{"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":"4.4.0"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":87793,"databundleVersionId":12276181,"sourceType":"competition"}],"dockerImageVersionId":30749,"isInternetEnabled":true,"language":"r","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This R environment comes with many helpful analytics packages installed\n# It is defined by the kaggle/rstats Docker image: https://github.com/kaggle/docker-rstats\n# For example, here's a helpful package to load\n\nlibrary(tidyverse) # metapackage of all tidyverse packages\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nlist.files(path = \"../input\")\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"051d70d956493feee0c6d64651c6a088724dca2a","_execution_state":"idle","trusted":true,"execution":{"iopub.status.busy":"2025-05-16T02:44:14.195026Z","iopub.execute_input":"2025-05-16T02:44:14.196746Z","iopub.status.idle":"2025-05-16T02:44:15.395408Z","shell.execute_reply":"2025-05-16T02:44:15.393562Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df <- read.csv('/kaggle/input/stanford-rna-3d-folding/train_labels.csv')\nhead(df)\nsummary(df)\nlibrary(neuralnet)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-16T03:09:13.565333Z","iopub.execute_input":"2025-05-16T03:09:13.567092Z","iopub.status.idle":"2025-05-16T03:09:14.36027Z","shell.execute_reply":"2025-05-16T03:09:14.358429Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"head(RNA.df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T16:04:01.008643Z","iopub.execute_input":"2025-05-19T16:04:01.010338Z","iopub.status.idle":"2025-05-19T16:04:01.045918Z","shell.execute_reply":"2025-05-19T16:04:01.043336Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"colSums(is.na(RNA.df))\ndim(RNA.df.test)\nlibrary(neuralnet)\nRNA.df.net.1 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 10,startweights = 0.7,learningrate = 0.0009,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nplot(RNA.df.net.1)\nlibrary(dplyr)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_1=predict(RNA.df.net.1,RNA.df.test,type=\"response\"))\nhead(RNA.df.test)\nRNA.df.net.2 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 12,startweights = 0.5,learningrate = 0.0004,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_1=predict(RNA.df.net.2,RNA.df.test,type=\"response\"))\nRNA.df.net.3 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 9,startweights = 0.2,learningrate = 0.0005,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_z_1=predict(RNA.df.net.3,RNA.df.test,type=\"response\"))\nRNA.df.net.4 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 11,startweights = 0.3,learningrate = 0.0006,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_2=predict(RNA.df.net.4,RNA.df.test,type=\"response\"))\nRNA.df.net.5 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 7,startweights = 0.4,learningrate = 0.0007,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_2=predict(RNA.df.net.5,RNA.df.test,type=\"response\"))\nRNA.df.net.6 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 8,startweights = 0.4,learningrate = 0.0002,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_Z_2=predict(RNA.df.net.6,RNA.df.test,type=\"response\"))\nRNA.df.net.7 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 13,startweights = 0.2,learningrate = 0.0004,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_3=predict(RNA.df.net.7,RNA.df.test,type=\"response\"))\nRNA.df.net.8 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 7,startweights = 0.7,learningrate = 0.0009,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_3=predict(RNA.df.net.8,RNA.df.test,type=\"response\"))\nRNA.df.net.9 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 15,startweights = 0.2,learningrate = 0.0005,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\n\nRNA.df.test<-RNA.df.test%>%mutate(pred_z_3=predict(RNA.df.net.9,RNA.df.test,type=\"response\"))\nRNA.df.net.10 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 13,startweights = 0.6,learningrate = 0.0002,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_4=predict(RNA.df.net.10,RNA.df.test,type=\"response\"))\nRNA.df.net.11 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 14,startweights = 0.7,learningrate = 0.0006,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_4=predict(RNA.df.net.11,RNA.df.test,type=\"response\"))\nRNA.df.net.12 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 16,startweights = 0.3,learningrate = 0.0005,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_z_4=predict(RNA.df.net.12,RNA.df.test,type=\"response\"))\nRNA.df.net.13 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 10,startweights = 0.6,learningrate = 0.0003,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_5=predict(RNA.df.net.13,RNA.df.test,type=\"response\"))\nRNA.df.net.14 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 16,startweights = 0.5,learningrate = 0.0004,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_5=predict(RNA.df.net.14,RNA.df.test,type=\"response\"))\nRNA.df.net.15 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 19,startweights = 0.4,learningrate = 0.0007,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T16:34:05.583818Z","iopub.execute_input":"2025-05-19T16:34:05.585585Z","iopub.status.idle":"2025-05-19T16:38:29.580926Z","shell.execute_reply":"2025-05-19T16:38:29.539985Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"RNA.df.net.10 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 13,startweights = 0.6,learningrate = 0.0002,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_4=predict(RNA.df.net.10,RNA.df.test,type=\"response\"))\nRNA.df.net.11 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 14,startweights = 0.7,learningrate = 0.0006,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_4=predict(RNA.df.net.11,RNA.df.test,type=\"response\"))\nRNA.df.net.12 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 16,startweights = 0.3,learningrate = 0.0005,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_z_4=predict(RNA.df.net.12,RNA.df.test,type=\"response\"))\nRNA.df.net.13 <- neuralnet(x_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 10,startweights = 0.6,learningrate = 0.0003,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_x_5=predict(RNA.df.net.13,RNA.df.test,type=\"response\"))\nRNA.df.net.14 <- neuralnet(y_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 16,startweights = 0.5,learningrate = 0.0004,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nRNA.df.test<-RNA.df.test%>%mutate(pred_y_5=predict(RNA.df.net.14,RNA.df.test,type=\"response\"))\nRNA.df.net.15 <- neuralnet(z_1~Adenine+Guanine+Cytosine+Uracil,data=RNA.df.train,hidden = 19,startweights = 0.4,learningrate = 0.0007,algorithm = \"rprop+\",err.fct = \"sse\",linear.output = FALSE)\nhead(RNA.df.test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T16:48:37.308607Z","iopub.execute_input":"2025-05-19T16:48:37.31026Z","iopub.status.idle":"2025-05-19T16:54:12.465501Z","shell.execute_reply":"2025-05-19T16:54:12.461094Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"RNA.df.test$x_1<-NULL\nRNA.df.test$y_1<-NULL\nRNA.df.test$z_1<-NULL\nRNA.df.test$z_1<-NULL\nRNA.df.test$Adenine<-NULL\nRNA.df.test$Guanine<-NULL\nRNA.df.test$Cytosine<-NULL\nRNA.df.test$Uracil<-NULL\nhead(RNA.df.test)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T16:58:44.116027Z","iopub.execute_input":"2025-05-19T16:58:44.117703Z","iopub.status.idle":"2025-05-19T16:58:44.17733Z","shell.execute_reply":"2025-05-19T16:58:44.175316Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"RNA.df.test<-RNA.df.test%>%rename(x_1=pred_x_1)\nRNA.df.test<-RNA.df.test%>%rename(y_1=pred_y_1)\nRNA.df.test<-RNA.df.test%>%rename(z_1=pred_z_1)\nRNA.df.test<-RNA.df.test%>%rename(x_2=pred_x_2)\nRNA.df.test<-RNA.df.test%>%rename(y_2=pred_y_2)\nRNA.df.test<-RNA.df.test%>%rename(z_2=pred_Z_2)\nRNA.df.test<-RNA.df.test%>%rename(x_3=pred_x_3)\nRNA.df.test<-RNA.df.test%>%rename(y_3=pred_y_3)\nRNA.df.test<-RNA.df.test%>%rename(z_3=pred_z_3)\nRNA.df.test<-RNA.df.test%>%rename(x_4=pred_x_4)\nRNA.df.test<-RNA.df.test%>%rename(y_4=pred_y_4)\nRNA.df.test<-RNA.df.test%>%rename(z_4=pred_z_4)\nRNA.df.test<-RNA.df.test%>%rename(x_5=pred_x_5)\nRNA.df.test<-RNA.df.test%>%rename(y_5=pred_y_5)\nRNA.df.test<-RNA.df.test%>%rename(z_5=pred_z_5)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"head(RNA.df.test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T17:01:21.440892Z","iopub.execute_input":"2025-05-19T17:01:21.442572Z","iopub.status.idle":"2025-05-19T17:01:21.487329Z","shell.execute_reply":"2025-05-19T17:01:21.484515Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"head(RNA.df.test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-19T17:07:39.287247Z","iopub.execute_input":"2025-05-19T17:07:39.288936Z","iopub.status.idle":"2025-05-19T17:07:39.376577Z","shell.execute_reply":"2025-05-19T17:07:39.373387Z"}},"outputs":[],"execution_count":null}]}