add csvs

csvs/baby_tests.csv

@@ -0,0 +1,7 @@
+questions
+What is the co-occurence frequency of somatic homozygous deletions in CDKN2A and CDKN2B in the mesothelioma project TCGA-MESO in the genomic data commons?
+What is the co-occurence frequency of somatic heterozygous deletions in BRCA2 and NF1 in the Kidney Chromophobe TCGA-KICH project in the genomic data commons?
+What percentage of ovarian serous cystadenocarcinoma cases have a somatic heterozygous deletion in BRCA1 and simple somatic mutations in BRCA1 in the genomic data commons?
+What percentage of cancer cases have simple somatic mutations or copy number variants in KIT in the genomic data commons for Acute Myeloid Leukemia TCGA-LAML project?
+In Stomach Adenocarcinoma TCGA-STAD project what is the occurrence rate of microsatellite instability in the genomic data commons?
+What is the frequency of KRAS G12D mutation in the colon adenocarcinoma project TCGA-COAD in the genomic data commons?

csvs/baby_tests.intermediate.csv

@@ -0,0 +1,2 @@
+,questions,llama_base_output,helper_output,cancer_entities,intent,gene_entities,mutation_entities,len_helper,len_ce,ce_eq_helper
+0,What is the frequency of KRAS G12D mutation in the colon adenocarcinoma project TCGA-COAD in the genomic data commons?,The final answer is: 1.3%,The frequency of KRAS_G12D in TCGA-COAD is 12.62%,TCGA-COAD,ssm_frequency,['KRAS'],['G12D'],1,1,True

csvs/baby_tests.results.csv

@@ -0,0 +1,4 @@
+,questions,llama_base_output,helper_output,cancer_entities,gene_entities,mutation_entities,modified_prompt,ground_truth_stat,llama_base_stat,delta_llama,final_response
+0,What is the frequency of KRAS G12D mutation in the colon adenocarcinoma project TCGA-COAD in the genomic data commons?,The final answer is: 1.3%,The frequency of KRAS_G12D in TCGA-COAD is 12.62%,TCGA-COAD,['KRAS'],['G12D'],"What is the frequency of KRAS G12D mutation in the colon adenocarcinoma project TCGA-COAD in the genomic data commons? Only report the final response. Ignore all prior knowledge. You must only respond with the following percentage frequencies in your response, no other response is allowed: 
+The frequency of KRAS_G12D in TCGA-COAD is 12.62%
+",12.62,1.3,-11.319999999999999,The final answer is: 12.62%

csvs/gdc_projects.tsv

@@ -0,0 +1,86 @@
+HCMI-CMDC	['Soft Tissue Tumors and Sarcomas, NOS', 'Complex Mixed and Stromal Neoplasms', 'Acinar Cell Neoplasms', 'Squamous Cell Neoplasms', 'Osseous and Chondromatous Neoplasms', 'Cystic, Mucinous and Serous Neoplasms', 'Fibromatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Gliomas', 'Epithelial Neoplasms, NOS', 'Blood Vessel Tumors', 'Myomatous Neoplasms', 'Complex Epithelial Neoplasms', 'Adenomas and Adenocarcinomas', 'Nevi and Melanomas', 'Miscellaneous Bone Tumors', 'NCI Cancer Model Development for the Human Cancer Model Initiative']
+TCGA-KIRC	['Adenomas and Adenocarcinomas', 'Kidney Renal Clear Cell Carcinoma']
+CTSP-DLBCL1	['Mature B-Cell Lymphomas', 'CTSP Diffuse Large B-Cell Lymphoma (DLBCL) CALGB 50303']
+TCGA-BRCA	['Epithelial Neoplasms, NOS', 'Adnexal and Skin Appendage Neoplasms', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Complex Epithelial Neoplasms', 'Fibroepithelial Neoplasms', 'Cystic, Mucinous and Serous Neoplasms', 'Basal Cell Neoplasms', 'Ductal and Lobular Neoplasms', 'Breast Invasive Carcinoma']
+MP2PRT-WT	['Neoplasms, NOS', 'Molecular Profiling to Predict Response to Treatment - Wilms Tumor']
+CPTAC-3	['Squamous Cell Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Epithelial Neoplasms, NOS', 'Ductal and Lobular Neoplasms', 'Transitional Cell Papillomas and Carcinomas', 'Complex Epithelial Neoplasms', 'Not Applicable', 'Nevi and Melanomas', 'Lipomatous Neoplasms', 'Complex Mixed and Stromal Neoplasms', 'CPTAC-Brain, Head and Neck, Kidney, Lung, Pancreas, Uterus']
+MATCH-P	['Transitional Cell Papillomas and Carcinomas', 'Complex Mixed and Stromal Neoplasms', 'Mesothelial Neoplasms', 'Ductal and Lobular Neoplasms', 'Nevi and Melanomas', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm P']
+MATCH-W	['Adenomas and Adenocarcinomas', 'Ductal and Lobular Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Gliomas', 'Transitional Cell Papillomas and Carcinomas', 'Genomic Characterization CS-MATCH-0007 Arm W']
+MATCH-Z1D	['Complex Mixed and Stromal Neoplasms', 'Myomatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Z1D']
+MATCH-Z1A	['Adenomas and Adenocarcinomas', 'Mesothelial Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Transitional Cell Papillomas and Carcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Z1A']
+MATCH-U	['Mesothelial Neoplasms', 'Fibromatous Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Nerve Sheath Tumors', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm U']
+MATCH-Z1I	['Ductal and Lobular Neoplasms', 'Nevi and Melanomas', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Z1I']
+MATCH-Q	['Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Q']
+MATCH-Z1B	['Transitional Cell Papillomas and Carcinomas', 'Squamous Cell Neoplasms', 'Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Z1B']
+MATCH-H	['Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm H']
+MATCH-C1	['Nevi and Melanomas', 'Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm C1']
+OHSU-CNL	['Chronic Myeloproliferative Disorders', 'Philadelphia-Negative Neutrophilic Leukemias (CNL/aCML/MDS/MPNu)']
+NCICCR-DLBCL	['Mature B-Cell Lymphomas', 'Genomic Variation in Diffuse Large B Cell Lymphomas']
+CMI-ASC	['Soft Tissue Tumors and Sarcomas, NOS', 'Count Me In (CMI): The Angiosarcoma (ASC) Project']
+CDDP_EAGLE-1	['Adenomas and Adenocarcinomas', 'CDDP Integrative Analysis of Lung Adenocarcinoma (Phase 2)']
+FM-AD	['Miscellaneous Tumors', 'Complex Mixed and Stromal Neoplasms', 'Mesothelial Neoplasms', 'Ductal and Lobular Neoplasms', 'Thymic Epithelial Neoplasms', 'Cystic, Mucinous and Serous Neoplasms', 'Paragangliomas and Glomus Tumors', 'Gliomas', 'Complex Epithelial Neoplasms', 'Nevi and Melanomas', 'Meningiomas', 'Neuroepitheliomatous Neoplasms', 'Not Reported', 'Mucoepidermoid Neoplasms', 'Adenomas and Adenocarcinomas', 'Acinar Cell Neoplasms', 'Adnexal and Skin Appendage Neoplasms', 'Basal Cell Neoplasms', 'Transitional Cell Papillomas and Carcinomas', 'Specialized Gonadal Neoplasms', 'Germ Cell Neoplasms', 'Epithelial Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Foundation Medicine Adult Cancer Clinical Dataset (FM-AD)']
+MATCH-Y	['Adenomas and Adenocarcinomas', 'Fibromatous Neoplasms', 'Myomatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Transitional Cell Papillomas and Carcinomas', 'Genomic Characterization CS-MATCH-0007 Arm Y']
+MATCH-B	['Transitional Cell Papillomas and Carcinomas', 'Ductal and Lobular Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Nerve Sheath Tumors', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm B']
+MATCH-N	['Complex Mixed and Stromal Neoplasms', 'Myomatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm N']
+CPTAC-2	['Ductal and Lobular Neoplasms', 'Cystic, Mucinous and Serous Neoplasms', 'Squamous Cell Neoplasms', 'Not Reported', 'Adenomas and Adenocarcinomas', 'CPTAC-Breast, Colon, Ovary']
+MATCH-I	['Soft Tissue Tumors and Sarcomas, NOS', 'Myomatous Neoplasms', 'Nevi and Melanomas', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Osseous and Chondromatous Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm I']
+MATCH-S1	['Complex Mixed and Stromal Neoplasms', 'Soft Tissue Tumors and Sarcomas, NOS', 'Myomatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Nerve Sheath Tumors', 'Squamous Cell Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm S1']
+MATCH-R	['Mature B-Cell Lymphomas', 'Ductal and Lobular Neoplasms', 'Nevi and Melanomas', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Mature T- and NK-Cell Lymphomas', 'Osseous and Chondromatous Neoplasms', 'Adenomas and Adenocarcinomas', 'Genomic Characterization CS-MATCH-0007 Arm R']
+VAREPOP-APOLLO	['Squamous Cell Neoplasms', 'Epithelial Neoplasms, NOS', 'VA Research Precision Oncology Program']
+MATCH-S2	['Nevi and Melanomas', 'Genomic Characterization CS-MATCH-0007 Arm S2']
+EXCEPTIONAL_RESPONDERS-ER	['Complex Mixed and Stromal Neoplasms', 'Myomatous Neoplasms', 'Ductal and Lobular Neoplasms', 'Nevi and Melanomas', 'Epithelial Neoplasms, NOS', 'Neoplasms, NOS', 'Squamous Cell Neoplasms', 'Gliomas', 'Adenomas and Adenocarcinomas', 'Exceptional Responders']
+ORGANOID-PANCREATIC	['Unknown', 'Adenomas and Adenocarcinomas', 'Pancreas Cancer Organoid Profiling']
+TRIO-CRU	['Not Applicable', 'Ukrainian National Research Center for Radiation Medicine Trio Study']
+BEATAML1.0-COHORT	['Plasma Cell Tumors', 'Myelodysplastic Syndromes', 'Unknown', 'Chronic Myeloproliferative Disorders', 'Myeloid Leukemias', 'Leukemias, NOS', 'Functional Genomic Landscape of Acute Myeloid Leukemia']
+BEATAML1.0-CRENOLANIB	['Myeloid Leukemias', 'Clinical Resistance to Crenolanib in Acute Myeloid Leukemia Due to Diverse Molecular Mechanisms']
+CMI-MPC	['Adenomas and Adenocarcinomas', 'Count Me In (CMI): The Metastatic Prostate Cancer (MPC) Project']
+CMI-MBC	['Ductal and Lobular Neoplasms', 'Count Me In (CMI): The Metastatic Breast Cancer (MBC) Project']
+TARGET-NBL	['Neuroepitheliomatous Neoplasms', 'Not Applicable', 'Neuroblastoma']
+TARGET-RT	['Complex Mixed and Stromal Neoplasms', 'Rhabdoid Tumor']
+TARGET-WT	['Complex Mixed and Stromal Neoplasms', 'High-Risk Wilms Tumor']
+TARGET-CCSK	['Complex Mixed and Stromal Neoplasms', 'Clear Cell Sarcoma of the Kidney']
+CGCI-HTMCP-LC	['Paragangliomas and Glomus Tumors', 'Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Epithelial Neoplasms, NOS', 'Complex Epithelial Neoplasms', 'Neoplasms, NOS', 'HIV+ Tumor Molecular Characterization Project - Lung Cancer']
+CGCI-HTMCP-CC	['Adenomas and Adenocarcinomas', 'Squamous Cell Neoplasms', 'Epithelial Neoplasms, NOS', 'Complex Epithelial Neoplasms', 'HIV+ Tumor Molecular Characterization Project - Cervical Cancer']
+TARGET-OS	['Osseous and Chondromatous Neoplasms', 'Osteosarcoma']
+TARGET-ALL-P2	['Lymphoid Leukemias', 'Acute Lymphoblastic Leukemia - Phase II']
+CGCI-HTMCP-DLBCL	['Mature B-Cell Lymphomas', 'HIV+ Tumor Molecular Characterization Project - Diffuse Large B-Cell Lymphoma']
+APOLLO-LUAD	['Adenomas and Adenocarcinomas', 'APOLLO1: Proteogenomic characterization of lung adenocarcinoma']
+WCDT-MCRPC	['Adenomas and Adenocarcinomas', 'Genomic Characterization of Metastatic Castration Resistant Prostate Cancer']
+MMRF-COMMPASS	['Plasma Cell Tumors', 'Multiple Myeloma CoMMpass Study']
+TARGET-AML	['Not Applicable', 'Myeloid Leukemias', 'Acute Myeloid Leukemia']
+TARGET-ALL-P3	['Myeloid Leukemias', 'Not Applicable', 'Lymphoid Leukemias', 'Leukemias, NOS', 'Acute Lymphoblastic Leukemia - Phase III']
+CGCI-BLGSP	['Mature B-Cell Lymphomas', 'Burkitt Lymphoma Genome Sequencing Project']
+MP2PRT-ALL	['Acute Lymphoblastic Leukemia', 'Lymphoid Leukemias', 'Molecular Profiling to Predict Response to Treatment for Acute Lymphoblastic Leukemia']
+TARGET-ALL-P1	['Lymphoid Leukemias', 'Acute Lymphoblastic Leukemia - Phase I']
+TCGA-DLBC	['Mature B-Cell Lymphomas', 'Not Reported', 'Lymphoid Neoplasm Diffuse Large B-cell Lymphoma']
+TCGA-PCPG	['Paragangliomas and Glomus Tumors', 'Pheochromocytoma and Paraganglioma']
+TCGA-READ	['Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Rectum Adenocarcinoma']
+TCGA-CHOL	['Adenomas and Adenocarcinomas', 'Cholangiocarcinoma']
+TCGA-ESCA	['Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Esophageal Carcinoma']
+TCGA-THYM	['Thymic Epithelial Neoplasms', 'Thymoma']
+TCGA-MESO	['Mesothelial Neoplasms', 'Mesothelioma']
+TCGA-UVM	['Nevi and Melanomas', 'Paragangliomas and Glomus Tumors', 'Uveal Melanoma']
+TCGA-KICH	['Adenomas and Adenocarcinomas', 'Kidney Chromophobe']
+TCGA-SARC	['Fibromatous Neoplasms', 'Nerve Sheath Tumors', 'Lipomatous Neoplasms', 'Synovial-like Neoplasms', 'Soft Tissue Tumors and Sarcomas, NOS', 'Myomatous Neoplasms', 'Sarcoma']
+TCGA-PAAD	['Epithelial Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Ductal and Lobular Neoplasms', 'Pancreatic Adenocarcinoma']
+TCGA-UCS	['Complex Mixed and Stromal Neoplasms', 'Basal Cell Neoplasms', 'Uterine Carcinosarcoma']
+TCGA-LIHC	['Adenomas and Adenocarcinomas', 'Liver Hepatocellular Carcinoma']
+TCGA-KIRP	['Adenomas and Adenocarcinomas', 'Kidney Renal Papillary Cell Carcinoma']
+TCGA-LAML	['Myeloid Leukemias', 'Acute Myeloid Leukemia']
+TCGA-ACC	['Adenomas and Adenocarcinomas', 'Adrenocortical Carcinoma']
+TCGA-TGCT	['Germ Cell Neoplasms', 'Testicular Germ Cell Tumors']
+TCGA-SKCM	['Nevi and Melanomas', 'Skin Cutaneous Melanoma']
+TCGA-CESC	['Complex Epithelial Neoplasms', 'Adenomas and Adenocarcinomas', 'Squamous Cell Neoplasms', 'Cystic, Mucinous and Serous Neoplasms', 'Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma']
+TCGA-COAD	['Complex Epithelial Neoplasms', 'Epithelial Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Colon Adenocarcinoma']
+TCGA-BLCA	['Epithelial Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Transitional Cell Papillomas and Carcinomas', 'Squamous Cell Neoplasms', 'Bladder Urothelial Carcinoma']
+TCGA-UCEC	['Epithelial Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Not Reported', 'Uterine Corpus Endometrial Carcinoma']
+TCGA-PRAD	['Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Acinar Cell Neoplasms', 'Ductal and Lobular Neoplasms', 'Prostate Adenocarcinoma']
+TCGA-STAD	['Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Stomach Adenocarcinoma']
+REBC-THYR	['Epithelial Neoplasms, NOS', 'Adenomas and Adenocarcinomas', 'Comprehensive genomic characterization of radiation-related papillary thyroid cancer in the Ukraine']
+TCGA-LGG	['Gliomas', 'Brain Lower Grade Glioma']
+TCGA-HNSC	['Squamous Cell Neoplasms', 'Head and Neck Squamous Cell Carcinoma']
+TCGA-LUAD	['Adenomas and Adenocarcinomas', 'Cystic, Mucinous and Serous Neoplasms', 'Acinar Cell Neoplasms', 'Ductal and Lobular Neoplasms', 'Lung Adenocarcinoma']
+TCGA-THCA	['Squamous Cell Neoplasms', 'Adenomas and Adenocarcinomas', 'Epithelial Neoplasms, NOS', 'Thyroid Carcinoma']
+TCGA-GBM	['Gliomas', 'Not Reported', 'Glioblastoma Multiforme']
+TCGA-LUSC	['Adenomas and Adenocarcinomas', 'Squamous Cell Neoplasms', 'Lung Squamous Cell Carcinoma']
+TCGA-OV	['Cystic, Mucinous and Serous Neoplasms', 'Not Reported', 'Ovarian Serous Cystadenocarcinoma']

csvs/mini_tests.csv

@@ -0,0 +1,14 @@
+questions
+What is the frequency of KRAS G12D mutation in the colon adenocarcinoma project TCGA-COAD in the genomic data commons?
+What is the co-occurence frequency of IDH1 R132H and TP53 R273C simple somatic mutations in the low grade glioma project TCGA-LGG in the genomic data commons?
+What is the frequency of somatic homozygous deletions in CDKN2A in the lung squamous cell carcinoma project TCGA-LUSC in the genomic data commons?
+What is the frequency of somatic heterozygous deletions in PTEN in the glioblastoma project TCGA-GBM in the genomic data commons?
+In Adrenocortical Carcinoma TCGA-ACC project data from the genomic  data commons what is the frequency of KRAS amplification?
+Can you provide the frequency of BRAF gain in Uveal Melanoma TCGA-UVM project in the genomic data commons?
+What is the co-occurence frequency of somatic homozygous deletions in CDKN2A and CDKN2B in the mesothelioma project TCGA-MESO in the genomic data commons?
+What is the co-occurence frequency of somatic heterozygous deletions in BRCA2 and NF1 in the Kidney Chromophobe TCGA-KICH project in the genomic data commons?
+What percentage of ovarian serous cystadenocarcinoma cases have a somatic heterozygous deletion in BRCA1 and simple somatic mutations in BRCA1 in the genomic data commons?
+What is the incidence of simple somatic mutations or copy number variants in PDGFRA in the genomic data commons for Uterine Carcinosarcoma TCGA-UCS project?
+What is the incidence of simple somatic mutations or copy number variants in KRAS in the genomic data commons for Testicular Germ Cell Tumors TCGA-TGCT project?
+What percentage of cancer cases have simple somatic mutations or copy number variants in KIT in the genomic data commons for Acute Myeloid Leukemia TCGA-LAML project?
+In Stomach Adenocarcinoma TCGA-STAD project what is the occurrence rate of microsatellite instability in the genomic data commons?