Correlation between aggregated molecular cancer subtypes and selected clinical features

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 10 different clustering approaches and 12 clinical features across 242 patients, 6 significant findings detected with P value < 0.05 and Q value < 0.25.

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 4 subtypes that do not correlate to any clinical features.
Consensus hierarchical clustering analysis on RPPA data identified 3 subtypes that do not correlate to any clinical features.
CNMF clustering analysis on sequencing-based mRNA expression data identified 3 subtypes that correlate to 'Time from Specimen Diagnosis to Death' and 'Time to Death'.
Consensus hierarchical clustering analysis on sequencing-based mRNA expression data identified 3 subtypes that correlate to 'Time from Specimen Diagnosis to Death', 'Time to Death', 'PRIMARY.SITE.OF.DISEASE', and 'PATHOLOGY.T.STAGE'.
3 subtypes identified in current cancer cohort by 'MIRSEQ CNMF'. These subtypes do not correlate to any clinical features.
3 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 10 different clustering approaches and 12 clinical features. Shown in the table are P values (Q values). Thresholded by P value < 0.05 and Q value < 0.25, 6 significant findings detected.


Clinical Features	Statistical Tests	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 from Specimen Diagnosis to Death	logrank test	0.0237 (1.00)	0.00258 (0.291)	0.256 (1.00)	0.188 (1.00)	2.12e-05 (0.0025)	6.49e-08 (7.79e-06)	0.0256 (1.00)	0.117 (1.00)	0.0042 (0.461)	0.158 (1.00)
Time to Death	logrank test	0.25 (1.00)	0.092 (1.00)	0.156 (1.00)	0.842 (1.00)	0.00212 (0.244)	6.92e-05 (0.00809)	0.0228 (1.00)	0.276 (1.00)	0.00506 (0.551)	0.206 (1.00)
AGE	ANOVA	0.479 (1.00)	0.312 (1.00)	0.171 (1.00)	0.949 (1.00)	0.0125 (1.00)	0.00238 (0.272)	0.573 (1.00)	0.791 (1.00)	0.0964 (1.00)	0.396 (1.00)
PRIMARY SITE OF DISEASE	Chi-square test	0.0881 (1.00)	0.00688 (0.743)	0.0639 (1.00)	0.494 (1.00)	0.00346 (0.387)	2.96e-07 (3.53e-05)	0.0314 (1.00)	0.672 (1.00)	0.0652 (1.00)	0.57 (1.00)
NEOPLASM DISEASESTAGE	Chi-square test	0.123 (1.00)	0.275 (1.00)	0.718 (1.00)	0.0936 (1.00)	0.167 (1.00)	0.0608 (1.00)	0.676 (1.00)	0.344 (1.00)	0.653 (1.00)	0.695 (1.00)
PATHOLOGY T STAGE	Chi-square test	0.714 (1.00)	0.131 (1.00)	0.484 (1.00)	0.744 (1.00)	0.0482 (1.00)	0.000177 (0.0205)	0.379 (1.00)	0.667 (1.00)	0.00397 (0.441)	0.4 (1.00)
PATHOLOGY N STAGE	Chi-square test	0.881 (1.00)	0.0316 (1.00)	0.368 (1.00)	0.0986 (1.00)	0.388 (1.00)	0.457 (1.00)	0.608 (1.00)	0.89 (1.00)	0.296 (1.00)	0.993 (1.00)
PATHOLOGY M STAGE	Chi-square test	0.43 (1.00)	0.862 (1.00)	0.214 (1.00)	0.942 (1.00)	0.8 (1.00)	0.0626 (1.00)	0.826 (1.00)	0.332 (1.00)	0.974 (1.00)	0.377 (1.00)
MELANOMA ULCERATION	Fisher's exact test	0.743 (1.00)	0.193 (1.00)	0.743 (1.00)	0.683 (1.00)	0.596 (1.00)	0.288 (1.00)	0.285 (1.00)	0.75 (1.00)	0.476 (1.00)	0.711 (1.00)
MELANOMA PRIMARY KNOWN	Fisher's exact test	0.663 (1.00)	0.23 (1.00)	0.441 (1.00)	0.0969 (1.00)	0.064 (1.00)	0.787 (1.00)	0.115 (1.00)	0.138 (1.00)	0.121 (1.00)	0.156 (1.00)
BRESLOW THICKNESS	ANOVA	0.361 (1.00)	0.897 (1.00)	0.944 (1.00)	0.554 (1.00)	0.174 (1.00)	0.0909 (1.00)	0.932 (1.00)	0.746 (1.00)	0.908 (1.00)	0.612 (1.00)
GENDER	Fisher's exact test	0.131 (1.00)	0.803 (1.00)	0.835 (1.00)	0.246 (1.00)	0.437 (1.00)	0.854 (1.00)	0.179 (1.00)	0.539 (1.00)	0.119 (1.00)	0.175 (1.00)

Clustering Approach #1: 'Copy Number Ratio CNMF subtypes'

Table S1. Description of clustering approach #1: 'Copy Number Ratio CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	77	97	68

'Copy Number Ratio CNMF subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 0.0237 (logrank test), Q value = 1

Table S2. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	210	101	0.1 - 124.3 (13.7)
subtype1	66	33	0.2 - 114.2 (13.0)
subtype2	84	34	1.0 - 124.3 (17.1)
subtype3	60	34	0.1 - 111.8 (11.5)

Figure S1. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

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

P value = 0.25 (logrank test), Q value = 1

Table S3. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	236	114	6.0 - 10870.0 (1484.5)
subtype1	76	38	6.0 - 8180.0 (1215.0)
subtype2	95	41	279.0 - 9567.0 (1543.0)
subtype3	65	35	28.0 - 10870.0 (1548.0)

Figure S2. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

'Copy Number Ratio CNMF subtypes' versus 'AGE'

P value = 0.479 (ANOVA), Q value = 1

Table S4. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	238	55.5 (15.9)
subtype1	76	55.7 (16.4)
subtype2	96	56.7 (14.5)
subtype3	66	53.6 (17.4)

Figure S3. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #3: 'AGE'

'Copy Number Ratio CNMF subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.0881 (Chi-square test), Q value = 1

Table S5. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	32	1	50	158
subtype1	17	0	15	45
subtype2	7	0	22	67
subtype3	8	1	13	46

Figure S4. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

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

P value = 0.123 (Chi-square test), Q value = 1

Table S6. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	17	10	12	9	20	10	21	39	10
subtype1	0	1	4	4	8	7	2	3	5	3	4	12	9	5
subtype2	3	2	12	3	9	6	6	7	2	8	5	4	19	2
subtype3	6	1	4	3	5	4	2	2	2	9	1	5	11	3

Figure S5. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.714 (Chi-square test), Q value = 1

Table S7. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	42	54	46	50
subtype1	15	17	16	14
subtype2	13	22	21	23
subtype3	14	15	9	13

Figure S6. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.881 (Chi-square test), Q value = 1

Table S8. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	127	39	28	28
subtype1	38	13	11	7
subtype2	55	14	9	13
subtype3	34	12	8	8

Figure S7. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.43 (Chi-square test), Q value = 1

Table S9. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	213	3	2	2	5
subtype1	64	1	0	1	4
subtype2	89	1	1	1	0
subtype3	60	1	1	0	1

Figure S8. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'Copy Number Ratio CNMF subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.743 (Fisher's exact test), Q value = 1

Table S10. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	92	61
subtype1	32	21
subtype2	39	23
subtype3	21	17

Figure S9. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'Copy Number Ratio CNMF subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.663 (Fisher's exact test), Q value = 1

Table S11. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	212
subtype1	10	67
subtype2	10	87
subtype3	10	58

Figure S10. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'Copy Number Ratio CNMF subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.361 (ANOVA), Q value = 1

Table S12. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	181	3.6 (5.2)
subtype1	61	3.1 (4.1)
subtype2	75	4.2 (6.7)
subtype3	45	3.0 (3.1)

Figure S11. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'Copy Number Ratio CNMF subtypes' versus 'GENDER'

P value = 0.131 (Fisher's exact test), Q value = 1

Table S13. Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	95	147
subtype1	32	45
subtype2	31	66
subtype3	32	36

Figure S12. Get High-res Image Clustering Approach #1: 'Copy Number Ratio CNMF subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #2: 'METHLYATION CNMF'

Table S14. Description of clustering approach #2: 'METHLYATION CNMF'

Cluster Labels	1	2	3
Number of samples	60	88	94

'METHLYATION CNMF' versus 'Time from Specimen Diagnosis to Death'

P value = 0.00258 (logrank test), Q value = 0.29

Table S15. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	210	101	0.1 - 124.3 (13.7)
subtype1	54	32	0.1 - 111.1 (10.7)
subtype2	75	35	0.2 - 114.2 (13.9)
subtype3	81	34	1.1 - 124.3 (18.6)

Figure S13. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'METHLYATION CNMF' versus 'Time to Death'

P value = 0.092 (logrank test), Q value = 1

Table S16. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	236	114	6.0 - 10870.0 (1484.5)
subtype1	59	35	6.0 - 7514.0 (1265.0)
subtype2	86	40	28.0 - 10870.0 (1606.0)
subtype3	91	39	98.0 - 10523.0 (1486.0)

Figure S14. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #2: 'Time to Death'

'METHLYATION CNMF' versus 'AGE'

P value = 0.312 (ANOVA), Q value = 1

Table S17. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	238	55.5 (15.9)
subtype1	59	54.8 (16.3)
subtype2	86	57.6 (16.4)
subtype3	93	54.1 (15.1)

Figure S15. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #3: 'AGE'

'METHLYATION CNMF' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.00688 (Chi-square test), Q value = 0.74

Table S18. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	32	1	50	158
subtype1	14	1	13	32
subtype2	14	0	20	54
subtype3	4	0	17	72

Figure S16. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'METHLYATION CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.275 (Chi-square test), Q value = 1

Table S19. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	17	10	12	9	20	10	21	39	10
subtype1	1	2	4	1	6	8	2	4	4	5	2	5	9	2
subtype2	6	1	5	6	9	4	5	6	5	4	5	7	11	3
subtype3	2	1	11	3	7	5	3	2	0	11	3	9	19	5

Figure S17. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.131 (Chi-square test), Q value = 1

Table S20. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	42	54	46	50
subtype1	5	19	10	15
subtype2	15	17	16	20
subtype3	22	18	20	15

Figure S18. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.0316 (Chi-square test), Q value = 1

Table S21. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	127	39	28	28
subtype1	33	13	5	3
subtype2	52	7	13	9
subtype3	42	19	10	16

Figure S19. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.862 (Chi-square test), Q value = 1

Table S22. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	213	3	2	2	5
subtype1	52	1	1	0	0
subtype2	79	1	0	1	2
subtype3	82	1	1	1	3

Figure S20. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'METHLYATION CNMF' versus 'MELANOMA.ULCERATION'

P value = 0.193 (Fisher's exact test), Q value = 1

Table S23. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	92	61
subtype1	15	17
subtype2	39	25
subtype3	38	19

Figure S21. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'METHLYATION CNMF' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.23 (Fisher's exact test), Q value = 1

Table S24. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	212
subtype1	6	54
subtype2	8	80
subtype3	16	78

Figure S22. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'METHLYATION CNMF' versus 'BRESLOW.THICKNESS'

P value = 0.897 (ANOVA), Q value = 1

Table S25. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	181	3.6 (5.2)
subtype1	47	3.7 (5.2)
subtype2	68	3.3 (2.8)
subtype3	66	3.7 (6.8)

Figure S23. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'METHLYATION CNMF' versus 'GENDER'

P value = 0.803 (Fisher's exact test), Q value = 1

Table S26. Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	95	147
subtype1	22	38
subtype2	37	51
subtype3	36	58

Figure S24. Get High-res Image Clustering Approach #2: 'METHLYATION CNMF' versus Clinical Feature #12: 'GENDER'

Clustering Approach #3: 'RPPA CNMF subtypes'

Table S27. Description of clustering approach #3: 'RPPA CNMF subtypes'

Cluster Labels	1	2	3	4
Number of samples	45	50	25	37

'RPPA CNMF subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 0.256 (logrank test), Q value = 1

Table S28. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	131	71	0.2 - 124.3 (13.0)
subtype1	38	18	3.5 - 103.6 (12.4)
subtype2	40	22	0.2 - 114.2 (15.0)
subtype3	21	12	2.4 - 68.1 (8.7)
subtype4	32	19	1.1 - 124.3 (16.2)

Figure S25. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'RPPA CNMF subtypes' versus 'Time to Death'

P value = 0.156 (logrank test), Q value = 1

Table S29. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	152	79	6.0 - 10870.0 (1487.0)
subtype1	43	20	301.0 - 10523.0 (1664.0)
subtype2	50	26	6.0 - 10870.0 (1645.5)
subtype3	24	13	111.0 - 4930.0 (1403.5)
subtype4	35	20	78.0 - 5370.0 (1096.0)

Figure S26. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

'RPPA CNMF subtypes' versus 'AGE'

P value = 0.171 (ANOVA), Q value = 1

Table S30. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	154	55.1 (16.0)
subtype1	44	50.8 (13.3)
subtype2	50	56.1 (16.0)
subtype3	25	56.0 (16.9)
subtype4	35	58.5 (17.8)

Figure S27. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #3: 'AGE'

'RPPA CNMF subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.0639 (Chi-square test), Q value = 1

Table S31. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	18	1	27	110
subtype1	2	0	14	29
subtype2	9	1	5	35
subtype3	4	0	5	16
subtype4	3	0	3	30

Figure S28. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'RPPA CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.718 (Chi-square test), Q value = 1

Table S32. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	7	2	12	8	14	8	5	5	3	14	5	15	25	7
subtype1	2	1	5	1	6	2	2	1	0	3	3	6	9	1
subtype2	2	1	5	1	5	2	2	2	3	5	1	1	6	4
subtype3	1	0	1	2	1	1	0	1	0	4	1	4	4	0
subtype4	2	0	1	4	2	3	1	1	0	2	0	4	6	2

Figure S29. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.484 (Chi-square test), Q value = 1

Table S33. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	28	33	28	30
subtype1	7	11	12	9
subtype2	6	10	6	12
subtype3	5	7	5	3
subtype4	10	5	5	6

Figure S30. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.368 (Chi-square test), Q value = 1

Table S34. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	76	23	21	19
subtype1	21	8	5	8
subtype2	28	5	4	6
subtype3	9	5	7	2
subtype4	18	5	5	3

Figure S31. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.214 (Chi-square test), Q value = 1

Table S35. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	133	3	2	2	2
subtype1	41	1	1	0	0
subtype2	38	2	1	2	0
subtype3	24	0	0	0	0
subtype4	30	0	0	0	2

Figure S32. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'RPPA CNMF subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.743 (Fisher's exact test), Q value = 1

Table S36. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	61	35
subtype1	19	8
subtype2	21	13
subtype3	10	5
subtype4	11	9

Figure S33. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'RPPA CNMF subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.441 (Fisher's exact test), Q value = 1

Table S37. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	23	134
subtype1	5	40
subtype2	8	42
subtype3	2	23
subtype4	8	29

Figure S34. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'RPPA CNMF subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.944 (ANOVA), Q value = 1

Table S38. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	111	3.5 (5.4)
subtype1	35	3.7 (8.3)
subtype2	34	3.5 (3.1)
subtype3	20	2.8 (3.9)
subtype4	22	3.6 (3.7)

Figure S35. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'RPPA CNMF subtypes' versus 'GENDER'

P value = 0.835 (Fisher's exact test), Q value = 1

Table S39. Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	62	95
subtype1	17	28
subtype2	19	31
subtype3	9	16
subtype4	17	20

Figure S36. Get High-res Image Clustering Approach #3: 'RPPA CNMF subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #4: 'RPPA cHierClus subtypes'

Table S40. Description of clustering approach #4: 'RPPA cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	62	53	42

'RPPA cHierClus subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 0.188 (logrank test), Q value = 1

Table S41. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	131	71	0.2 - 124.3 (13.0)
subtype1	49	28	0.2 - 103.6 (11.7)
subtype2	46	24	3.5 - 124.3 (15.5)
subtype3	36	19	1.4 - 84.7 (16.3)

Figure S37. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'RPPA cHierClus subtypes' versus 'Time to Death'

P value = 0.842 (logrank test), Q value = 1

Table S42. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	152	79	6.0 - 10870.0 (1487.0)
subtype1	61	31	6.0 - 7562.0 (1349.0)
subtype2	52	27	195.0 - 10870.0 (1622.5)
subtype3	39	21	301.0 - 10523.0 (1620.0)

Figure S38. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

'RPPA cHierClus subtypes' versus 'AGE'

P value = 0.949 (ANOVA), Q value = 1

Table S43. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	154	55.1 (16.0)
subtype1	62	55.6 (16.9)
subtype2	52	54.7 (15.5)
subtype3	40	55.0 (15.5)

Figure S39. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #3: 'AGE'

'RPPA cHierClus subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.494 (Chi-square test), Q value = 1

Table S44. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	18	1	27	110
subtype1	7	0	11	43
subtype2	8	1	6	38
subtype3	3	0	10	29

Figure S40. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'RPPA cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0936 (Chi-square test), Q value = 1

Table S45. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	7	2	12	8	14	8	5	5	3	14	5	15	25	7
subtype1	1	0	4	5	6	7	0	2	0	6	2	7	7	3
subtype2	3	1	6	2	4	0	4	3	3	4	1	2	7	2
subtype3	3	1	2	1	4	1	1	0	0	4	2	6	11	2

Figure S41. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.744 (Chi-square test), Q value = 1

Table S46. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	28	33	28	30
subtype1	12	14	12	12
subtype2	9	9	5	11
subtype3	7	10	11	7

Figure S42. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.0986 (Chi-square test), Q value = 1

Table S47. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	76	23	21	19
subtype1	31	10	10	4
subtype2	29	3	5	7
subtype3	16	10	6	8

Figure S43. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.942 (Chi-square test), Q value = 1

Table S48. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	133	3	2	2	2
subtype1	54	1	1	1	1
subtype2	41	1	0	1	0
subtype3	38	1	1	0	1

Figure S44. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'RPPA cHierClus subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.683 (Fisher's exact test), Q value = 1

Table S49. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	61	35
subtype1	29	14
subtype2	19	11
subtype3	13	10

Figure S45. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'RPPA cHierClus subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.0969 (Fisher's exact test), Q value = 1

Table S50. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	23	134
subtype1	5	57
subtype2	12	41
subtype3	6	36

Figure S46. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'RPPA cHierClus subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.554 (ANOVA), Q value = 1

Table S51. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	111	3.5 (5.4)
subtype1	48	3.0 (3.4)
subtype2	33	3.3 (3.1)
subtype3	30	4.4 (9.0)

Figure S47. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'RPPA cHierClus subtypes' versus 'GENDER'

P value = 0.246 (Fisher's exact test), Q value = 1

Table S52. Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	62	95
subtype1	27	35
subtype2	23	30
subtype3	12	30

Figure S48. Get High-res Image Clustering Approach #4: 'RPPA cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #5: 'RNAseq CNMF subtypes'

Table S53. Description of clustering approach #5: 'RNAseq CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	85	63	93

'RNAseq CNMF subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 2.12e-05 (logrank test), Q value = 0.0025

Table S54. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	209	101	0.1 - 124.3 (13.7)
subtype1	71	39	1.7 - 111.8 (15.3)
subtype2	56	16	1.1 - 124.3 (24.6)
subtype3	82	46	0.1 - 99.5 (10.1)

Figure S49. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'RNAseq CNMF subtypes' versus 'Time to Death'

P value = 0.00212 (logrank test), Q value = 0.24

Table S55. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	235	114	6.0 - 10870.0 (1486.0)
subtype1	82	46	194.0 - 10870.0 (1737.0)
subtype2	62	19	220.0 - 8180.0 (1686.5)
subtype3	91	49	6.0 - 7514.0 (1265.0)

Figure S50. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

'RNAseq CNMF subtypes' versus 'AGE'

P value = 0.0125 (ANOVA), Q value = 1

Table S56. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	237	55.5 (15.9)
subtype1	82	51.6 (15.9)
subtype2	63	56.1 (15.5)
subtype3	92	58.7 (15.7)

Figure S51. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #3: 'AGE'

'RNAseq CNMF subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.00346 (Chi-square test), Q value = 0.39

Table S57. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	32	1	49	158
subtype1	10	0	27	48
subtype2	4	0	7	52
subtype3	18	1	15	58

Figure S52. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'RNAseq CNMF subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.167 (Chi-square test), Q value = 1

Table S58. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	17	10	12	9	20	10	20	39	10
subtype1	4	3	9	2	8	7	3	3	1	11	4	5	10	5
subtype2	2	1	7	4	4	5	4	1	2	6	0	4	14	2
subtype3	3	0	4	4	10	5	3	8	6	3	6	11	15	3

Figure S53. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.0482 (Chi-square test), Q value = 1

Table S59. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	42	54	46	49
subtype1	17	25	14	11
subtype2	15	11	12	12
subtype3	10	18	20	26

Figure S54. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.388 (Chi-square test), Q value = 1

Table S60. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	127	39	27	28
subtype1	44	16	9	8
subtype2	37	10	3	9
subtype3	46	13	15	11

Figure S55. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.8 (Chi-square test), Q value = 1

Table S61. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	212	3	2	2	5
subtype1	74	0	1	1	3
subtype2	57	1	0	0	1
subtype3	81	2	1	1	1

Figure S56. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'RNAseq CNMF subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.596 (Fisher's exact test), Q value = 1

Table S62. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	91	61
subtype1	27	17
subtype2	25	13
subtype3	39	31

Figure S57. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'RNAseq CNMF subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.064 (Fisher's exact test), Q value = 1

Table S63. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	211
subtype1	13	72
subtype2	11	52
subtype3	6	87

Figure S58. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'RNAseq CNMF subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.174 (ANOVA), Q value = 1

Table S64. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	180	3.6 (5.2)
subtype1	60	3.0 (6.6)
subtype2	45	2.9 (3.6)
subtype3	75	4.4 (4.6)

Figure S59. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'RNAseq CNMF subtypes' versus 'GENDER'

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

Table S65. Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	95	146
subtype1	38	47
subtype2	22	41
subtype3	35	58

Figure S60. Get High-res Image Clustering Approach #5: 'RNAseq CNMF subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #6: 'RNAseq cHierClus subtypes'

Table S66. Description of clustering approach #6: 'RNAseq cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	52	123	66

'RNAseq cHierClus subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 6.49e-08 (logrank test), Q value = 7.8e-06

Table S67. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	209	101	0.1 - 124.3 (13.7)
subtype1	48	33	0.1 - 95.4 (8.7)
subtype2	104	36	0.2 - 124.3 (21.2)
subtype3	57	32	1.7 - 111.1 (15.2)

Figure S61. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'RNAseq cHierClus subtypes' versus 'Time to Death'

P value = 6.92e-05 (logrank test), Q value = 0.0081

Table S68. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	235	114	6.0 - 10870.0 (1486.0)
subtype1	51	33	6.0 - 7514.0 (874.0)
subtype2	120	43	28.0 - 10523.0 (1547.5)
subtype3	64	38	236.0 - 10870.0 (1737.0)

Figure S62. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

'RNAseq cHierClus subtypes' versus 'AGE'

P value = 0.00238 (ANOVA), Q value = 0.27

Table S69. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	237	55.5 (15.9)
subtype1	51	62.0 (16.1)
subtype2	122	54.6 (15.9)
subtype3	64	52.1 (14.6)

Figure S63. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #3: 'AGE'

'RNAseq cHierClus subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 2.96e-07 (Chi-square test), Q value = 3.5e-05

Table S70. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	32	1	49	158
subtype1	15	0	10	26
subtype2	9	1	13	100
subtype3	8	0	26	32

Figure S64. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'RNAseq cHierClus subtypes' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.0608 (Chi-square test), Q value = 1

Table S71. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	17	10	12	9	20	10	20	39	10
subtype1	1	0	2	1	3	5	2	6	4	0	3	7	10	3
subtype2	5	1	12	9	11	7	5	3	3	13	2	9	22	4
subtype3	3	3	6	0	8	5	3	3	2	7	5	4	7	3

Figure S65. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.000177 (Chi-square test), Q value = 0.02

Table S72. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	42	54	46	49
subtype1	2	9	14	18
subtype2	33	24	18	21
subtype3	7	21	14	10

Figure S66. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.457 (Chi-square test), Q value = 1

Table S73. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	127	39	27	28
subtype1	25	6	9	6
subtype2	67	19	12	17
subtype3	35	14	6	5

Figure S67. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.0626 (Chi-square test), Q value = 1

Table S74. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	212	3	2	2	5
subtype1	44	3	0	0	0
subtype2	111	0	1	1	4
subtype3	57	0	1	1	1

Figure S68. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'RNAseq cHierClus subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.288 (Fisher's exact test), Q value = 1

Table S75. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	91	61
subtype1	21	17
subtype2	52	27
subtype3	18	17

Figure S69. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'RNAseq cHierClus subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.787 (Fisher's exact test), Q value = 1

Table S76. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	211
subtype1	5	47
subtype2	17	106
subtype3	8	58

Figure S70. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'RNAseq cHierClus subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.0909 (ANOVA), Q value = 1

Table S77. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	180	3.6 (5.2)
subtype1	43	5.0 (5.0)
subtype2	87	2.9 (3.5)
subtype3	50	3.5 (7.2)

Figure S71. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'RNAseq cHierClus subtypes' versus 'GENDER'

P value = 0.854 (Fisher's exact test), Q value = 1

Table S78. Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	95	146
subtype1	20	32
subtype2	47	76
subtype3	28	38

Figure S72. Get High-res Image Clustering Approach #6: 'RNAseq cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #7: 'MIRSEQ CNMF'

Table S79. Description of clustering approach #7: 'MIRSEQ CNMF'

Cluster Labels	1	2	3
Number of samples	57	97	82

'MIRSEQ CNMF' versus 'Time from Specimen Diagnosis to Death'

P value = 0.0256 (logrank test), Q value = 1

Table S80. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	204	100	0.1 - 124.3 (13.9)
subtype1	48	15	0.1 - 114.2 (16.0)
subtype2	84	49	0.8 - 124.3 (12.4)
subtype3	72	36	1.0 - 111.1 (15.2)

Figure S73. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'MIRSEQ CNMF' versus 'Time to Death'

P value = 0.0228 (logrank test), Q value = 1

Table S81. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	230	113	6.0 - 10870.0 (1466.5)
subtype1	55	18	6.0 - 10870.0 (1204.0)
subtype2	97	55	78.0 - 7514.0 (1371.0)
subtype3	78	40	236.0 - 9567.0 (1704.5)

Figure S74. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #2: 'Time to Death'

'MIRSEQ CNMF' versus 'AGE'

P value = 0.573 (ANOVA), Q value = 1

Table S82. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	232	55.6 (15.7)
subtype1	56	56.2 (15.1)
subtype2	97	56.5 (16.7)
subtype3	79	54.1 (14.9)

Figure S75. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #3: 'AGE'

'MIRSEQ CNMF' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.0314 (Chi-square test), Q value = 1

Table S83. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	30	1	49	155
subtype1	5	1	10	41
subtype2	14	0	13	69
subtype3	11	0	26	45

Figure S76. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'MIRSEQ CNMF' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.676 (Chi-square test), Q value = 1

Table S84. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	15	9	12	8	19	10	21	38	10
subtype1	4	1	3	2	2	4	2	0	2	3	2	6	11	4
subtype2	3	1	6	6	10	8	4	7	3	7	3	10	13	4
subtype3	2	2	11	2	10	3	3	5	3	9	5	5	14	2

Figure S77. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.379 (Chi-square test), Q value = 1

Table S85. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	41	54	44	47
subtype1	12	6	9	11
subtype2	16	23	21	19
subtype3	13	25	14	17

Figure S78. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.608 (Chi-square test), Q value = 1

Table S86. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	123	38	28	27
subtype1	23	9	6	10
subtype2	54	15	11	9
subtype3	46	14	11	8

Figure S79. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.826 (Chi-square test), Q value = 1

Table S87. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	207	3	2	2	5
subtype1	44	1	1	1	2
subtype2	86	1	1	1	2
subtype3	77	1	0	0	1

Figure S80. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'MIRSEQ CNMF' versus 'MELANOMA.ULCERATION'

P value = 0.285 (Fisher's exact test), Q value = 1

Table S88. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	90	59
subtype1	14	15
subtype2	45	24
subtype3	31	20

Figure S81. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'MIRSEQ CNMF' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.115 (Fisher's exact test), Q value = 1

Table S89. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	206
subtype1	12	45
subtype2	10	87
subtype3	8	74

Figure S82. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'MIRSEQ CNMF' versus 'BRESLOW.THICKNESS'

P value = 0.932 (ANOVA), Q value = 1

Table S90. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	175	3.5 (5.2)
subtype1	34	3.4 (3.2)
subtype2	76	3.4 (4.1)
subtype3	65	3.7 (7.0)

Figure S83. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'MIRSEQ CNMF' versus 'GENDER'

P value = 0.179 (Fisher's exact test), Q value = 1

Table S91. Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	91	145
subtype1	27	30
subtype2	38	59
subtype3	26	56

Figure S84. Get High-res Image Clustering Approach #7: 'MIRSEQ CNMF' versus Clinical Feature #12: 'GENDER'

Clustering Approach #8: 'MIRSEQ CHIERARCHICAL'

Table S92. Description of clustering approach #8: 'MIRSEQ CHIERARCHICAL'

Cluster Labels	1	2	3
Number of samples	28	75	133

'MIRSEQ CHIERARCHICAL' versus 'Time from Specimen Diagnosis to Death'

P value = 0.117 (logrank test), Q value = 1

Table S93. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	204	100	0.1 - 124.3 (13.9)
subtype1	24	7	0.2 - 114.2 (20.4)
subtype2	65	34	1.0 - 111.1 (15.5)
subtype3	115	59	0.1 - 124.3 (12.9)

Figure S85. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

'MIRSEQ CHIERARCHICAL' versus 'Time to Death'

P value = 0.276 (logrank test), Q value = 1

Table S94. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	230	113	6.0 - 10870.0 (1466.5)
subtype1	27	9	6.0 - 10870.0 (1044.0)
subtype2	71	37	220.0 - 10523.0 (1709.0)
subtype3	132	67	28.0 - 9567.0 (1443.5)

Figure S86. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #2: 'Time to Death'

'MIRSEQ CHIERARCHICAL' versus 'AGE'

P value = 0.791 (ANOVA), Q value = 1

Table S95. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	232	55.6 (15.7)
subtype1	28	55.4 (16.8)
subtype2	72	54.6 (13.4)
subtype3	132	56.2 (16.7)

Figure S87. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #3: 'AGE'

'MIRSEQ CHIERARCHICAL' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.672 (Chi-square test), Q value = 1

Table S96. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	30	1	49	155
subtype1	3	0	8	17
subtype2	9	0	19	47
subtype3	18	1	22	91

Figure S88. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

'MIRSEQ CHIERARCHICAL' versus 'NEOPLASM.DISEASESTAGE'

P value = 0.344 (Chi-square test), Q value = 1

Table S97. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	15	9	12	8	19	10	21	38	10
subtype1	1	0	1	1	1	3	2	0	1	1	1	6	4	2
subtype2	3	3	9	1	7	3	2	4	2	11	3	3	14	2
subtype3	5	1	10	8	14	9	5	8	5	7	6	12	20	6

Figure S89. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.667 (Chi-square test), Q value = 1

Table S98. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	41	54	44	47
subtype1	5	3	6	7
subtype2	14	18	10	14
subtype3	22	33	28	26

Figure S90. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.89 (Chi-square test), Q value = 1

Table S99. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	123	38	28	27
subtype1	12	6	4	3
subtype2	37	12	10	10
subtype3	74	20	14	14

Figure S91. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.332 (Chi-square test), Q value = 1

Table S100. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	207	3	2	2	5
subtype1	23	1	1	1	0
subtype2	68	1	0	0	1
subtype3	116	1	1	1	4

Figure S92. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'MIRSEQ CHIERARCHICAL' versus 'MELANOMA.ULCERATION'

P value = 0.75 (Fisher's exact test), Q value = 1

Table S101. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	90	59
subtype1	9	8
subtype2	23	16
subtype3	58	35

Figure S93. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'MIRSEQ CHIERARCHICAL' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.138 (Fisher's exact test), Q value = 1

Table S102. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	206
subtype1	5	23
subtype2	13	62
subtype3	12	121

Figure S94. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'MIRSEQ CHIERARCHICAL' versus 'BRESLOW.THICKNESS'

P value = 0.746 (ANOVA), Q value = 1

Table S103. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	175	3.5 (5.2)
subtype1	18	3.4 (3.2)
subtype2	51	4.0 (7.9)
subtype3	106	3.3 (3.7)

Figure S95. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'MIRSEQ CHIERARCHICAL' versus 'GENDER'

P value = 0.539 (Fisher's exact test), Q value = 1

Table S104. Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	91	145
subtype1	11	17
subtype2	25	50
subtype3	55	78

Figure S96. Get High-res Image Clustering Approach #8: 'MIRSEQ CHIERARCHICAL' versus Clinical Feature #12: 'GENDER'

Clustering Approach #9: 'MIRseq Mature CNMF subtypes'

Table S105. Description of clustering approach #9: 'MIRseq Mature CNMF subtypes'

Cluster Labels	1	2	3
Number of samples	78	96	62

'MIRseq Mature CNMF subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 0.0042 (logrank test), Q value = 0.46

Table S106. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	204	100	0.1 - 124.3 (13.9)
subtype1	67	23	0.1 - 114.2 (16.0)
subtype2	84	51	0.8 - 124.3 (11.1)
subtype3	53	26	1.0 - 111.1 (18.0)

Figure S97. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

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

P value = 0.00506 (logrank test), Q value = 0.55

Table S107. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	230	113	6.0 - 10870.0 (1466.5)
subtype1	75	26	6.0 - 10870.0 (1446.0)
subtype2	96	56	78.0 - 7562.0 (1290.0)
subtype3	59	31	236.0 - 9567.0 (1861.0)

Figure S98. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #2: 'Time to Death'

'MIRseq Mature CNMF subtypes' versus 'AGE'

P value = 0.0964 (ANOVA), Q value = 1

Table S108. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	232	55.6 (15.7)
subtype1	76	56.6 (14.6)
subtype2	96	57.2 (17.2)
subtype3	60	51.9 (14.3)

Figure S99. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #3: 'AGE'

'MIRseq Mature CNMF subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.0652 (Chi-square test), Q value = 1

Table S109. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	30	1	49	155
subtype1	9	1	15	53
subtype2	13	0	13	69
subtype3	8	0	21	33

Figure S100. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

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

P value = 0.653 (Chi-square test), Q value = 1

Table S110. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	15	9	12	8	19	10	21	38	10
subtype1	5	2	7	5	3	5	2	1	3	5	2	8	15	3
subtype2	2	1	5	4	10	8	4	7	4	7	3	9	14	4
subtype3	2	1	8	1	9	2	3	4	1	7	5	4	9	3

Figure S101. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.00397 (Chi-square test), Q value = 0.44

Table S111. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	41	54	44	47
subtype1	21	10	10	16
subtype2	14	20	21	21
subtype3	6	24	13	10

Figure S102. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.296 (Chi-square test), Q value = 1

Table S112. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	123	38	28	27
subtype1	35	10	8	14
subtype2	53	15	11	9
subtype3	35	13	9	4

Figure S103. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.974 (Chi-square test), Q value = 1

Table S113. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	207	3	2	2	5
subtype1	64	1	1	1	1
subtype2	85	1	1	1	2
subtype3	58	1	0	0	2

Figure S104. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'MIRseq Mature CNMF subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.476 (Fisher's exact test), Q value = 1

Table S114. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	90	59
subtype1	23	20
subtype2	41	26
subtype3	26	13

Figure S105. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'MIRseq Mature CNMF subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.121 (Fisher's exact test), Q value = 1

Table S115. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	206
subtype1	15	63
subtype2	10	86
subtype3	5	57

Figure S106. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'MIRseq Mature CNMF subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.908 (ANOVA), Q value = 1

Table S116. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	175	3.5 (5.2)
subtype1	51	3.4 (4.3)
subtype2	74	3.7 (4.1)
subtype3	50	3.4 (7.2)

Figure S107. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'MIRseq Mature CNMF subtypes' versus 'GENDER'

P value = 0.119 (Fisher's exact test), Q value = 1

Table S117. Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	91	145
subtype1	36	42
subtype2	37	59
subtype3	18	44

Figure S108. Get High-res Image Clustering Approach #9: 'MIRseq Mature CNMF subtypes' versus Clinical Feature #12: 'GENDER'

Clustering Approach #10: 'MIRseq Mature cHierClus subtypes'

Table S118. Description of clustering approach #10: 'MIRseq Mature cHierClus subtypes'

Cluster Labels	1	2	3
Number of samples	70	136	30

'MIRseq Mature cHierClus subtypes' versus 'Time from Specimen Diagnosis to Death'

P value = 0.158 (logrank test), Q value = 1

Table S119. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	204	100	0.1 - 124.3 (13.9)
subtype1	61	31	1.0 - 111.1 (18.6)
subtype2	117	61	0.1 - 124.3 (12.6)
subtype3	26	8	0.2 - 114.2 (16.0)

Figure S109. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #1: 'Time from Specimen Diagnosis to Death'

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

P value = 0.206 (logrank test), Q value = 1

Table S120. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

	nPatients	nDeath	Duration Range (Median), Month
ALL	230	113	6.0 - 10870.0 (1466.5)
subtype1	67	34	236.0 - 10523.0 (1861.0)
subtype2	133	69	28.0 - 9567.0 (1438.0)
subtype3	30	10	6.0 - 10870.0 (1090.0)

Figure S110. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #2: 'Time to Death'

'MIRseq Mature cHierClus subtypes' versus 'AGE'

P value = 0.396 (ANOVA), Q value = 1

Table S121. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'AGE'

	nPatients	Mean (Std.Dev)
ALL	232	55.6 (15.7)
subtype1	67	53.7 (13.6)
subtype2	135	56.0 (16.5)
subtype3	30	58.2 (16.5)

Figure S111. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #3: 'AGE'

'MIRseq Mature cHierClus subtypes' versus 'PRIMARY.SITE.OF.DISEASE'

P value = 0.57 (Chi-square test), Q value = 1

Table S122. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

nPatients	DISTANT METASTASIS	PRIMARY TUMOR	REGIONAL CUTANEOUS OR SUBCUTANEOUS TISSUE	REGIONAL LYMPH NODE
ALL	30	1	49	155
subtype1	9	0	19	42
subtype2	18	1	22	94
subtype3	3	0	8	19

Figure S112. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #4: 'PRIMARY.SITE.OF.DISEASE'

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

P value = 0.695 (Chi-square test), Q value = 1

Table S123. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

nPatients	I OR II NOS	STAGE 0	STAGE I	STAGE IA	STAGE IB	STAGE II	STAGE IIA	STAGE IIB	STAGE IIC	STAGE III	STAGE IIIA	STAGE IIIB	STAGE IIIC	STAGE IV
ALL	9	4	20	10	22	15	9	12	8	19	10	21	38	10
subtype1	3	3	9	1	6	3	2	3	2	10	3	3	13	2
subtype2	5	1	9	8	15	9	5	8	5	8	5	14	21	6
subtype3	1	0	2	1	1	3	2	1	1	1	2	4	4	2

Figure S113. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #5: 'NEOPLASM.DISEASESTAGE'

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

P value = 0.4 (Chi-square test), Q value = 1

Table S124. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

nPatients	T0+T1	T2	T3	T4
ALL	41	54	44	47
subtype1	12	18	9	14
subtype2	23	34	28	26
subtype3	6	2	7	7

Figure S114. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #6: 'PATHOLOGY.T.STAGE'

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

P value = 0.993 (Chi-square test), Q value = 1

Table S125. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

nPatients	N0	N1	N2	N3
ALL	123	38	28	27
subtype1	35	12	9	9
subtype2	74	21	15	15
subtype3	14	5	4	3

Figure S115. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #7: 'PATHOLOGY.N.STAGE'

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

P value = 0.377 (Chi-square test), Q value = 1

Table S126. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

nPatients	M0	M1	M1A	M1B	M1C
ALL	207	3	2	2	5
subtype1	64	1	0	0	1
subtype2	119	1	1	1	4
subtype3	24	1	1	1	0

Figure S116. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #8: 'PATHOLOGY.M.STAGE'

'MIRseq Mature cHierClus subtypes' versus 'MELANOMA.ULCERATION'

P value = 0.711 (Fisher's exact test), Q value = 1

Table S127. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

nPatients	NO	YES
ALL	90	59
subtype1	22	15
subtype2	58	35
subtype3	10	9

Figure S117. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #9: 'MELANOMA.ULCERATION'

'MIRseq Mature cHierClus subtypes' versus 'MELANOMA.PRIMARY.KNOWN'

P value = 0.156 (Fisher's exact test), Q value = 1

Table S128. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

nPatients	NO	YES
ALL	30	206
subtype1	11	59
subtype2	13	123
subtype3	6	24

Figure S118. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #10: 'MELANOMA.PRIMARY.KNOWN'

'MIRseq Mature cHierClus subtypes' versus 'BRESLOW.THICKNESS'

P value = 0.612 (ANOVA), Q value = 1

Table S129. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

	nPatients	Mean (Std.Dev)
ALL	175	3.5 (5.2)
subtype1	48	4.2 (8.1)
subtype2	107	3.3 (3.7)
subtype3	20	3.3 (3.1)

Figure S119. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #11: 'BRESLOW.THICKNESS'

'MIRseq Mature cHierClus subtypes' versus 'GENDER'

P value = 0.175 (Fisher's exact test), Q value = 1

Table S130. Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

nPatients	FEMALE	MALE
ALL	91	145
subtype1	21	49
subtype2	56	80
subtype3	14	16

Figure S120. Get High-res Image Clustering Approach #10: 'MIRseq Mature cHierClus subtypes' versus Clinical Feature #12: 'GENDER'

Methods & Data

Input

Cluster data file = SKCM-TM.mergedcluster.txt
Clinical data file = SKCM-TM.clin.merged.picked.txt
Number of patients = 242
Number of clustering approaches = 10
Number of selected clinical features = 12
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

ANOVA analysis

For continuous numerical clinical features, one-way analysis of variance (Howell 2002) was applied to compare the clinical values between tumor subtypes using 'anova' function in R

Chi-square test

For multi-class clinical features (nominal or ordinal), Chi-square tests (Greenwood and Nikulin 1996) were used to estimate the P values using the 'chisq.test' 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.

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] Howell, D, Statistical Methods for Psychology. (5th ed.), Duxbury Press:324-5 (2002)

[5] Greenwood and Nikulin, A guide to chi-squared testing, Wiley, New York. ISBN 047155779X (1996)

[6] 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)

[7] 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