CDS-102: Lab 7 Workbook

Name:

March 9, 2017

# Run this code block to load the Tidyverse package
-s.libPaths(new = "~/Rlibs")
library(tidyverse)

Error in eval(expr, envir, enclos): could not find function "s.libPaths"
Traceback:

# Import the dataset
original_data <- read_csv("Brauer2008_Dataset1.csv")

Error in eval(expr, envir, enclos): could not find function "read_csv"
Traceback:

original_data

GID	YORF	NAME	GWEIGHT	G0.05	G0.1	G0.15	G0.2	G0.25	G0.3	⋯	L0.15	L0.2	L0.25	L0.3	U0.05	U0.1	U0.15	U0.2	U0.25	U0.3
GENE1331X	A_06_P5820	SFB2 || ER to Golgi transport || molecular function unknown || YNL049C || 1082129	1	-0.24	-0.13	-0.21	-0.15	-0.05	-0.05	⋯	0.13	0.20	0.17	0.11	-0.06	-0.26	-0.05	-0.28	-0.19	0.09
GENE4924X	A_06_P5866	|| biological process unknown || molecular function unknown || YNL095C || 1086222	1	0.28	0.13	-0.40	-0.48	-0.11	0.17	⋯	0.02	0.04	0.03	0.01	-1.02	-0.91	-0.59	-0.61	-0.17	0.18
GENE4690X	A_06_P1834	QRI7 || proteolysis and peptidolysis || metalloendopeptidase activity || YDL104C || 1085955	1	-0.02	-0.27	-0.27	-0.02	0.24	0.25	⋯	-0.07	-0.05	-0.13	-0.04	-0.91	-0.94	-0.42	-0.36	-0.49	-0.47
GENE1177X	A_06_P4928	CFT2 || mRNA polyadenylylation* || RNA binding || YLR115W || 1081958	1	-0.33	-0.41	-0.24	-0.03	-0.03	0.00	⋯	-0.05	0.02	0.00	0.08	-0.53	-0.51	-0.26	0.05	-0.14	-0.01
GENE511X	A_06_P5620	SSO2 || vesicle fusion* || t-SNARE activity || YMR183C || 1081214	1	0.05	0.02	0.40	0.34	-0.13	-0.14	⋯	0.00	-0.11	0.04	0.01	-0.45	-0.09	-0.13	0.02	-0.09	-0.03
GENE2133X	A_06_P5307	PSP2 || biological process unknown || molecular function unknown || YML017W || 1083036	1	-0.69	-0.03	0.23	0.20	0.00	-0.27	⋯	0.25	-0.21	0.12	-0.11	NA	-0.65	0.09	0.06	-0.07	-0.10
GENE1002X	A_06_P6258	RIB2 || riboflavin biosynthesis || pseudouridylate synthase activity* || YOL066C || 1081766	1	-0.55	-0.30	-0.12	-0.03	-0.16	-0.11	⋯	0.27	0.24	0.05	0.19	0.07	-0.31	-0.08	0.12	0.05	0.06
GENE5478X	A_06_P7082	VMA13 || vacuolar acidification || hydrogen-transporting ATPase activity, rotational mechanism || YPR036W || 1086860	1	-0.75	-0.12	-0.07	0.02	-0.32	-0.41	⋯	0.15	0.15	0.00	0.03	-0.40	-0.02	0.26	0.31	0.14	0.11
GENE2065X	A_06_P2554	EDC3 || deadenylylation-independent decapping || molecular function unknown || YEL015W || 1082963	1	-0.24	-0.22	0.14	0.06	0.00	-0.13	⋯	0.17	0.07	0.10	0.11	0.01	-0.16	0.07	0.20	0.02	0.10
GENE2440X	A_06_P6431	VPS5 || protein retention in Golgi* || protein transporter activity || YOR069W || 1083389	1	-0.16	-0.38	0.05	0.14	-0.04	-0.01	⋯	0.11	0.00	0.02	0.09	-0.26	-0.13	-0.10	0.07	-0.04	-0.12
GENE4180X	A_06_P6220	|| biological process unknown || molecular function unknown || YOL029C || 1085380	1	-0.22	-0.18	0.27	0.18	0.03	-0.04	⋯	-0.04	-0.13	-0.08	0.10	-0.02	0.04	0.16	0.02	-0.03	-0.22
GENE5247X	A_06_P1410	AMN1 || negative regulation of exit from mitosis* || protein binding || YBR158W || 1086594	1	0.18	0.61	1.55	1.34	0.23	-0.03	⋯	-0.35	-0.27	-0.07	-0.11	-1.15	0.41	0.28	0.00	0.17	-0.01
GENE2121X	A_06_P2983	SCW11 || cytokinesis, completion of separation || glucan 1,3-beta-glucosidase activity || YGL028C || 1083024	1	-0.67	-0.47	1.16	1.05	-0.18	-0.68	⋯	-0.11	0.01	-0.27	-0.51	-1.48	-0.43	-0.27	-0.32	-0.24	-0.15
GENE1985X	A_06_P3720	DSE2 || cell wall organization and biogenesis* || glucan 1,3-beta-glucosidase activity || YHR143W || 1082870	1	-0.59	-0.17	1.17	0.85	-0.12	-0.61	⋯	-0.39	-0.42	-0.48	-0.65	-1.24	0.41	0.18	0.09	0.13	-0.04
GENE4728X	A_06_P2774	COX15 || cytochrome c oxidase complex assembly* || oxidoreductase activity, acting on NADH or NADPH, heme protein as acceptor || YER141W || 1085995	1	-0.28	-0.81	-0.39	0.24	0.01	0.01	⋯	-0.18	-0.02	0.15	-0.18	-1.91	-0.31	0.09	-0.24	-0.03	0.19
GENE3153X	A_06_P4597	SPE1 || pantothenate biosynthesis* || ornithine decarboxylase activity || YKL184W || 1084207	1	-0.19	0.24	0.03	0.17	0.00	-0.01	⋯	0.04	-0.07	0.06	-0.20	-1.53	-0.43	-0.46	-0.73	-0.48	-0.25
GENE3704X	A_06_P5667	MTF1 || transcription from mitochondrial promoter || S-adenosylmethionine-dependent methyltransferase activity* || YMR228W || 1084832	1	-0.42	-0.43	-0.36	-0.12	0.05	0.24	⋯	-0.07	-0.14	-0.03	-0.04	-0.62	-0.53	-0.30	-0.17	-0.44	-0.35
GENE2141X	A_06_P3260	KSS1 || invasive growth (sensu Saccharomyces)* || MAP kinase activity || YGR040W || 1083046	1	-0.76	-0.32	-0.05	-0.27	-0.31	-0.01	⋯	0.15	0.06	0.20	-0.11	-0.80	-0.18	-0.05	-0.26	-0.58	-0.18
GENE2978X	A_06_P3607	|| biological process unknown || molecular function unknown || YHR036W || 1084002	1	-0.91	-0.43	-0.05	-0.09	-0.27	-0.45	⋯	-0.08	-0.12	-0.13	-0.05	-1.04	-0.59	-0.47	-0.29	-0.33	-0.20
GENE1203X	A_06_P5929	|| biological process unknown || molecular function unknown || YNL158W || 1081987	1	-0.47	-0.43	-0.15	0.08	-0.26	-0.25	⋯	0.02	-0.17	-0.30	-0.41	-0.67	-0.01	-0.20	-0.36	-0.30	-0.04
GENE3214X	A_06_P6219	YAP7 || positive regulation of transcription from RNA polymerase II promoter || RNA polymerase II transcription factor activity || YOL028C || 1084281	1	-0.51	-0.04	0.06	0.26	-0.19	-0.22	⋯	-0.16	-0.13	-0.13	-0.03	-1.09	-0.26	0.02	-0.09	-0.43	-0.21
GENE443X	A_06_P1322	|| proteolysis and peptidolysis || metalloendopeptidase activity || YBR074W || 1081132	1	-1.01	-0.55	-0.72	-0.54	-0.55	-0.19	⋯	-0.08	-0.25	0.12	-0.09	NA	-0.23	-0.32	-0.49	0.01	0.24
GENE1570X	A_06_P6449	YVC1 || cation homeostasis || calcium channel activity* || YOR087W || 1082401	1	-0.40	-0.14	-0.06	0.00	-0.22	-0.07	⋯	-0.10	-0.15	0.03	0.09	NA	-0.39	-0.30	-0.28	-0.01	0.14
GENE4434X	A_06_P2356	CDC40 || nuclear mRNA splicing, via spliceosome* || RNA splicing factor activity, transesterification mechanism* || YDR364C || 1085655	1	-0.19	-0.08	-0.16	-0.10	-0.12	-0.10	⋯	-0.38	-0.19	-0.01	0.01	-1.07	-0.01	0.05	-0.10	-0.04	0.12
GENE2486X	A_06_P6921	|| biological process unknown || molecular function unknown || YPL162C || 1083440	1	-0.10	-0.02	-0.37	-0.09	-0.14	0.10	⋯	-0.22	-0.04	-0.10	0.05	-1.19	0.15	-0.09	-0.17	0.05	0.12
GENE2099X	A_06_P1729	RMD1 || biological process unknown || molecular function unknown || YDL001W || 1083001	1	-0.22	-0.03	-0.26	-0.19	-0.10	0.15	⋯	-0.21	-0.16	-0.10	-0.03	-0.76	-0.03	-0.13	-0.20	-0.13	-0.03
GENE5137X	A_06_P2688	PCL6 || regulation of glycogen biosynthesis* || cyclin-dependent protein kinase regulator activity || YER059W || 1086466	1	-0.25	-0.35	0.04	0.15	0.02	0.09	⋯	0.12	0.02	0.04	0.13	-1.10	-0.19	-0.12	0.08	0.00	0.06
GENE2691X	A_06_P1007	AI4 || RNA splicing* || endonuclease activity || Q0065 || 1083679	1	-0.36	-0.39	0.42	-0.09	0.00	0.12	⋯	0.49	0.22	-0.09	-0.80	-1.59	-1.24	-0.65	-0.62	-0.61	-0.81
GENE2673X	A_06_P1933	GGC1 || mitochondrial genome maintenance* || guanine nucleotide transporter activity || YDL198C || 1083659	1	0.76	0.33	-0.21	-0.16	0.00	0.09	⋯	-0.15	-0.08	-0.72	-1.25	-2.31	-1.70	-1.37	-1.24	-0.73	-0.83
GENE3094X	A_06_P1548	SUL1 || sulfate transport || sulfate transporter activity || YBR294W || 1084134	1	-0.32	-0.54	-0.37	-0.64	-0.09	-0.10	⋯	-0.56	-0.77	-0.95	-1.32	-5.55	-4.59	-3.34	-1.98	-3.09	-1.79
⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋱	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮	⋮
GENE5335X	A_06_P5817	|| biological process unknown || molecular function unknown || YNL046W || 1086698	1	0.09	0.23	0.13	0.27	0.11	-0.08	⋯	0.02	0.25	0.10	-0.03	-0.13	0.56	0.39	0.38	0.40	0.36
GENE3931X	A_06_P4860	RPS0B || protein biosynthesis* || structural constituent of ribosome || YLR048W || 1085091	1	-0.12	-0.42	-0.12	0.09	0.01	0.08	⋯	0.24	0.32	0.16	0.12	0.32	0.41	0.03	-0.12	0.16	0.30
GENE2273X	A_06_P3220	COS12 || biological process unknown || molecular function unknown || YGL263W || 1083201	1	-1.30	0.09	0.29	-0.03	-0.14	-0.20	⋯	0.77	1.07	0.95	1.17	0.51	0.50	1.03	1.64	1.27	1.33
GENE1180X	A_06_P6178	|| biological process unknown || molecular function unknown || YNR065C || 1081961	1	-0.16	-0.02	0.15	0.17	-0.21	-0.12	⋯	0.13	-0.06	-0.21	-0.11	0.22	0.51	0.59	0.14	0.38	0.34
GENE4771X	A_06_P2485	IZH1 || lipid metabolism* || metal ion binding || YDR492W || 1086044	1	-0.10	-0.13	0.28	0.46	0.23	-0.25	⋯	-0.47	-0.62	-0.60	-0.51	0.39	0.35	0.31	-0.07	0.56	0.44
GENE321X	A_06_P7110	|| || || YPR064W || 1080987	1	0.13	0.17	0.53	1.21	0.38	-0.02	⋯	-0.28	-0.11	-0.31	-0.37	1.21	1.54	0.93	0.50	0.52	0.27
GENE236X	A_06_P6294	IZH4 || lipid metabolism* || metal ion binding || YOL101C || 1080893	1	0.64	0.44	1.31	1.35	0.97	0.26	⋯	-0.13	-0.73	-0.46	-0.42	3.36	2.87	2.25	2.00	2.32	1.15
GENE2516X	A_06_P2042	PST1 || cell wall organization and biogenesis || molecular function unknown || YDR055W || 1083475	1	0.62	0.25	1.12	1.05	0.13	-0.12	⋯	0.28	0.15	-0.05	-0.29	1.95	2.00	1.40	0.50	0.81	0.64
GENE1687X	A_06_P4130	PRM10 || conjugation with cellular fusion || molecular function unknown || YJL108C || 1082535	1	0.63	0.59	0.73	0.65	0.23	0.29	⋯	-0.24	-0.40	-0.42	-0.08	0.54	1.26	0.77	0.61	0.82	0.54
GENE5522X	A_06_P4129	|| biological process unknown || molecular function unknown || YJL107C || 1086909	1	0.65	0.62	0.71	0.71	0.04	0.10	⋯	-0.29	-0.56	-0.73	-0.21	NA	1.06	0.58	0.39	0.53	0.48
GENE2461X	A_06_P1902	SFA1 || formaldehyde catabolism || alcohol dehydrogenase activity* || YDL168W || 1083412	1	0.81	0.30	0.16	0.36	0.38	0.37	⋯	-0.07	-0.01	-0.09	0.01	0.12	0.53	0.41	0.02	0.40	0.32
GENE5154X	A_06_P3834	CAP2 || filamentous growth* || actin filament binding || YIL034C || 1086485	1	0.10	-0.33	0.05	0.25	0.09	-0.05	⋯	0.24	0.12	-0.01	-0.05	0.09	0.76	0.35	0.04	0.20	0.14
GENE2896X	A_06_P5553	|| biological process unknown || molecular function unknown || YMR122W-A || 1083907	1	0.01	-0.22	0.67	0.72	0.36	0.04	⋯	-0.19	0.10	0.02	0.05	-0.06	0.87	0.88	0.28	0.49	0.49
GENE4037X	A_06_P4180	CIS3 || cell wall organization and biogenesis || structural constituent of cell wall || YJL158C || 1085216	1	-0.01	-0.21	0.20	0.60	0.48	0.18	⋯	-0.02	-0.06	0.07	0.03	0.49	1.47	1.13	0.04	0.69	0.32
GENE674X	A_06_P7057	|| || || YPR012W || 1081403	1	-0.23	0.05	0.25	0.28	0.22	0.27	⋯	-0.14	0.02	0.13	0.04	0.32	0.14	-0.01	0.17	0.02	0.27
GENE3957X	A_06_P6469	RGS2 || G-protein signaling, coupled to cAMP nucleotide second messenger || GTPase activator activity || YOR107W || 1085121	1	0.00	0.01	-0.13	0.02	-0.07	-0.32	⋯	-0.09	-0.32	-0.30	-0.29	0.45	0.24	0.18	-0.24	-0.26	-0.08
GENE2250X	A_06_P7164	|| biological process unknown || molecular function unknown || YPR117W || 1083173	1	-0.22	-0.51	0.28	0.32	0.00	-0.38	⋯	-0.49	-0.57	-0.53	-0.48	0.79	1.04	0.32	-0.14	0.29	-0.16
GENE785X	A_06_P7198	|| || || YPR150W || 1081527	1	-0.10	-0.24	-0.06	-0.04	-0.37	-0.67	⋯	-0.21	-0.16	-0.17	-0.52	-0.13	0.67	0.39	-0.11	0.33	0.09
GENE4483X	A_06_P1283	CSG2 || calcium ion homeostasis* || enzyme regulator activity || YBR036C || 1085710	1	0.06	-0.22	-0.09	0.15	-0.12	-0.27	⋯	0.15	0.16	0.03	-0.15	0.11	0.26	-0.04	-0.24	-0.05	-0.01
GENE491X	A_06_P3540	SPO11 || meiotic DNA double-strand break formation || endodeoxyribonuclease activity, producing 3'-phosphomonoesters || YHL022C || 1081188	1	-0.83	0.21	0.04	-0.19	-0.41	-0.15	⋯	0.04	0.27	-0.17	-0.23	NA	0.07	0.33	0.19	0.01	-0.34
GENE4050X	A_06_P2650	CHO1 || phosphatidylserine biosynthesis || CDP-diacylglycerol-serine O-phosphatidyltransferase activity || YER026C || 1085231	1	-0.74	-0.63	-0.07	0.11	-0.18	-0.31	⋯	0.26	0.11	0.04	-0.16	-0.28	0.81	-0.10	-0.03	-0.13	-0.20
GENE17X	A_06_P6055	WSC2 || cell wall organization and biogenesis* || transmembrane receptor activity || YNL283C || 1080641	1	-0.62	-0.26	-0.19	-0.03	-0.09	-0.27	⋯	-0.33	-0.21	-0.16	-0.20	0.67	0.78	0.08	-0.34	-0.09	-0.21
GENE4426X	A_06_P6690	MYO2 || endocytosis* || microfilament motor activity || YOR326W || 1085645	1	-0.67	-0.38	-0.12	-0.05	-0.15	-0.24	⋯	-0.12	-0.24	-0.15	-0.24	0.11	0.69	0.36	-0.12	0.08	-0.04
GENE1274X	A_06_P6825	|| biological process unknown || molecular function unknown || YPL066W || 1082066	1	-0.14	0.06	0.78	0.81	0.30	0.14	⋯	0.28	0.13	0.30	0.06	-0.75	1.91	0.47	0.25	0.37	0.15
GENE410X	A_06_P4625	DOA1 || ubiquitin-dependent protein catabolism* || molecular function unknown || YKL213C || 1081094	1	0.12	-0.07	0.14	0.29	0.17	0.09	⋯	0.19	0.17	0.03	0.02	0.16	0.28	0.36	0.22	0.29	0.14
GENE2833X	A_06_P6094	KRE1 || cell wall organization and biogenesis || structural constituent of cell wall || YNL322C || 1083836	1	0.41	-0.28	0.30	0.50	-0.05	-0.08	⋯	0.38	0.23	0.21	0.15	0.32	0.62	0.54	0.01	0.56	0.28
GENE271X	A_06_P3243	MTL1 || cell wall organization and biogenesis || molecular function unknown || YGR023W || 1080930	1	0.50	-0.12	0.25	0.24	0.13	0.02	⋯	0.25	-0.02	-0.06	-0.10	NA	0.50	0.29	-0.14	0.47	0.27
GENE1691X	A_06_P4196	KRE9 || cell wall organization and biogenesis* || molecular function unknown || YJL174W || 1082539	1	0.15	0.09	0.21	0.46	0.19	-0.02	⋯	0.37	0.21	0.16	-0.01	-0.68	0.63	0.41	0.09	0.48	0.43
GENE1755X	A_06_P4680	UTH1 || mitochondrion organization and biogenesis* || molecular function unknown || YKR042W || 1082610	1	0.63	0.38	0.05	0.12	0.13	-0.01	⋯	-0.07	0.02	0.24	0.18	-0.89	0.19	0.03	0.04	0.13	0.19
GENE4255X	A_06_P6304	|| biological process unknown || molecular function unknown || YOL111C || 1085465	1	0.18	0.05	0.11	0.09	-0.02	0.03	⋯	-0.07	-0.08	-0.02	-0.06	0.03	0.14	0.00	-0.21	0.07	0.04

cleaning_data_step1 <- separate(original_data, NAME, c("name", "BP", "MF", "systematic_name",  "number"), sep = "\\|\\|")

cleaning_data_step2 <- mutate_each(cleaning_data_step1, funs(trimws), name:systematic_name)

cleaning_data_step3 <- select(cleaning_data_step2, -number, -GID, -YORF, -GWEIGHT)

cleaning_data_step4 <- gather(cleaning_data_step3, sample, expression, G0.05:U0.3)

cleaning_data_step5 <- separate(cleaning_data_step4, sample, c("nutrient", "rate"), sep =1, convert = TRUE)

glimpse(cleaning_data_step5)

Observations: 199,332
Variables: 7
$ name            <chr> "SFB2", "", "QRI7", "CFT2", "SSO2", "PSP2", "RIB2",...
$ BP              <chr> "ER to Golgi transport", "biological process unknow...
$ MF              <chr> "molecular function unknown", "molecular function u...
$ systematic_name <chr> "YNL049C", "YNL095C", "YDL104C", "YLR115W", "YMR183...
$ nutrient        <chr> "G", "G", "G", "G", "G", "G", "G", "G", "G", "G", "...
$ rate            <dbl> 0.05, 0.05, 0.05, 0.05, 0.05, 0.05, 0.05, 0.05, 0.0...
$ expression      <dbl> -0.24, 0.28, -0.02, -0.33, 0.05, -0.69, -0.55, -0.7...

data.filtered <- filter(cleaning_data_step5, name == "LEU1")
print(data.filtered)

# A tibble: 36 × 7
    name                   BP                                     MF
   <chr>                <chr>                                  <chr>
1   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
2   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
3   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
4   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
5   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
6   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
7   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
8   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
9   LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
10  LEU1 leucine biosynthesis 3-isopropylmalate dehydratase activity
# ... with 26 more rows, and 4 more variables: systematic_name <chr>,
#   nutrient <chr>, rate <dbl>, expression <dbl>

clean.plot <- ggplot(data = data.filtered) + geom_line(mapping = aes(x = rate, y = expression, color = nutrient))
ggsave("CleanPlot.png", plot = clean.plot, device = "png", scale = 1, width = 5, height = 4)