{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":695579747,"defaultBranch":"main","name":"ML-reveals-endotypes-in-lupus-samples-using-transcriptomic-features","ownerLogin":"pbachali16","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-09-23T15:47:01.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/126444454?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1695484022.0","currentOid":""},"activityList":{"items":[{"before":"8e5c616876026a1e0f072b43fbbbc13819c57cb8","after":"cd90ba32acdc06e587ff320cdec32688e7d08563","ref":"refs/heads/main","pushedAt":"2023-09-23T19:05:03.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"update readme","shortMessageHtmlLink":"update readme"}},{"before":"a0498ecfedf5875ff4c1dccbfd761de78d4b15d6","after":"8e5c616876026a1e0f072b43fbbbc13819c57cb8","ref":"refs/heads/main","pushedAt":"2023-09-23T18:59:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"updating bullet points","shortMessageHtmlLink":"updating bullet points"}},{"before":"df1c24b9da60f60e02b4e73e77bc7fec7ec48bf4","after":"a0498ecfedf5875ff4c1dccbfd761de78d4b15d6","ref":"refs/heads/main","pushedAt":"2023-09-23T18:56:56.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"updating readme","shortMessageHtmlLink":"updating readme"}},{"before":"54a46b4dfe05941439c29c9fff9da67881954646","after":"df1c24b9da60f60e02b4e73e77bc7fec7ec48bf4","ref":"refs/heads/main","pushedAt":"2023-09-23T18:51:52.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"initial commit","shortMessageHtmlLink":"initial commit"}},{"before":"107e9763e18a9d6621fbd862c8ac8ed80b43918b","after":"54a46b4dfe05941439c29c9fff9da67881954646","ref":"refs/heads/main","pushedAt":"2023-09-23T18:15:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create Multi-class ML classification","shortMessageHtmlLink":"Create Multi-class ML classification"}},{"before":"6b8620d981794305abc57bcf10b1c3d4b7638f5c","after":"107e9763e18a9d6621fbd862c8ac8ed80b43918b","ref":"refs/heads/main","pushedAt":"2023-09-23T18:15:05.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create SHAP Analysis","shortMessageHtmlLink":"Create SHAP Analysis"}},{"before":"3cd3b77f6029bf0513ba81462cb258c6f8fd2ea4","after":"6b8620d981794305abc57bcf10b1c3d4b7638f5c","ref":"refs/heads/main","pushedAt":"2023-09-23T18:14:50.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create KMeans Clustering","shortMessageHtmlLink":"Create KMeans Clustering"}},{"before":"4967f5f41ac8abd781c0da332fce05e253cf44be","after":"3cd3b77f6029bf0513ba81462cb258c6f8fd2ea4","ref":"refs/heads/main","pushedAt":"2023-09-23T16:25:35.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create Binary ML classification\n\nBinary classification was performed on GSVA scores in Python (v3.8.2) using scikit-learn(0.24.1) to classify the most abnormal endotype [B-H] from the least abnormal endotype (A) using the molecular features. SMOTE was applied to account the class imbalance. 9 different classifiers were built on train data and evaluated the accuracy on test data. The performance of the classifiers was evaluated using accuracy, sensitivity, specificity, Cohen's Kappa score. ROC and Precision-Recall curves were plotted using the Python library matplotlib (v3.3.4).","shortMessageHtmlLink":"Create Binary ML classification"}},{"before":"fe5d5da755970819194ee65e53caeb54b5eac263","after":"4967f5f41ac8abd781c0da332fce05e253cf44be","ref":"refs/heads/main","pushedAt":"2023-09-23T16:10:53.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create Gene Set Variation Analysis\n\nGSVA is a non-parametric, unsupervised method for estimating the variation of pre-defined gene sets in patient and control samples of transcriptomic expression data sets. GSVA works by transforming gene matrix (genebysample) into a gene set by sample matrix resulting in an enrichment-score for each samples and pre-defined gene-set. The input for the GSVA algorithm were a gene expression matrix of log2 expression values and a collection of pre-defined gene sets. Enrichment scores (GSVA scores) were calculated non-parametrically using a Kolmogorov Smirnoff KS-like random walk statistic and a negative value for a particular sample and gene set, means that the gene set has a lower expression than the same gene set with a positive value. The enrichment scores ES were the largest positive and negative random walk deviation from zero, respectively, for sample and gene set. The positive and negative enrichment scores for a particular gene-set depends on the expression levels of the genes that form the pre-defined gene set. If the genes forming the pre-defined gene set were mostly with decreased expression levels with respective sample, then the gene set with respective sample would most likely get negative KS-like random walk statistic (GSVA score) whereas the genes forming the pre-defined gene set were mostly with increased expression levels with respective sample, the gene set with respective sample would most likely get positive KS-like random walk statistic (GSVA score).","shortMessageHtmlLink":"Create Gene Set Variation Analysis"}},{"before":"24814e6550b2188e9d23e789e4ab02e083312305","after":"fe5d5da755970819194ee65e53caeb54b5eac263","ref":"refs/heads/main","pushedAt":"2023-09-23T16:05:41.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Create Data Normalization\n\nWhole-blood gene expression data acquired from publicly available repositories is pre-processed, normalized, log2 transformed and annotated with right gene annotations.","shortMessageHtmlLink":"Create Data Normalization"}},{"before":null,"after":"24814e6550b2188e9d23e789e4ab02e083312305","ref":"refs/heads/main","pushedAt":"2023-09-23T15:47:02.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"pbachali16","name":null,"path":"/pbachali16","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/126444454?s=80&v=4"},"commit":{"message":"Initial commit","shortMessageHtmlLink":"Initial commit"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAADh1E9tQA","startCursor":null,"endCursor":null}},"title":"Activity · pbachali16/ML-reveals-endotypes-in-lupus-samples-using-transcriptomic-features"}