Predicting cancer drug mechanisms of action using molecular network signatures
Molecular signatures are a powerful approach to characterize novel small molecules and derivatized small molecule libraries. While new experimental techniques are being developed in diverse model systems, informatics approaches lag behind these exciting advances. We propose an analysis pipeline for...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Royal Society of Chemistry
2014
|
| Online Access: | http://hdl.handle.net/1721.1/88980 https://orcid.org/0000-0003-3383-0118 |
| _version_ | 1826188324519280640 |
|---|---|
| author | Pritchard, Justin R. Bruno, Peter Michael Hemann, Michael Lauffenburger, Douglas A |
| author2 | Massachusetts Institute of Technology. Department of Biological Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Biological Engineering Pritchard, Justin R. Bruno, Peter Michael Hemann, Michael Lauffenburger, Douglas A |
| author_sort | Pritchard, Justin R. |
| collection | MIT |
| description | Molecular signatures are a powerful approach to characterize novel small molecules and derivatized small molecule libraries. While new experimental techniques are being developed in diverse model systems, informatics approaches lag behind these exciting advances. We propose an analysis pipeline for signature based drug annotation. We develop an integrated strategy, utilizing supervised and unsupervised learning methodologies that are bridged by network based statistics. Using this approach we can: 1, predict new examples of drug mechanisms that we trained our model upon; 2, identify “New” mechanisms of action that do not belong to drug categories that our model was trained upon; and 3, update our training sets with these “New” mechanisms and accurately predict entirely distinct examples from these new categories. Thus, not only does our strategy provide statistical generalization but it also offers biological generalization. Additionally, we show that our approach is applicable to diverse types of data, and that distinct biological mechanisms characterize its resolution of categories across different data types. As particular examples, we find that our predictive resolution of drug mechanisms from mRNA expression studies relies upon the analog measurement of a cell stress-related transcriptional rheostat along with a transcriptional representation of cell cycle state; whereas, in contrast, drug mechanism resolution from functional RNAi studies rely upon more dichotomous (e.g., either enhances or inhibits) association with cell death states. We believe that our approach can facilitate molecular signature-based drug mechanism understanding from different technology platforms and across diverse biological phenomena. |
| first_indexed | 2024-09-23T07:57:55Z |
| format | Article |
| id | mit-1721.1/88980 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T07:57:55Z |
| publishDate | 2014 |
| publisher | Royal Society of Chemistry |
| record_format | dspace |
| spelling | mit-1721.1/889802022-09-23T09:55:43Z Predicting cancer drug mechanisms of action using molecular network signatures Pritchard, Justin R. Bruno, Peter Michael Hemann, Michael Lauffenburger, Douglas A Massachusetts Institute of Technology. Department of Biological Engineering Massachusetts Institute of Technology. Department of Biology Koch Institute for Integrative Cancer Research at MIT Pritchard, Justin R. Bruno, Peter Michael Hemann, Michael Lauffenburger, Douglas A. Molecular signatures are a powerful approach to characterize novel small molecules and derivatized small molecule libraries. While new experimental techniques are being developed in diverse model systems, informatics approaches lag behind these exciting advances. We propose an analysis pipeline for signature based drug annotation. We develop an integrated strategy, utilizing supervised and unsupervised learning methodologies that are bridged by network based statistics. Using this approach we can: 1, predict new examples of drug mechanisms that we trained our model upon; 2, identify “New” mechanisms of action that do not belong to drug categories that our model was trained upon; and 3, update our training sets with these “New” mechanisms and accurately predict entirely distinct examples from these new categories. Thus, not only does our strategy provide statistical generalization but it also offers biological generalization. Additionally, we show that our approach is applicable to diverse types of data, and that distinct biological mechanisms characterize its resolution of categories across different data types. As particular examples, we find that our predictive resolution of drug mechanisms from mRNA expression studies relies upon the analog measurement of a cell stress-related transcriptional rheostat along with a transcriptional representation of cell cycle state; whereas, in contrast, drug mechanism resolution from functional RNAi studies rely upon more dichotomous (e.g., either enhances or inhibits) association with cell death states. We believe that our approach can facilitate molecular signature-based drug mechanism understanding from different technology platforms and across diverse biological phenomena. National Cancer Institute (U.S.) (NCI Integrative Cancer Biology Program grant U54-CA112967) 2014-08-22T15:50:00Z 2014-08-22T15:50:00Z 2013 2012-10 Article http://purl.org/eprint/type/JournalArticle 1742-206X 1742-2051 http://hdl.handle.net/1721.1/88980 Pritchard, Justin R., Peter M. Bruno, Michael T. Hemann, and Douglas A. Lauffenburger. “Predicting Cancer Drug Mechanisms of Action Using Molecular Network Signatures.” Mol. BioSyst. 9, no. 7 (2013): 1604. https://orcid.org/0000-0003-3383-0118 en_US http://dx.doi.org/10.1039/c2mb25459j Molecular BioSystems Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Royal Society of Chemistry PMC |
| spellingShingle | Pritchard, Justin R. Bruno, Peter Michael Hemann, Michael Lauffenburger, Douglas A Predicting cancer drug mechanisms of action using molecular network signatures |
| title | Predicting cancer drug mechanisms of action using molecular network signatures |
| title_full | Predicting cancer drug mechanisms of action using molecular network signatures |
| title_fullStr | Predicting cancer drug mechanisms of action using molecular network signatures |
| title_full_unstemmed | Predicting cancer drug mechanisms of action using molecular network signatures |
| title_short | Predicting cancer drug mechanisms of action using molecular network signatures |
| title_sort | predicting cancer drug mechanisms of action using molecular network signatures |
| url | http://hdl.handle.net/1721.1/88980 https://orcid.org/0000-0003-3383-0118 |
| work_keys_str_mv | AT pritchardjustinr predictingcancerdrugmechanismsofactionusingmolecularnetworksignatures AT brunopetermichael predictingcancerdrugmechanismsofactionusingmolecularnetworksignatures AT hemannmichael predictingcancerdrugmechanismsofactionusingmolecularnetworksignatures AT lauffenburgerdouglasa predictingcancerdrugmechanismsofactionusingmolecularnetworksignatures |