{"id":326,"date":"2022-06-10T01:12:07","date_gmt":"2022-06-10T01:12:07","guid":{"rendered":"https:\/\/shayhmaor.dev\/?page_id=326"},"modified":"2025-10-07T01:55:15","modified_gmt":"2025-10-07T01:55:15","slug":"boston-university-cs-677-final-project","status":"publish","type":"page","link":"https:\/\/shayhmaor.dev\/?page_id=326","title":{"rendered":"Boston University CS 677 Final Project"},"content":{"rendered":"\n<h1 class=\"wp-block-heading\">Data Science &#8211; Memorial Sloan Kettering Cancer Center Breast Cancer Study 2018 (cBioPortal)<\/h1>\n\n\n\n<p>An implementation of Machine Learning and Data Science on a Breast Cancer study from Memorial Sloan Kettering Cancer Center from 2018. This project was part of an intensive 7 week Boston University CS 677 course on Data Science Fundamentals. All data was made available on cBioPortal and I&#8217;ve added it here as well.<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-vimeo wp-block-embed-vimeo\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"Data Science Final Project\" src=\"https:\/\/player.vimeo.com\/video\/1125032137?dnt=1&amp;app_id=122963\" width=\"500\" height=\"321\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>(<a href=\"https:\/\/github.com\/mentatpsi\/RandomizedCancerGenomics\/blob\/main\/Final%20Project%20Continued%20Work.ipynb\">View on GitHub<\/a>).<\/p>\n\n\n\n<h2 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#features\"><\/a><strong>Features<\/strong><\/h2>\n\n\n\n<p>In this study we perform relational data analysis, we perform several machine learning algorithms. We end it with creating a contingency table to find association between gene mutations to possibly help visualize relations across gene networks that were discovered in the decision tree step. The Genes choosen to build the contigency table is non-deterministic, running this locally will produce a different set each time.<\/p>\n\n\n\n<h2 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#purpose\"><\/a><strong>Purpose<\/strong><\/h2>\n\n\n\n<p>The purpose of this analysis was to help researchers with a collection of tools for data science. It contains query functions, dataframes based on clinical outcome, relational data mapping, and more. I have provided some analysis of the genetics based on small research into each gene mutation. My background is Computer Science, with some minor Computational Biology work. I have highlighted as well some genes that have only been present in each outcome.<\/p>\n\n\n\n<p>I hope this serves a greater purpose to help out researchers.<\/p>\n\n\n\n<h3 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#algorithms\"><\/a><strong>Algorithms<\/strong><\/h3>\n\n\n\n<h4 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#random-tree-ensemble\"><\/a>Random Tree Ensemble<\/h4>\n\n\n\n<p>A Random Tree Ensemble is a collection of Decision trees with non-deterministic properties designed to prevent over-fitting through random selection of sample training data and feature sets (columns &#8211; in our case gene mutations). They construct a decision tree through usuage of information entropy to enhance the gain of information across a decision node. These trees then form a collection of decision makers that vote on a classification together.<\/p>\n\n\n\n<h4 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#neural-network\"><\/a>Neural Network<\/h4>\n\n\n\n<p>The neural network used focuses on a logistic regression activation function, which works through passing a linear regression through a sigmoid function to inspire logical classifcation (binary). In the case of activation, it uses this for propagation throughout the Neural network. We attempt to predict survival based on gene mutations.<\/p>\n\n\n\n<h4 class=\"wp-block-heading has-text-align-center\"><a href=\"https:\/\/github.com\/mentatpsi\/BCDataScience\/#naive-bayes\"><\/a>Naive Bayes<\/h4>\n\n\n\n<p>Naive Bayes employs conditional probabilities and Bayes Theorem to determine class. It is called Naive because it employs the notion of independence to determine class which allows for unique mathematical operations not possible in dependence.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Data Science &#8211; Memorial Sloan Kettering Cancer Center Breast Cancer Study 2018 (cBioPortal) An implementation of Machine Learning and Data Science on a Breast Cancer study from Memorial Sloan Kettering Cancer Center from 2018. This project was part of an intensive 7 week Boston University CS 677 course on Data Science Fundamentals. All data was [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"class_list":["post-326","page","type-page","status-publish","hentry"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/pages\/326","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=326"}],"version-history":[{"count":3,"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/pages\/326\/revisions"}],"predecessor-version":[{"id":483,"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=\/wp\/v2\/pages\/326\/revisions\/483"}],"wp:attachment":[{"href":"https:\/\/shayhmaor.dev\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=326"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}