Day_3/Exercise_2-custom_background/id_list.txt

+EntrezGene ID	GeneName
+51703	ACSL5
+94	ACVRL1
+211	ALAS1
+23092	ARHGAP26
+9459	ARHGEF6
+55589	BMP2K
+1234	CCR5
+253175	CDY1
+9085	CDY1
+203611	CDY1
+9426	CDY1
+253175	CDY1B
+9085	CDY1B
+203611	CDY1B
+9426	CDY1B
+203611	CDY2A
+9426	CDY2A
+253175	CDY2A
+9085	CDY2A
+203611	CDY2B
+9426	CDY2B
+253175	CDY2B
+9085	CDY2B
+9620	CELSR1
+101928723	CHD5
+26038	CHD5
+1131	CHRM3
+1138	CHRNA5
+1259	CNGA1
+10699	CORIN
+1359	CPA3
+1472	CST4
+10800	CYSLTR1
+2191	FAP
+2213	FCGR2B
+54328	GPR173
+338442	HCAR2
+57657	HCN3
+9146	HGS
+8518	IKBKAP
+3559	IL2RA
+10994	ILVBL
+3619	INCENP
+10788	IQGAP2
+3704	ITPA
+4058	LTK
+4063	LY9
+4216	MAP3K4
+5871	MAP4K2
+4593	MUSK
+83463	MXD3
+91807	MYLK3
+8386	OR1D5
+5122	PCSK1
+5833	PCYT2
+5142	PDE4B
+5213	PFKM
+11284	PNKP
+5430	POLR2A
+5510	PPP1R7
+5523	PPP2R3A
+5531	PPP4C
+5538	PPT1
+85481	PSKH2
+11251	PTGDR2
+10076	PTPRU
+25945	PVRL3
+51762	RAB8B
+64080	RBKS
+8607	RUVBL1
+122042	RXFP2
+89777	SERPINB12
+6494	SIPA1
+8877	SPHK1
+7980	TFPI2
+112858	TP53RK
+7179	TPTE
+51175	TUBE1
+5756	TWF1

Day_3/Exercise_3-comparing_conditions/550prot_clusters.txt

+UniProt	cluster
+A0A087WPR9	1
+A0A0A6YY91	1
+A1L332	1
+A2A9X5	1
+A2AGS2	1
+A2AGS6	1
+A2AM29	1
+A3KG01	1
+A3KGE4	1
+B1AS34	1
+B1AV01	1
+B1AWZ5	1
+B2RWX4	1
+C9K0Z6	1
+D3Z0V7	1
+E2QRQ3	1
+E9PWE8	1
+E9Q6Q2	1
+E9Q8X9	1
+E9QMD3	1
+E9QN14	1
+E9QNZ2	1
+F2Z470	1
+F7BGR7	1
+F7C528	1
+F8WGN6	1
+G3X9L6	1
+H3BLR1	1
+J3JRU4	1
+O08553	1
+O08599	1
+O35098	1
+O54879	1
+O55126	1
+P08551	1
+P12025	1
+P20152	1
+P20357	1
+P22935	1
+P28738	1
+P45591	1
+P46660	1
+P61264	1
+Q00915	1
+Q14AX3	1
+Q14DQ3	1
+Q3TEA8	1
+Q3TRK3	1
+Q3TVU9	1
+Q3TWM9	1
+Q3U8W9	1
+Q3UID0	1
+Q3UWS9	1
+Q3UZJ4	1
+Q5DTK0	1
+Q5SQX6	1
+Q61301	1
+Q64511	1
+Q66JR8	1
+Q6A051	1
+Q6GR78	1
+Q6NZL0	1
+Q6PDL0	1
+Q6R891	1
+Q78IK4	1
+Q80YA7	1
+Q8BJS4	1
+Q8BP00	1
+Q8BUK6	1
+Q8C1Y3	1
+Q8CCK0	1
+Q8CDZ6	1
+Q8K394	1
+Q8K3C3	1
+Q8R572	1
+Q8VBT0	1
+Q8VCW8	1
+Q8VDP4	1
+Q8VEH3	1
+Q91XV3	1
+Q922J3	1
+Q99KJ8	1
+Q9BCZ4	1
+Q9CQ54	1
+Q9CZC8	1
+Q9D394	1
+Q9D5H8	1
+Q9D8S3	1
+Q9DCJ5	1
+Q9EQF6	1
+Q9JJV2	1
+Q9JKN6	1
+Q9JLZ3	1
+Q9JMG7	1
+Q9QYS9	1
+Q9QZM4	1
+Q9R226	1
+Q9WUL7	1
+A0JLN6	2
+A2TJV2	2
+A8CA96	2
+A8Y5N8	2
+B2RX07	2
+D0VLQ4	2
+D3Z112	2
+D3Z3H0	2
+E3WH30	2
+E9PV84	2
+E9Q391	2
+E9Q616	2
+E9Q6S4	2
+E9Q7E5	2
+E9Q8D0	2
+F6VY18	2
+F6Y247	2
+F8WIT2	2
+G3UYN0	2
+G5E8P4	2
+H7BX50	2
+J7I1C3	2
+O35488	2
+O88735	2
+P02798	2
+P08226	2
+P14602	2
+P24472	2
+P48678	2
+P56371	2
+P58242	2
+P59178	2
+P68368	2
+P70700	2
+P97384	2
+Q03145	2
+Q07133	2
+Q3TA91	2
+Q3TIJ5	2
+Q3TLA8	2
+Q3U0X6	2
+Q3U202	2
+Q3U3X7	2
+Q3UGF9	2
+Q3UKP5	2
+Q3V492	2
+Q4V9T7	2
+Q5FWJ5	2
+Q5SSZ5	2
+Q61539	2
+Q62315	2
+Q69ZR9	2
+Q6GU23	2
+Q6IE82	2
+Q6NSQ7	2
+Q6QMT3	2
+Q6ZPI0	2
+Q6ZQL4	2
+Q7TN89	2
+Q7TSZ8	2
+Q80UY2	2
+Q80VR2	2
+Q8BLG0	2
+Q8C6P8	2
+Q8CD92	2
+Q8CGZ0	2
+Q8CIB9	2
+Q8K403	2
+Q8K4R9	2
+Q8R0F5	2
+Q8R0K9	2
+Q8R0W0	2
+Q8R2Q8	2
+Q8R3C6	2
+Q8R409	2
+Q8VCF1	2
+Q8VCN5	2
+Q91XC0	2
+Q91YU8	2
+Q921M7	2
+Q99JX6	2
+Q99PB4	2
+Q9CWR8	2
+Q9CYX7	2
+Q9D6D9	2
+Q9EQK5	2
+Q9JJ66	2
+Q9QUR4	2
+Q9QYY0	2
+Q9R069	2
+Q9R0X4	2
+Q9Z0P5	2
+A2AFW6	3
+A2AKX3	3
+A2ATU0	3
+A6H605	3
+A6PWY4	3
+B2RRE4	3
+B2RRE7	3
+B2ZRS8	3
+B9EJX5	3
+D3YVL0	3
+D3YVU7	3
+E9PUB0	3
+E9QN31	3
+F8VQJ3	3
+G3UXN4	3
+G3X8Q0	3
+G3X9B1	3
+O08901	3
+O09130	3
+O54946	3
+O70445	3
+O88792	3
+P04184	3
+P05064	3
+P10852	3
+P23492	3
+P29351	3
+P51432	3
+P62911	3
+P70278	3
+P97329	3
+Q04692	3
+Q0VGV0	3
+Q3TLD5	3
+Q3TQZ0	3
+Q3U1G5	3
+Q3U2S8	3
+Q3UGK4	3
+Q3UH06	3
+Q3UH94	3
+Q3UHX9	3
+Q3UIL6	3
+Q3UJP8	3
+Q3UJY3	3
+Q3UZD6	3
+Q3V0N4	3
+Q3V1Z5	3
+Q5FW75	3
+Q5SFM8	3
+Q5SWD9	3
+Q60848	3
+Q61792	3
+Q69ZJ6	3
+Q6P5B0	3
+Q6PFE3	3
+Q6ZPR6	3
+Q75N73	3
+Q7TND5	3
+Q8BGA5	3
+Q8BGS0	3
+Q8BHX3	3
+Q8BJW7	3
+Q8BKG3	3
+Q8BKS9	3
+Q8BMA5	3
+Q8BP47	3
+Q8BP67	3
+Q8BPY9	3
+Q8BU22	3
+Q8BY71	3
+Q8BZA9	3
+Q8C605	3
+Q8CCJ8	3
+Q8CIH5	3
+Q8CJ53	3
+Q8K224	3
+Q8K298	3
+Q8K2C1	3
+Q8K3Y3	3
+Q8R3F9	3
+Q8R3N1	3
+Q8VCD7	3
+Q8VDF2	3
+Q8VEE4	3
+Q91WA1	3
+Q924A9	3
+Q925B0	3
+Q99KR3	3
+Q99KV5	3
+Q99L48	3
+Q99LI5	3
+Q99ME9	3
+Q9CR57	3
+Q9CWJ9	3
+Q9CXX1	3
+Q9CY49	3
+Q9CZJ1	3
+Q9CZS1	3
+Q9D0I8	3
+Q9D0R9	3
+Q9D297	3
+Q9DBC7	3
+Q9DBZ5	3
+Q9ESV0	3
+Q9JJ89	3
+Q9JLB9	3
+Q9QXA3	3
+Q9R1C0	3
+Q9WTI7	3
+Q9WU62	3
+Q9WVP1	3
+Q9Z179	3
+Q9Z2Q2	3
+A0A087WNZ7	4
+A2ARV4	4
+A2AW86	4
+D3YW26	4
+D3YWX2	4
+D3YZ57	4
+D3Z1F9	4
+D3Z5I9	4
+D6RCK1	4
+E9Q1M6	4
+E9Q557	4
+E9Q9B7	4
+F8VQ75	4
+F8WGX0	4
+G3UW89	4
+G3UXR9	4
+P07356	4
+P59999	4
+P60603	4
+Q06138	4
+Q14BE1	4
+Q3TDD1	4
+Q3TE06	4
+Q3TJG6	4
+Q3TYE1	4
+Q3TZ13	4
+Q3U3I6	4
+Q3UDH4	4
+Q3UMW9	4
+Q3V3I6	4
+Q52KE3	4
+Q571J5	4
+Q58E29	4
+Q5DTZ0	4
+Q5XKN4	4
+Q62517	4
+Q6NZQ4	4
+Q6PGL7	4
+Q6PIC6	4
+Q6VNB8	4
+Q6ZPY2	4
+Q6ZWX2	4
+Q80X90	4
+Q8BHC1	4
+Q8BRE9	4
+Q8K2Q9	4
+Q8R307	4
+Q8R3H7	4
+Q8VCH8	4
+Q91UZ1	4
+Q922H9	4
+Q9CPV7	4
+Q9CUU5	4
+Q9DCI9	4
+A0A068BGR9	5
+A0A087WQ61	5
+A0A0A0MQD2	5
+A0A0A6YWR9	5
+A1L3S7	5
+A2AJH3	5
+A2AR60	5
+A2AUY4	5
+B1AT10	5
+B1AXI9	5
+B1AXN9	5
+B2RUG6	5
+B2RY27	5
+B7ZCR6	5
+B7ZNN5	5
+B8X349	5
+D3YU12	5
+D3YUM1	5
+D3YVZ8	5
+D3YW87	5
+D3YWT0	5
+D3Z0K6	5
+D3Z0V2	5
+D3Z1R8	5
+E0CZF3	5
+E3SRG9	5
+E9QAN4	5
+E9QKE9	5
+E9QM06	5
+E9QMA2	5
+E9QMI6	5
+E9QQ10	5
+F8VPK5	5
+G3UWE1	5
+G3UWG1	5
+G3UXY0	5
+G3UYF9	5
+G3X940	5
+G3X9K3	5
+G5E884	5
+H3BKQ7	5
+K3W4L0	5
+O08738	5
+O55127	5
+O55137	5
+O55222	5
+O70480	5
+O88396	5
+P05532	5
+P06837	5
+P09041	5
+P10711	5
+P10833	5
+P12265	5
+P14873	5
+P15209	5
+P16045	5
+P16125	5
+P19536	5
+P20060	5
+P27661	5
+P28650	5
+P29758	5
+P30415	5
+P30681	5
+P32233	5
+P41241	5
+P41731	5
+P43274	5
+P50396	5
+P51174	5
+P51569	5
+P52479	5
+P54227	5
+P55012	5
+P56812	5
+P59708	5
+P60521	5
+P68181	5
+P70188	5
+P97302	5
+P97494	5
+Q0KL02	5
+Q0P6B2	5
+Q148V8	5
+Q1W5W7	5
+Q3TFD2	5
+Q3TGW0	5
+Q3TJZ7	5
+Q3TN84	5
+Q3TQX1	5
+Q3TSP9	5
+Q3TWT5	5
+Q3TX35	5
+Q3TXK6	5
+Q3TXQ4	5
+Q3TXV7	5
+Q3U0V1	5
+Q3U3W7	5
+Q3U7E0	5
+Q3U9P7	5
+Q3UK08	5
+Q3ULB1	5
+Q3UM57	5
+Q3UPH1	5
+Q3UQA7	5
+Q3UUG6	5
+Q3UZ20	5
+Q5SS83	5
+Q60575	5
+Q61879	5
+Q62241	5
+Q63810	5
+Q64444	5
+Q6GYP7	5
+Q6IRU2	5
+Q6P6F6	5
+Q6PB99	5
+Q6ZQ68	5
+Q6ZQK5	5
+Q7TMR0	5
+Q7TPD2	5
+Q7TQ95	5
+Q80UK0	5
+Q80YW9	5
+Q8BFZ9	5
+Q8BGT8	5
+Q8BI72	5
+Q8BL66	5
+Q8BLY2	5
+Q8BM29	5
+Q8BM72	5
+Q8BPK2	5
+Q8BTJ4	5
+Q8BUB4	5
+Q8BUV3	5
+Q8BVA5	5
+Q8BVQ5	5
+Q8BXA1	5
+Q8C0C2	5
+Q8C0E2	5
+Q8C7C4	5
+Q8CDK8	5
+Q8CEW9	5
+Q8CFV9	5
+Q8K1C0	5
+Q8K2I4	5
+Q8K2N3	5
+Q8R146	5
+Q8R1T2	5
+Q8R378	5
+Q8R3I2	5
+Q8R3R8	5
+Q8R5H6	5
+Q8VCX5	5
+Q91V01	5
+Q91V35	5
+Q91YM2	5
+Q91YS7	5
+Q921N8	5
+Q922S5	5
+Q99K51	5
+Q99M51	5
+Q99ML4	5
+Q9CQB5	5
+Q9CQI6	5
+Q9CQS8	5
+Q9CQW2	5
+Q9CRD0	5
+Q9CRY7	5
+Q9CX83	5
+Q9CYH2	5
+Q9CZE9	5
+Q9D0J4	5
+Q9D104	5
+Q9D365	5
+Q9D4V7	5
+Q9D600	5
+Q9D735	5
+Q9D8B3	5
+Q9DBS5	5
+Q9DC23	5
+Q9DCE6	5
+Q9ERD7	5
+Q9JHP7	5
+Q9QYB1	5
+Q9QZH3	5
+Q9QZM0	5
+Q9R0P9	5
+Q9WUU7	5
+Q9Z0H8	5
+Q9Z2D6	5
+Z4YKC4	5

Day_3/Solutions/Exercise_2_R_code_2020.R

+#---------------------------------------------------------------------------------------
+# Exercise 2
+#---------------------------------------------------------------------------------------
+
+# Given a list of hits and a background in folder /Exercise 2
+# background.txt and id_list.txt
+
+# perform enrichment analysis against 
+# 1. Gene Ontology,
+# 2. Kegg modules, and
+# 3. DisGeNet (diseases)
+
+# For each result produce a cnetplot and an upsetplot.
+# - you will need to provide the correct id's for the functions to execute - use converters
+# - vary the p-value q-value thresholds in case of an empty result
+# - make the disgenet output readable (gene names, not entrez id's)
+
+
+background <- read.csv("/Users/rogon/Work/01. Teaching/CBNA Courses/2020 Online Course Series/2020 CBNA-DeNBI Enrichment course - my materials/Part 2 - R-code session ClusterProfiler, ReactomePA, pathfindR/Exercise 2 (custom background)/Background.txt", sep="")
+id_list <- read.delim("/Users/rogon/Work/01. Teaching/CBNA Courses/2020 Online Course Series/2020 CBNA-DeNBI Enrichment course - my materials/Part 2 - R-code session ClusterProfiler, ReactomePA, pathfindR/Exercise 2 (custom background)/id_list.txt")
+
+
+
+keytypes(org.Hs.eg.db)
+entrez_map <- bitr(background$GeneID, fromType="SYMBOL", toType="ENTREZID", OrgDb="org.Hs.eg.db", drop= FALSE)
+
+
+# or biomart:
+
+# you will need to convert identifiers - for that purpose I suggest using the biomaRt package in R, alternatively you can use the website itselt
+# ensembl biomart http://www.ensembl.org/biomart/martview/
+library("biomaRt")
+ensembl = biomaRt::useMart("ensembl")
+ensembl = useDataset("hsapiens_gene_ensembl", mart=ensembl)
+datasets_biomart <- listDatasets(ensembl)
+attributes_biomart <- listAttributes(ensembl)
+
+id_list_biomart= getBM(attributes = c("hgnc_symbol","entrezgene_id", "ensembl_gene_id"),
+               filters = c(filters = "entrezgene_id"),
+               values = id_list$EntrezGene.ID,
+               mart = ensembl)
+
+
+background_biomart= getBM(attributes = c("hgnc_symbol","entrezgene_id", "ensembl_gene_id"),
+                          filters = c(filters = "hgnc_symbol"),
+                          values = background$GeneID,
+                          mart = ensembl)
+
+
+# part 1
+id_list_go <- enrichGO(gene = id_list_biomart$entrezgene_id, 'org.Hs.eg.db', pvalueCutoff = 0.05, pAdjustMethod = "BH", universe = names(background_biomart$entrezgene_id), minGSSize = 5, maxGSSize = 500, qvalueCutoff = 0.05, readable = TRUE)
+head(id_list_go)
+cnetplot(id_list_go)
+upsetplot(id_list_go)
+
+# part 2 
+id_list_mkegg <- enrichMKEGG(gene = id_list_biomart$entrezgene_id, pvalueCutoff = 0.1, pAdjustMethod = "BH", universe = names(background_biomart$entrezgene_id), minGSSize = 5, maxGSSize = 500, qvalueCutoff = 0.1)
+head(id_list_mkegg)
+cnetplot(id_list_mkegg)
+upsetplot(id_list_mkegg)
+
+# part 3
+id_list_dgn <- enrichDGN(gene = id_list_biomart$entrezgene_id, pvalueCutoff = 0.05, pAdjustMethod = "BH", universe = names(background_biomart$entrezgene_id), minGSSize = 5, maxGSSize = 500, qvalueCutoff = 0.05, readable = TRUE)
+head(id_list_dgn)
+cnetplot(id_list_dgn)
+upsetplot(id_list_dgn)
+
+# GO without background 
+id_list_go_noBckg <- enrichGO(gene = id_list_biomart$entrezgene_id, 'org.Hs.eg.db', pvalueCutoff = 0.05, pAdjustMethod = "BH", minGSSize = 5, maxGSSize = 500, qvalueCutoff = 0.05, readable = TRUE)
+head(id_list_go_noBckg)
+cnetplot(id_list_go_noBckg)
+upsetplot(id_list_go_noBckg)
+
+