Predicting and characterizing a cancer dependency map of tumors with deep learning
Open accessAbstract
A novel deep learning method links in vitro CRISPR screens to the context of cancer genomics and translates to individual tumors.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The pretrain-and-finetune framework has shown effectiveness in computer vision learning, neural language processing, and biomedical learning for prognosis prediction and cancer dependency prediction.
“The pretrain-and-finetune framework has shown its effectiveness in computer vision learning, neural language processing, and biomedical learning for prognosis prediction [179] and cancer dependency prediction [180].”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [180]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1× · see citing works
“We optimized the model by an Adam optimizer (66) with a loss function of MSE.”
MethodHallmarks of Cancer: The Next Generation
Hanahan, D., & Weinberg, R. A. (2011) · Cell · doi:10.1016/j.cell.2011.02.013 · Cited by 66,590 · cited 1× · see citing works
“Mitochondrial dysfunction is a hallmark of cancer (48).”
BackgroundSubramanian, A., Tamayo, P., Mootha, V. K., Mukherjee, S., Ebert, B. L., Gillette, M. A., Paulovich, A., Pomeroy, S. L., Golub, T. R., Lander, E. S., et al. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0506580102 · Cited by 53,625 · see citing works
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1× · see citing works
“14 of 17 not pretrained and randomly initialized by the He’s uniform distribution (68).”
MethodThe cancer genome atlas pan-cancer analysis project
The Cancer Genome Atlas Research Network, Weinstein, J. N., Collisson, E. A., Mills, G. B., Shaw, K. R. M., Ozenberger, B. A., Ellrott, K., Shmulevich, I., Sander, C., & Stuart, J. M. (2013) · Nature Genetics · doi:10.1038/ng.2764 · Cited by 9,092 · see citing works
The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity
Barretina, J., Caponigro, G., Stransky, N., Venkatesan, K., Margolin, A. A., Kim, S., Wilson, C. J., Lehár, J., Kryukov, G. V., Sonkin, D., et al. (2012) · Nature · doi:10.1038/nature11003 · Cited by 7,950 · see citing works
Self-citationMolecular signatures database (MSigDB) 3.0
Liberzon, A., Subramanian, A., Pinchback, R., Thorvaldsdóttir, H., Tamayo, P., & Mesirov, J. P. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr260 · Cited by 7,111 · cited 1× · see citing works
“Each signature was analyzed by GSEA ( 71 ) using a single-sample setting (i.e., ranked by the levels, instead of differences) for the association with hallmark gene sets of the MSigDB ( 24 ).”
MethodTCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data
Colaprico, A., Silva, T. C., Olsen, C., Garofano, L., Cava, C., Garolini, D., Sabedot, T. S., Malta, T. M., Pagnotta, S. M., Castiglioni, I., et al. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv1507 · Cited by 4,137 · cited 2× · see citing works
“Association analyses of gene dependencies with clinical data Clinical data of TCGA were downloaded using the R/Bioconductor package TCGAbiolinks (72).”
MethodDefining a Cancer Dependency Map
Tsherniak, A., Vazquez, F., Montgomery, P. G., Weir, B. A., Kryukov, G., Cowley, G. S., Gill, S., Harrington, W. F., Pantel, S., Krill-Burger, J. M., et al. (2017) · Cell · doi:10.1016/j.cell.2017.06.010 · Cited by 3,276 · see citing works
A census of human cancer genes
Futreal, P. A., Coin, L., Marshall, M., Down, T., Hubbard, T., Wooster, R., Rahman, N., & Stratton, M. R. (2004) · Nature Reviews Cancer · doi:10.1038/nrc1299 · Cited by 3,184 · cited 3× · see citing works
“2) and those listed in the Cancer Gene Census of COSMIC (59).”
BackgroundInfluentialWhy Does Unsupervised Pre-training Help Deep Learning?
Erhan, D., Bengio, Y., Courville, A. C., Manzagol, P.-A., Vincent, P., & Bengio, S. (2010) · International Conference on Artificial Intelligence and Statistics · doi:10.5555/1756006.1756025 · Cited by 2,579 · cited 2× · see citing works
“Our model is established with an emerging “un-supervised pretraining” design of transfer learning ( 22 ) that has lately revolutionized the field of natural language processing but yet adapted to genomic applications.”
MethodA Landscape of Pharmacogenomic Interactions in Cancer
Iorio, F., Knijnenburg, T. A., Vis, D. J., Bignell, G. R., Menden, M. P., Schubert, M., Aben, N., Gonçalves, E., Barthorpe, S., Lightfoot, H., et al. (2016) · Cell · doi:10.1016/j.cell.2016.06.017 · Cited by 2,090 · see citing works
Drugging the undruggable RAS: Mission Possible?
Cox, A. D., Fesik, S. W., Kimmelman, A. C., Luo, J., & Der, C. J. (2014) · Nature Reviews Drug Discovery · doi:10.1038/nrd4389 · Cited by 1,997 · cited 1× · see citing works
“Thus, targeting its SE interactors may be an effective alternative (42).”
BackgroundMeyers, R., Bryan, J. G., McFarland, J. M., Weir, B., Sizemore, A. E., Xu, H., Dharia, N., Montgomery, P. G., Cowley, G., Pantel, S., et al. (2017) · Nature Genetics · doi:10.1101/160861 · Cited by 1,766
Gagnon, D., Bissonnette, P., & Lapointe, J. (2006) · The Journal of General Physiology · doi:10.1085/jgp.200509439 · Cited by 1,731
High-Resolution CRISPR Screens Reveal Fitness Genes and Genotype-Specific Cancer Liabilities.
Hart, T., Chandrashekhar, M., Aregger, M., Steinhart, Z., Brown, K. R., MacLeod, G., Mis, M., Zimmermann, M., Fradet-Turcotte, A., Sun, S., et al. (2015) · Cell · doi:10.1016/j.cell.2015.11.015 · Cited by 1,571 · see citing works
Landscape of Microsatellite Instability Across 39 Cancer Types
Bonneville, R., Krook, M. A., Kautto, E. A., Miya, J., Wing, M. R., Chen, H., Reeser, J. W., Yu, L., & Roychowdhury, S. (2017) · JCO Precision Oncology · doi:10.1200/po.17.00073 · Cited by 1,474 · cited 1× · see citing works
“We collected the MSI status of pan-cancer tumors that were experimentally determined by TCGA [curated by (73)] or predicted by the MANTIS algorithm (74).”
MethodGao, H., Korn, J. M., Ferretti, S., Monahan, J. E., Wang, Y., Singh, M., Zhang, C., Schnell, C., Yang, G., Zhang, Y., et al. (2015) · Nature Medicine · doi:10.1038/nm.3954 · Cited by 1,393 · see citing works
Prioritization of cancer therapeutic targets using CRISPR–Cas9 screens
Behan, F. M., Iorio, F., Picco, G., Gonçalves, E., Beaver, C. M., Migliardi, G., Santos, R., Rao, Y., Sassi, F., Pinnelli, M., et al. (2019) · Nature · doi:10.1038/s41586-019-1103-9 · Cited by 1,338 · cited 5× · see citing works
“Recently, the Cancer Dependency Map (DepMap) projects of the Broad Institute (4–6) and Wellcome Sanger Institute (7) performed genome-wide CRISPR-Cas9 knockout screens in extensive collections of CCLs.”
BackgroundMethodInfluentialIn vivo CRISPR screening identifies Ptpn2 as a cancer immunotherapy target
Manguso, R. T., Pope, H. W., Zimmer, M. D., Brown, F. D., Yates, K. B., Miller, B. C., Collins, N. B., Bi, K., LaFleur, M. W., Juneja, V. R., et al. (2017) · Nature · doi:10.1038/nature23270 · Cited by 1,147 · see citing works
Deep learning-based multi-omics integration robustly predicts survival in liver cancer
Chaudhary, K., Poirion, O. B., Lu, L., & Garmire, L. X. (2018) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-17-0853 · Cited by 1,091 · cited 1× · see citing works
“DL is increasingly being used in genomics research for cancer survival ( 11 , 12 ) and cancer classification ( 13 – 15 ).”
MethodHyperopt: a Python library for model selection and hyperparameter optimization
Bergstra, J., Komer, B., Eliasmith, C., Yamins, D., & Cox, D. D. (2015) · Computational Science & Discovery · doi:10.1088/1749-4699/8/1/014008 · Cited by 1,002 · cited 1× · see citing works
“Hyperas is a grid-searching algorithm that searches a prefixed parameter space by a fixed number of parameter combinations using the Hyperopt optimization library (67).”
Methody-Randomization and Its Variants in QSPR/QSAR
Rücker, C., Rücker, G., & Meringer, M. (2007) · Journal of Chemical Information and Modeling · doi:10.1021/ci700157b · Cited by 978 · see citing works
Genome-wide CRISPR Screen in a Mouse Model of Tumor Growth and Metastasis
Chen, S., Sanjana, N. E., Zheng, K., Shalem, O., Lee, K., Shi, X., Scott, D. A., Song, J. W., Pan, J. Q., Weissleder, R., et al. (2015) · Cell · doi:10.1016/j.cell.2015.02.038 · Cited by 891 · cited 1× · see citing works
“However, such a screen remains challenging and costly and can only be carried out in few mouse models (38, 39).”
BackgroundEnergy Substrate Modulates Mitochondrial Structure and Oxidative Capacity in Cancer Cells
Rossignol, R., Gilkerson, R., Aggeler, R., Yamagata, K., Remington, S., & Capaldi, R. (2004) · Cancer Research · doi:10.1158/0008-5472.can-03-1101 · Cited by 865 · cited 1× · see citing works
“However, activity of the OXPHOS pathway in CCLs can be modulated by the culture medium (49) and confounded by the timing that a CCL is derived relative to chemotherapy.”
BackgroundScalable Open Science Approach for Mutation Calling of Tumor Exomes Using Multiple Genomic Pipelines
Ellrott, K., Bailey, M. H., Saksena, G., Covington, K. R., Kandoth, C., Stewart, C., Hess, J. M., Ma, S., Chiotti, K., McLellan, M. D., et al. (2018) · Cell Systems · doi:10.1016/j.cels.2018.03.002 · Cited by 826 · see citing works
Ideker, T., & Krogan, N. J. (2012) · Molecular Systems Biology · doi:10.1038/msb.2011.99 · Cited by 784 · cited 1× · see citing works
“On the basis of the concepts of differential network biology (56) and genetic coessentiality (57), an interactive tool called FIREWORKS (58) interrogates functional relationships between gene dependencies using context-specific “coessentiality networks” and identifies multiomic signatures associated with differential…”
MethodA community effort to assess and improve drug sensitivity prediction algorithms
Community, N. D., Costello, J. C., Heiser, L. M., Georgii, E., Gönen, M., Menden, M. P., Wang, N. J., Bansal, M., Ammad-ud-din, M., Hintsanen, P., et al. (2014) · Nature Biotechnology · doi:10.1038/nbt.2877 · Cited by 761 · see citing works
McDonald, E. R., de Weck, A., Schlabach, M. R., Billy, E., Mavrakis, K. J., Hoffman, G. R., Belur, D., Castelletti, D., Frias, E., Gampa, K., et al. (2017) · Cell · doi:10.1016/j.cell.2017.07.005 · Cited by 658 · see citing works
A molecular portrait of microsatellite instability across multiple cancers
Cortés‐Ciriano, I., Lee, S., Park, W., Kim, T., & Park, P. J. (2017) · Nature Communications · doi:10.1038/ncomms15180 · Cited by 651 · cited 1× · see citing works
“We collected the MSI status of pan-cancer tumors that were experimentally determined by TCGA [curated by ( 73 )] or predicted by the MANTIS algorithm ( 74 ).”
MethodPredicting drug response and synergy using a deep learning model of human cancer cells
Kuenzi, B. M., Park, J., Fong, S. H., Sanchez, K. S., Lee, J., Kreisberg, J. F., Ma, J., & Ideker, T. (2020) · Cancer Cell · doi:10.1016/j.ccell.2020.09.014 · Cited by 544 · cited 1× · see citing works
“DL methods have also been applied to pharmacogenomics for predicting drug sensitivity and synergy (16, 17).”
MethodOncogenic KRAS signalling in pancreatic cancer
EŞER, S., Schnieke, A., Schneider, G., & Saur, D. (2014) · British Journal of Cancer · doi:10.1038/bjc.2014.215 · Cited by 506 · cited 1× · see citing works
“4C; reviewed in ( 47 )].”
Gillet, J.-P., Calcagno, A. M., Varma, S., Marino, M., Green, L. J., Vora, M. I., Patel, C., Orina, J. N., Eliseeva, T. A., Singal, V., et al. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1111840108 · Cited by 477 · cited 1× · see citing works
“Furthermore, a model trained using merely CCL data may not fully capture tumor-specific contexts such as tumor heterogeneity and its microenvironment (19, 20).”
MethodSynthetic Lethality and Cancer Therapy: Lessons Learned from the Development of PARP Inhibitors
Lord, C. J., Tutt, A. N. J., & Ashworth, A. (2014) · Annual Review of Medicine · doi:10.1146/annurev-med-050913-022545 · Cited by 476 · cited 1× · see citing works
“We examined two of the best-known SE pairs, PTEN mutation/ CHD1 depletion (27) and BRCA1/PARP1 (28); the latter is more synergistic and also categorized as synthetic lethality.”
BackgroundWRN helicase is a synthetic lethal target in microsatellite unstable cancers
Chan, E. M., Shibue, T., McFarland, J. M., Gaeta, B., Ghandi, M., Dumont, N., Gonzalez, A., McPartlan, J. S., Li, T., Zhang, Y., et al. (2019) · Nature · doi:10.1038/s41586-019-1102-x · Cited by 458 · see citing works
Am I ready for CRISPR? A user's guide to genetic screens
Doench, J. G. (2018) · Nature Reviews Genetics · doi:10.1038/nrg.2017.97 · Cited by 452 · see citing works
Functional Genomic Landscape of Human Breast Cancer Drivers, Vulnerabilities, and Resistance
Marcotte, R., Sayad, A., Brown, K. R., Sanchez-Garcia, F., Reimand, J., Haider, M., Virtanen, C., Bradner, J. E., Bader, G. D., Mills, G. B., et al. (2016) · Cell · doi:10.1016/j.cell.2015.11.062 · Cited by 439 · cited 4× · see citing works
“(1), Project Achilles (2), and Project DRIVE (3) completed several high-throughput screenings of hundreds of cancer cell lines (CCLs).”
BackgroundMethodInfluentialUsing deep learning to model the hierarchical structure and function of a cell
Ma, J., Yu, M. K., Fong, S., Ono, K., Sage, E., Demchak, B., Sharan, R., & Ideker, T. (2018) · Nature Methods · doi:10.1038/nmeth.4627 · Cited by 435 · cited 1× · see citing works
“A promising alternative of model construction/interpretation may be the visible neural network ( 54 ) that integrates the GO hierarchy into DL architecture to enable gene set level interpretation.”
BackgroundCancer Cell Lines for Drug Discovery and Development
Wilding, J. L., & Bodmer, W. F. (2014) · Cancer Research · doi:10.1158/0008-5472.can-13-2971 · Cited by 432 · cited 1× · see citing works
“Furthermore, a model trained using merely CCL data may not fully capture tumor-specific contexts such as tumor heterogeneity and its microenvironment (19, 20).”
MethodEGF Receptor Signaling Is Essential for K-Ras Oncogene-Driven Pancreatic Ductal Adenocarcinoma
Navas, C., Hernández-Porras, I., Schuhmacher, A. J., Sibilia, M., Guerra, C., & Barbacid, M. (2012) · Cancer Cell · doi:10.1016/j.ccr.2012.08.001 · Cited by 391 · see citing works
Deckers, M., van Dinther, M., Buijs, J., Que, I., Löwik, C., van der Pluijm, G., & ten Dijke, P. (2006) · Cancer Research · doi:10.1158/0008-5472.can-05-3560 · Cited by 379 · cited 1× · see citing works
“We found that tumors with stronger dependency on SMAD4 had significantly better survival in multiple cancers including BRCA, echoing a previous in vivo study demonstrating knockdown of SMAD4 in BRCA cells effectively inhibits bone metastasis (52).”
BackgroundDempster, J. M., Rossen, J., Kazachkova, M., Pan, J., Kugener, G., Root, D., & Tsherniak, A. (2019) · bioRxiv · doi:10.1101/720243 · Cited by 348 · cited 11× · see citing works
“Gene effect scores estimated and corrected by CERES (4) were used as the measure of gene dependency (5).”
BackgroundMethodInfluentialMcFarland, J. M., Ho, Z. V., Kugener, G., Dempster, J. M., Montgomery, P. G., Bryan, J. G., Krill-Burger, J., Green, T. M., Vazquez, F., Boehm, J., et al. (2018) · Nature Communications · doi:10.1038/s41467-018-06916-5 · Cited by 348 · cited 3× · see citing works
“To further assess the performance on the DepOIs that cannot be simply predicted by the mean value across CCLs (25), we focused on two subsets of highly variable DepOIs: 61 DepOIs with SD in dependency scores of >0.”
BackgroundMethodMitochondria and cancer chemoresistance
Guerra, F., Arbini, A., & Moro, L. (2017) · Biochimica et Biophysica Acta (BBA) - Bioenergetics · doi:10.1016/j.bbabio.2017.01.012 · Cited by 321 · cited 2× · see citing works
“7C), echoing the dependency of chemoresistant cells on the energy metabolism ( 36 , 37 ).”
BackgroundEmerging and evolving concepts in gene essentiality
Rancati, G. I., Moffat, J., Typas, A., & Pavelka, N. (2017) · Nature Reviews Genetics · doi:10.1038/nrg.2017.74 · Cited by 272 · cited 2× · see citing works
“Gene essentiality depends on the genomic context of a CCL (2, 3, 23).”
BackgroundConvolutional neural network models for cancer type prediction based on gene expression
Mostavi, M., Chiu, Y., Huang, Y., & Chen, Y. (2020) · BMC Medical Genomics · doi:10.1186/s12920-020-0677-2 · Cited by 266 · cited 1× · see citing works
“DL is increasingly being used in genomics research for cancer survival ( 11 , 12 ) and cancer classification ( 13 – 15 ).”
MethodSelf-citationAgreement between two large pan-cancer CRISPR-Cas9 gene dependency data sets
Dempster, J. M., Pacini, C., Pantel, S., Behan, F. M., Green, T., Krill-Burger, J. M., Beaver, C., Younger, S. T., Zhivich, V., Najgebauer, H., et al. (2019) · Nature Communications · doi:10.1038/s41467-019-13805-y · Cited by 250 · cited 2× · see citing works
“Because the CRISPR technology is less susceptible to off-target effects (8), these efforts produce the two largest catalogs of gene dependencies with high concordance (9).”
BackgroundPredicting drug response of tumors from integrated genomic profiles by deep neural networks
Chiu, Y., Chen, H.-I. H., Zhang, T., Zhang, S., Gorthi, A., Wang, L., Huang, Y., & Chen, Y. (2019) · BMC Medical Genomics · doi:10.1186/s12920-018-0460-9 · Cited by 227 · cited 2× · see citing works
“The benefits of this strategy were demonstrated in our previous study for predicting drug response ( 16 ).”
MethodSelf-citationSynthetic essentiality of chromatin remodelling factor CHD1 in PTEN-deficient cancer
Zhao, D., Lü, X., Wang, G., Lan, Z., Liao, W., Li, J., Liang, X., Chen, J., Shah, S. R., Shang, X., et al. (2017) · Nature · doi:10.1038/nature21357 · Cited by 220 · see citing works
Smith, I. C. P., Greenside, P., Natoli, T. E., Lahr, D. L., Wadden, D., Tirosh, I., Narayan, R., Root, D. E., Golub, T. R., Subramanian, A., et al. (2017) · PLoS Biology · doi:10.1371/journal.pbio.2003213 · Cited by 188 · see citing works
Ma, J., Fong, S. H., Luo, Y., Bakkenist, C. J., Shen, J. P., Mourragui, S., Wessels, L. F. A., Hafner, M., Sharan, R., Peng, J., et al. (2021) · Nature Cancer · doi:10.1038/s43018-020-00169-2 · Cited by 180 · cited 2× · see citing works
“A recent study used the “few-shot learning” technique of DL to translate high-throughput drug screens of CCLs to individual tumors with small samples ( 21 ).”
BackgroundMethodWerner syndrome helicase is a selective vulnerability of microsatellite instability-high tumor cells
Lieb, S., Blaha-Ostermann, S., Kamper, E., Rippka, J., Schwarz, C., Ehrenhöfer-Wölfer, K., Schlattl, A., Wernitznig, A., Lipp, J., Nagasaka, K., et al. (2019) · eLife · doi:10.7554/elife.43333 · Cited by 151 · cited 1× · see citing works
“Another important dependency previously reported from in vitro and in vivo studies ( 34 , 35 ) was WRN in cancer with high microsatellite instability (MSI).”
BackgroundClassification of Cancer Types Using Graph Convolutional Neural Networks
Ramirez, R., Chiu, Y., Hererra, A., Mostavi, M., Ramirez, J., Chen, Y., Huang, Y., & Jin, Y.-F. (2020) · Frontiers in Physics · doi:10.3389/fphy.2020.00203 · Cited by 136 · see citing works
Self-citationGlobal computational alignment of tumor and cell line transcriptional profiles
Warren, A. C., Chen, Y., Jones, A., Shibue, T., Hahn, W., Boehm, J., Vazquez, F., Tsherniak, A., & McFarland, J. M. (2020) · Nature Communications · doi:10.1038/s41467-020-20294-x · Cited by 134 · cited 1× · see citing works
“Furthermore, methods that align genomic profiles between CCLs and tumors ( 40 , 41 ) may help to reduce the differences between tumor and CCL domains.”
MethodSelf-citationAfatinib restrains K-RAS–driven lung tumorigenesis
Moll, H. P., Pranz, K., Musteanu, M., Grabner, B., Hruschka, N., Mohrherr, J., Aigner, P., Stiedl, P., Brcic, L., Laszlo, V., et al. (2018) · Science Translational Medicine · doi:10.1126/scitranslmed.aao2301 · Cited by 125 · cited 2× · see citing works
“Thus, a pan-ERBB inhibitor, afatinib, effectively inhibited tumor growth of KRAS-mutated NSCLC on patient- or cell line– derived xenografts (44).”
BackgroundMitochondrial dysfunction in cancer
Księżakowska‐Łakoma, K., Żyła, M. M., & Wilczyński, J. R. (2014) · Menopause Review/Przegląd Menopauzalny · doi:10.5114/pm.2014.42717 · Cited by 120 · cited 1× · see citing works
“7C), echoing the dependency of chemoresistant cells on the energy metabolism (36, 37).”
BackgroundSynthetic Lethal Vulnerabilities in <i>KRAS</i>-Mutant Cancers
Aguirre, A. J., & Hahn, W. C. (2018) · Cold Spring Harbor Perspectives in Medicine · doi:10.1101/cshperspect.a031518 · Cited by 90 · cited 1× · see citing works
“As a demonstrating example, we investigated SE genes associated with mutations in KRAS, one of the hardest-to-target oncogenic variants (26, 29).”
BackgroundA network of human functional gene interactions from knockout fitness screens in cancer cells
Kim, E., Dede, M., Lenoir, W. F., Wang, G., Srinivasan, S., Colic, M., & Hart, T. (2019) · Life Science Alliance · doi:10.26508/lsa.201800278 · Cited by 84 · cited 1× · see citing works
“On the basis of the concepts of differential network biology (56) and genetic coessentiality (57), an interactive tool called FIREWORKS (58) interrogates functional relationships between gene dependencies using context-specific “coessentiality networks” and identifies multiomic signatures associated with differential…”
MethodMitochondrial dysfunction in cancer chemoresistance
Guaragnella, N., Giannattasio, S., & Moro, L. (2014) · Biochemical Pharmacology · doi:10.1016/j.bcp.2014.07.027 · Cited by 84 · cited 1× · see citing works
“7C), echoing the dependency of chemoresistant cells on the energy metabolism ( 36 , 37 ).”
BackgroundMannava, S., Moparthy, K., Wheeler, L. J., Natarajan, V., Zucker, S. N., Fink, E. E., Im, M. M., Flanagan, S. A., Burhans, W. C., Zeitouni, N. C., et al. (2012) · American Journal Of Pathology · doi:10.1016/j.ajpath.2012.09.011 · Cited by 82 · cited 1× · see citing works
“Our finding agreed with previous reports that mitochondrial dysfunction is closely related to the induction of DNA damage (30) and it may be targeted to enhance tumor vulnerability due to the interplay among mitochondrial metabolism, cell cycle checkpoint regulators, and mutation burden [reviewed in (31)].”
BackgroundMitochondrial Metabolism: Yin and Yang for Tumor Progression
Valcárcel-Jiménez, L., Gaude, E., Torrano, V., Frezza, C., & Carracedo, A. (2017) · Trends in Endocrinology and Metabolism · doi:10.1016/j.tem.2017.06.004 · Cited by 75 · cited 1× · see citing works
“…agreed with previous reports that mitochondrial dysfunction is closely related to the induction of DNA damage ( 30 ) and it may be targeted to enhance tumor vulnerability due to the interplay among mitochondrial metabolism, cell cycle checkpoint regulators, and mutation burden [reviewed in ( 31 )].”
BackgroundTumorMap: Exploring the Molecular Similarities of Cancer Samples in an Interactive Portal
Newton, Y., Novak, A. M., Swatloski, T., McColl, D., Chopra, S., Graim, K. S., Weinstein, A., Baertsch, R., Salama, S. R., Ellrott, K., et al. (2017) · Cancer Research · doi:10.1158/0008-5472.can-17-0580 · Cited by 66 · see citing works
Prediction and interpretation of cancer survival using graph convolution neural networks
Ramirez, R., Chiu, Y., Zhang, S., Ramirez, J., Chen, Y., Huang, Y., & Jin, Y.-F. (2021) · Methods · doi:10.1016/j.ymeth.2021.01.004 · Cited by 61 · cited 1× · see citing works
“DL is increasingly being used in genomics research for cancer survival ( 11 , 12 ) and cancer classification ( 13 – 15 ).”
MethodSelf-citationFIREWORKS: a bottom-up approach to integrative coessentiality network analysis
Amici, D. R., Jackson, J. M., Truica, M., Smith, R. S., Abdulkadir, S., & Mendillo, M. L. (2020) · Life Science Alliance · doi:10.26508/lsa.202000882 · Cited by 44 · cited 1× · see citing works
“On the basis of the concepts of differential network biology ( 56 ) and genetic coessentiality ( 57 ), an interactive tool called FIREWORKS ( 58 ) interrogates functional relationships between gene dependencies using context-specific “coessentiality networks” and identifies multiomic signatures…”
MethodGene expression has more power for predicting in vitro cancer cell vulnerabilities than genomicsPreprint
Dempster, J. M., Krill-Burger, J., McFarland, J. M., Warren, A. C., Boehm, J., Vazquez, F., Hahn, W. C., Golub, T., & Tsherniak, A. (2020) · bioRxiv · doi:10.1101/2020.02.21.959627 · Cited by 36 · cited 1× · see citing works
“5, D and E), echoing a recent study showing that gene expression had higher power than DNA level features in predicting cancer cell vulnerability (32).”
BackgroundEndogenous IL-2 in Cancer Cells: A Marker of Cellular Proliferation
Reichert, T., Watkins, S., Stanson, J., Johnson, J. T., & Whiteside, T. (1998) · Journal of Histochemistry and Cytochemistry · doi:10.1177/002215549804600506 · Cited by 34 · cited 1×
“12 of 17 different cancer lineages (50).”
Synthetic essentiality: Targeting tumor suppressor deficiencies in cancer
Zhao, D., & DePinho, R. A. (2017) · BioEssays · doi:10.1002/bies.201700076 · Cited by 27 · cited 4× · see citing works
“The study of SE between a mutation and an essentiality may lead to the critical discovery of cancer-specific vulnerabilities and thus context-specific therapeutic targets ( 26 , 27 ).”
BackgroundMethodInfluentialCEN‐tools: an integrative platform to identify the contexts of essential genes
Sharma, S., Dinçer, C., Weidemüller, P., Wright, G. J., & Petsalaki, E. (2020) · Molecular Systems Biology · doi:10.15252/msb.20209698 · Cited by 25 · cited 1× · see citing works
“Ex-panding the range of biological contexts, computational tools such as CEN-tools ( 55 ) identify dependencies that are specific to the tissue of origin and/or individual mutation state and expression level.”
MethodPrediction of drug induced liver injury using molecular and biological descriptors.
Muller, C., Pekthong, D., Alexandre, E., Marcou, G., Horvath, D., Richert, L., & Varnek, A. (2015) · Combinatorial chemistry & high throughput screening · doi:10.2174/1386207318666150305144650 · Cited by 24 · cited 1×
“We also performed y-scrambling validation to verify that the achieved performance was “real” and not by random chance according to previous reports ( 69 , 70 ).”
ResultSalvadores, M., Fuster-Tormo, F., & Supek, F. (2019) · bioRxiv · doi:10.1101/809400 · Cited by 21 · cited 1×
“Furthermore, methods that align genomic profiles between CCLs and tumors (40, 41) may help to reduce the differences between tumor and CCL domains.”
MethodGönen, M., Weir, B., Cowley, G., Vazquez, F., Guan, Y., Jaiswal, A., Karasuyama, M., Uzunangelov, V., Wang, T., Tsherniak, A., et al. (2017) · Cell Systems · doi:10.1016/j.cels.2017.09.004 · Cited by 20 · cited 2× · see citing works
“We evaluated the model by the correlation (per-DepOI ) between predicted and original dependency scores of each DepOI among testing CCLs, a metric commonly used to measure the prediction performance of genetic and chemical screening data ( 10 , 18 ).”
BackgroundMethodMostavi, M., Chiu, Y.-C., Chen, Y.-D., & Huang, Y. (2021) · BMC Bioinformatics · doi:10.1186/s12859-021-04157-w · Cited by 16
Self-citationMa, Q.-Z., Gu, L., Liao, S.-P., Zheng, Y.-J., Zhang, S., Cao, Y.-Y., Zhang, J., & Wang, Y.-F. (2018) · Apoptosis · doi:10.1007/s10495-018-1498-z · Cited by 15 · cited 1×
“…that (i) shRNA-based depletion of MAP3K7 has the most potent and selective effects among a panel of kinases in inhibiting the viability of KRAS -mutant colon CCLs ( 45 ); and (ii) pharmacologic inhibition of MAP3K7 suppresses KRAS - mutated colorectal cancer growth in vitro and in vivo ( 46 ).”
BackgroundAbstract LB-427: TAK1 (MAP3K7) inhibition promotes apoptosis in KRAS dependent colon cancers
Singh, A., Sweeney, M. F., Min, Y., Burger, A., Greninger, P., Benes, C., Haber, D., & Settleman, J. (2012) · doi:10.1158/1538-7445.am2012-lb-427 · Cited by 7 · cited 1×
“…that (i) shRNA-based depletion of MAP3K7 has the most potent and selective effects among a panel of kinases in inhibiting the viability of KRAS -mutant colon CCLs ( 45 ); and (ii) pharmacologic inhibition of MAP3K7 suppresses KRAS - mutated colorectal cancer growth in vitro and in vivo ( 46 ).”
Background
Flagged first, then by citations
3 of the 77 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- [45]A. Singh, M. F. Sweeney, M. Yu, A. Burger, P. Greninger, C. Benes, D. A. Haber, J. Settleman, TAK1 (MAP3K7) inhibition promotes apoptosis in KRAS-dependent colon cancers. Cell 148, 639– 650 (2012). 22341439 PMC3291475
- [62]R. Patro, G. Duggal, M. I. Love, R. A. Irizarry, C. Kingsford, Salmon provides fast and bias-aware quantification of transcript expression. Nat. Methods 14, 417– 419 (2017). 28263959 PMC5600148
Cited by
Sorted by citations
Multimodal Deep Learning Approaches for Precision Oncology: A Comprehensive Review
Yang, H., Yang, M., Chen, J., Yao, G., Zou, Q., & Jia, L. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae699 · Cited by 115 · see citing works
Wysocka, M., Wysocki, O., Zufferey, M., Landers, D., & Freitas, A. (2022) · BMC Bioinformatics · doi:10.1186/s12859-023-05262-8 · Cited by 75 · see citing works
Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis
Liu, J., Cen, X., Yi, C., Wang, F.-A., Ding, J., Cheng, J., Wu, Q., Gai, B., Zhou, Y., He, R., et al. (2025) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzaf011 · Cited by 75 · see citing works
“The pretrain-and-finetune framework has shown its effectiveness in computer vision learning, neural language processing, and biomedical learning for prognosis prediction [179] and cancer dependency prediction [180].”
TMO-Net: an explainable pretrained multi-omics model for multi-task learning in oncology
Wang, F.-A., Zhuang, Z., Gao, F., He, R., Zhang, S., Wang, L., Liu, J., & Li, Y. (2024) · Genome Biology · doi:10.1186/s13059-024-03293-9 · Cited by 51 · see citing works
Self-citationBuilding a translational cancer dependency map for The Cancer Genome Atlas
Shi, X., Gekas, C., Verduzco, D., Petiwala, S. M., Jeffries, C. T., Lu, C., Murphy, E., Anton, T., Vo, A. H., Xiao, Z., et al. (2024) · Nature Cancer · doi:10.1038/s43018-024-00789-y · Cited by 39 · see citing works
“During the completion of this study, Chiu et al. 27 took a complementary approach to building a translational dependency map (DeepDEP) using deep learning and the genomic, epigenomic and transcriptomic profiles of TCGA patients and DEPMAP cell lines.”
InfluentialIntelligent oncology: The convergence of artificial intelligence and oncology
Lin, B., Tan, Z., Mo, Y., Yang, X., Liu, Y., & Xu, B. (2022) · Journal of the National Cancer Center · doi:10.1016/j.jncc.2022.11.004 · Cited by 41 · see citing works
“9 , 10 Although these semantic features are hard to understand and interpret, they enable very accurate performance of the target task, making machine intelligent.”
BackgroundMachine learning approaches for biomolecular, biophysical, and biomaterials research.
Rickert, C., & Lieleg, O. (2022) · Biophysical Reviews · doi:10.1063/5.0082179 · Cited by 28 · see citing works
Translation of Epigenetics in Cell-Free DNA Liquid Biopsy Technology and Precision Oncology
Tan, W. Y., Nagabhyrava, S., Ang-Olson, O., Das, P., Ladel, L., Sailo, B., He, L., Sharma, A. R., & Ahuja, N. (2024) · Current Issues in Molecular Biology · doi:10.3390/cimb46070390 · Cited by 27 · see citing works
“The inadequacy of genetic mutations to account for cancer’s complexity arises from several key factors that underscore the importance of looking beyond DNA alterations alone [13,14].”
BackgroundZeng, J.-J., Li, K., Cao, F.-Y., & Zheng, Y.-B. (2023) · Frontiers in Oncology · doi:10.3389/fonc.2023.1131859 · Cited by 19 · see citing works
Gross, B., Dauvin, A., Cabeli, V., Kmetzsch, V., Khoury, J. E., Dissez, G., Ouardini, K., Grouard, S., Davi, A., Loeb, R., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-67023-8 · Cited by 15 · see citing works
“1, in the indication-specific survival prediction task, we observed that the choice of the representation model had minimal impact on performance, as they consistently achieved similar scores in terms of mean c-index, with less than 10% difference in most cohorts between the best and worst models…”
BackgroundMethodHigh-Throughput CRISPR Screening in Hematological Neoplasms
Ancos-Pintado, R., Bragado-García, I., Morales, M. L., García-Vicente, R., Arroyo-Barea, A., Rodríguez-García, A., Martínez-López, J., Linares, M., & Hernández-Sánchez, M. (2022) · Cancers · doi:10.3390/cancers14153612 · Cited by 15 · see citing works
Perovskite Probe-Based Machine Learning Imaging Model for Rapid Pathologic Diagnosis of Cancers
Chi, J., Xue, Y., Zhou, Y., Han, T., Ning, B., Cheng, L., Xie, H., Wang, H., Wang, W., Meng, Q., et al. (2024) · ACS Nano · doi:10.1021/acsnano.4c06351 · Cited by 16 · see citing works
Jubran, J., Slutsky, R., Rozenblum, N., Rokach, L., Ben‐David, U., & Yeger‐Lotem, E. (2024) · Genome biology · doi:10.1186/s13059-024-03225-7 · Cited by 14 · see citing works
Luo, L.-X., Chen, X.-M., & Huang, F.-F. (2023) · Chemico-Biological Interactions · doi:10.2139/ssrn.4090853 · Cited by 13
Predicting molecular mechanisms of hereditary diseases by using their tissue‐selective manifestation
Simonovsky, E., Sharon, M., Ziv, M., Mauer, O., Hekselman, I., Jubran, J., Vinogradov, E., Argov, C. M., Basha, O., Kerber, L., et al. (2023) · Molecular Systems Biology · doi:10.15252/msb.202211407 · Cited by 11 · see citing works
Ma, Y., Shih, C.-H., Cheng, J., Chen, H.-C., Wang, L., Tan, Y., Zhang, Y., Brown, D. D., Oesterreich, S., Lee, A. V., et al. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.4c05138 · Cited by 14 · see citing works
Self-citationPrecise metabolic dependencies of cancer through deep learning and validations
Wu, T., Zhao, X., Zhang, Y., Qiu, D., Diao, K., Xu, D., Wang, W., Xiong, X., Li, X.-X., & Liu, X.-S. (2025) · bioRxiv · doi:10.1101/2025.02.26.640327 · Cited by 10
Hardware-efficient quantum principal component analysis for medical image recognition
Lin, Z., Liu, H., Tang, K., Liu, Y., Che, L., Long, X., Wang, X., Fan, Y.-A., Huang, K., Yang, X., et al. (2024) · Frontiers of Physics · doi:10.1007/s11467-024-1391-x · Cited by 11 · see citing works
Vasanthakumari, P., Zhu, Y.-T., Brettin, T. S., Partin, A., Shukla, M., Xia, F., Narykov, O., Weil, M. R., & Stevens, R. L. (2024) · Cancers · doi:10.3390/cancers16030530 · Cited by 10
“Thus, drug response prediction becomes an important task, the success of which can assist precision medicine, which allows healthcare providers to offer personalized treatment after a comprehensive genomic analysis of the patient’s cancer cells [4,5].”
BackgroundStuart, D. D., Guzman-Perez, A., Brooijmans, N., Jackson, E. L., Kryukov, G. V., Friedman, A. A., & Hoos, A. (2023) · Cancer Discovery · doi:10.1158/2159-8290.cd-23-0280 · Cited by 16 · see citing works
Zhang, G., Feng, Z.-F., Zeng, Q.-X., & Huang, P. (2023) · Aging · doi:10.18632/aging.204859 · Cited by 9 · see citing works
Development and validation of a prognostic 15-gene signature for stratifying HER2+/ER+ breast cancer
Liu, Q., Huang, S., Desautels, D., McManus, K., Murphy, L., & Hu, P. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.05.002 · Cited by 8 · see citing works
“developed a deep learning model named DeepDep to predict the effect scores of the dependency of interest (DepOI) from genomics data [41].”
BackgroundAgrawal, P., Jain, N., Gopalan, V., Timon, A. J., Singh, A., Rajagopal, P., & Hannenhalli, S. (2024) · iScience · doi:10.1016/j.isci.2024.109752 · Cited by 7 · see citing works
“…reporting cellular viability upon genome-wide CRISPR-Cas9 knock out (KO) across hundreds of cell lines, providing a dependency probability score for each gene in each cell line, where a higher score indicates greater essentiality or dependency 17 ; by default, a score >0.5 indicates dependency.”
InfluentialWeisskittel, T., Cao, A., Meng-Lin, K., Lehmann, Z., Feng, B., Correia, C., Zhang, C., Wisniewski, P., Zhu, S., Ung, C. Y., et al. (2023) · Pharmaceuticals · doi:10.3390/ph16050752 · Cited by 10 · see citing works
Artificial Intelligence Imaging for Predicting High-risk Molecular Markers of Gliomas
Liang, Q., Jing, H., Shao, Y.-B., Wang, Y.-H., & Zhang, H. (2024) · Clinical Neuroradiology · doi:10.1007/s00062-023-01375-y · Cited by 6
“DL, a subset of ML based on neural networks, extracts meaningful features from raw input us-ing multilayer neural networks [22, 23].”
Oncogenic dependency plays a dominant role in the immune response to cancer
Li, J., D’Amico, S., Kirillov, V., Petrenko, O., & Reich, N. C. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2308635120 · Cited by 6 · see citing works
“However, certain trends prevail, as ~ 70% of CRC metastases no longer display the mesenchymal characteristics of their primary tumors (33).”
BackgroundDimensionality reduction methods for extracting functional networks from large-scale CRISPR screens
Hassan, A. Z., Ward, H. N., Rahman, M., Billmann, M., Lee, Y., & Myers, C. L. (2023) · bioRxiv · doi:10.1101/2023.02.22.529573 · Cited by 6
“…al , 2021; Gheorghe & Hart, 2022) but we note is distinct from other important applications of the DepMap goals such as direct clustering of the cell lines/genes (Pan et al , 2022), or more focused target/drug discovery-oriented analyses (Chiu et al , 2021; Ma et al , 2021; Shimada et al , 2021).”
Context-dependent synthetic lethality — an emerging precision therapeutic approach
Chang, L., Shaw, K. L., Vázquez, F., & Sellers, W. R. (2026) · Nature reviews. Cancer · doi:10.1038/s41568-026-00929-9 · Cited by 4 · see citing works
Scalvini, L., Tagliazucchi, L., Elisi, G. M., Zappaterra, D., Moschella, M. G., Fantini, S., Aiello, D., Guerrini, R., Albanese, V., Pacifico, S., et al. (2025) · European journal of medicinal chemistry · doi:10.1016/j.ejmech.2025.118056 · Cited by 5 · see citing works
Yeh, S.-J., Paithankar, S., Chen, R., Xing, J., Sun, M., Liu, K., Zhou, J.-Y., & Chen, B. (2023) · Genomics, Proteomics & Bioinformatics · doi:10.1093/gpbjnl/qzad008 · Cited by 5
“Notably, many outstanding efforts have been made toward using DepMap to predict individual measurement types, e.g. , drug sensitivity [10,26], metabolite [27], and gene effect [28].”
BackgroundCancer target discovery enabled by transcriptome-based virtual CRISPR screeningPreprint
Sadagopan, A., Li, B., Li, J., Cui, Y., Deodhar, R., Yang, D., Wu, Y., Konda, P., Biji, C., Thapa, D. R., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.24.620074 · Cited by 5 · see citing works
“Recent studies have reported approaches to predict a tumor’s dependency profile by virtue of its transcriptional and/or genomic features (54,56,118).”
BackgroundImpact of CRISPR in cancer drug discovery
Moffat, J., Komor, A. C., & Lum, L. (2024) · Science · doi:10.1126/science.adi6884 · Cited by 4 · see citing works
Zhang, X.-L., Guo, H.-J., Li, X.-L., Tao, W., Ma, X.-Q., Zhang, Y.-X., & Xiao, W.-D. (2024) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-024-06001-z · Cited by 4
“…cell cycle and differential expression analysis, we have constructed a risk scoring model based on genes related to polyamine metabolism, providing a new method for enhancing prognostic evaluation of breast cancer and guiding personalized treatment strategies (Tran et al. 2021; Chiu et al. 2021).”
MethodRetractedDimensionality reduction methods for extracting functional networks from large‐scale CRISPR screens
Hassan, A. Z., Ward, H. N., Rahman, M., Billmann, M., Lee, Y., & Myers, C. L. (2023) · Molecular Systems Biology · doi:10.15252/msb.202311657 · Cited by 7 · see citing works
“…al , 2021; Gheorghe & Hart, 2022) but we note is distinct from other important applications of the DepMap goals such as direct clustering of the cell lines/genes (Pan et al , 2022), or more focused target/drug discovery-oriented analyses (Chiu et al , 2021; Ma et al , 2021; Shimada et al , 2021).”
Liu, Y., Wang, Y.-L., Zhang, N., Xiong, H., Zhao, L.-P., Qi, Y., Xie, J.-P., Duan, X., Yue, D.-S., & Qie, S. (2025) · Science China Life Sciences · doi:10.1007/s11427-024-3015-1 · Cited by 3 · see citing works
“The tumour types were chosen according to current ongoing clinical trials with CDK4/6 inhibitors based on data from the website (Chiu et al., 2021): https://classic.clinicaltrials.gov.”
Interpretable neural networks prioritize cancer driver genes from genome-wide dependency landscapes
Yin, Q.-Y., & Chen, L. (2025) · bioRxiv · doi:10.1371/journal.pcbi.1014869 · Cited by 3 · see citing works
“CRISPR-Cas9 has advanced gene perturbation in terms of precision and scale [8].”
Cancer Dependency Map: Past and Present
Arafeh, R., Shibue, T., Vázquez, F., & Hahn, W. C. (2025) · Annual Review of Cancer Biology · doi:10.1146/annurev-cancerbio-062722-024239 · Cited by 3 · see citing works
Wang, F., Liu, J., Gao, F., & Li, Y. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.05.547886 · Cited by 3 · see citing works
“For multi-omics data, in line with previous studies [29], we included five types of nonsynonymous mutations: missense and nonsense mutations, frameshift insertions and deletions, and splice sites.”
MethodGRETTA: an R package for mapping in silico genetic interaction and essentiality networks
Takemon, Y., & Marra, M. (2022) · bioRxiv · doi:10.1093/bioinformatics/btad381 · Cited by 3 · see citing works
Shi, Y., Xu, W., & Hu, P. (2026) · Genetic Epidemiology · doi:10.1002/gepi.70044 · Cited by 2 · see citing works
“…(PDXE), and the Genotype‐Tissue Expression (GTEx) project with CCLs. Chiu et al. integrate unsupervised pretraining on unlabeled tumor data from TCGA with subsequent fine‐tuning on labeled CCL data, aiming to apply a deep learning (DL) model to dependency score prediction (Chiu et al. 2021).”
Khazal, F. J. A., Emch, M., Correia, C., Favier, J., Hawse, J. R., & Maher, L. J. (2026) · iScience · doi:10.1016/j.isci.2026.115885 · Cited by 2 · see citing works
“…on the neddylation pathway in Sdhb-loss lines By comparing our screen results against the dependency map (DepMap) essentiality scores from the Broad Institute in relevant tumors after artificially introduced SDH loss, 29 we noted both tissue-specific and Sdhb loss-specific dependencies.”
Zeng, H.-T., Yang, Y., Tan, H., Wang, Z., Hao, T.-T., Zhang, Q.-Q., & Guo, Z.-Y. (2026) · Microchemical journal (Print) · doi:10.1016/j.microc.2026.117275 · Cited by 2 · see citing works
Beyond human capacity: How artificial intelligence (AI) is enhancing cancer diagnosis and treatment
Ravari, M. S., & Momeny, M. (2023) · Iranian Journal of Blood and Cancer · doi:10.61186/ijbc.15.3.4 · Cited by 1 · see citing works
Jubran, J., Slutsky, R., Rozenblum, N., Rokach, L., Ben-David, U., & Yeger-Lotem, E. (2023) · bioRxiv · doi:10.1101/2023.07.05.547626 · Cited by 2
“Yet, unlike classical ML-based studies that mainly aim to improve prediction, for example by using deep learning to predict gene dependency in tumors (Chiu et al. 2021), our focus was on interpretability.”
BackgroundMethodAgrawal, P., Jain, N., Gopalan, V., Timon, A. J., Singh, A. K., Rajagopal, P., & Hannenhalli, S. (2023) · bioRxiv · doi:10.1101/2023.05.21.541618 · Cited by 2
Deep learning - cancer genetics and application of deep learning to cancer oncology
Hoang, D., & Hoang, S. (2022) · Vietnam Journal of Science and Technology · doi:10.15625/2525-2518/17256 · Cited by 2 · see citing works
Measuring dependencies between variables of a dynamical system using fuzzy affiliations
Wulkow, N. (2022) · AppliedMath · doi:10.48550/arxiv.2203.05993 · Cited by 2
Kimura, T., Yamakawa, A., Mitsumori, R., Niida, S., Ozaki, K., & Shigemizu, D. (2026) · Translational Psychiatry · doi:10.1038/s41398-026-04027-0 · Cited by 1 · see citing works
Challenges and opportunities for oncology drug repurposing informed by synthetic lethality
Vermeulen, M., Craig, A. W., & Babak, T. (2025) · npj Systems Biology and Applications · doi:10.1038/s41540-025-00618-7 · Cited by 1
“Approaches range from univariate tests 5 – 8 , linear models such as mixed-model regressions 9 , analysis of variance (ANOVA) 10 , and machine learning techniques including ran-domforests(RF) 11 – 16 ,neuralnetworks 17 andautoencoders 18,19 .”
He, J.-M., Akhtar, A., Li, J., Wei, Q., Yuan, Y., Ran, J.-H., Ma, Y.-P., & Chen, D.-L. (2025) · Journal of Inflammation Research · doi:10.2147/jir.s523147 · Cited by 1
Bodinier, B., Dissez, G., Bleistein, L., & Dauvin, A. (2025) · arXiv.org · doi:10.48550/arxiv.2502.15646 · Cited by 1
“In PP-LGBM , we use a pan-perturbation regression model to predict the response to any perturbation in a given cell line based on both sample-level features (RNAseq) and perturbation-level features (fingerprints) 10,12 .”
InfluentialHalawani, R., Büchert, M., & Chen, Y. P. (2024) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2024.3503761 · Cited by 3 · see citing works
“DeepDEP [93] model learned features from high-dimensional omics data using separate encoders for DNA mutation, gene expression, DNA methylation, copy number alteration, and dependency of interest, then concatenated into DNN to predict a dependency score.”
InfluentialSelf-citationModeling cancer dependency with deep graph modelsPreprint
Fu, H., Zhao, B., & Wang, P. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.26.582022 · Cited by 1 · see citing works
“Currently, majority of the available methods still rely on traditional machine learning methods, and could not generalize well to unseen samples 18-21 。 Currently only one deep learning method based on autoencoders, deepDep, has been developed to predict cancer dependencies 22 .”
MethodShi, X., Gekas, C., Verduzco, D., Petiwala, S. M., Jeffries, C., Lu, C., Murphy, E. R., Anton, T., Vo, A. H., Xiao, Z., et al. (2022) · bioRxiv · doi:10.1101/2022.03.24.485544 · Cited by 1 · see citing works
“TCGA DEPMAP was built using the expression-only elastic-net models of gene essentiality, based on the evidence here ( Figure 1 ) and elsewhere ( 26 , 27 ) that only marginal gains were made in model performance by including genomic features.”
BackgroundMethodInfluentialArtificial Intelligence and Medicine: A literature review
Jittprasong, C. (2022) · arXiv.org · doi:10.48550/arxiv.2205.00322 · Cited by 1
“Predicting and characterizing a cancer dependency map of tumors with deep learning (Chiu et al. 2021) The paper created a deep learning model, "DeepDEP," with an unsupervised pre-training structure to study the genomic profiles of tumors and predict their dependencies, which may allow them to…”
MethodDing, T.-N., Li, W., Yi, Y.-T., Fan, X., Tan, J.-H., Han, A.-Q., & Tang, Y. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27219604
Pınar, A., Çolak, C., & Arslan, A. (2026) · Intelligent Data Analysis · doi:10.1177/1088467x261490986
Fırat, Y., & Kılıçaslan, Y. (2026) · Biology · doi:10.3390/biology15191782
“DeepDEP demonstrated that multi-omic profiles can predict cancer dependencies [16], while transcriptome-based dependency maps developed for The Cancer Genome Atlas showed that Elastic Net models can prioritize putative tumor vulnerabilities [17].”
Cracking MYC addiction: Synthetic-lethal vulnerabilities for precision cancer therapy
Deng, K.-L., Hong, Z.-Y., Wang, Y.-X., Wu, Y., Zhang, W.-D., Luan, X., & Sun, Z. (2026) · Genes & Diseases · doi:10.1016/j.gendis.2026.102534
Bai, J., Faure, J. S., Khalfe, T. A., Huang, R., Burmeister, C. A., van Niekerk, A., & Prince, S. (2026) · Frontiers in Oncology · doi:10.3389/fonc.2026.1937655
Essentiality-driven prediction of anticancer drug responses in preclinical and clinical contexts
Cui, H., Du, X., Guo, H.-X., Liao, Z., Wang, B., Lian, X., Zhang, J.-Y., Lu, X., Zhang, D., Ye, A., et al. (2026) · iScience · doi:10.1016/j.isci.2026.116980
“Although computational methods for predicting gene essentiality have been developed, 19,20 they are frequently not designed for direct integration into drug-response prediction frameworks or depend on multi-modal genomic inputs that limit their suitability for routine clinical use.”
InfluentialBodinier, B., Dissez, G., Ter-Minassian, L., Bleistein, L., Codato, R., Klein, J., Durand, E. Y., & Dauvin, A. (2026) · Scientific Reports · doi:10.1038/s41598-026-56381-0
“We use the same 3115 chemical and genetic perturbations (CGP) curated gene sets as in DeepDEP 10 , which were obtained after filtering out the 318 sets that do not involve any of the 1298 genes studied in their paper.”
InfluentialCharacterizing selection signatures in coding and noncoding regions of 14,886 cancer genomes
Zheng, M., Sun, X., Hou, J., Guo, M., Liu, X., Yang, W., & Yang, J. (2026) · Journal of genetics and genomics/Journal of Genetics and Genomics · doi:10.1016/j.jgg.2026.06.008 · Cited by 1 · see citing works
Multi-Group Quadratic Discriminant Analysis via Projection
Wang, Y.-C., & Wang, T.-Y. (2026) · Journal of Computational And Graphical Statistics · doi:10.1080/10618600.2026.2653763
“…DepMap Public 23Q2 release (DepMap, Broad, 2023; Arafeh et al., 2025), which provides large-scale genomic and functional profiles of cancer cell lines and is widely used to study genetic dependencies and vulnerabilities in cancer (Killian and Gatto, 2021; Bazaga et al., 2020; Chiu et al., 2021).”
Context-aware gene dependency modeling via graph attention networks for precision oncology
Yu, G., Gong, Y., Fan, B., Gao, J., & Fan, Q. (2025) · Journal of Translational Medicine · doi:10.1186/s12967-025-07501-3
“Expression-based models such as DeepDEP [21] and DepMap’s random forest predictors rely on global transcriptional similarity but fail to incorporate biological priors like gene networks.”
InfluentialDeepVul: A Multi-Task Transformer Model for Joint Prediction of Gene Essentiality and Drug ResponsePreprint
Jararweh, A., Bach, M. N., Arredondo, D., Macaulay, O. S., Dicome, M., Tafoya, L. E., Hu, Y., Virupakshappa, K., Boland, G., Flaherty, K., et al. (2025) · bioRxiv · doi:10.1101/2024.10.17.618944
“DeepDEP, [3], a deep learning model, predicts essential genes for cancer cell proliferation using integrative genomic profiles.”
Padhi, D., Majumdar, S. D., & Muralidharan, A. (2025) · Asian Pacific Journal of Cancer Prevention · doi:10.31557/apjcp.2025.26.7.2669
Chang, D., & Zhang, X. (2023) · bioRxiv · doi:10.1101/2023.11.29.569083
“Using the DepMap 2018Q2 release, Chiu et al. recently developed DeepDEP, a deep learning method for predicting genetic dependency profiles of CCLs given their multi-omics ( 6 ) .”
MethodYuan, R., Feng, J., Zhang, H., Chen, Y., Payne, P., & Li, F. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.09.16.508281
“Compared with the traditional computational models, in the recent study 11 , the DeepDep model was developed based on the combination of deep belief network (DBN) 12 and auto-encoders 13,14 , to integrate the multi-omics data of CCLE and TCGA for the DepMap target effect prediction.”
MethodSelf-citationSequents, barcodes, and homology
Basu, S., Karisani, N., & Parida, L. (2022) · arXiv.org · doi:10.48550/arxiv.2208.01450
“However, models that are able to automatically predict gene dependencies are of a great importance to help scientists with this aim [5, 4].”
BackgroundRandom Graph-Based Neuromorphic Learning with a Layer-Weaken StructurePreprint
Mao, R.-Q., & Cui, R. (2021) · arXiv.org · doi:10.48550/arxiv.2111.08888
Vaithiyanathan, M., & Bala, K. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111208
Laurent, S., Dubois, P., Lefevre, M., & Moreau, C. (2026) · Journal of Artificial Intelligence for Healthcare Systems · doi:10.68159/t715039840
Islam, M., Akhter, N., & Alam, S. (2025) · International Journal of Pharmaceutical and Phytopharmacological Research · doi:10.51847/kpnw8cpaff
- Authors
- Chiu, Y.-C., Zheng, S., Wang, L.-J., Iskra, B. S., Rao, M. K., Houghton, P. J., Huang, Y., & Chen, Y.
- Affiliations
- The University of Texas at San Antonio Health Science Center (US)
- University of Pittsburgh (US)
- Corresponding author
- Huang, Yufei
- Chen, Yidong
- ORCID
- Venue
- Science Advances
- Published
- 2021-08-20
- Volume
- 7
- Issue
- 34
- ISSN
- 2375-2548 (ISSN-L)
- PMC
- PMC8378822
- OpenAlex
- W3196171893
- Cited by
- 84
- References
- 77
- Citations by year
- 2026: 17 · 2025: 14 · 2024: 28 · 2023: 14 · 2022: 10 · 2021: 1
- FWCI
- 5.87
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Science Advances (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (K99CA248944, CTSA 1UL1RR025767-01, R01GM113245, P30CA54174, T32GM113896, F30AG057213)
- Cancer Prevention and Research Institute of Texas (RP160732, RR170055, RP190346)
- Fund for Innovation in Cancer Informatics (ICI Fund)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Cancer Genomics and Diagnostics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Chromatin Remodeling and Cancer
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- cancer dependency, dependency map, loss-of-function screen, essential genes, unsupervised pre-training, pan-cancer genomics, tumor genomic profiles, model interpretability
- MeSH terms
- Machine Learning, Deep Learning, Humans, Neoplasms, Genomics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
