient-specific treatments. Here we report AstraZeneca's large drug combination dataset, consisting of 11,576 experiments from 910 combinations across 85 molecularly characterized cancer cell lines, and results of a DREAM Challenge to evaluate computational strategies for predicting synergistic drug pairs and biomarkers. 160 teams participated to provide a comprehensive methodological development and benchmarking. Winning methods incorporate prior knowledge of drug-target interactions. Synergy is predicted with an accuracy matching biological replicates for >60% of combinations. However, 20% of drug combinations are poorly predicted by all methods. Genomic rationale for synergy predictions are identified, including ADAM17 inhibitor antagonism when combined with PIK3CB/D inhibition contrasting to synergy when combined with other PI3K-pathway inhibitors in PIK3CA mutant cells.
10aADAM17 Protein10aAntineoplastic Combined Chemotherapy Protocols10aBenchmarking10aBiomarkers, Tumor10aCell Line, Tumor10aComputational Biology10aDatasets as Topic10aDrug Antagonism10aDrug Resistance, Neoplasm10aDrug Synergism10aGenomics10aHumans10aMolecular Targeted Therapy10amutation10aNeoplasms10apharmacogenetics10aPhosphatidylinositol 3-Kinases10aPhosphoinositide-3 Kinase Inhibitors10aTreatment Outcome1 aMenden, Michael, P1 aWang, Dennis1 aMason, Mike, J1 aSzalai, Bence1 aBulusu, Krishna, C1 aGuan, Yuanfang1 aYu, Thomas1 aKang, Jaewoo1 aJeon, Minji1 aWolfinger, Russ1 aNguyen, Tin1 aZaslavskiy, Mikhail1 aJang, In, Sock1 aGhazoui, Zara1 aAhsen, Mehmet, Eren1 aVogel, Robert1 aNeto, Elias, Chaibub1 aNorman, Thea1 aK Y Tang, Eric1 aGarnett, Mathew, J1 aDi Veroli, Giovanni, Y1 aFawell, Stephen1 aStolovitzky, Gustavo1 aGuinney, Justin1 aDry, Jonathan, R1 aSaez-Rodriguez, Julio1 aAstraZeneca-Sanger Drug Combination DREAM Consortium uhttps://www.clinbioinfosspa.es/content/community-assessment-advance-computational-prediction-cancer-drug-combinations