gistfile1.txt

# mnake sure all rows have 99 fields
$ awk 'BEGIN{FS="\t"} {print NF}' /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt | uniq
99

# how many HET (1) and HOM_ALT (3) genotypes were there?
$ awk 'BEGIN{FS="\t"} {print $99}' /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt | sort | uniq -c

# get rid of headers except for the first one
(head -n 1 /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt; grep -v gt_types /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt)

# make sure there are no LOW entries (note grep -w for specifificty)
(head -n 1 /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt; grep -v gt_types /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt) | grep -w LOW

# what col number is the gene column?
head -1 /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt | tr "\t" "\n" | cat -n | grep gene
20	gene

# print, in descending order, the number of variants observed per gene
awk '{print $20}' /uufs/chpc.utah.edu/common/home/u1072926/gemini_queries/all.txt | sort | uniq -c | awk '{print $2"\t"$1}' | sort -k2,2nr | head -n 50
MUC16	25126
MUC6	20998
AHNAK2	8647
TTN	8244
MUC5B	6907
MUC19	6872
FLG	6681
NBPF10	6375
ANKRD36	5687
HRNR	5576
NBPF1	5472
FAM230A	4745
PABPC3	4733
FAM182B	4497
FRG1B	4409
PDE4DIP	4334
TAS2R31	4208
IGFN1	4176
FCGBP	3925
OBSCN	3869
MUC2	3636
AHNAK	3621
TAS2R43	3586
SERPINA1	3432
CTD-3088G3.8	3371
TAS2R19	3115
ANKRD36C	3096
MKI67	3073
ANKRD30B	2986
TAS2R46	2905
NBPF14	2796
GOLGA6L2	2717
NEB	2652
PRAMEF1	2621
TCHH	2564
FLG2	2548
KRT18	2455
ZNF257	2412
NBPF12	2374
PLIN4	2371
NBPF9	2349
FAM186A	2348
PRAMEF2	2345
PRAMEF4	2251
OR4A16	2247
GXYLT1	2228
CNN2	2200
FSIP2	2194
RP11-683L23.1	2173
LILRA6	2137