{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T03:21:08Z","timestamp":1774581668939,"version":"3.50.1"},"reference-count":58,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T00:00:00Z","timestamp":1593388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Deep learning\u2019s automatic feature extraction has proven its superior performance over traditional fingerprint-based features in the implementation of virtual screening models. However, these models face multiple challenges in the field of early drug discovery, such as over-training and generalization to unseen data, due to the inherently unbalanced and small datasets. In this work, the TranScreen pipeline is proposed, which utilizes transfer learning and a collection of weight initializations to overcome these challenges. An amount of 182 graph convolutional neural networks are trained on molecular source datasets and the learned knowledge is transferred to the target task for fine-tuning. The target task of p53-based bioactivity prediction, an important factor for anti-cancer discovery, is chosen to showcase the capability of the pipeline. Having trained a collection of source models, three different approaches are implemented to compare and rank them for a given task before fine-tuning. The results show improvement in performance of the model in multiple cases, with the best model increasing the area under receiver operating curve ROC-AUC from 0.75 to 0.91 and the recall from 0.25 to 1. This improvement is vital for practical virtual screening via lowering the false negatives and demonstrates the potential of transfer learning. The code and pre-trained models are made accessible online.<\/jats:p>","DOI":"10.3390\/bdcc4030016","type":"journal-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T03:40:07Z","timestamp":1593402007000},"page":"16","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["TranScreen: Transfer Learning on Graph-Based Anti-Cancer Virtual Screening Model"],"prefix":"10.3390","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6703-6839","authenticated-orcid":false,"given":"Milad","family":"Salem","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USA"}]},{"given":"Aminollah","family":"Khormali","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USA"}]},{"given":"Arash Keshavarzi","family":"Arshadi","sequence":"additional","affiliation":[{"name":"Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL 32816, USA"}]},{"given":"Julia","family":"Webb","sequence":"additional","affiliation":[{"name":"Burnett School of Biomedical Sciences, University of Central Florida, Orlando, FL 32816, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2548-8327","authenticated-orcid":false,"given":"Jiann-Shiun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Central Florida, Orlando, FL 32816, USA"}]}],"member":"1968","published-online":{"date-parts":[[2020,6,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1007\/s12094-006-0048-2","article-title":"High throughput screening in drug discovery","volume":"8","author":"Carnero","year":"2006","journal-title":"Clin. Transl. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.trci.2017.10.005","article-title":"Drug discovery and development: Role of basic biological research","volume":"3","author":"Mohs","year":"2017","journal-title":"Alzheimer\u2019s Dement. (N. Y.)"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Miljkovi\u0107, F., Rodr\u00edguez-P\u00e9rez, R., and Bajorath, J. (2019). Machine Learning Models for Accurate Prediction of Kinase Inhibitors with Different Binding Modes. J. Med. Chem.","DOI":"10.1021\/acs.jmedchem.9b00867"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1016\/j.drudis.2017.05.008","article-title":"From flamingo dance to (desirable) drug discovery: A nature-inspired approach","volume":"22","author":"Nicolotti","year":"2017","journal-title":"Drug Discov. Today"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1093\/toxsci\/kft209","article-title":"Chemoinformatics Profiling of Ionic Liquids\u2014Automatic and Chemically Interpretable Cytotoxicity Profiling, Virtual Screening, and Cytotoxicophore Identification","volume":"136","author":"Jorge","year":"2013","journal-title":"Toxicol. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Perez-Castillo, Y., S\u00e1nchez-Rodr\u00edguez, A., Tejera, E., Cruz-Monteagudo, M., Borges, F., Cordeiro, M.N.D., Le-Thi-Thu, H., and Pham-The, H. (2018). A desirability-based multi objective approach for the virtual screening discovery of broad-spectrum anti-gastric cancer agents. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0192176"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"4462","DOI":"10.1021\/acs.molpharmaceut.7b00578","article-title":"Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets","volume":"14","author":"Korotcov","year":"2017","journal-title":"Mol. Pharm."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"eaap7885","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2018","journal-title":"Sci. Adv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1021\/acs.jcim.9b01053","article-title":"AMPL: A Data-Driven Modeling Pipeline for Drug Discovery","volume":"60","author":"Minnich","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1007\/s10822-016-9938-8","article-title":"Molecular graph convolutions: Moving beyond fingerprints","volume":"30","author":"Kearnes","year":"2016","journal-title":"J. Comput. Aided Mol. Des."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gimeno, A., Ojeda-Montes, M.J., Tom\u00e1s-Hern\u00e1ndez, S., Cereto-Massagu\u00e9, A., Beltr\u00e1n-Deb\u00f3n, R., Mulero, M., Pujadas, G., and Garcia-Vallv\u00e9, S. (2019). The Light and Dark Sides of Virtual Screening: What Is There to Know?. Int. J. Mol. Sci., 20.","DOI":"10.3390\/ijms20061375"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Sianes, J., P\u00e9rez-S\u00e1nchez, H., and D\u00edaz, F. (2016). Virtual Screening: A Challenge for Deep Learning. 10th International Conference on Practical Applications of Computational Biology & Bioinformatics, Springer International Publishing.","DOI":"10.1007\/978-3-319-40126-3_2"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Fischer, B., Merlitz, H., and Wenzel, W. (2005). Increasing Diversity in In-silico Screening with Target Flexibility. Computational Life Sciences, Springer.","DOI":"10.1007\/11560500_17"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1021\/ci034231b","article-title":"Comparison of Fingerprint-Based Methods for Virtual Screening Using Multiple Bioactive Reference Structures","volume":"44","author":"Hert","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_15","unstructured":"Ramsundar, B., Kearnes, S., Riley, P., Webster, D., Konerding, D., and Pande, V. (2015). Massively multitask networks for drug discovery. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1021\/acscentsci.6b00367","article-title":"Low Data Drug Discovery with One-Shot Learning","volume":"3","author":"Ramsundar","year":"2017","journal-title":"ACS Cent. Sci."},{"key":"ref_17","unstructured":"Hu, W., Liu, B., Gomes, J., Zitnik, M., Liang, P., Pande, V., and Leskovec, J. (2019). Strategies for Pre-training graph neural networks. arXiv."},{"key":"ref_18","unstructured":"Liu, S. (2018). Exploration on Deep Drug Discovery: Representation and Learning, Computer Science, University of Wisconsin-Madison."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: A benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1038\/cdd.2017.180","article-title":"Why are there hotspot mutations in the TP53 gene in human cancers?","volume":"25","author":"Baugh","year":"2018","journal-title":"Cell Death Differ."},{"key":"ref_21","unstructured":"PubChem Database (2020, May 18). Source=NCGC AID=904, Available online: https:\/\/pubchem.ncbi.nlm.nih.gov\/bioassay\/904."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity Fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4131","DOI":"10.1021\/acs.jcim.9b00628","article-title":"Graph Convolutional Neural Networks for Predicting Drug-Target Interactions","volume":"59","author":"Torng","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1039\/C8SC04228D","article-title":"A graph-convolutional neural network model for the prediction of chemical reactivity","volume":"10","author":"Coley","year":"2019","journal-title":"Chem. Sci."},{"key":"ref_25","unstructured":"Ramsundar, B., Eastman, P., Walters, P., Pande, V., Leswing, K., and Wu, Z. (2019). Deep Learning for the Life Sciences, O\u2019Reilly Media."},{"key":"ref_26","unstructured":"Bjerrum, E.J. (2017). Smiles enumeration as data augmentation for neural network modeling of molecules. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.3389\/fphar.2019.01526","article-title":"DeepMalaria: Artificial Intelligence Driven Discovery of Potent Antiplasmodials","volume":"10","author":"Arshadi","year":"2019","journal-title":"Front. Pharmacol."},{"key":"ref_28","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","article-title":"Speech Recognition Using Deep Neural Networks: A Systematic Review","volume":"7","author":"Nassif","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","unstructured":"Boumi, S., Vela, A., and Chini, J. (2020). Quantifying the relationship between student enrollment patterns and student performance. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9872","DOI":"10.1109\/ACCESS.2018.2890127","article-title":"Multiple Feature Reweight DenseNet for Image Classification","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sun, Q., Liu, Y., Chua, T.-S., and Schiele, B. (2019, January 16\u201320). Meta-transfer learning for few-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., and Davison, A.J. (2019, January 16\u201320). End-to-end multi-task learning with attention. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref_34","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., and He, Q. (2019). A Comprehensive Survey on Transfer Learning. arXiv."},{"key":"ref_35","unstructured":"Frankle, J., and Carbin, M. (2018). The lottery ticket hypothesis: Finding sparse trainable neural networks. arXiv."},{"key":"ref_36","unstructured":"Fawaz, H.I., Forestier, G., Weber, J., Idoumghar, L., and Muller, P. (2018, January 10\u201313). Transfer learning for time series classification. Proceedings of the 2018 IEEE International Conference on Big Data (Big Data), Zurich, Switzerland Seattle, WA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","article-title":"Deep visual domain adaptation: A survey","volume":"312","author":"Wang","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Koniusz, P. (2019). Model Selection for Generalized Zero-Shot Learning. Computer Vision\u2014ECCV 2018 Workshops, Springer International Publishing.","DOI":"10.1007\/978-3-030-11012-3_16"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Koniusz, P. (2018, January 18\u201322). Zero-Shot Kernel Learning. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00800"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., and Pereira, F. (2007). Analysis of representations for domain adaptation. Advances in NEURAL Information Processing Systems, The MIT Press.","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"6190","DOI":"10.1109\/ACCESS.2019.2963742","article-title":"Source Model Selection for Deep Learning in the Time Series Domain","volume":"8","author":"Meiseles","year":"2020","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1021\/acs.jcim.8b00363","article-title":"Practical Model Selection for Prospective Virtual Screening","volume":"59","author":"Liu","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1021\/ci8004379","article-title":"Influence relevance voting: An accurate and interpretable virtual high throughput screening method. (in eng)","volume":"49","author":"Swamidass","year":"2009","journal-title":"J. Chem. Inf. Model."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Zhang, H., and Koniusz, P. (2019, January 7\u201311). Power Normalizing Second-Order Similarity Network for Few-Shot Learning. Proceedings of the 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, HI, USA.","DOI":"10.1109\/WACV.2019.00131"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J. Clin."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1038\/ncponc0978","article-title":"Costs of cancer care in the USA: A descriptive review","volume":"4","author":"Yabroff","year":"2007","journal-title":"Nat. Clin. Pract. Oncol."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: The next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0065-2776(06)90001-7","article-title":"Cancer immunosurveillance and immunoediting: The roles of immunity in suppressing tumor development and shaping tumor immunogenicity","volume":"90","author":"Smyth","year":"2006","journal-title":"Adv. Immunol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1038\/nrc1694","article-title":"Opinion: Migrating cancer stem cells\u2014An integrated concept of malignant tumour progression","volume":"5","author":"Brabletz","year":"2005","journal-title":"Nat. Rev. Cancer"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.tips.2013.11.004","article-title":"Molecularly targeted cancer therapy: Some lessons from the past decade","volume":"35","author":"Huang","year":"2014","journal-title":"Trends Pharmacol. Sci."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1056\/NEJMra072367","article-title":"Oncogenes and cancer","volume":"358","author":"Croce","year":"2008","journal-title":"N. Engl. J. Med."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"2647","DOI":"10.1159\/000495956","article-title":"Loss of Tumor Suppressor Gene Function in Human Cancer: An Overview","volume":"51","author":"Wang","year":"2018","journal-title":"Cell Physiol. Biochem."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/358015a0","article-title":"Cancer. p53, guardian of the genome","volume":"358","author":"Lane","year":"1992","journal-title":"Nature"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"3224","DOI":"10.1128\/MCB.20.9.3224-3233.2000","article-title":"Stress signals utilize multiple pathways to stabilize p53","volume":"20","author":"Ashcroft","year":"2000","journal-title":"Mol. Cell Biol."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1038\/sj.cdd.4401183","article-title":"Decision making by p53: Life, death and cancer","volume":"10","author":"Oren","year":"2003","journal-title":"Cell Death Differ."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1002\/path.2784","article-title":"The role of mutant p53 in human cancer","volume":"223","author":"Goh","year":"2011","journal-title":"J. Pathol."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"288","DOI":"10.3389\/fonc.2015.00288","article-title":"Targeting Oncogenic Mutant p53 for Cancer Therapy","volume":"5","author":"Parrales","year":"2015","journal-title":"Front. Oncol."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1158\/2159-8290.CD-13-0136","article-title":"Contribution of p53 to metastasis","volume":"4","author":"Powell","year":"2014","journal-title":"Cancer Discov."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/4\/3\/16\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:44:14Z","timestamp":1760175854000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/4\/3\/16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,29]]},"references-count":58,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["bdcc4030016"],"URL":"https:\/\/doi.org\/10.3390\/bdcc4030016","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,29]]}}}