Test_2

#load tidyverse google libraries and dplyr
library(googledrive)
library(googlesheets4)
library(dplyr)
library(knitr)
library(kableExtra)

#log in to google account
drive_auth()

## Using an auto-discovered, cached token.
## To suppress this message, modify your code or options to clearly consent to the use of a cached token.
## See gargle's "Non-interactive auth" vignette for more details:
## https://gargle.r-lib.org/articles/non-interactive-auth.html
## The googledrive package is using a cached token for amhresearch123@gmail.com.

sheets_auth(token = drive_token())

#get Protein sheet
proteins <- read_sheet("https://docs.google.com/spreadsheets/d/1rk_tJAh_0SiXwOBlJlNYq25w0ZREu0I_QWWB_dwOAXo/edit#gid=0", sheet = "Protein_Test_Table")

num_candidate_proteins <- nrow(proteins)

num_target_proteins <- nrow(filter(proteins, In_Final_Shortlist == "Y"))

Target proteins

71 candidate proteins were selected from the literature review.
25 target proteins were selected for PRS analysis.

kable(proteins) %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

Protein	UniProtID	SOMAmerID	In_Sun_GWAS	In_Final_Shortlist	Previous_Studies
Alpha-1-antitrypsin	P01009	NA	N	N	3
Clusterin	P10909	CLU.4542.24.2	Y	Y	3
Insulin-like growth factor-binding protein 2	P18065	IGFBP2.2570.72.5	Y	Y	2
Transthyretin (Prealbumin)	P02766	NA	N	N	2
Complement C4 A/B	P0C0L4,P0C0L5	C4A.C4B.4481.34.2	Y	Y	2
Apolipoprotein A-1	P02647	NA	N	N	2
Pancreatic prohormone	P01298	PPY.4588.1.2	Y	Y	2
Granulocyte colony-stimulating factor	P09919	CSF3.8952.65.3	Y	Y	1
Complement C3	P01024	C3.2755.8.2	Y	Y	1
Complement component C6	P13671	C6.4127.75.1	Y	Y	1
Inter-alpha-trypsin inhibitor heavy chain H4	Q14624	NA	N	N	1
C-C motif chemokine 18	P55774	NA	N	N	1
Cystatin C	P01034	NA	N	N	1
A1AcidG	N/A	NA	N	N	1
Intercellular adhesion molecule 1	P05362	ICAM1.4342.10.3	Y	N	1
Pigment epithelium-derived factor	P36955	SERPINF1.7735.17.3	Y	N	1
C-C motif chemokine 5	P13501	CCL5.5480.49.3	Y	N	1
Apolipoprotein C-III	P02656	NA	N	N	1
enoyl-CoA hydratase 1	P30084	NA	N	N	1
NHL repeat-containing protein 2	Q8NBF2	NA	N	N	1
Homeobox protein Hox-B7	P09629	NA	N	N	1
Fibronectin	P02751	FN1.3435.53.2	Y	Y	2
Receptor tyrosine-protein kinase erbB-2	P04626	ERBB2.2616.23.18	Y	Y	1
Sodium- and chloride-dependent GABA transporter 2	Q9NSD5	NA	N	N	1
Alpha-2-HS-glycoprotein	P02765	AHSG.3581.53.3	Y	Y	1
Afamin	P43652	NA	N	N	1
Apolipoprotein A-4	P06727	NA	N	N	1
Fibrinogen gamma chain	P02671,P02675,P02679	FGA.FGB.FGG.4907.56.1	Y	Y	1
Ceruloplasmin	P00450	NA	N	N	1
Haptoglobin	P00738	HP.3054.3.2	Y	Y	1
Inter-alpha-trypsin inhibitor heavy chain H1	P19827	ITIH1.7955.195.3	Y	Y	1
Fibulin-1	P23142	FBLN1.6470.19.3	Y	Y	1
Plasma protease C1 inhibitor	P05155	SERPING1.4479.14.2	Y	Y	1
Thrombospondin-1	P07996	NA	N	N	1
Angiotensinogen	P01019	NA	N	N	1
Osteopontin	P10451	NA	N	N	1
Serum amyloid P component	P02743	APCS.2474.54.5	Y	Y	1
Cathepsin D	P07339	NA	N	N	1
Brain-derived neurotrophic factor	P23560	BDNF.2421.7.3	Y	Y	1
Amyloid beta A4 protein	P05067	APP.3171.57.2	Y	Y	1
Neurogenin-2	Q9H2A3	NA	N	N	1
Neurofilament light polypeptide	P07196	NA	N	N	1
Amyloid-beta A4 precursor protein-binding family B member 3	O95704	APBB3.13589.10.3	Y	Y	1
RE1-silencing transcription factor	Q13127	NA	N	N	1
G-protein-signaling modulator 2	P81274	NA	N	N	1
Secreted phosphoprotein 24	Q13103	NA	N	N	1
Dynein heavy chain 10, axonemal	Q8IVF4	NA	N	N	1
Forkhead-associated domain-containing protein 1	B1AJZ9	NA	N	N	1
Ribosomal protein S6 kinase alpha-3	P51812	NA	N	N	1
Prothrombin	P00734	F2.5316.54.3	Y	N	1
Adhesion G protein-coupled receptor F4	Q8IZF3	NA	N	N	1
Apolipoprotein E	P02649	APOE.2937.10.2	Y	Y	1
Complement factor H	P08603	CFH.4159.130.1	Y	Y	1
Vitronectin	P04004	VTN.13125.45.3	Y	Y	1
Interleukin-3	P08700	IL3.4717.55.2	Y	Y	1
Interleukin-10	P22301	IL10.2773.50.2	Y	Y	1
Alpha-2-macroglobulin	P01023	NA	N	N	1
Serum albumin	P02768	NA	N	N	1
Prostate-specific antigen	P07288	KLK3.8468.19.3	Y	Y	1
Fetuin B	Q9UGM5	NA	N	N	1
Placenta growth factor	P49763	PGF.3078.1.2	Y	N	1
Interleukin-17F	Q96PD4	IL17F.2775.54.2	Y	N	1
Fibronectin FN1.4	P02751	FN1.3435.53.2	Y	N	1
Secretory leukocyte protease inhibitor	P03973	NA	N	N	1
Fibronectin FN1.3	N/A	NA	N	N	1
Epithelial cell kinase	Q08345	NA	N	N	1
Prolactin	P01236	PRL.2585.2.5	Y	N	1
C-C motif chemokine 14	Q16627	CCL14.2900.53.3	Y	N	1
Calcium/calmodulin-dependent protein kinase type II subunit α	Q9UQM7	CAMK2A.3350.53.2	Y	N	1
Seprase	Q12884	FAP.5029.3.1	Y	N	1
Coagulation factor XI	P03951	NA	N	N	1