{"metadata":{"kernelspec":{"name":"ir","display_name":"R","language":"R"},"language_info":{"name":"R","codemirror_mode":"r","pygments_lexer":"r","mimetype":"text/x-r-source","file_extension":".r","version":"4.0.5"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"install.packages(\"protr\")\nlibrary(devtools)\ninstall_github(\"dosorio/Peptides\")","metadata":{"execution":{"iopub.status.busy":"2023-07-21T06:57:26.651080Z","iopub.execute_input":"2023-07-21T06:57:26.654178Z","iopub.status.idle":"2023-07-21T06:59:25.824133Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"library(protr)\nlibrary(data.table)\nlibrary(Peptides)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T15:45:28.267379Z","iopub.execute_input":"2023-07-21T15:45:28.269279Z","iopub.status.idle":"2023-07-21T15:45:28.527022Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"seq_train_raw <- readFASTA(\"/kaggle/input/cafa-5-protein-function-prediction/Train/train_sequences.fasta\")\n\nseq_test_raw <- readFASTA(\"/kaggle/input/cafa-5-protein-function-prediction/Test (Targets)/testsuperset.fasta\")","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:19:28.160304Z","iopub.execute_input":"2023-07-21T11:19:28.162341Z","iopub.status.idle":"2023-07-21T11:19:53.458046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Looking for duplicate proteiuns**","metadata":{}},{"cell_type":"code","source":"length(unique(names(seq_train_raw))) == length(seq_train_raw)\nlength(unique(names(seq_test_raw))) == length(seq_test_raw)","metadata":{"execution":{"iopub.status.busy":"2023-07-19T13:20:09.667823Z","iopub.execute_input":"2023-07-19T13:20:09.669389Z","iopub.status.idle":"2023-07-19T13:20:09.726733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sort( table(names(seq_test_raw)), decreasing=TRUE)[1:3]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"seq_test_raw[names(seq_test_raw)=='A0A1D6E0S8\\t4577']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"names(seq_test_raw)[names(seq_test_raw)==\"A0A1D6E0S8\\t4577\"][2] = \"A0A1D6E0S8\\t4577*\"\nlength(unique(names(seq_test_raw))) == length(seq_test_raw)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:21:25.727881Z","iopub.execute_input":"2023-07-21T11:21:25.730802Z","iopub.status.idle":"2023-07-21T11:21:25.775139Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"length(seq_train_raw);   sum((sapply(seq_train_raw, protcheck)))\nlength(seq_test_raw);    sum((sapply(seq_test_raw, protcheck)))","metadata":{"execution":{"iopub.status.busy":"2023-07-21T07:08:23.632108Z","iopub.execute_input":"2023-07-21T07:08:23.634395Z","iopub.status.idle":"2023-07-21T07:08:36.907922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# valid<-list('A','C','D','E','F','G','H','I','K','L','M','N','P','Q','R','S','T','V','W','Y')\n# not_standard <- seq_train_raw[(!sapply(seq_train_raw, protcheck))]\n# u <- unique(as.list(strsplit(paste(list(not_standard)), \"\")[[1]]))\n# u[! u %in% valid]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<table>\n    <tr> <th>Symbol</th> <th>Name</th> <th>Matches</th> </tr>\n    <tr> <td>X *</td> <td>Any amino acid</td> <td>A C D E F G H I K L M N P Q R S T V W Y</td> </tr>\n    <tr> <td>B</td> <td>Asparagine or Aspartic</td> <td>D N</td> </tr>\n    <tr> <td>Z</td> <td>Glutamine or Glutamic acid</td> <td>E Q</td> </tr>\n    <tr> <td>J</td> <td>Leucine or Isoleucine</td> <td>I L</td> </tr>\n</table>\n\n<a href=\"https://meme-suite.org/meme/doc/alphabets.html\">Refrence</a><br>","metadata":{}},{"cell_type":"code","source":"seq_train_standard <- removeGaps(seq_train_raw, pattern = \"-\", replacement = \"\")\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"*\", replacement = \"\")\n\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"X\", replacement = \"\")\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"B\", replacement = \"D\")\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"Z\", replacement = \"E\")\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"J\", replacement = \"L\")\n\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"U\", replacement = \"\")\nseq_train_standard <- removeGaps(seq_train_standard, pattern = \"O\", replacement = \"\")\n\nseq_train <- seq_train_standard[(sapply(seq_train_standard, protcheck))]\nlength(seq_train_raw);  length(seq_train)\n\nseq_train_raw[4];       seq_train[4]","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:21:43.619346Z","iopub.execute_input":"2023-07-21T11:21:43.621008Z","iopub.status.idle":"2023-07-21T11:22:15.124674Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"seq_test_standard <- removeGaps(seq_test_raw, pattern = \"-\", replacement = \"\")\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"*\", replacement = \"\")\n\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"X\", replacement = \"\")\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"B\", replacement = \"D\")\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"Z\", replacement = \"E\")\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"J\", replacement = \"L\")\n\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"U\", replacement = \"\")\nseq_test_standard <- removeGaps(seq_test_standard, pattern = \"O\", replacement = \"\")\n\nseq_test <- seq_test_standard[(sapply(seq_test_standard, protcheck))]\nlength(seq_test_raw);  length(seq_test)\n\nseq_test_raw[4];       seq_test[4]","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:22:15.127568Z","iopub.execute_input":"2023-07-21T11:22:15.129078Z","iopub.status.idle":"2023-07-21T11:22:43.255639Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train <- data.frame(matrix(unlist(seq_train), nrow=length(seq_train),byrow=TRUE),stringsAsFactors=FALSE)\ncolnames(df_train) <- c('seq')\nnrow(df_train)\n\ndf_test <- data.frame(matrix(unlist(seq_test), nrow=length(seq_test),byrow=TRUE),stringsAsFactors=FALSE)\ncolnames(df_test) <- c('seq')\nnrow(df_test)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:22:43.258492Z","iopub.execute_input":"2023-07-21T11:22:43.259967Z","iopub.status.idle":"2023-07-21T11:22:43.316727Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_seq_length <- nchar(seq_train_raw)\ntest_seq_length <- nchar(seq_test_raw)\nsort(train_seq_length)[1:10]\nsort(test_seq_length)[1:10]","metadata":{"execution":{"iopub.status.busy":"2023-07-21T11:23:09.741439Z","iopub.execute_input":"2023-07-21T11:23:09.743281Z","iopub.status.idle":"2023-07-21T11:23:10.176318Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h1><b><center>Protr package</center></b></h1>","metadata":{}},{"cell_type":"markdown","source":"<h3><b><center>extractAAC:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n    \ndf_temp <- (data.frame((lapply(df_train$seq , extractAAC ))))\ndf_extractAAC_train <- transpose(df_temp)\ncolnames(df_extractAAC_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractAAC ))))\ndf_extractAAC_test <- transpose(df_temp)\ncolnames(df_extractAAC_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractAAC_train) <- names(seq_train_raw)\nrownames(df_extractAAC_test) <- names(seq_test_raw)\n\nnrow(df_extractAAC_train);  head(df_extractAAC_train,3)\n\nnrow(df_extractAAC_test);   head(df_extractAAC_test,3)\n\nwrite.csv(df_extractAAC_train,'df_extractAAC_train.csv', row.names=TRUE)\nwrite.csv(df_extractAAC_test, 'df_extractAAC_test.csv', row.names=TRUE)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>extractDC:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , extractDC ))))\ndf_extractDC_train <- transpose(df_temp)\ncolnames(df_extractDC_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractDC ))))\ndf_extractDC_test <- transpose(df_temp)\ncolnames(df_extractDC_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractDC_train) <- names(seq_train_raw)\nrownames(df_extractDC_test) <- names(seq_test_raw)\n\nnrow(df_extractDC_train);  head(df_extractDC_train,3)\n\nnrow(df_extractDC_test);   head(df_extractDC_test,3)\n\nwrite.csv(df_extractDC_train,'df_extractDC_train.csv', row.names=TRUE)\nwrite.csv(df_extractDC_test, 'df_extractDC_test.csv', row.names=TRUE)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>extractCTDC:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , extractCTDC ))))\ndf_extractCTDC_train <- transpose(df_temp)\ncolnames(df_extractCTDC_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractCTDC ))))\ndf_extractCTDC_test <- transpose(df_temp)\ncolnames(df_extractCTDC_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractCTDC_train) <- names(seq_train_raw)\nrownames(df_extractCTDC_test) <- names(seq_test_raw)\n\nnrow(df_extractCTDC_train);  head(df_extractCTDC_train,3)\n\nnrow(df_extractCTDC_test);   head(df_extractCTDC_test,3)\n\nwrite.csv(df_extractCTDC_train,'df_extractCTDC_train.csv', row.names=TRUE)\nwrite.csv(df_extractCTDC_test, 'df_extractCTDC_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-19T09:10:06.031966Z","iopub.execute_input":"2023-07-19T09:10:06.034174Z","iopub.status.idle":"2023-07-19T09:15:12.246309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>extractCTDD:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , extractCTDD ))))\ndf_extractCTDD_train <- transpose(df_temp)\ncolnames(df_extractCTDD_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractCTDD ))))\ndf_extractCTDD_test <- transpose(df_temp)\ncolnames(df_extractCTDD_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractCTDD_train) <- names(seq_train_raw)\nrownames(df_extractCTDD_test) <- names(seq_test_raw)\n\nnrow(df_extractCTDD_train);  head(df_extractCTDD_train,3)\n\nnrow(df_extractCTDD_test);   head(df_extractCTDD_test,3)\n\nwrite.csv(df_extractCTDD_train,'df_extractCTDD_train.csv', row.names=TRUE)\nwrite.csv(df_extractCTDD_test, 'df_extractCTDD_test.csv', row.names=TRUE)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>extractCTDT:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , extractCTDT ))))\ndf_extractCTDT_train <- transpose(df_temp)\ncolnames(df_extractCTDT_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractCTDT ))))\ndf_extractCTDT_test <- transpose(df_temp)\ncolnames(df_extractCTDT_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractCTDT_train) <- names(seq_train_raw)\nrownames(df_extractCTDT_test) <- names(seq_test_raw)\n\nnrow(df_extractCTDT_train);  head(df_extractCTDT_train,3)\n\nnrow(df_extractCTDT_test);   head(df_extractCTDT_test,3)\n\nwrite.csv(df_extractCTDT_train,'df_extractCTDT_train.csv', row.names=TRUE)\nwrite.csv(df_extractCTDT_test, 'df_extractCTDT_test.csv', row.names=TRUE)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>extractBLOSUM:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , extractBLOSUM , k=7 , lag=1))))\ndf_extractBLOSUM_train <- transpose(df_temp)\ncolnames(df_extractBLOSUM_train) <- rownames(df_temp)\n\ndf_temp <- (data.frame((lapply(df_test$seq , extractBLOSUM , k=7 , lag=1))))\ndf_extractBLOSUM_test <- transpose(df_temp)\ncolnames(df_extractBLOSUM_test) <- rownames(df_temp)\n\nprint( Sys.time() - st_time)\n\nrownames(df_extractBLOSUM_train) <- names(seq_train_raw)\nrownames(df_extractBLOSUM_test) <- names(seq_test_raw)\n\nnrow(df_extractBLOSUM_train);  head(df_extractBLOSUM_train,3)\n\nnrow(df_extractBLOSUM_test);   head(df_extractBLOSUM_test,3)\n\nwrite.csv(df_extractBLOSUM_train,'df_extractBLOSUM_k7_l1_train.csv', row.names=TRUE)\nwrite.csv(df_extractBLOSUM_test, 'df_extractBLOSUM_k7_l1_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-19T13:01:27.896236Z","iopub.execute_input":"2023-07-19T13:01:28.076553Z","iopub.status.idle":"2023-07-19T13:13:08.999430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h1><b><center>Peptide package</center></b></h1>","metadata":{}},{"cell_type":"markdown","source":"<h3><b><center>aIndex, boman, mz & instaIndex:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp1 <- (data.frame((lapply(df_train$seq , aIndex ))));\ndf_temp2 <- (data.frame((lapply(df_train$seq , boman ))));\ndf_temp3 <- (data.frame((lapply(df_train$seq , mz ))));\ndf_temp4 <- (data.frame((lapply(df_train$seq , instaIndex )))); \ndf_temp <- rbindlist(list(df_temp1,df_temp2,df_temp3,df_temp4),use.names=FALSE)\ndf_peptides_4index_train <- transpose(df_temp)\ncolnames(df_peptides_4index_train) <- c('aIndex','boman','mz','instaIndex')\nrownames(df_peptides_4index_train) <- names(seq_train_raw)\n\n\ndf_temp1 <- (data.frame((lapply(df_test$seq , aIndex ))));\ndf_temp2 <- (data.frame((lapply(df_test$seq , boman ))));\ndf_temp3 <- (data.frame((lapply(df_test$seq , mz ))));\ndf_test$seq[df_test$seq=='EI'] <- 'EEII'\ndf_temp4 <- (data.frame((lapply(df_test$seq , instaIndex )))); \ndf_test$seq[df_test$seq=='EEII'] <- 'EI'\ndf_temp <- rbindlist(list(df_temp1,df_temp2,df_temp3,df_temp4),use.names=FALSE)\ndf_peptides_4index_test <- transpose(df_temp)\ncolnames(df_peptides_4index_test) <- c('aIndex','boman','mz','instaIndex')\nrownames(df_peptides_4index_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_peptides_4index_train);  head(df_peptides_4index_train,3)\nnrow(df_peptides_4index_test);   head(df_peptides_4index_test,3)\n\nwrite.csv(df_peptides_4index_train,'df_peptides_4index_train.csv', row.names=TRUE)\nwrite.csv(df_peptides_4index_test, 'df_peptides_4index_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T12:03:10.708457Z","iopub.execute_input":"2023-07-21T12:03:10.711132Z","iopub.status.idle":"2023-07-21T12:03:11.979097Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>blosumIndices:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , blosumIndices ))))\ndf_blosumIndices_train <- transpose(df_temp)\ncolnames(df_blosumIndices_train) <- rownames(df_temp)\nrownames(df_blosumIndices_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , blosumIndices ))))\ndf_blosumIndices_test <- transpose(df_temp)\ncolnames(df_blosumIndices_test) <- rownames(df_temp)\nrownames(df_blosumIndices_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_blosumIndices_train);  head(df_blosumIndices_train,3)\nnrow(df_blosumIndices_test);   head(df_blosumIndices_test,3)\n\nwrite.csv(df_blosumIndices_train,'df_blosumIndices_train.csv', row.names=TRUE)\nwrite.csv(df_blosumIndices_test, 'df_blosumIndices_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T09:31:38.435518Z","iopub.execute_input":"2023-07-21T09:31:38.439539Z","iopub.status.idle":"2023-07-21T09:34:51.521599Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>crucianiProperties:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , crucianiProperties ))))\ndf_crucianiProperties_train <- transpose(df_temp)\ncolnames(df_crucianiProperties_train) <- rownames(df_temp)\nrownames(df_crucianiProperties_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , crucianiProperties ))))\ndf_crucianiProperties_test <- transpose(df_temp)\ncolnames(df_crucianiProperties_test) <- rownames(df_temp)\nrownames(df_crucianiProperties_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_crucianiProperties_train);  head(df_crucianiProperties_train,3)\nnrow(df_crucianiProperties_test);   head(df_crucianiProperties_test,3)\n\nwrite.csv(df_crucianiProperties_train,'df_crucianiProperties_train.csv', row.names=TRUE)\nwrite.csv(df_crucianiProperties_test, 'df_crucianiProperties_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T09:39:15.446833Z","iopub.execute_input":"2023-07-21T09:39:15.448703Z","iopub.status.idle":"2023-07-21T09:41:25.317719Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>fasgaiVectors:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , fasgaiVectors ))))\ndf_fasgaiVectors_train <- transpose(df_temp)\ncolnames(df_fasgaiVectors_train) <- rownames(df_temp)\nrownames(df_fasgaiVectors_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , fasgaiVectors ))))\ndf_fasgaiVectors_test <- transpose(df_temp)\ncolnames(df_fasgaiVectors_test) <- rownames(df_temp)\nrownames(df_fasgaiVectors_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_fasgaiVectors_train);  head(df_fasgaiVectors_train,3)\nnrow(df_fasgaiVectors_test);   head(df_fasgaiVectors_test,3)\n\nwrite.csv(df_fasgaiVectors_train,'df_fasgaiVectors_train.csv', row.names=TRUE)\nwrite.csv(df_fasgaiVectors_test, 'df_fasgaiVectors_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T09:44:32.484422Z","iopub.execute_input":"2023-07-21T09:44:32.486284Z","iopub.status.idle":"2023-07-21T09:47:27.285224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>kideraFactors:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , kideraFactors ))))\ndf_kideraFactors_train <- transpose(df_temp)\ncolnames(df_kideraFactors_train) <- rownames(df_temp)\nrownames(df_kideraFactors_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , kideraFactors ))))\ndf_kideraFactors_test <- transpose(df_temp)\ncolnames(df_kideraFactors_test) <- rownames(df_temp)\nrownames(df_kideraFactors_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_kideraFactors_train);  head(df_kideraFactors_train,3)\nnrow(df_kideraFactors_test);   head(df_kideraFactors_test,3)\n\nwrite.csv(df_kideraFactors_train,'df_kideraFactors_train.csv', row.names=TRUE)\nwrite.csv(df_kideraFactors_test, 'df_kideraFactors_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T09:48:46.971119Z","iopub.execute_input":"2023-07-21T09:48:46.973042Z","iopub.status.idle":"2023-07-21T09:52:28.625283Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>mswhimScores:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , mswhimScores ))))\ndf_mswhimScores_train <- transpose(df_temp)\ncolnames(df_mswhimScores_train) <- rownames(df_temp)\nrownames(df_mswhimScores_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , mswhimScores ))))\ndf_mswhimScores_test <- transpose(df_temp)\ncolnames(df_mswhimScores_test) <- rownames(df_temp)\nrownames(df_mswhimScores_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_mswhimScores_train);  head(df_mswhimScores_train,3)\nnrow(df_mswhimScores_test);   head(df_mswhimScores_test,3)\n\nwrite.csv(df_mswhimScores_train, 'df_mswhimScores_train.csv', row.names=TRUE)\nwrite.csv(df_mswhimScores_test, 'df_mswhimScores_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T09:53:26.644207Z","iopub.execute_input":"2023-07-21T09:53:26.646001Z","iopub.status.idle":"2023-07-21T09:55:49.186507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>protFP:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , protFP ))))\ndf_protFP_train <- transpose(df_temp)\ncolnames(df_protFP_train) <- rownames(df_temp)\nrownames(df_protFP_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , protFP ))))\ndf_protFP_test <- transpose(df_temp)\ncolnames(df_protFP_test) <- rownames(df_temp)\nrownames(df_protFP_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_protFP_train);  head(df_protFP_train,3)\nnrow(df_protFP_test);   head(df_protFP_test,3)\n\nwrite.csv(df_protFP_train,'df_protFP_train.csv', row.names=TRUE)\nwrite.csv(df_protFP_test, 'df_protFP_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T10:05:06.776823Z","iopub.execute_input":"2023-07-21T10:05:06.778632Z","iopub.status.idle":"2023-07-21T10:08:02.498759Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>stScales:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , stScales ))))\ndf_stScales_train <- transpose(df_temp)\ncolnames(df_stScales_train) <- rownames(df_temp)\nrownames(df_stScales_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , stScales ))))\ndf_stScales_test <- transpose(df_temp)\ncolnames(df_stScales_test) <- rownames(df_temp)\nrownames(df_stScales_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_stScales_train);  head(df_stScales_train,3)\nnrow(df_stScales_test);   head(df_stScales_test,3)\n\nwrite.csv(df_stScales_train,'df_stScales_train.csv', row.names=TRUE)\nwrite.csv(df_stScales_test, 'df_stScales_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T10:18:20.696491Z","iopub.execute_input":"2023-07-21T10:18:20.698892Z","iopub.status.idle":"2023-07-21T10:21:21.146459Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>tScales:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , tScales ))))\ndf_tScales_train <- transpose(df_temp)\ncolnames(df_tScales_train) <- rownames(df_temp)\nrownames(df_tScales_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , tScales ))))\ndf_tScales_test <- transpose(df_temp)\ncolnames(df_tScales_test) <- rownames(df_temp)\nrownames(df_tScales_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_tScales_train);  head(df_tScales_train,3)\nnrow(df_tScales_test);   head(df_tScales_test,3)\n\nwrite.csv(df_tScales_train,'df_tScales_train.csv', row.names=TRUE)\nwrite.csv(df_tScales_test, 'df_tScales_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T10:21:21.150688Z","iopub.execute_input":"2023-07-21T10:21:21.152302Z","iopub.status.idle":"2023-07-21T10:23:37.141589Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>vhseScales:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , vhseScales ))))\ndf_vhseScales_train <- transpose(df_temp)\ncolnames(df_vhseScales_train) <- rownames(df_temp)\nrownames(df_vhseScales_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , vhseScales ))))\ndf_vhseScales_test <- transpose(df_temp)\ncolnames(df_vhseScales_test) <- rownames(df_temp)\nrownames(df_vhseScales_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_vhseScales_train);  head(df_vhseScales_train,3)\nnrow(df_vhseScales_test);   head(df_vhseScales_test,3)\n\nwrite.csv(df_vhseScales_train,'df_vhseScales_train.csv', row.names=TRUE)\nwrite.csv(df_vhseScales_test, 'df_vhseScales_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T10:23:37.144305Z","iopub.execute_input":"2023-07-21T10:23:37.145823Z","iopub.status.idle":"2023-07-21T10:26:17.672864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<h3><b><center>zScales:</center></b></h3>","metadata":{}},{"cell_type":"code","source":"st_time <- Sys.time() \n\ndf_temp <- (data.frame((lapply(df_train$seq , zScales ))))\ndf_zScales_train <- transpose(df_temp)\ncolnames(df_zScales_train) <- rownames(df_temp)\nrownames(df_zScales_train) <- names(seq_train_raw)\n\ndf_temp <- (data.frame((lapply(df_test$seq , zScales ))))\ndf_zScales_test <- transpose(df_temp)\ncolnames(df_zScales_test) <- rownames(df_temp)\nrownames(df_zScales_test) <- names(seq_test_raw)\n\nprint( Sys.time() - st_time)\n\nnrow(df_zScales_train);  head(df_zScales_train,3)\nnrow(df_zScales_test);   head(df_zScales_test,3)\n\nwrite.csv(df_zScales_train,'df_zScales_train.csv', row.names=TRUE)\nwrite.csv(df_zScales_test, 'df_zScales_test.csv', row.names=TRUE)","metadata":{"execution":{"iopub.status.busy":"2023-07-21T10:28:25.034440Z","iopub.execute_input":"2023-07-21T10:28:25.036390Z","iopub.status.idle":"2023-07-21T10:30:41.257492Z"},"trusted":true},"execution_count":null,"outputs":[]}]}