Correlation between aggregated molecular cancer subtypes and selected clinical features

Lung Squamous Cell Carcinoma (Primary solid tumor)

17 October 2014 | analyses__2014_10_17

Maintainer Information

Citation Information

Maintained by TCGA GDAC Team (Broad Institute/MD Anderson Cancer Center/Harvard Medical School)

Cite as Broad Institute TCGA Genome Data Analysis Center (2014): Correlation between aggregated molecular cancer subtypes and selected clinical features. Broad Institute of MIT and Harvard. doi:10.7908/C1CC0ZKG

Overview

Introduction

This pipeline computes the correlation between cancer subtypes identified by different molecular patterns and selected clinical features.

Summary

Testing the association between subtypes identified by 12 different clustering approaches and 14 clinical features across 422 patients, 4 significant findings detected with P value < 0.05 and Q value < 0.25.

CNMF clustering analysis on array-based mRNA expression data identified 4 subtypes that correlate to 'PATHOLOGY.T.STAGE'.
Consensus hierarchical clustering analysis on array-based mRNA expression data identified 3 subtypes that correlate to 'PATHOLOGY.T.STAGE'.
3 subtypes identified in current cancer cohort by 'Copy Number Ratio CNMF subtypes'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'METHLYATION CNMF'. These subtypes do not correlate to any clinical features.
CNMF clustering analysis on RPPA data identified 3 subtypes that do not correlate to any clinical features.
Consensus hierarchical clustering analysis on RPPA data identified 4 subtypes that do not correlate to any clinical features.
CNMF clustering analysis on sequencing-based mRNA expression data identified 4 subtypes that do not correlate to any clinical features.
Consensus hierarchical clustering analysis on sequencing-based mRNA expression data identified 3 subtypes that do not correlate to any clinical features.
5 subtypes identified in current cancer cohort by 'MIRSEQ CNMF'. These subtypes correlate to 'PATHOLOGY.M.STAGE' and 'KARNOFSKY.PERFORMANCE.SCORE'.
4 subtypes identified in current cancer cohort by 'MIRSEQ CHIERARCHICAL'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'MIRseq Mature CNMF subtypes'. These subtypes do not correlate to any clinical features.
3 subtypes identified in current cancer cohort by 'MIRseq Mature cHierClus subtypes'. These subtypes do not correlate to any clinical features.

Results

Overview of the results

Table 1. Get Full Table Overview of the association between subtypes identified by 12 different clustering approaches and 14 clinical features. Shown in the table are P values (Q values). Thresholded by P value < 0.05 and Q value < 0.25, 4 significant findings detected.


Clinical Features	Statistical Tests	mRNA CNMF subtypes	mRNA cHierClus subtypes	Copy Number Ratio CNMF subtypes	METHLYATION CNMF	RPPA CNMF subtypes	RPPA cHierClus subtypes	RNAseq CNMF subtypes	RNAseq cHierClus subtypes	MIRSEQ CNMF	MIRSEQ CHIERARCHICAL	MIRseq Mature CNMF subtypes	MIRseq Mature cHierClus subtypes
Time to Death	logrank test	0.145 (1.00)	0.293 (1.00)	0.755 (1.00)	0.75 (1.00)	0.0176 (1.00)	0.0416 (1.00)	0.306 (1.00)	0.412 (1.00)	0.00899 (1.00)	0.0947 (1.00)	0.791 (1.00)	0.0433 (1.00)
AGE	Kruskal-Wallis (anova)	0.924 (1.00)	0.645 (1.00)	0.0586 (1.00)	0.0324 (1.00)	0.0128 (1.00)	0.288 (1.00)	0.0218 (1.00)	0.00523 (0.843)	0.00346 (0.56)	0.0533 (1.00)	0.0527 (1.00)	0.0762 (1.00)
NEOPLASM DISEASESTAGE	Fisher's exact test	0.0118 (1.00)	0.0226 (1.00)	0.653 (1.00)	0.765 (1.00)	0.398 (1.00)	0.784 (1.00)	0.0832 (1.00)	0.0714 (1.00)	0.00216 (0.354)	0.334 (1.00)	0.386 (1.00)	0.113 (1.00)
PATHOLOGY T STAGE	Fisher's exact test	0.00049 (0.0808)	0.0001 (0.0167)	0.543 (1.00)	0.635 (1.00)	0.146 (1.00)	0.5 (1.00)	0.767 (1.00)	0.136 (1.00)	0.0738 (1.00)	0.7 (1.00)	0.255 (1.00)	0.117 (1.00)
PATHOLOGY N STAGE	Fisher's exact test	0.906 (1.00)	0.359 (1.00)	0.301 (1.00)	0.816 (1.00)	0.31 (1.00)	0.0659 (1.00)	0.48 (1.00)	0.956 (1.00)	0.468 (1.00)	0.891 (1.00)	0.502 (1.00)	0.297 (1.00)
PATHOLOGY M STAGE	Fisher's exact test	0.107 (1.00)	0.0707 (1.00)	0.64 (1.00)	0.362 (1.00)	0.61 (1.00)	0.911 (1.00)	0.413 (1.00)	0.432 (1.00)	0.00044 (0.073)	0.28 (1.00)	1 (1.00)	0.463 (1.00)
GENDER	Fisher's exact test	0.334 (1.00)	0.0577 (1.00)	0.00658 (1.00)	0.594 (1.00)	0.264 (1.00)	0.666 (1.00)	0.549 (1.00)	0.0321 (1.00)	0.174 (1.00)	0.536 (1.00)	0.376 (1.00)	0.722 (1.00)
KARNOFSKY PERFORMANCE SCORE	Kruskal-Wallis (anova)	0.166 (1.00)	0.0261 (1.00)	0.466 (1.00)	0.0445 (1.00)	0.373 (1.00)	0.927 (1.00)	0.907 (1.00)	0.451 (1.00)	7.6e-05 (0.0128)	0.0856 (1.00)	0.979 (1.00)	0.108 (1.00)
HISTOLOGICAL TYPE	Fisher's exact test	0.293 (1.00)	0.323 (1.00)	0.0549 (1.00)	0.248 (1.00)	0.0839 (1.00)	0.0658 (1.00)	0.507 (1.00)	0.102 (1.00)	0.164 (1.00)	0.0348 (1.00)	0.274 (1.00)	0.0252 (1.00)
RADIATIONS RADIATION REGIMENINDICATION	Fisher's exact test	0.551 (1.00)	0.533 (1.00)	0.467 (1.00)	0.638 (1.00)	0.85 (1.00)	0.895 (1.00)	0.437 (1.00)	0.83 (1.00)	0.712 (1.00)	0.203 (1.00)	0.182 (1.00)	0.696 (1.00)
NUMBERPACKYEARSSMOKED	Kruskal-Wallis (anova)	0.485 (1.00)	0.999 (1.00)	0.0609 (1.00)	0.413 (1.00)	0.0791 (1.00)	0.604 (1.00)	0.585 (1.00)	0.741 (1.00)	0.82 (1.00)	0.599 (1.00)	0.354 (1.00)	0.116 (1.00)
COMPLETENESS OF RESECTION	Fisher's exact test	0.561 (1.00)	0.817 (1.00)	0.0213 (1.00)	0.302 (1.00)	0.0156 (1.00)	0.0489 (1.00)	0.646 (1.00)	0.716 (1.00)	0.42 (1.00)	0.314 (1.00)	0.407 (1.00)	0.556 (1.00)
RACE	Fisher's exact test	0.985 (1.00)	0.975 (1.00)	0.326 (1.00)	0.0711 (1.00)	0.197 (1.00)	0.833 (1.00)	0.618 (1.00)	0.563 (1.00)	0.129 (1.00)	0.0443 (1.00)	0.227 (1.00)	0.00321 (0.523)
ETHNICITY	Fisher's exact test	0.269 (1.00)	0.069 (1.00)	0.221 (1.00)	0.578 (1.00)	0.383 (1.00)	0.84 (1.00)	0.173 (1.00)	0.748 (1.00)	0.948 (1.00)	0.861 (1.00)	0.807 (1.00)	0.204 (1.00)

Clustering Approach #1: 'mRNA CNMF subtypes'

Table S1. Description of clustering approach #1: 'mRNA CNMF subtypes'

Cluster Labels	1	2	3	4
Number of samples	42	52	32	28

'mRNA CNMF subtypes' versus 'Time to Death'

P value = 0.145 (logrank test), Q value = 1

Table S2. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	147	63	12.0 - 5287.0 (762.0)
subtype1	41	17	13.0 - 3724.0 (717.0)
subtype2	49	18	12.0 - 3016.0 (1058.0)
subtype3	30	17	12.0 - 5287.0 (819.0)
subtype4	27	11	12.0 - 1966.0 (358.0)

Figure S1. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA CNMF subtypes' versus 'AGE'

P value = 0.924 (Kruskal-Wallis (anova)), Q value = 1

Table S3. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	152	66.5 (8.6)
subtype1	41	66.4 (7.7)
subtype2	51	66.5 (8.2)
subtype3	32	67.2 (9.8)
subtype4	28	66.0 (9.4)

Figure S2. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #2: 'AGE'

'mRNA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0118 (Fisher's exact test), Q value = 1

Table S4. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	20	61	7	27	19	15	4
subtype1	2	21	0	9	6	2	2
subtype2	2	24	4	9	6	7	0
subtype3	8	11	2	4	4	2	0
subtype4	8	5	1	5	3	4	2

Figure S3. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.00049 (Fisher's exact test), Q value = 0.081

Table S5. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	30	100	12	12
subtype1	5	30	6	1
subtype2	4	41	1	6
subtype3	11	18	2	1
subtype4	10	11	3	4

Figure S4. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.906 (Fisher's exact test), Q value = 1

Table S6. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	96	40	13	5
subtype1	26	11	3	2
subtype2	28	17	5	2
subtype3	22	6	3	1
subtype4	20	6	2	0

Figure S5. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'mRNA CNMF subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.107 (Fisher's exact test), Q value = 1

Table S7. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1
ALL	146	4
subtype1	38	2
subtype2	50	0
subtype3	32	0
subtype4	26	2

Figure S6. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'mRNA CNMF subtypes' versus 'GENDER'

P value = 0.334 (Fisher's exact test), Q value = 1

Table S8. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	44	110
subtype1	9	33
subtype2	13	39
subtype3	11	21
subtype4	11	17

Figure S7. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'mRNA CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.166 (Kruskal-Wallis (anova)), Q value = 1

Table S9. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	26	24.2 (38.5)
subtype1	4	0.0 (0.0)
subtype2	4	0.0 (0.0)
subtype3	9	31.1 (46.8)
subtype4	9	38.9 (39.5)

Figure S8. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'mRNA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.293 (Fisher's exact test), Q value = 1

Table S10. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	5	1	148
subtype1	0	0	42
subtype2	3	0	49
subtype3	1	0	31
subtype4	1	1	26

Figure S9. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'mRNA CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.551 (Fisher's exact test), Q value = 1

Table S11. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	2	152
subtype1	1	41
subtype2	0	52
subtype3	1	31
subtype4	0	28

Figure S10. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'mRNA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.485 (Kruskal-Wallis (anova)), Q value = 1

Table S12. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	133	54.8 (36.5)
subtype1	38	60.2 (41.4)
subtype2	47	52.0 (25.5)
subtype3	27	48.6 (36.2)
subtype4	21	59.6 (47.7)

Figure S11. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'mRNA CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.561 (Fisher's exact test), Q value = 1

Table S13. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	139	3	2	5
subtype1	38	0	1	1
subtype2	47	1	1	1
subtype3	27	1	0	3
subtype4	27	1	0	0

Figure S12. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'mRNA CNMF subtypes' versus 'RACE'

P value = 0.985 (Fisher's exact test), Q value = 1

Table S14. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	3	7	91
subtype1	1	2	24
subtype2	1	3	27
subtype3	1	1	21
subtype4	0	1	19

Figure S13. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #13: 'RACE'

'mRNA CNMF subtypes' versus 'ETHNICITY'

P value = 0.269 (Fisher's exact test), Q value = 1

Table S15. Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	88
subtype1	3	23
subtype2	1	26
subtype3	0	20
subtype4	0	19

Figure S14. Get High-res Image Clustering Approach #1: 'mRNA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #2: 'mRNA cHierClus subtypes'

Table S16. Description of clustering approach #2: 'mRNA cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	47	56	51

'mRNA cHierClus subtypes' versus 'Time to Death'

P value = 0.293 (logrank test), Q value = 1

Table S17. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	147	63	12.0 - 5287.0 (762.0)
subtype1	46	21	13.0 - 3724.0 (708.0)
subtype2	53	20	12.0 - 3016.0 (913.0)
subtype3	48	22	12.0 - 5287.0 (663.0)

Figure S15. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'mRNA cHierClus subtypes' versus 'AGE'

P value = 0.645 (Kruskal-Wallis (anova)), Q value = 1

Table S18. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	152	66.5 (8.6)
subtype1	46	66.0 (8.7)
subtype2	55	66.2 (8.0)
subtype3	51	67.4 (9.1)

Figure S16. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'mRNA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0226 (Fisher's exact test), Q value = 1

Table S19. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE IA	STAGE IB	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	20	61	7	27	19	15	4
subtype1	4	20	2	9	7	2	3
subtype2	2	25	4	10	6	9	0
subtype3	14	16	1	8	6	4	1

Figure S17. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 1e-04 (Fisher's exact test), Q value = 0.017

Table S20. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	30	100	12	12
subtype1	6	32	7	2
subtype2	4	44	1	7
subtype3	20	24	4	3

Figure S18. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.359 (Fisher's exact test), Q value = 1

Table S21. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	96	40	13	5
subtype1	28	14	4	1
subtype2	30	18	5	3
subtype3	38	8	4	1

Figure S19. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'mRNA cHierClus subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.0707 (Fisher's exact test), Q value = 1

Table S22. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1
ALL	146	4
subtype1	42	3
subtype2	54	0
subtype3	50	1

Figure S20. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'mRNA cHierClus subtypes' versus 'GENDER'

P value = 0.0577 (Fisher's exact test), Q value = 1

Table S23. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	44	110
subtype1	10	37
subtype2	13	43
subtype3	21	30

Figure S21. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'mRNA cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.0261 (Kruskal-Wallis (anova)), Q value = 1

Table S24. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	26	24.2 (38.5)
subtype1	8	0.0 (0.0)
subtype2	5	10.0 (22.4)
subtype3	13	44.6 (44.6)

Figure S22. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'mRNA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.323 (Fisher's exact test), Q value = 1

Table S25. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	5	1	148
subtype1	0	1	46
subtype2	3	0	53
subtype3	2	0	49

Figure S23. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'mRNA cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.533 (Fisher's exact test), Q value = 1

Table S26. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	2	152
subtype1	1	46
subtype2	0	56
subtype3	1	50

Figure S24. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'mRNA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.999 (Kruskal-Wallis (anova)), Q value = 1

Table S27. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	133	54.8 (36.5)
subtype1	41	57.5 (41.9)
subtype2	51	51.1 (24.6)
subtype3	41	56.8 (43.0)

Figure S25. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'mRNA cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.817 (Fisher's exact test), Q value = 1

Table S28. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	139	3	2	5
subtype1	42	0	1	2
subtype2	51	1	1	1
subtype3	46	2	0	2

Figure S26. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'mRNA cHierClus subtypes' versus 'RACE'

P value = 0.975 (Fisher's exact test), Q value = 1

Table S29. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	3	7	91
subtype1	1	2	27
subtype2	1	3	30
subtype3	1	2	34

Figure S27. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'mRNA cHierClus subtypes' versus 'ETHNICITY'

P value = 0.069 (Fisher's exact test), Q value = 1

Table S30. Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	88
subtype1	3	25
subtype2	1	29
subtype3	0	34

Figure S28. Get High-res Image Clustering Approach #2: 'mRNA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #3: 'Copy Number Ratio CNMF subtypes'

Table S31. Description of clustering approach #3: 'Copy Number Ratio CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	158	138	124

'Copy Number Ratio CNMF subtypes' versus 'Time to Death'

P value = 0.755 (logrank test), Q value = 1

Table S32. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	388	123	1.0 - 5287.0 (641.5)
subtype1	146	55	3.0 - 5287.0 (710.0)
subtype2	129	37	3.0 - 3636.0 (734.0)
subtype3	113	31	1.0 - 3724.0 (430.0)

Figure S29. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'Copy Number Ratio CNMF subtypes' versus 'AGE'

P value = 0.0586 (Kruskal-Wallis (anova)), Q value = 1

Table S33. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	412	67.2 (8.7)
subtype1	155	67.4 (9.6)
subtype2	135	65.9 (8.3)
subtype3	122	68.4 (7.6)

Figure S30. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'AGE'

'Copy Number Ratio CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.653 (Fisher's exact test), Q value = 1

Table S34. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	1	72	137	1	52	71	57	20	6
subtype1	0	29	57	0	20	26	17	6	1
subtype2	0	18	46	1	19	24	19	9	2
subtype3	1	25	34	0	13	21	21	5	3

Figure S31. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.543 (Fisher's exact test), Q value = 1

Table S35. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	98	254	48	20
subtype1	36	94	22	6
subtype2	28	88	16	6
subtype3	34	72	10	8

Figure S32. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.301 (Fisher's exact test), Q value = 1

Table S36. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	261	113	35	5
subtype1	107	35	10	2
subtype2	77	46	12	2
subtype3	77	32	13	1

Figure S33. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'Copy Number Ratio CNMF subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.64 (Fisher's exact test), Q value = 1

Table S37. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	358	5	1	50
subtype1	133	1	0	23
subtype2	118	2	0	15
subtype3	107	2	1	12

Figure S34. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'Copy Number Ratio CNMF subtypes' versus 'GENDER'

P value = 0.00658 (Fisher's exact test), Q value = 1

Table S38. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	107	313
subtype1	54	104
subtype2	26	112
subtype3	27	97

Figure S35. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'Copy Number Ratio CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.466 (Kruskal-Wallis (anova)), Q value = 1

Table S39. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	93	52.6 (41.9)
subtype1	28	55.7 (42.1)
subtype2	31	54.2 (43.0)
subtype3	34	48.5 (41.7)

Figure S36. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'Copy Number Ratio CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0549 (Fisher's exact test), Q value = 1

Table S40. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	12	6	1	401
subtype1	1	4	1	152
subtype2	8	1	0	129
subtype3	3	1	0	120

Figure S37. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'Copy Number Ratio CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.467 (Fisher's exact test), Q value = 1

Table S41. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	13	407
subtype1	5	153
subtype2	6	132
subtype3	2	122

Figure S38. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'Copy Number Ratio CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0609 (Kruskal-Wallis (anova)), Q value = 1

Table S42. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	356	53.0 (31.7)
subtype1	132	49.8 (31.9)
subtype2	119	53.8 (31.8)
subtype3	105	56.1 (31.3)

Figure S39. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'Copy Number Ratio CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.0213 (Fisher's exact test), Q value = 1

Table S43. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	342	8	4	18
subtype1	122	3	2	11
subtype2	113	3	2	7
subtype3	107	2	0	0

Figure S40. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'Copy Number Ratio CNMF subtypes' versus 'RACE'

P value = 0.326 (Fisher's exact test), Q value = 1

Table S44. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	9	17	298
subtype1	6	4	114
subtype2	2	6	97
subtype3	1	7	87

Figure S41. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #13: 'RACE'

'Copy Number Ratio CNMF subtypes' versus 'ETHNICITY'

P value = 0.221 (Fisher's exact test), Q value = 1

Table S45. Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	8	267
subtype1	6	106
subtype2	1	81
subtype3	1	80

Figure S42. Get High-res Image Clustering Approach #3: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #4: 'METHLYATION CNMF'

Table S46. Description of clustering approach #4: 'METHLYATION CNMF'

Cluster Labels	1	2	3
Number of samples	118	91	79

'METHLYATION CNMF' versus 'Time to Death'

P value = 0.75 (logrank test), Q value = 1

Table S47. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	260	71	1.0 - 5287.0 (492.5)
subtype1	104	31	3.0 - 5287.0 (430.0)
subtype2	82	21	4.0 - 2754.0 (548.0)
subtype3	74	19	1.0 - 1970.0 (492.5)

Figure S43. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time to Death'

'METHLYATION CNMF' versus 'AGE'

P value = 0.0324 (Kruskal-Wallis (anova)), Q value = 1

Table S48. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	280	67.6 (8.8)
subtype1	115	68.9 (9.6)
subtype2	89	66.0 (8.6)
subtype3	76	67.4 (7.5)

Figure S44. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #2: 'AGE'

'METHLYATION CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.765 (Fisher's exact test), Q value = 1

Table S49. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	57	82	1	47	48	41	5	3
subtype1	1	25	30	0	19	23	15	2	3
subtype2	1	15	33	1	15	12	12	2	0
subtype3	0	17	19	0	13	13	14	1	0

Figure S45. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.T.STAGE'

P value = 0.635 (Fisher's exact test), Q value = 1

Table S50. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	76	166	37	9
subtype1	30	66	17	5
subtype2	26	49	14	2
subtype3	20	51	6	2

Figure S46. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.N.STAGE'

P value = 0.816 (Fisher's exact test), Q value = 1

Table S51. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2
ALL	179	79	24
subtype1	72	32	9
subtype2	60	24	6
subtype3	47	23	9

Figure S47. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'METHLYATION CNMF' versus 'PATHOLOGY.M.STAGE'

P value = 0.362 (Fisher's exact test), Q value = 1

Table S52. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	233	2	1	50
subtype1	90	2	1	25
subtype2	76	0	0	15
subtype3	67	0	0	10

Figure S48. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'METHLYATION CNMF' versus 'GENDER'

P value = 0.594 (Fisher's exact test), Q value = 1

Table S53. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	73	215
subtype1	33	85
subtype2	23	68
subtype3	17	62

Figure S49. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #7: 'GENDER'

'METHLYATION CNMF' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.0445 (Kruskal-Wallis (anova)), Q value = 1

Table S54. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	70	60.9 (39.4)
subtype1	19	75.8 (32.0)
subtype2	28	54.6 (43.3)
subtype3	23	56.1 (38.3)

Figure S50. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'METHLYATION CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.248 (Fisher's exact test), Q value = 1

Table S55. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	9	5	1	273
subtype1	1	3	0	114
subtype2	5	1	0	85
subtype3	3	1	1	74

Figure S51. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'METHLYATION CNMF' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.638 (Fisher's exact test), Q value = 1

Table S56. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	11	277
subtype1	5	113
subtype2	2	89
subtype3	4	75

Figure S52. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'METHLYATION CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.413 (Kruskal-Wallis (anova)), Q value = 1

Table S57. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	244	52.2 (29.6)
subtype1	98	50.1 (29.2)
subtype2	76	51.3 (25.6)
subtype3	70	56.1 (34.1)

Figure S53. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'METHLYATION CNMF' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.302 (Fisher's exact test), Q value = 1

Table S58. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	222	5	2	13
subtype1	88	1	0	8
subtype2	73	3	1	4
subtype3	61	1	1	1

Figure S54. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'METHLYATION CNMF' versus 'RACE'

P value = 0.0711 (Fisher's exact test), Q value = 1

Table S59. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	7	10	224
subtype1	6	5	88
subtype2	1	1	77
subtype3	0	4	59

Figure S55. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #13: 'RACE'

'METHLYATION CNMF' versus 'ETHNICITY'

P value = 0.578 (Fisher's exact test), Q value = 1

Table S60. Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	6	189
subtype1	4	81
subtype2	1	59
subtype3	1	49

Figure S56. Get High-res Image Clustering Approach #4: 'METHLYATION CNMF' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #5: 'RPPA CNMF subtypes'

Table S61. Description of clustering approach #5: 'RPPA CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	60	73	62

'RPPA CNMF subtypes' versus 'Time to Death'

P value = 0.0176 (logrank test), Q value = 1

Table S62. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	181	70	1.0 - 5287.0 (833.0)
subtype1	57	17	1.0 - 5287.0 (941.0)
subtype2	69	30	12.0 - 3636.0 (911.0)
subtype3	55	23	3.0 - 3644.0 (700.0)

Figure S57. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA CNMF subtypes' versus 'AGE'

P value = 0.0128 (Kruskal-Wallis (anova)), Q value = 1

Table S63. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	187	67.4 (9.5)
subtype1	59	65.5 (10.5)
subtype2	69	66.6 (8.5)
subtype3	59	70.3 (9.1)

Figure S58. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RPPA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.398 (Fisher's exact test), Q value = 1

Table S64. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB
ALL	1	28	71	1	23	33	22	14
subtype1	0	10	17	0	7	11	7	8
subtype2	0	7	28	0	10	15	8	4
subtype3	1	11	26	1	6	7	7	2

Figure S59. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.146 (Fisher's exact test), Q value = 1

Table S65. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	45	119	20	11
subtype1	15	35	4	6
subtype2	11	51	9	2
subtype3	19	33	7	3

Figure S60. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.31 (Fisher's exact test), Q value = 1

Table S66. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	124	49	16	4
subtype1	34	17	7	2
subtype2	44	21	5	2
subtype3	46	11	4	0

Figure S61. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'RPPA CNMF subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.61 (Fisher's exact test), Q value = 1

Table S67. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	MX
ALL	176	16
subtype1	54	6
subtype2	67	4
subtype3	55	6

Figure S62. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RPPA CNMF subtypes' versus 'GENDER'

P value = 0.264 (Fisher's exact test), Q value = 1

Table S68. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	49	146
subtype1	12	48
subtype2	17	56
subtype3	20	42

Figure S63. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.373 (Kruskal-Wallis (anova)), Q value = 1

Table S69. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	34	30.3 (39.3)
subtype1	8	43.8 (35.0)
subtype2	14	28.6 (40.0)
subtype3	12	23.3 (42.3)

Figure S64. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0839 (Fisher's exact test), Q value = 1

Table S70. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	3	2	190
subtype1	2	2	56
subtype2	0	0	73
subtype3	1	0	61

Figure S65. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RPPA CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.85 (Fisher's exact test), Q value = 1

Table S71. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	10	185
subtype1	4	56
subtype2	3	70
subtype3	3	59

Figure S66. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.0791 (Kruskal-Wallis (anova)), Q value = 1

Table S72. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	165	51.7 (32.3)
subtype1	51	60.6 (39.7)
subtype2	62	49.3 (30.0)
subtype3	52	45.9 (25.1)

Figure S67. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RPPA CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.0156 (Fisher's exact test), Q value = 1

Table S73. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	149	4	4	9
subtype1	43	0	2	5
subtype2	55	4	2	4
subtype3	51	0	0	0

Figure S68. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RPPA CNMF subtypes' versus 'RACE'

P value = 0.197 (Fisher's exact test), Q value = 1

Table S74. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	3	9	147
subtype1	2	1	46
subtype2	0	6	53
subtype3	1	2	48

Figure S69. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #13: 'RACE'

'RPPA CNMF subtypes' versus 'ETHNICITY'

P value = 0.383 (Fisher's exact test), Q value = 1

Table S75. Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	120
subtype1	1	37
subtype2	3	45
subtype3	0	38

Figure S70. Get High-res Image Clustering Approach #5: 'RPPA CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #6: 'RPPA cHierClus subtypes'

Table S76. Description of clustering approach #6: 'RPPA cHierClus subtypes'

Cluster Labels	1	2	3	4
Number of samples	54	41	52	48

'RPPA cHierClus subtypes' versus 'Time to Death'

P value = 0.0416 (logrank test), Q value = 1

Table S77. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	181	70	1.0 - 5287.0 (833.0)
subtype1	53	19	1.0 - 5287.0 (1213.0)
subtype2	36	19	10.0 - 1967.0 (869.0)
subtype3	50	20	3.0 - 3636.0 (708.0)
subtype4	42	12	6.0 - 3016.0 (790.5)

Figure S71. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RPPA cHierClus subtypes' versus 'AGE'

P value = 0.288 (Kruskal-Wallis (anova)), Q value = 1

Table S78. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	187	67.4 (9.5)
subtype1	52	65.8 (10.9)
subtype2	40	68.2 (9.5)
subtype3	49	66.8 (8.3)
subtype4	46	69.2 (9.0)

Figure S72. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RPPA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.784 (Fisher's exact test), Q value = 1

Table S79. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB
ALL	1	28	71	1	23	33	22	14
subtype1	0	9	16	0	7	9	8	5
subtype2	0	7	17	1	6	5	3	1
subtype3	0	4	19	0	7	12	5	4
subtype4	1	8	19	0	3	7	6	4

Figure S73. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.5 (Fisher's exact test), Q value = 1

Table S80. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	45	119	20	11
subtype1	13	32	4	5
subtype2	9	26	5	1
subtype3	7	36	6	3
subtype4	16	25	5	2

Figure S74. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.0659 (Fisher's exact test), Q value = 1

Table S81. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	124	49	16	4
subtype1	32	14	8	0
subtype2	31	7	3	0
subtype3	29	19	1	2
subtype4	32	9	4	2

Figure S75. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'RPPA cHierClus subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.911 (Fisher's exact test), Q value = 1

Table S82. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	MX
ALL	176	16
subtype1	49	5
subtype2	36	4
subtype3	47	3
subtype4	44	4

Figure S76. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RPPA cHierClus subtypes' versus 'GENDER'

P value = 0.666 (Fisher's exact test), Q value = 1

Table S83. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	49	146
subtype1	14	40
subtype2	9	32
subtype3	11	41
subtype4	15	33

Figure S77. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RPPA cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.927 (Kruskal-Wallis (anova)), Q value = 1

Table S84. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	34	30.3 (39.3)
subtype1	9	25.6 (35.4)
subtype2	13	30.8 (42.7)
subtype3	8	28.8 (39.8)
subtype4	4	42.5 (49.2)

Figure S78. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RPPA cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0658 (Fisher's exact test), Q value = 1

Table S85. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	3	2	190
subtype1	3	1	50
subtype2	0	1	40
subtype3	0	0	52
subtype4	0	0	48

Figure S79. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RPPA cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.895 (Fisher's exact test), Q value = 1

Table S86. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	10	185
subtype1	3	51
subtype2	1	40
subtype3	3	49
subtype4	3	45

Figure S80. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RPPA cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.604 (Kruskal-Wallis (anova)), Q value = 1

Table S87. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	165	51.7 (32.3)
subtype1	47	61.0 (46.0)
subtype2	34	48.5 (24.3)
subtype3	44	47.2 (23.8)
subtype4	40	48.4 (25.1)

Figure S81. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RPPA cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.0489 (Fisher's exact test), Q value = 1

Table S88. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	149	4	4	9
subtype1	46	0	0	4
subtype2	29	0	0	3
subtype3	37	4	2	1
subtype4	37	0	2	1

Figure S82. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RPPA cHierClus subtypes' versus 'RACE'

P value = 0.833 (Fisher's exact test), Q value = 1

Table S89. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	3	9	147
subtype1	2	2	43
subtype2	1	2	32
subtype3	0	2	39
subtype4	0	3	33

Figure S83. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'RPPA cHierClus subtypes' versus 'ETHNICITY'

P value = 0.84 (Fisher's exact test), Q value = 1

Table S90. Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	120
subtype1	2	34
subtype2	1	26
subtype3	1	30
subtype4	0	30

Figure S84. Get High-res Image Clustering Approach #6: 'RPPA cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #7: 'RNAseq CNMF subtypes'

Table S91. Description of clustering approach #7: 'RNAseq CNMF subtypes'

Cluster Labels	1	2	3	4
Number of samples	96	128	124	71

'RNAseq CNMF subtypes' versus 'Time to Death'

P value = 0.306 (logrank test), Q value = 1

Table S92. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	386	120	1.0 - 5287.0 (640.0)
subtype1	91	29	1.0 - 3724.0 (717.0)
subtype2	117	32	4.0 - 3016.0 (862.0)
subtype3	117	36	1.0 - 5287.0 (407.0)
subtype4	61	23	13.0 - 2589.0 (684.0)

Figure S85. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq CNMF subtypes' versus 'AGE'

P value = 0.0218 (Kruskal-Wallis (anova)), Q value = 1

Table S93. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	411	67.1 (8.6)
subtype1	94	67.1 (9.3)
subtype2	126	65.4 (8.1)
subtype3	121	68.3 (8.2)
subtype4	70	68.3 (8.7)

Figure S86. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0832 (Fisher's exact test), Q value = 1

Table S94. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	73	136	1	52	70	57	19	6
subtype1	1	17	35	0	8	17	14	2	1
subtype2	1	14	51	1	16	23	14	8	0
subtype3	0	23	30	0	21	23	18	6	2
subtype4	0	19	20	0	7	7	11	3	3

Figure S87. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.767 (Fisher's exact test), Q value = 1

Table S95. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	100	252	48	19
subtype1	21	61	11	3
subtype2	24	83	14	7
subtype3	33	70	15	6
subtype4	22	38	8	3

Figure S88. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.48 (Fisher's exact test), Q value = 1

Table S96. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	262	111	35	5
subtype1	60	24	9	1
subtype2	80	37	9	1
subtype3	77	38	8	1
subtype4	45	12	9	2

Figure S89. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'RNAseq CNMF subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.413 (Fisher's exact test), Q value = 1

Table S97. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	357	5	1	50
subtype1	80	1	0	13
subtype2	114	0	0	12
subtype3	105	2	0	16
subtype4	58	2	1	9

Figure S90. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RNAseq CNMF subtypes' versus 'GENDER'

P value = 0.549 (Fisher's exact test), Q value = 1

Table S98. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	107	312
subtype1	23	73
subtype2	28	100
subtype3	35	89
subtype4	21	50

Figure S91. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'RNAseq CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.907 (Kruskal-Wallis (anova)), Q value = 1

Table S99. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	93	52.6 (41.9)
subtype1	16	58.1 (40.9)
subtype2	28	56.1 (41.7)
subtype3	29	51.4 (42.0)
subtype4	20	45.0 (45.0)

Figure S92. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.507 (Fisher's exact test), Q value = 1

Table S100. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	12	6	1	400
subtype1	2	2	0	92
subtype2	5	1	0	122
subtype3	5	1	1	117
subtype4	0	2	0	69

Figure S93. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RNAseq CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.437 (Fisher's exact test), Q value = 1

Table S101. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	13	406
subtype1	2	94
subtype2	2	126
subtype3	6	118
subtype4	3	68

Figure S94. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.585 (Kruskal-Wallis (anova)), Q value = 1

Table S102. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	355	52.8 (31.5)
subtype1	84	50.0 (32.3)
subtype2	109	52.1 (27.7)
subtype3	102	54.7 (33.1)
subtype4	60	54.7 (34.4)

Figure S95. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RNAseq CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.646 (Fisher's exact test), Q value = 1

Table S103. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	341	8	4	18
subtype1	75	2	2	3
subtype2	111	4	0	5
subtype3	99	2	1	5
subtype4	56	0	1	5

Figure S96. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RNAseq CNMF subtypes' versus 'RACE'

P value = 0.618 (Fisher's exact test), Q value = 1

Table S104. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	9	16	297
subtype1	2	5	62
subtype2	1	5	91
subtype3	3	3	94
subtype4	3	3	50

Figure S97. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #13: 'RACE'

'RNAseq CNMF subtypes' versus 'ETHNICITY'

P value = 0.173 (Fisher's exact test), Q value = 1

Table S105. Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	8	265
subtype1	4	57
subtype2	1	77
subtype3	1	87
subtype4	2	44

Figure S98. Get High-res Image Clustering Approach #7: 'RNAseq CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #8: 'RNAseq cHierClus subtypes'

Table S106. Description of clustering approach #8: 'RNAseq cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	156	157	106

'RNAseq cHierClus subtypes' versus 'Time to Death'

P value = 0.412 (logrank test), Q value = 1

Table S107. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	386	120	1.0 - 5287.0 (640.0)
subtype1	145	48	1.0 - 3724.0 (734.0)
subtype2	143	38	4.0 - 3016.0 (822.0)
subtype3	98	34	1.0 - 5287.0 (361.0)

Figure S99. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'RNAseq cHierClus subtypes' versus 'AGE'

P value = 0.00523 (Kruskal-Wallis (anova)), Q value = 0.84

Table S108. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	411	67.1 (8.6)
subtype1	153	68.7 (8.4)
subtype2	153	65.5 (8.6)
subtype3	105	67.2 (8.5)

Figure S100. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'RNAseq cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0714 (Fisher's exact test), Q value = 1

Table S109. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	73	136	1	52	70	57	19	6
subtype1	1	26	56	0	16	26	23	3	4
subtype2	1	21	57	1	19	28	19	10	0
subtype3	0	26	23	0	17	16	15	6	2

Figure S101. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.136 (Fisher's exact test), Q value = 1

Table S110. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	100	252	48	19
subtype1	32	96	22	6
subtype2	32	101	17	7
subtype3	36	55	9	6

Figure S102. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.956 (Fisher's exact test), Q value = 1

Table S111. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	262	111	35	5
subtype1	101	39	12	1
subtype2	96	44	13	3
subtype3	65	28	10	1

Figure S103. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'RNAseq cHierClus subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.432 (Fisher's exact test), Q value = 1

Table S112. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	357	5	1	50
subtype1	128	3	1	21
subtype2	137	0	0	17
subtype3	92	2	0	12

Figure S104. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'RNAseq cHierClus subtypes' versus 'GENDER'

P value = 0.0321 (Fisher's exact test), Q value = 1

Table S113. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	107	312
subtype1	50	106
subtype2	30	127
subtype3	27	79

Figure S105. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'RNAseq cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.451 (Kruskal-Wallis (anova)), Q value = 1

Table S114. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	93	52.6 (41.9)
subtype1	31	47.4 (43.0)
subtype2	35	59.7 (40.4)
subtype3	27	49.3 (42.9)

Figure S106. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'RNAseq cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.102 (Fisher's exact test), Q value = 1

Table S115. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	12	6	1	400
subtype1	1	3	0	152
subtype2	6	1	0	150
subtype3	5	2	1	98

Figure S107. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'RNAseq cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.83 (Fisher's exact test), Q value = 1

Table S116. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	13	406
subtype1	4	152
subtype2	6	151
subtype3	3	103

Figure S108. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'RNAseq cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.741 (Kruskal-Wallis (anova)), Q value = 1

Table S117. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	355	52.8 (31.5)
subtype1	134	54.8 (33.9)
subtype2	132	50.9 (27.1)
subtype3	89	52.5 (33.7)

Figure S109. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'RNAseq cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.716 (Fisher's exact test), Q value = 1

Table S118. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	341	8	4	18
subtype1	125	2	1	9
subtype2	130	4	3	6
subtype3	86	2	0	3

Figure S110. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'RNAseq cHierClus subtypes' versus 'RACE'

P value = 0.563 (Fisher's exact test), Q value = 1

Table S119. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	9	16	297
subtype1	3	8	102
subtype2	2	5	113
subtype3	4	3	82

Figure S111. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'RNAseq cHierClus subtypes' versus 'ETHNICITY'

P value = 0.748 (Fisher's exact test), Q value = 1

Table S120. Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	8	265
subtype1	4	95
subtype2	2	94
subtype3	2	76

Figure S112. Get High-res Image Clustering Approach #8: 'RNAseq cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #9: 'MIRSEQ CNMF'

Table S121. Description of clustering approach #9: 'MIRSEQ CNMF'

Cluster Labels	1	2	3	4	5
Number of samples	121	94	99	53	29

'MIRSEQ CNMF' versus 'Time to Death'

P value = 0.00899 (logrank test), Q value = 1

Table S122. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	363	109	1.0 - 5287.0 (639.0)
subtype1	115	48	1.0 - 5287.0 (699.0)
subtype2	82	14	2.0 - 2167.0 (385.5)
subtype3	88	23	1.0 - 2589.0 (757.5)
subtype4	51	14	6.0 - 2754.0 (555.0)
subtype5	27	10	3.0 - 1967.0 (833.0)

Figure S113. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CNMF' versus 'AGE'

P value = 0.00346 (Kruskal-Wallis (anova)), Q value = 0.56

Table S123. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	389	67.4 (8.7)
subtype1	120	67.2 (8.2)
subtype2	92	65.3 (8.7)
subtype3	96	68.6 (9.4)
subtype4	52	66.8 (8.4)
subtype5	29	71.6 (6.8)

Figure S114. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #2: 'AGE'

'MIRSEQ CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.00216 (Fisher's exact test), Q value = 0.35

Table S124. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	68	128	1	49	69	55	17	5
subtype1	0	16	48	0	6	19	21	8	3
subtype2	1	10	27	1	20	18	15	1	0
subtype3	1	20	27	0	17	17	12	3	2
subtype4	0	12	21	0	5	7	3	4	0
subtype5	0	10	5	0	1	8	4	1	0

Figure S115. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.T.STAGE'

P value = 0.0738 (Fisher's exact test), Q value = 1

Table S125. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	92	240	46	18
subtype1	22	80	11	8
subtype2	17	64	12	1
subtype3	27	51	16	5
subtype4	15	32	3	3
subtype5	11	13	4	1

Figure S116. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.N.STAGE'

P value = 0.468 (Fisher's exact test), Q value = 1

Table S126. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	244	107	35	4
subtype1	76	28	13	4
subtype2	51	31	10	0
subtype3	62	27	6	0
subtype4	37	13	3	0
subtype5	18	8	3	0

Figure S117. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRSEQ CNMF' versus 'PATHOLOGY.M.STAGE'

P value = 0.00044 (Fisher's exact test), Q value = 0.073

Table S127. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	336	4	1	49
subtype1	113	3	0	3
subtype2	75	0	0	18
subtype3	78	1	1	19
subtype4	44	0	0	6
subtype5	26	0	0	3

Figure S118. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRSEQ CNMF' versus 'GENDER'

P value = 0.174 (Fisher's exact test), Q value = 1

Table S128. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	101	295
subtype1	31	90
subtype2	20	74
subtype3	25	74
subtype4	12	41
subtype5	13	16

Figure S119. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CNMF' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 7.6e-05 (Kruskal-Wallis (anova)), Q value = 0.013

Table S129. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	86	53.1 (41.9)
subtype1	25	15.6 (32.7)
subtype2	26	75.8 (25.5)
subtype3	19	64.2 (38.1)
subtype4	9	62.2 (47.4)
subtype5	7	61.4 (43.0)

Figure S120. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CNMF' versus 'HISTOLOGICAL.TYPE'

P value = 0.164 (Fisher's exact test), Q value = 1

Table S130. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	10	6	1	379
subtype1	1	1	0	119
subtype2	4	2	1	87
subtype3	1	3	0	95
subtype4	4	0	0	49
subtype5	0	0	0	29

Figure S121. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRSEQ CNMF' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.712 (Fisher's exact test), Q value = 1

Table S131. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	12	384
subtype1	4	117
subtype2	3	91
subtype3	4	95
subtype4	0	53
subtype5	1	28

Figure S122. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CNMF' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.82 (Kruskal-Wallis (anova)), Q value = 1

Table S132. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	337	53.6 (32.2)
subtype1	109	56.0 (37.8)
subtype2	78	50.1 (26.8)
subtype3	81	54.0 (29.0)
subtype4	46	50.8 (29.8)
subtype5	23	57.7 (36.2)

Figure S123. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CNMF' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.42 (Fisher's exact test), Q value = 1

Table S133. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	322	7	3	16
subtype1	109	2	2	2
subtype2	74	1	0	6
subtype3	75	2	0	5
subtype4	42	2	0	2
subtype5	22	0	1	1

Figure S124. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CNMF' versus 'RACE'

P value = 0.129 (Fisher's exact test), Q value = 1

Table S134. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	9	16	282
subtype1	3	4	73
subtype2	2	0	75
subtype3	4	6	75
subtype4	0	4	39
subtype5	0	2	20

Figure S125. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #13: 'RACE'

'MIRSEQ CNMF' versus 'ETHNICITY'

P value = 0.948 (Fisher's exact test), Q value = 1

Table S135. Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	252
subtype1	3	67
subtype2	1	63
subtype3	2	69
subtype4	1	35
subtype5	0	18

Figure S126. Get High-res Image Clustering Approach #9: 'MIRSEQ CNMF' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #10: 'MIRSEQ CHIERARCHICAL'

Table S136. Description of clustering approach #10: 'MIRSEQ CHIERARCHICAL'

Cluster Labels	1	2	3	4
Number of samples	75	105	156	60

'MIRSEQ CHIERARCHICAL' versus 'Time to Death'

P value = 0.0947 (logrank test), Q value = 1

Table S137. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	363	109	1.0 - 5287.0 (639.0)
subtype1	71	19	6.0 - 3016.0 (700.0)
subtype2	97	34	2.0 - 5287.0 (578.0)
subtype3	145	43	1.0 - 2524.0 (573.0)
subtype4	50	13	17.0 - 2979.0 (758.5)

Figure S127. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time to Death'

'MIRSEQ CHIERARCHICAL' versus 'AGE'

P value = 0.0533 (Kruskal-Wallis (anova)), Q value = 1

Table S138. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	389	67.4 (8.7)
subtype1	73	66.0 (8.5)
subtype2	103	66.2 (9.3)
subtype3	154	68.2 (7.9)
subtype4	59	69.1 (9.5)

Figure S128. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'AGE'

'MIRSEQ CHIERARCHICAL' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.334 (Fisher's exact test), Q value = 1

Table S139. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	68	128	1	49	69	55	17	5
subtype1	0	11	27	0	9	14	7	7	0
subtype2	0	16	40	1	13	18	13	2	2
subtype3	2	32	45	0	15	26	28	5	1
subtype4	0	9	16	0	12	11	7	3	2

Figure S129. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.T.STAGE'

P value = 0.7 (Fisher's exact test), Q value = 1

Table S140. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	92	240	46	18
subtype1	16	47	7	5
subtype2	21	68	13	3
subtype3	42	90	19	5
subtype4	13	35	7	5

Figure S130. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.N.STAGE'

P value = 0.891 (Fisher's exact test), Q value = 1

Table S141. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	244	107	35	4
subtype1	44	25	5	1
subtype2	70	25	9	1
subtype3	98	41	16	1
subtype4	32	16	5	1

Figure S131. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'PATHOLOGY.M.STAGE'

P value = 0.28 (Fisher's exact test), Q value = 1

Table S142. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	336	4	1	49
subtype1	66	0	0	7
subtype2	93	2	0	10
subtype3	130	1	0	21
subtype4	47	1	1	11

Figure S132. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'GENDER'

P value = 0.536 (Fisher's exact test), Q value = 1

Table S143. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	101	295
subtype1	16	59
subtype2	25	80
subtype3	46	110
subtype4	14	46

Figure S133. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'GENDER'

'MIRSEQ CHIERARCHICAL' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.0856 (Kruskal-Wallis (anova)), Q value = 1

Table S144. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	86	53.1 (41.9)
subtype1	15	66.7 (42.2)
subtype2	21	39.5 (44.1)
subtype3	36	51.1 (40.0)
subtype4	14	64.3 (39.9)

Figure S134. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRSEQ CHIERARCHICAL' versus 'HISTOLOGICAL.TYPE'

P value = 0.0348 (Fisher's exact test), Q value = 1

Table S145. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	10	6	1	379
subtype1	4	0	0	71
subtype2	5	3	0	97
subtype3	1	1	1	153
subtype4	0	2	0	58

Figure S135. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRSEQ CHIERARCHICAL' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.203 (Fisher's exact test), Q value = 1

Table S146. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	12	384
subtype1	1	74
subtype2	1	104
subtype3	8	148
subtype4	2	58

Figure S136. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRSEQ CHIERARCHICAL' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.599 (Kruskal-Wallis (anova)), Q value = 1

Table S147. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	337	53.6 (32.2)
subtype1	67	56.6 (32.7)
subtype2	86	53.5 (36.3)
subtype3	137	52.8 (28.5)
subtype4	47	51.7 (34.6)

Figure S137. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRSEQ CHIERARCHICAL' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.314 (Fisher's exact test), Q value = 1

Table S148. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	322	7	3	16
subtype1	62	3	1	2
subtype2	90	2	0	4
subtype3	127	1	1	5
subtype4	43	1	1	5

Figure S138. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRSEQ CHIERARCHICAL' versus 'RACE'

P value = 0.0443 (Fisher's exact test), Q value = 1

Table S149. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	9	16	282
subtype1	0	4	54
subtype2	3	1	72
subtype3	2	10	113
subtype4	4	1	43

Figure S139. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #13: 'RACE'

'MIRSEQ CHIERARCHICAL' versus 'ETHNICITY'

P value = 0.861 (Fisher's exact test), Q value = 1

Table S150. Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	7	252
subtype1	1	50
subtype2	1	57
subtype3	3	104
subtype4	2	41

Figure S140. Get High-res Image Clustering Approach #10: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #11: 'MIRseq Mature CNMF subtypes'

Table S151. Description of clustering approach #11: 'MIRseq Mature CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	65	118	72

'MIRseq Mature CNMF subtypes' versus 'Time to Death'

P value = 0.791 (logrank test), Q value = 1

Table S152. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	230	53	1.0 - 2589.0 (438.5)
subtype1	56	12	3.0 - 1972.0 (629.5)
subtype2	105	25	1.0 - 2167.0 (378.0)
subtype3	69	16	2.0 - 2589.0 (555.0)

Figure S141. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature CNMF subtypes' versus 'AGE'

P value = 0.0527 (Kruskal-Wallis (anova)), Q value = 1

Table S153. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	251	67.5 (8.7)
subtype1	63	69.0 (10.2)
subtype2	116	67.7 (8.1)
subtype3	72	65.9 (8.1)

Figure S142. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.386 (Fisher's exact test), Q value = 1

Table S154. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	50	74	1	42	43	34	5	2
subtype1	1	10	21	0	9	14	7	3	0
subtype2	1	27	36	1	20	15	14	0	2
subtype3	0	13	17	0	13	14	13	2	0

Figure S143. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.255 (Fisher's exact test), Q value = 1

Table S155. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	66	148	34	7
subtype1	13	38	11	3
subtype2	38	66	11	3
subtype3	15	44	12	1

Figure S144. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.502 (Fisher's exact test), Q value = 1

Table S156. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2
ALL	159	69	21
subtype1	41	17	5
subtype2	78	28	8
subtype3	40	24	8

Figure S145. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRseq Mature CNMF subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 1 (Fisher's exact test), Q value = 1

Table S157. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	202	1	1	49
subtype1	52	0	0	13
subtype2	92	1	1	22
subtype3	58	0	0	14

Figure S146. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRseq Mature CNMF subtypes' versus 'GENDER'

P value = 0.376 (Fisher's exact test), Q value = 1

Table S158. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	62	193
subtype1	20	45
subtype2	27	91
subtype3	15	57

Figure S147. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature CNMF subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.979 (Kruskal-Wallis (anova)), Q value = 1

Table S159. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	64	65.3 (37.2)
subtype1	12	65.0 (36.6)
subtype2	25	70.4 (32.8)
subtype3	27	60.7 (41.8)

Figure S148. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRseq Mature CNMF subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.274 (Fisher's exact test), Q value = 1

Table S160. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	7	5	1	242
subtype1	0	2	0	63
subtype2	3	1	1	113
subtype3	4	2	0	66

Figure S149. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRseq Mature CNMF subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.182 (Fisher's exact test), Q value = 1

Table S161. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	9	246
subtype1	0	65
subtype2	6	112
subtype3	3	69

Figure S150. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature CNMF subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.354 (Kruskal-Wallis (anova)), Q value = 1

Table S162. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	214	51.7 (28.6)
subtype1	50	56.0 (35.0)
subtype2	101	48.6 (24.7)
subtype3	63	53.3 (28.7)

Figure S151. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRseq Mature CNMF subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.407 (Fisher's exact test), Q value = 1

Table S163. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	193	5	2	13
subtype1	44	2	0	6
subtype2	87	1	1	4
subtype3	62	2	1	3

Figure S152. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRseq Mature CNMF subtypes' versus 'RACE'

P value = 0.227 (Fisher's exact test), Q value = 1

Table S164. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	6	9	201
subtype1	2	4	46
subtype2	2	5	100
subtype3	2	0	55

Figure S153. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #13: 'RACE'

'MIRseq Mature CNMF subtypes' versus 'ETHNICITY'

P value = 0.807 (Fisher's exact test), Q value = 1

Table S165. Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	174
subtype1	1	45
subtype2	3	85
subtype3	0	44

Figure S154. Get High-res Image Clustering Approach #11: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #14: 'ETHNICITY'

Clustering Approach #12: 'MIRseq Mature cHierClus subtypes'

Table S166. Description of clustering approach #12: 'MIRseq Mature cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	26	107	122

'MIRseq Mature cHierClus subtypes' versus 'Time to Death'

P value = 0.0433 (logrank test), Q value = 1

Table S167. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Year
ALL	230	53	1.0 - 2589.0 (438.5)
subtype1	24	7	16.0 - 1955.0 (427.0)
subtype2	97	24	1.0 - 2167.0 (449.0)
subtype3	109	22	1.0 - 2589.0 (428.0)

Figure S155. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time to Death'

'MIRseq Mature cHierClus subtypes' versus 'AGE'

P value = 0.0762 (Kruskal-Wallis (anova)), Q value = 1

Table S168. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	251	67.5 (8.7)
subtype1	26	69.5 (6.7)
subtype2	107	66.2 (8.5)
subtype3	118	68.3 (9.2)

Figure S156. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'AGE'

'MIRseq Mature cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.113 (Fisher's exact test), Q value = 1

Table S169. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

nPatients	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIIA	STAGE IIIB	STAGE IV
ALL	2	50	74	1	42	43	34	5	2
subtype1	1	5	6	0	1	5	7	1	0
subtype2	1	18	28	0	20	22	16	1	0
subtype3	0	27	40	1	21	16	11	3	2

Figure S157. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'NEOPLASM.DISEASESTAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY.T.STAGE'

P value = 0.117 (Fisher's exact test), Q value = 1

Table S170. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

nPatients	T1	T2	T3	T4
ALL	66	148	34	7
subtype1	6	12	7	1
subtype2	23	69	14	1
subtype3	37	67	13	5

Figure S158. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PATHOLOGY.T.STAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY.N.STAGE'

P value = 0.297 (Fisher's exact test), Q value = 1

Table S171. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2
ALL	159	69	21
subtype1	17	5	4
subtype2	62	35	9
subtype3	80	29	8

Figure S159. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'PATHOLOGY.N.STAGE'

'MIRseq Mature cHierClus subtypes' versus 'PATHOLOGY.M.STAGE'

P value = 0.463 (Fisher's exact test), Q value = 1

Table S172. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	MX
ALL	202	1	1	49
subtype1	21	0	0	5
subtype2	90	0	0	16
subtype3	91	1	1	28

Figure S160. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.M.STAGE'

'MIRseq Mature cHierClus subtypes' versus 'GENDER'

P value = 0.722 (Fisher's exact test), Q value = 1

Table S173. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

nPatients	FEMALE	MALE
ALL	62	193
subtype1	8	18
subtype2	25	82
subtype3	29	93

Figure S161. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'GENDER'

'MIRseq Mature cHierClus subtypes' versus 'KARNOFSKY.PERFORMANCE.SCORE'

P value = 0.108 (Kruskal-Wallis (anova)), Q value = 1

Table S174. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

	nPatients	Mean (Std.Dev)
ALL	64	65.3 (37.2)
subtype1	5	44.0 (40.4)
subtype2	39	63.3 (39.3)
subtype3	20	74.5 (30.7)

Figure S162. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'KARNOFSKY.PERFORMANCE.SCORE'

'MIRseq Mature cHierClus subtypes' versus 'HISTOLOGICAL.TYPE'

P value = 0.0252 (Fisher's exact test), Q value = 1

Table S175. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

nPatients	LUNG BASALOID SQUAMOUS CELL CARCINOMA	LUNG PAPILLARY SQUAMOUS CELL CARICNOMA	LUNG SMALL CELL SQUAMOUS CELL CARCINOMA	LUNG SQUAMOUS CELL CARCINOMA- NOT OTHERWISE SPECIFIED (NOS)
ALL	7	5	1	242
subtype1	0	1	0	25
subtype2	7	2	1	97
subtype3	0	2	0	120

Figure S163. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'HISTOLOGICAL.TYPE'

'MIRseq Mature cHierClus subtypes' versus 'RADIATIONS.RADIATION.REGIMENINDICATION'

P value = 0.696 (Fisher's exact test), Q value = 1

Table S176. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

nPatients	NO	YES
ALL	9	246
subtype1	0	26
subtype2	5	102
subtype3	4	118

Figure S164. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'RADIATIONS.RADIATION.REGIMENINDICATION'

'MIRseq Mature cHierClus subtypes' versus 'NUMBERPACKYEARSSMOKED'

P value = 0.116 (Kruskal-Wallis (anova)), Q value = 1

Table S177. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

	nPatients	Mean (Std.Dev)
ALL	214	51.7 (28.6)
subtype1	19	60.3 (25.5)
subtype2	94	50.6 (25.6)
subtype3	101	51.2 (31.6)

Figure S165. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'NUMBERPACKYEARSSMOKED'

'MIRseq Mature cHierClus subtypes' versus 'COMPLETENESS.OF.RESECTION'

P value = 0.556 (Fisher's exact test), Q value = 1

Table S178. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

nPatients	R0	R1	R2	RX
ALL	193	5	2	13
subtype1	19	1	0	1
subtype2	87	2	2	4
subtype3	87	2	0	8

Figure S166. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'COMPLETENESS.OF.RESECTION'

'MIRseq Mature cHierClus subtypes' versus 'RACE'

P value = 0.00321 (Fisher's exact test), Q value = 0.52

Table S179. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RACE'

nPatients	ASIAN	BLACK OR AFRICAN AMERICAN	WHITE
ALL	6	9	201
subtype1	0	3	15
subtype2	1	0	94
subtype3	5	6	92

Figure S167. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #13: 'RACE'

'MIRseq Mature cHierClus subtypes' versus 'ETHNICITY'

P value = 0.204 (Fisher's exact test), Q value = 1

Table S180. Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

nPatients	HISPANIC OR LATINO	NOT HISPANIC OR LATINO
ALL	4	174
subtype1	0	16
subtype2	0	71
subtype3	4	87

Figure S168. Get High-res Image Clustering Approach #12: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #14: 'ETHNICITY'

Methods & Data

Input

Cluster data file = LUSC-TP.mergedcluster.txt
Clinical data file = LUSC-TP.merged_data.txt
Number of patients = 422
Number of clustering approaches = 12
Number of selected clinical features = 14
Exclude small clusters that include fewer than K patients, K = 3

Clustering approaches

CNMF clustering

consensus non-negative matrix factorization clustering approach (Brunet et al. 2004)

Consensus hierarchical clustering

Resampling-based clustering method (Monti et al. 2003)

Survival analysis

For survival clinical features, the Kaplan-Meier survival curves of tumors with and without gene mutations were plotted and the statistical significance P values were estimated by logrank test (Bland and Altman 2004) using the 'survdiff' function in R

Fisher's exact test

For binary clinical features, two-tailed Fisher's exact tests (Fisher 1922) were used to estimate the P values using the 'fisher.test' function in R

Q value calculation

For multiple hypothesis correction, Q value is the False Discovery Rate (FDR) analogue of the P value (Benjamini and Hochberg 1995), defined as the minimum FDR at which the test may be called significant. We used the 'Benjamini and Hochberg' method of 'p.adjust' function in R to convert P values into Q values.

Download Results

In addition to the links below, the full results of the analysis summarized in this report can also be downloaded programmatically using firehose_get, or interactively from either the Broad GDAC website or TCGA Data Coordination Center Portal.

References

[1] Brunet et al., Metagenes and molecular pattern discovery using matrix factorization, PNAS 101(12):4164-9 (2004)

[2] Monti et al., Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data, Machine Learning 52(1):91-118 (2003)

[3] Bland and Altman, Statistics notes: The logrank test, BMJ 328(7447):1073 (2004)

[4] Fisher, R.A., On the interpretation of chi-square from contingency tables, and the calculation of P, Journal of the Royal Statistical Society 85(1):87-94 (1922)

[5] Benjamini and Hochberg, Controlling the false discovery rate: a practical and powerful approach to multiple testing, Journal of the Royal Statistical Society Series B 59:289-300 (1995)

Made with Nozzle