Merge pull request #600 from d3b-center/subtype_integrate

Undo cancer_group manual override for select sample_ID as per OPC_566
d3b-center · Aug 16, 2024 · 945dfab · 945dfab
2 parents b300e28 + 770d497
commit 945dfab
Show file tree

Hide file tree

Showing 22 changed files with 472 additions and 671 deletions.
diff --git a/analyses/molecular-subtyping-integrate/01-integrate-subtyping.Rmd b/analyses/molecular-subtyping-integrate/01-integrate-subtyping.Rmd
@@ -205,7 +205,6 @@ histology_cg <- histology %>%
     (grepl("xanthogranuloma", pathology_free_text_diagnosis) & broad_histology == "Histiocytic tumor" & pathology_diagnosis == "Other" & 
        sample_id != "7316-188") ~ "Juvenile xanthogranuloma",
     sample_id == "7316-3066" ~ "Neurofibroma/Plexiform",
-    sample_id == "7316-3240" ~ "Diffuse intrinsic pontine glioma",
     cancer_group == "Histiocytic Tumor" ~ str_to_sentence(cancer_group),
     short_histology == "JXG" ~ "Histiocytic tumor",
     cancer_group == "Melanocytoma" ~ "Melanocytic tumor",

diff --git a/analyses/molecular-subtyping-integrate/01-integrate-subtyping.nb.html b/analyses/molecular-subtyping-integrate/01-integrate-subtyping.nb.html
diff --git a/analyses/molecular-subtyping-integrate/results/cancer_group_table_for_README.tsv b/analyses/molecular-subtyping-integrate/results/cancer_group_table_for_README.tsv
@@ -37,6 +37,7 @@ Congenital Mesoblastic Nephroma	Other tumor
 Cranial fasciitis	NA
 Cyst	Other tumor
 Dermoid cyst	NA
+Diffuse intrinsic pontine glioma	Diffuse midline glioma
 Dysembryoplastic neuroepithelial tumor (DNET)	Dysembryoplastic neuroepithelial tumor
 Dysembryoplastic neuroepithelial tumor (DNET);Dysplasia/Gliosis;Ganglioglioma	NA
 Dysembryoplastic neuroepithelial tumor (DNET);Ganglioglioma	Dysembryoplastic neuroepithelial tumor

diff --git a/analyses/molecular-subtyping-integrate/results/harmonized_diagnosis_cancer_group_table.tsv b/analyses/molecular-subtyping-integrate/results/harmonized_diagnosis_cancer_group_table.tsv
@@ -60,7 +60,6 @@ PBTA	Desmoplastic infantile astrocytoma and ganglioglioma, RTK	Desmoplastic infa
 PBTA	Diffuse fibrillary astrocytoma	Diffuse fibrillary astrocytoma	No	No
 PBTA	Diffuse hemispheric glioma, H3 G35-mutant	Diffuse hemispheric glioma	Yes	No
 PBTA	Brainstem glioma- Diffuse intrinsic pontine glioma	Diffuse intrinsic pontine glioma	No	Yes
-PBTA	Diffuse intrinsic pontine glioma	Diffuse intrinsic pontine glioma	No	No
 PPTC	Brainstem glioma- Diffuse intrinsic pontine glioma	Diffuse intrinsic pontine glioma	No	Yes
 PBTA	Diffuse leptomeningeal glioneuronal tumor,  MAPK	Diffuse leptomeningeal glioneuronal tumor	Yes	No
 PBTA	Diffuse leptomeningeal glioneuronal tumor,  To be classified	Diffuse leptomeningeal glioneuronal tumor	Yes	No
@@ -69,6 +68,7 @@ DGD	Diffuse leptomeningeal glioneuronal tumor,  To be classified	Diffuse leptome
 PBTA	Diffuse midline glioma, H3 K28-altered	Diffuse midline glioma	Yes	No
 PBTA	Diffuse midline glioma, H3 K28-mutant	Diffuse midline glioma	Yes	No
 PBTA	Diffuse midline glioma, H3 K28-altered (EGFR mutant)	Diffuse midline glioma	Yes	No
+PBTA	Diffuse intrinsic pontine glioma	Diffuse midline glioma	No	Yes
 PBTA	Dysembryoplastic neuroepithelial tumor (DNET)	Dysembryoplastic neuroepithelial tumor	No	Yes
 PBTA	Dysembryoplastic neuroepithelial tumor (DNET);Ganglioglioma	Dysembryoplastic neuroepithelial tumor	No	Yes
 DGD	EBV-Positive Diffuse Large B-Cell Lymphoma, Not Otherwise Specified	EBV-Positive Diffuse Large B-Cell Lymphoma	Yes	No

diff --git a/analyses/molecular-subtyping-integrate/results/histologies.tsv b/analyses/molecular-subtyping-integrate/results/histologies.tsv
@@ -6144,7 +6144,7 @@ PT_VWZZTK38	BS_DQ4MMXWD	7316-1844	1107958	Tumor	Initial CNS Tumor	Solid Tissue	N
 PT_GHFG41Q2	BS_DQ53BKED	7316-8429	1247709	Tumor	Initial CNS Tumor	Solid Tissue	NA	NA	Medulloblastoma	medulloblastoma	None documented	PBTA	PBTA-X01-FY22	WGS	NA	PT_GHFG41Q2_7316-8429_Solid Tissue_Initial CNS Tumor	C3631329	Cerebellum/Posterior Fossa	Posterior fossa	Male	Male	Native Hawaiian or Other Pacific Islander	Hispanic or Latino	129	LIVING	129	Not Applicable	Gross/Near total resection	4278	4329	Alive	4344	4329	4407	Not Available	Embryonal tumor	Medulloblastoma	MB, Group3	MB, Group3	Medulloblastoma	Medulloblastoma, group 3	Medulloblastoma, group 3	Subtype based on prediction;Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.330646995176	0.669353004824	3	NA	NA	NA	NA	NA
 PASFXC	BS_DQ5RVSH4	12	12A	Normal	NA	Saliva	NA	NA	NA	NA	NA	GMKF	NBL-X01-FY16	WGS	NA	NA	PT_XDPN4357	Thorax, NOS; Axilla, NOS; Chest, NOS; Chest wall, NOS	NA	Male	Unknown	Black or African American	Not Hispanic or Latino	3647	LIVING	NA	NA	NA	141	NA	NA	NA	NA	NA	Hudson Alpha	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
 PT_B5DQ8FF0	BS_DQEQPEHF	7316-4517	1115905	Tumor	Initial CNS Tumor	Solid Tissue	NA	NA	Ependymoma	anaplastic ependymoma who grade iii	None documented	PBTA	CBTN	Methylation	NA	PT_B5DQ8FF0_7316-4517_Solid Tissue_Initial CNS Tumor	C1207614	Cerebellum/Posterior Fossa	Posterior fossa	Male	Male	White	Not Hispanic or Latino	871	LIVING	871	Progressive	Partial resection	1057	1057	Alive	NA	NA	1928	National Institutes of Health	Ependymal tumor	Ependymoma	EPN, PF A	EPN, PF A	Ependymoma	Posterior fossa group A (PFA) ependymoma	Posterior fossa group A (PFA) ependymoma	Updated via OpenPedCan subtyping	EPN_PFA_2A	0.825460748623806	unmethylated	0.0475051921651162	EPN, PF A	0.999	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.6291065	0.945962069999999	0.906060465590101	NA	NA
-PT_FFHQ1B9R	BS_DQJ933JK	7316-3240	1242286	Tumor	NA	Derived Cell Line	Serum-free	15	Not Reported	NA	None documented	PBTA	CBTN	RNA-Seq	poly-A stranded	PT_FFHQ1B9R_7316-3240_Derived Cell Line_NA_Serum-free_15	C1066533	NA	NA	Male	NA	White	Not Hispanic or Latino	NA	LIVING	NA	Not Applicable	NA	NA	NA	NA	NA	NA	2943	Not Available	Diffuse astrocytic and oligodendroglial tumor	HGAT	HGG, To be classified	NA	Diffuse intrinsic pontine glioma	NA	Diffuse intrinsic pontine glioma	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
+PT_FFHQ1B9R	BS_DQJ933JK	7316-3240	1242286	Tumor	NA	Derived Cell Line	Serum-free	15	Not Reported	NA	None documented	PBTA	CBTN	RNA-Seq	poly-A stranded	PT_FFHQ1B9R_7316-3240_Derived Cell Line_NA_Serum-free_15	C1066533	NA	NA	Male	NA	White	Not Hispanic or Latino	NA	LIVING	NA	Not Applicable	NA	NA	NA	NA	NA	NA	2943	Not Available	Diffuse astrocytic and oligodendroglial tumor	HGAT	DMG, H3 K28	NA	Diffuse midline glioma	Diffuse midline glioma, H3 K28-mutant	Diffuse intrinsic pontine glioma	NA,Updated to DMG, H3 K28 from clinical review	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
 PT_7ENM97P8	BS_DQX4P2C1	7316-4992	7316-4992_methylation	Tumor	Unknown	Solid Tissue	NA	NA	High-grade glioma/astrocytoma (WHO grade III/IV)	glioblastoma multiforme	None documented	PBTA	CBTN	Methylation	NA	PT_7ENM97P8_7316-4992_Solid Tissue_Unknown	C1277232	Other locations NOS	Other	Male	NA	White	Not Hispanic or Latino	NA	NA	NA	Not Applicable	Unavailable	6148	6148	Alive	NA	NA	NA	Broad Institute	Diffuse astrocytic and oligodendroglial tumor	HGAT	DHG, H3 G35	DHG, H3 G35	Diffuse hemispheric glioma	Diffuse hemispheric glioma, H3 G35-mutant	Diffuse hemispheric glioma, H3 G35-mutant	Updated via OpenPedCan subtyping	DHG_G34	0.9991282	methylated	0.99	NA	NA	Pediatric_type_high_grade_gliomas	0.991	1	DHG_G34	0.995	1	Matched	Matched	NA	NA	NA	0.62	0.88	0.62	NA	NA
 PT_1AAYYGGY	BS_DQZV6K2W	7316-4996	A14750	Normal	NA	Peripheral Whole Blood	NA	NA	NA	NA	None documented	PBTA	PNOC	WGS	NA	NA	C3079920	Peripheral Whole Blood	NA	Male	Female	Reported Unknown	Not Available	244	DECEASED	NA	NA	NA	4608	4608	NA	NA	NA	4852	Novogene	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
 PT_JDS5171S	BS_DR079H0D	C4111152-Tumor	C4111152-RNA-Tumor	Tumor	Recurrence	Solid Tissue	NA	NA	High-grade glioma/astrocytoma (WHO grade III/IV)	gl (glioma); dmg, h3k27m mutant, who gr iv	None documented	PBTA	Mioncoseq	RNA-Seq	exome_capture	PT_JDS5171S_C4111152-Tumor_Solid Tissue_Recurrence	C4111152	Brain Stem- Midbrain/Tectum;Thalamus	Midline	Male	Unknown	Reported Unknown	Not Available	2463	DECEASED	532	Recurrence	Unavailable	1707	3542	Alive	3872	NA	4170	Not Available	Diffuse astrocytic and oligodendroglial tumor	HGAT	DMG, H3 K28	NA	Diffuse midline glioma	Diffuse midline glioma, H3 K28-altered	Diffuse midline glioma, H3 K28-altered	Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
@@ -13904,7 +13904,7 @@ PT_TH18S0JQ	BS_YZ2Z1Q6Y	7316-3068	734528	Tumor	Initial CNS Tumor	Solid Tissue	NA
 PT_5F4N0CAP	BS_YZ3MRCXX	7316-219	394877	Normal	NA	Peripheral Whole Blood	NA	NA	NA	NA	None documented	PBTA	CBTN	WGS	NA	NA	C67527	Peripheral Whole Blood	NA	Female	Female	White	Not Hispanic or Latino	42	LIVING	42	Not Applicable	NA	3680	3722	Alive	NA	NA	3722	Genomic Clinical Core at Sidra Medical and Research Center	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
 PT_R604JG6B	BS_YZ736WBP	7316-8817	1251109	Tumor	Deceased	Solid Tissue	NA	NA	Medulloblastoma	recurrent/residual medulloblastoma, viable, status post treatment	None documented	PBTA	CBTN	Methylation	NA	PT_R604JG6B_7316-8817_Solid Tissue_Deceased	C3552978	Cerebellum/Posterior Fossa;Meninges/Dura;Other locations NOS;Spinal Cord- Cervical;Spinal Cord- Thoracic	Mixed	Male	Unknown	Reported Unknown	Hispanic or Latino	744	DECEASED	468	Progressive - Metastatic	NA	3335	4079	Deceased-due to disease	3477	3379	4079	Not Available	Embryonal tumor	Medulloblastoma	MB, Group4	MB, Group4	Medulloblastoma	Medulloblastoma, group 4	Medulloblastoma, group 4	Subtype based on prediction;Updated via OpenPedCan subtyping	MB_G34_VII	0.981497922546401	unmethylated	0.00932964831659413	MB_G4	0.979	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.613780666666667	0.880833288333332	0.803814668771406	NA	NA
 PT_GTHZF21E	BS_YZ84234G	7316-9066	1238355	Tumor	Deceased	Solid Tissue	NA	NA	High-grade glioma/astrocytoma (WHO grade III/IV)	thalamic dmg	None documented	PBTA	PBTA-X01-FY22	WGS	NA	PT_GTHZF21E_7316-9066_Solid Tissue_Deceased	C3232317	Brain Stem- Pons;Cerebellum/Posterior Fossa;Frontal Lobe;Parietal Lobe;Spinal Cord- Cervical;Spinal Cord- Lumbar/Thecal Sac;Spinal Cord- Thoracic;Thalamus;Ventricles	Mixed	Female	Female	Reported Unknown	Not Hispanic or Latino	527	DECEASED	192	Progressive	NA	3795	4322	Deceased-due to disease	3827	3826	4322	Not Available	Diffuse astrocytic and oligodendroglial tumor	HGAT	DMG, H3 K28, TP53	DMG, H3 K28	Diffuse midline glioma	Diffuse midline glioma, H3 K28-altered	Diffuse midline glioma, H3 K28-altered	Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.29788864417800004	0.702111355822	3	NA	NA	NA	NA	NA
-PT_V1HNAC2Q	BS_YZD4SSMA	7316-3240	556566	Tumor	Initial CNS Tumor	Derived Cell Line	Serum-free	0	Brainstem glioma- Diffuse intrinsic pontine glioma	Infiltrating Dipg	None documented	PBTA	PNOC	WGS	NA	PT_V1HNAC2Q_7316-3240_Derived Cell Line_Initial CNS Tumor_Serum-free_0	C3079305	Pons/Brainstem	Midline	Male	Female	Reported Unknown	Not Hispanic or Latino	392	DECEASED	NA	NA	NA	2786	2786	NA	NA	NA	3178	NantOmics	Diffuse astrocytic and oligodendroglial tumor	HGAT	DMG, H3 K28, TP53	NA	Diffuse intrinsic pontine glioma	Diffuse midline glioma, H3 K28-altered	Diffuse intrinsic pontine glioma	Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.117921371143	0.8820786288570001	2	NA	NA	NA	NA	NA
+PT_V1HNAC2Q	BS_YZD4SSMA	7316-3240	556566	Tumor	Initial CNS Tumor	Derived Cell Line	Serum-free	0	Brainstem glioma- Diffuse intrinsic pontine glioma	Infiltrating Dipg	None documented	PBTA	PNOC	WGS	NA	PT_V1HNAC2Q_7316-3240_Derived Cell Line_Initial CNS Tumor_Serum-free_0	C3079305	Pons/Brainstem	Midline	Male	Female	Reported Unknown	Not Hispanic or Latino	392	DECEASED	NA	NA	NA	2786	2786	NA	NA	NA	3178	NantOmics	Diffuse astrocytic and oligodendroglial tumor	HGAT	DMG, H3 K28, TP53	NA	Diffuse midline glioma	Diffuse midline glioma, H3 K28-altered	Diffuse intrinsic pontine glioma	Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.117921371143	0.8820786288570001	2	NA	NA	NA	NA	NA
 PT_F9ANPADH	BS_YZDD793H	16510-18	936193	Normal	NA	Peripheral Whole Blood	NA	NA	NA	NA	None documented	PBTA	Oligo	WGS	NA	NA	C3532314	Peripheral Whole Blood	NA	NA	Male	NA	NA	NA	NA	NA	NA	NA	9496	17166	Alive	NA	NA	NA	Novogene	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA
 PT_VJZN69T9	BS_YZFQG0FH	7316-3669	1228839	Tumor	Progressive	Solid Tissue	NA	NA	Medulloblastoma	medulloblastoma	None documented	PBTA	PBTA-X01-FY22	WGS	NA	PT_VJZN69T9_7316-3669_Solid Tissue_Progressive	C979203	Cerebellum/Posterior Fossa	Posterior fossa	Male	Male	White	Not Hispanic or Latino	128	LIVING	128	Progressive	Gross/Near total resection	880	1008	Alive	NA	NA	1008	Not Available	Embryonal tumor	Medulloblastoma	MB, Group3	MB, Group3	Medulloblastoma	Medulloblastoma, group 3	Medulloblastoma, group 3	Subtype based on prediction;Updated via OpenPedCan subtyping	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.396809417949	0.603190582051	4	NA	NA	NA	NA	NA
 PT_HE8FBFNA	BS_YZGBDN88	7316-8846	1250365	Tumor	Progressive	Solid Tissue	NA	NA	Atypical Teratoid Rhabdoid Tumor (ATRT)	residual/recurrent at/rt	Rhabdoid tumor predisposition syndrome (SMARCB1, SMARCA4)	PBTA	CBTN	Methylation	NA	PT_HE8FBFNA_7316-8846_Solid Tissue_Progressive	C3422106	Cerebellum/Posterior Fossa	Posterior fossa	Male	Male	White	Not Hispanic or Latino	836	LIVING	158	Progressive	Partial resection	25	183	Alive	37	414	861	Not Available	Embryonal tumor	ATRT	ATRT, TYR	ATRT, TYR	Atypical Teratoid Rhabdoid Tumor	Atypical Teratoid Rhabdoid Tumor, TYR	Atypical Teratoid Rhabdoid Tumor, TYR	Subtype based on methylation;Updated via OpenPedCan subtyping	ATRT_TYR	0.985213254846805	unmethylated	8.9900955959598e-4	ATRT_TYR	0.999	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	NA	0.532603	0.848027276666667	0.744440507207474	NA	NA

diff --git a/analyses/molecular-subtyping-integrate/results/pediatric_cancer_groups.tsv b/analyses/molecular-subtyping-integrate/results/pediatric_cancer_groups.tsv
@@ -77,17 +77,17 @@ Diffuse hemispheric glioma	Primary Tumor	4
 Diffuse hemispheric glioma	Recurrence	15
 Diffuse hemispheric glioma	Unknown	1
 Diffuse intrinsic pontine glioma	Deceased	11
-Diffuse intrinsic pontine glioma	Initial CNS Tumor	6
+Diffuse intrinsic pontine glioma	Initial CNS Tumor	5
 Diffuse intrinsic pontine glioma	Relapse	1
-Diffuse intrinsic pontine glioma	NA	1
 Diffuse leptomeningeal glioneuronal tumor	Initial CNS Tumor	3
 Diffuse leptomeningeal glioneuronal tumor	Progressive	5
 Diffuse leptomeningeal glioneuronal tumor	NA	1
 Diffuse midline glioma	Deceased	308
-Diffuse midline glioma	Initial CNS Tumor	500
+Diffuse midline glioma	Initial CNS Tumor	501
 Diffuse midline glioma	Progressive	55
 Diffuse midline glioma	Progressive Disease Post-Mortem	12
 Diffuse midline glioma	Recurrence	18
+Diffuse midline glioma	NA	1
 Dysembryoplastic neuroepithelial tumor	Initial CNS Tumor	128
 Dysembryoplastic neuroepithelial tumor	Primary Tumor	4
 Dysembryoplastic neuroepithelial tumor	Progressive	22

diff --git a/analyses/molecular-subtyping-integrate/results/subtype_tumor_counts_table.tsv b/analyses/molecular-subtyping-integrate/results/subtype_tumor_counts_table.tsv
@@ -20,13 +20,12 @@ Desmoplastic infantile astrocytoma and ganglioglioma	GNT, wildtype	4
 Diffuse fibrillary astrocytoma	LGG, To be classified	1
 Diffuse hemispheric glioma	DHG, H3 G35	26
 Diffuse hemispheric glioma	DHG, H3 G35, TP53	82
-Diffuse intrinsic pontine glioma	DMG, H3 K28, TP53	1
-Diffuse intrinsic pontine glioma	HGG, To be classified	18
+Diffuse intrinsic pontine glioma	HGG, To be classified	17
 Diffuse leptomeningeal glioneuronal tumor	GNT, KIAA1549-BRAF	4
 Diffuse leptomeningeal glioneuronal tumor	GNT, MAPK	3
 Diffuse leptomeningeal glioneuronal tumor	GNT, To be classified	2
-Diffuse midline glioma	DMG, H3 K28	385
-Diffuse midline glioma	DMG, H3 K28, TP53	508
+Diffuse midline glioma	DMG, H3 K28	386
+Diffuse midline glioma	DMG, H3 K28, TP53	509
 Embryonal tumor with multilayer rosettes	ETMR, C19MC-altered	12
 Embryonal tumor with multilayer rosettes	ETMR, NOS	22
 Ependymoma	EPN, MPE	49

diff --git a/analyses/molecular-subtyping-pathology/01-compile-subtyping-results.nb.html b/analyses/molecular-subtyping-pathology/01-compile-subtyping-results.nb.html