"]},"metadata":{"tags":[],"needs_background":"light"}}]},{"cell_type":"markdown","metadata":{"id":"RO1sfVjpMvOf"},"source":["###Desafio 01: Encontrar o TOP 10 das ações do MOA (inibidor,agonista...)"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":363},"id":"TyCE31fIXhzE","executionInfo":{"status":"ok","timestamp":1620350242765,"user_tz":180,"elapsed":654,"user":{"displayName":"Lucas Alves","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GggnLgsIu7-n6jYQ_ljAdv3Gc4bgSyInJ-NQwATIFU=s64","userId":"05442089660626989204"}},"outputId":"9df2ca78-a558-4ccd-f08f-0015b1075f49"},"source":["#contagem_moa = dados_resultados.select_dtypes('int64').sum().sort_values(ascending=False)\n","#contagem_moa\n","\n","MOA = np.unique([col.split('_')[-1] for col in dados_resultados.drop('id',axis=1).columns])\n","freq = dados_resultados.drop(['id','n_moa','ativo_moa'],axis=1).sum()\n","contador = dict.fromkeys(MOA,[0])\n","for name in freq.index:\n"," contador[name.split('_')[-1]] += freq[name]\n","count = pd.DataFrame.from_dict(contador).T.rename({0:\"count\"},axis=1).sort_values(by='count', ascending=False)\n","count.head(10)"],"execution_count":46,"outputs":[{"output_type":"execute_result","data":{"text/html":["
\n","\n","
\n"," \n","
\n","
\n","
count
\n","
\n"," \n"," \n","
\n","
inhibitor
\n","
9693
\n","
\n","
\n","
antagonist
\n","
3449
\n","
\n","
\n","
agonist
\n","
2330
\n","
\n","
\n","
blocker
\n","
323
\n","
\n","
\n","
agent
\n","
150
\n","
\n","
\n","
activator
\n","
115
\n","
\n","
\n","
local
\n","
80
\n","
\n","
\n","
antioxidant
\n","
73
\n","
\n","
\n","
anti-inflammatory
\n","
73
\n","
\n","
\n","
immunosuppressant
\n","
73
\n","
\n"," \n","
\n","
"],"text/plain":[" count\n","inhibitor 9693\n","antagonist 3449\n","agonist 2330\n","blocker 323\n","agent 150\n","activator 115\n","local 80\n","antioxidant 73\n","anti-inflammatory 73\n","immunosuppressant 73"]},"metadata":{"tags":[]},"execution_count":46}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"0u_77nL0YWkK","executionInfo":{"status":"ok","timestamp":1620349913045,"user_tz":180,"elapsed":630,"user":{"displayName":"Lucas Alves","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GggnLgsIu7-n6jYQ_ljAdv3Gc4bgSyInJ-NQwATIFU=s64","userId":"05442089660626989204"}},"outputId":"e07908a8-7658-42a6-8585-0b9e8a5c22b3"},"source":["contagem_moa"],"execution_count":43,"outputs":[{"output_type":"execute_result","data":{"text/plain":["n_moa 50532\n","nfkb_inhibitor 832\n","proteasome_inhibitor 726\n","cyclooxygenase_inhibitor 435\n","dopamine_receptor_antagonist 424\n"," ... \n","elastase_inhibitor 6\n","steroid 6\n","calcineurin_inhibitor 6\n","atp-sensitive_potassium_channel_antagonist 1\n","erbb2_inhibitor 1\n","Length: 207, dtype: int64"]},"metadata":{"tags":[]},"execution_count":43}]},{"cell_type":"markdown","metadata":{"id":"P2lX0Q8bRF0c"},"source":["###Desafio 02: Criar a coluna eh_controle para quando na linha tratamento == com_controle"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":255},"id":"CaeHmjYYZrQV","executionInfo":{"status":"ok","timestamp":1620350408886,"user_tz":180,"elapsed":617,"user":{"displayName":"Lucas Alves","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GggnLgsIu7-n6jYQ_ljAdv3Gc4bgSyInJ-NQwATIFU=s64","userId":"05442089660626989204"}},"outputId":"9364b8f0-d303-43c6-9567-bdd776008784"},"source":["dados_combinados['eh_controle'] = (dados_combinados['tratamento'] == 'com_controle')\n","dados_combinados.head()"],"execution_count":48,"outputs":[{"output_type":"execute_result","data":{"text/html":["
"],"text/plain":[" id tratamento tempo ... tempo_24 tempo_48 tempo_72\n","0 id_000644bb2 com_droga 24 ... True False False\n","1 id_000779bfc com_droga 72 ... False False True\n","2 id_000a6266a com_droga 48 ... False True False\n","3 id_0015fd391 com_droga 48 ... False True False\n","4 id_001626bd3 com_droga 72 ... False False True\n","\n","[5 rows x 883 columns]"]},"metadata":{"tags":[]},"execution_count":51}]},{"cell_type":"markdown","metadata":{"id":"DYOr1dzpRp-Z"},"source":["###Desafio 04: Estudar obre combinações de DF"]},{"cell_type":"markdown","metadata":{"id":"0mYEgaIfUq-R"},"source":["###Desafio 05: Fazer análise mais detalhada considerando tempo e dose, para comparar as distribuições (Escolher uma droga e comparar com controle)"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":532},"id":"RksiwOy2atZN","executionInfo":{"status":"ok","timestamp":1620351031089,"user_tz":180,"elapsed":1283,"user":{"displayName":"Lucas Alves","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GggnLgsIu7-n6jYQ_ljAdv3Gc4bgSyInJ-NQwATIFU=s64","userId":"05442089660626989204"}},"outputId":"688e8963-c925-4fa0-8cf4-8d0d4d34cae3"},"source":["composto = dados_combinados[dados_combinados['composto']=='8c7f86626']\n","controle = dados_combinados[dados_combinados['tratamento']=='com_controle']\n","\n","fig, axs = plt.subplots(1,2,figsize=(20,8))\n","\n","sns.boxplot(data=composto,y='g-0', x='tempo', hue='dose',ax=axs[0])\n","axs[0].set_title('Composto 8c7f86626')\n","sns.boxplot(data=controle,y='g-0', x='tempo', hue='dose',ax=axs[1])\n","axs[1].set_title('Controle')"],"execution_count":67,"outputs":[{"output_type":"execute_result","data":{"text/plain":["Text(0.5, 1.0, 'Controle')"]},"metadata":{"tags":[]},"execution_count":67},{"output_type":"display_data","data":{"image/png":"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\n","text/plain":["
"]},"metadata":{"tags":[],"needs_background":"light"}}]},{"cell_type":"markdown","metadata":{"id":"b7uMkYFbU1rb"},"source":["###Desafio 06: Descobrir se tem algum composto que dependendo da configuraçõa do experimento, ativa ou não ativa algum MOA"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":424},"id":"PgG1R4wAc2k5","executionInfo":{"status":"ok","timestamp":1620351318136,"user_tz":180,"elapsed":608,"user":{"displayName":"Lucas Alves","photoUrl":"https://lh3.googleusercontent.com/a-/AOh14GggnLgsIu7-n6jYQ_ljAdv3Gc4bgSyInJ-NQwATIFU=s64","userId":"05442089660626989204"}},"outputId":"71427ea6-2fee-429f-8237-69277000ec52"},"source":["dados_combinados[['composto','ativo_moa']].query('ativo_moa == True')"],"execution_count":69,"outputs":[{"output_type":"execute_result","data":{"text/html":["
"],"text/plain":["Empty DataFrame\n","Columns: [composto, ativo_moa_x, ativo_moa_y]\n","Index: []"]},"metadata":{"tags":[]},"execution_count":71}]},{"cell_type":"markdown","metadata":{"id":"-3kgmxB2VSTJ"},"source":["###Desafio 07: Descobrir se tem algum composto que dependendo da configuraçõa do experimento, ativa MOAs diferentes"]},{"cell_type":"markdown","metadata":{"id":"GCVh7clWVfrF"},"source":["###Desafio 08: Resumo do que voce aprendeu com os dados"]},{"cell_type":"markdown","metadata":{"id":"lg8_b4ffVyYl"},"source":["Analisamos a base de resultados e verificamos qual mecanismos de ação ele estava acionando."]},{"cell_type":"code","metadata":{"id":"lVIEhd1cM7OZ"},"source":[""],"execution_count":null,"outputs":[]}]}
\ No newline at end of file