Cuffdiff mining by MySQL

Schema file for isoform_exp.diff from cuffdiff
isoformdiff.sql

DROP TABLE IF EXISTS `isoformdiff`;
SET @saved_cs_client     = @@character_set_client;
SET character_set_client = utf8;
CREATE TABLE `isoformdiff` (
  `diff_id` varchar(31) NOT NULL,
  `test_id` varchar(31) NOT NULL,
  `gene_id` varchar(31) NOT NULL,
  `gene` varchar(31) NOT NULL,
  `locus` varchar(31) NOT NULL,
  `sample_1` varchar(31) NOT NULL,
  `sample_2` varchar(31) NOT NULL,
  `status` varchar(10) NOT NULL,
  `value_1` float NOT NULL,
  `value_2` float NOT NULL,
  `log2_foldchange` float NOT NULL,
  `test_stat` varchar(10) NOT NULL,
  `p_value` float NOT NULL,
  `q_value` float NOT NULL,
  `significant` varchar(5) NOT NULL,
   KEY `test_id` (`test_id`),
   KEY `locus` (`locus`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1;
SET character_set_client = @saved_cs_client;

Generate db and populates

mysql -u suk mm9 < isoformdiff.sql
mawk 'BEGIN {FS="\t"};{print "hippo_vs_heart\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10"\t"$11"\t"$12"\t"$13"\t"$14}' gene_exp.diff |mysql -u suk mm9 --local-infile=1  -e 'LOAD DATA LOCAL INFILE "/dev/stdin" INTO TABLE isoformdiff FIELDS TERMINATED BY "\t";'

Some query

SELECT isoformdiff.diff_id, isoformdiff.test_id, isoformdiff.log2_foldchange, isoformdiff.q_value, GROUP_CONCAT(uniprotTogo.go),COALESCE(sp.description, kg.description, re.description)
FROM isoformdiff
LEFT JOIN kgXref as sp on isoformdiff.test_id = sp.spID
LEFT JOIN kgXref as kg on isoformdiff.test_id = kg.kgID
LEFT JOIN kgXref as re on isoformdiff.test_id = re.protAcc
INNER JOIN uniprotTogo on sp.spID = uniprotTogo.uniprot
WHERE 
isoformdiff.significant="yes" AND 
isoformdiff.q_value  1 OR isoformdiff.value_2 >1) 
GROUP BY isoformdiff.test_id;

Count by GO accessions

SELECT uniprotTogo.go, COUNT(uniprotTogo.go), t.name
FROM isoformdiff
LEFT JOIN kgXref as sp on isoformdiff.test_id = sp.spID
LEFT JOIN kgXref as kg on isoformdiff.test_id = kg.kgID
LEFT JOIN kgXref as re on isoformdiff.test_id = re.protAcc
INNER JOIN uniprotTogo on sp.spID = uniprotTogo.uniprot
INNER JOIN mygo.term as t on t.acc = uniprotTogo.go
WHERE 
isoformdiff.significant="yes" AND 
isoformdiff.q_value  1 OR isoformdiff.value_2 >1) 
GROUP BY uniprotTogo.go
ORDER BY COUNT(uniprotTogo.go);

Yes,I know my sql queries are suck ๐Ÿ˜› Anyway, they are just for my reminders…LOL

Advertisements

Web vs App

์–ด๋””์„ ๊ฐ€์—์„œ ์Šค๋งˆํŠธํฐ ๋“ฑ์˜ ๋ชจ๋ฐ”์ผ์˜ ์ฆ๊ฐ€์†๋„๊ฐ€ PC์˜ ์ฆ๊ฐ€์†๋„๋ณด๋‹ค ํ›จ์”ฌ ๋น ๋ฅธ ๊ฒƒ์„ ๋ณผ๋•Œ ์•ž์œผ๋กœ ์•ฑ์ด๋ผ๋Š” ๋น„์ง€๋‹ˆ์Šค๋Š” ์›น์œผ๋กœ ๋Œ€๋ณ€๋˜๋Š” ์ธํ„ฐ๋„ท์— ๋น„๊ฒฌ๋˜๋Š” ํฐ ์‹œ์žฅ์ด ๋  ์ˆ˜ ์žˆ๋‹ค..๋ญ ์ด๋Ÿฐ ์š”์ง€์˜ ๊ธ€์„ ๋ณด์•˜๋‹ค.

์‹ค์ œ๋กœ ์•ฑ ๋น„์ฆˆ๋‹ˆ์Šค๊ฐ€ ํ˜„์žฌ์˜ ์›น ๊ธฐ๋ฐ˜์˜ ์ธํ„ฐ๋„ท๋งŒํผ ํฐ ๋น„์ฆˆ๋‹ˆ์Šค๊ฐ€ ๋ ์ง€ ์•ˆ๋ ์ง€๋Š” ๋ชจ๋ฅด๊ฒ ์œผ๋‚˜, ๋‚ด ์ƒ๊ฐ์—๋Š” ์›น์ด ๊ทธ๋ ‡๊ฒŒ ์„ฑ๊ณต์ ์ด๊ฒŒ ๋œ ์š”์†Œ๊ฐ€ ํ˜„์žฌ์˜ ๋ชจ๋ฐ”์ผ ์•ฑ์—์„œ๋Š” ๊ฒฐ์—ฌ๋˜์–ด ์žˆ๋‹ค๊ณ  ์ƒ๊ฐํ•œ๋‹ค.

๋ญ๋ƒ๊ณ ?

ํ•˜์ดํผ๋งํฌ (Hyperlink).

์ฆ‰ ์›น์ด ๊ทธ๋ ‡๊ฒŒ ์„ฑ๊ณต์ ์ผ ์ˆ˜ ์žˆ์—ˆ๋˜ ์š”์ธ ์ค‘์˜ ํ•˜๋‚˜๋ผ๋ฉด ์›น์—์„œ ์›น์œผ๋กœ ์ด๋™ํ•˜๋Š” ํ•˜์ดํผ๋งํฌ๊ฐ€ ๊ทธ ์š”์ธ์ด๋ผ๊ณ  ํ•ด๋„ ๊ณผ์–ธ์ด ์•„๋‹ˆ๋‹ค. ์‚ฌ์‹ค ์ด๊ฒƒ์€ ์›น ์ด์ „์˜ ์ธํ„ฐ๋„ท (ํ…”๋„ท, ftp, gopher..do you remember gopher? -.-) ๋ฅผ ์จ๋ณธ ์‚ฌ๋žŒ์ด๋ผ๋ฉด ๋ˆ„๊ตฌ๋ผ๋„ ์‹ค๊ฐํ•˜๋Š” ๊ฒƒ์ด๋‹ค.

์ฆ‰ ํ˜„์žฌ์˜ ์•ฑ์—์„œ๋Š” ๋‹ค๋ฅธ ๋งค๊ฐœ์ˆ˜๋‹จ (์•ฑ ์Šคํ† ์–ด ๋“ฑ) ์„ ๊ฒฝ์œ ํ•˜์ง€ ์•Š๊ณ  ๋‹ค๋ฅธ ์•ฑ์„ ๋‹ค์šด๋กœ๋“œํ•ด์„œ ์–ต์„ธ์Šคํ•˜๋Š” ๊ฒƒ์€ ๊ทนํžˆ ์ œํ•œ๋˜์–ด ์žˆ๋‹ค. ์ฆ‰, ์›น์—์„œ ์›น์œผ๋กœ ์ด์–ด์ง€๋Š” ๊ฑฐ๋ฏธ์ค„๊ฐ™์€ ๋„คํŠธ์›Œํฌ์— ์˜ํ•ด WWW๊ฐ€ ํญ๋ฐœ์ ์ธ ๋ฐœ์ „์„ ์ด๋ฃฌ ๊ฒƒ๊ณผ ๊ฐ™์€ ์ž๊ฐ€ ์ฆ์‹๋ ฅ์ด ์•ฑ์—์„œ๋Š” ๊ฒฐ์—ฌ๋˜์–ด ์žˆ๋‹ค๋Š” ๊ฒƒ. ํŠนํžˆ ์•ฑ์ด ์œ ํ†ต๋˜๋Š” ์ˆ˜๋‹จ์ด ์ผ์›ํ™”๋˜์–ด์žˆ๋Š” ์• ํ”Œ ์ƒํƒœ๊ณ„์—์„œ ‘์•ฑ’ ์„ ๋ฐœ๊ฒฌํ•˜๋Š” ๊ธฐํšŒ๋Š” ์ ์–ด๋„ ‘์›น’ ์ด๋‚˜ ‘์•ฑ์Šคํ† ์–ด’ ๋“ฑ์„ ํ†ตํ•˜์ง€ ์•Š๊ณ ์„œ๋Š” ํž˜๋“ค๋‹ค. ๊ณผ์—ฐ ์›น ๋ธŒ๋ผ์šฐ์ง•์„ ํ•  ๋•Œ ํ•˜์ดํผ๋งํฌ๋ผ๋Š” ์กด์žฌ ์—†์ด ํฌํ„ธ ์‚ฌ์ดํŠธ๋ฅผ ํ†ตํ•ด์„œ ํŠน์ •ํ•œ ์›น ์‚ฌ์ดํŠธ๋ฅผ ์–ต์„ธ์Šคํ•  ์ˆ˜ ์žˆ๋Š” ๋ชจ๋ธ๋กœ WWW๊ฐ€ ๊ตฌ์„ฑ๋˜์—ˆ๋‹ค๋ฉด ์ง€๊ธˆ๊ณผ ๊ฐ™์€ ๋ฐœ์ „์ด ๊ฐ€๋Šฅํ–ˆ์„๊นŒ?

์—ฌํŠผ ์•ฑ์ด ์›น์„ ๋Œ€์ฒดํ•˜๋Š” ๋ญ”๊ฐ€๊ฐ€ ๋˜๋ ค๋ฉด ์•ฑ ์ž์ฒด์—์„œ ๋‹ค๋ฅธ ์•ฑ์„ ๋ฐœ๊ฒฌํ•˜๊ณ  ๋งํฌํ•  ์ˆ˜ ์žˆ๋Š” ์–ด๋–ค ๋ฉ”์ปค๋‹ˆ์ฆ˜์ด ์žˆ์–ด์•ผ ํ•  ๊ฒƒ์œผ๋กœ ์ƒ๊ฐ๋œ๋‹ค. ์ง€๊ธˆ๊ณผ ๊ฐ™์ด ์•ฑ์Šคํ† ์–ด ๊ธฐ๋ฐ˜์œผ๋กœ ์›น์„ ๊ฒ€์ƒ‰ํ•˜๊ณ  ์ฐพ๋Š” ์‹œ์Šคํ…œ์€..๋งˆ์น˜ ํฌํ„ธ์„ ํ†ตํ•ด์„œ๋งŒ ์›น์„ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๊ณ , ์›น ์ƒํ˜ธ๊ฐ„์˜ ์—ฐ๊ฒฐ์ด ๊ฒฐ์—ฌ๋˜์–ด ์žˆ๋Š” ์ƒํ™ฉ์„ ์—ฐ์ƒ์‹œํ‚ค๊ธฐ ๋•Œ๋ฌธ์ด๋‹ค.

 

์ง€๋†ˆ๊ณ„์˜ ์„ฑ๊ณจ/์ง„๊ณจ/6๋‘ํ’ˆ

์กฐ (์กฐ๋ฐฅ ๋จน๋Š”๋‹ค ํ• ๋•Œ ๊ทธ๋•Œ ์กฐ)์ง€๋†ˆ 2๊ฑด์ด Nature Biotechnology์— ๋“ฑ์žฅ.

๊ฑฐ์˜ ๋งˆ์ง€๋ง‰ ์ƒ๊ฑฐ ์ง€๋†ˆ์ด ๋˜์ง€ ์•Š์„๊นŒ๋„ ์‹ถ๋„ค

๋™์ผํ•œ ๊ฒƒ์˜ BGI NGS ์ง€๋†ˆ

Assembly Stat ๋ฅผ ๋น„๊ตํ•ด๋ณด๋ฉด ์•„์ง๊นŒ์ง€ De Novo Assembly์—์„œ ์ƒ๊ฑฐ์™€ ๊ธฐํƒ€์˜ ์ฐจ์ด๋Š” ๋„˜์‚ฌ๋ฒฝ ์ˆ˜์ค€์ธ๋ฐ, ์ƒ๊ฑฐ์˜ ๊ฒฝ์šฐ N50 Contig/Scaffold๊ฐ€ 126.3KB/47.3MB, ๊ฐœ์ˆ˜๊ฐ€ 4/982๊ฐœ์ธ๋ฐ NGS๋Š” 25.4Kb/1.0Mb, 136/4667..๋ญ ์‰ฝ๊ฒŒ ๋งํ•˜์ž๋ฉด ์ƒ๊ฑฐ๋กœ ํ•œ ๊ฒƒ์— ๋น„ํ•ด์„œ NGS๋กœ ํ•œ ์ง€๋†ˆ์ด 5-10๋ฐฐ๋Š” ๋” ์ชผ๊ฐ€๋ฆฌ์ชผ๊ฐ€๋ฆฌ๊ฐ€ ๋‚˜์žˆ๋Š” ์ƒํ™ฉ ใ…‹ ๋ฌผ๋ก  ์ƒ๊ฑฐ์ชฝ์ด ์•„๋งˆ ๋น„์šฉ์ ์œผ๋กœ ์ˆ˜์‹ญ๋ฐฐ๋Š” ๋“ค์—ˆ๊ณ  ๊ณผ์—ฐ ์ด๋Ÿฌํ•œ ์ถ”๊ฐ€ ๋น„์šฉ์œผ๋กœ ์–ป์„ ์ˆ˜ ์žˆ๋Š” ๋ฐ์ดํ„ฐ๊ฐ€ ๊ณผ์—ฐ ๊ฐ’์„ ํ•˜๋Š๋ƒ๋Š” ์ข€ ์˜๋ฌธ์˜ ์—ฌ์ง€๊ฐ€ ๋‚จ์ง€๋งŒ..

์—ฌํŠผ ์ƒ๊ฑฐ ๋จธ์‹ ์€ ์ด์ œ ๋‹ค๋“ค ์‹œํ€€์‹ฑ ์„ผํ„ฐ์—์„œ๋Š” ๋นผ๋ฒ„๋ ธ์œผ๋‹ˆ ์ด์ œ ์‹ ๊ทœ๋กœ ์ง„ํ–‰๋  ํ”„๋กœ์ ํŠธ๋กœ ์ƒ๊ฑฐ์— ๊ธฐ๋ฐ˜ํ•œ ์ง€๋†ˆ์ด ๋‚˜์˜ฌ ์ผ์€ ์—†์„ ๋“ฏ. (๊ทผ๋ฐ ๋ถ„์„์˜ ๋น„์šฉ์—์„œ๋Š” ๊ฒฐ์ฝ” NGS ๋“œ๋…ธ๋ณด ๋ถ„์„์ด ์‹ธ์ง€ ์•Š์„๋“ฏ ใ…‹)

์ฆ‰ ํ˜„์žฌ์˜ ์ƒํ™ฉ์„ ์ƒ๊ฐํ•ด ๋ณด๋ฉด ์•„์ง๊นŒ์ง€ ์‹œํ€€์‹ฑ์ด ์•ˆ๋œ ์‹๋ฌผ, ๋™๋ฌผ๋“ค์€ ๊ธฐ์กด์— ์‹œํ€€์‹ฑ๋œ ๋„ค์ž„๋“œ ๋™์‹๋ฌผ, ๋ชจ๋ธ์ƒ๋ฌผ์— ๋น„ํ•ด์„œ ํ›จ์”ฌ ๊ตฌ๋ฆฐ ํ€„๋ฆฌํ‹ฐ๋กœ ๋‚˜์˜ฌ ๊ฒƒ์ด๋ผ๋Š” ๊ฒƒ. NNGS ๊ธฐ๊ธฐ๊ฐ€ ์ƒ๊ฑฐ๋ณด๋‹ค ๋” ๊ธธ๊ณ  ํ€„๋ฆฌํ‹ฐ ์ข‹์€ ๋ฆฌ๋“œ๋ฅผ ๋ฝ‘์•„๋‚ด๊ธฐ ์ „์—๋Š”. ๊ฐœ์ธ ์ง€๋†ˆ์„ ์ƒ๊ฑฐ์‹œํ€€์‹ฑ์œผ๋กœ ํ•œ ์œ ์ผํ•œ ์ธ๊ฐ„์ธ ๋ฒคํ„ฐ๊ฐ€ ์ƒ๊ฑฐ์ž๋ถ€์‹ฌ ๋‹๋“ฏ์ด (ํ•ญ์ƒ ์ด์•ผ๊ธฐํ•˜๋Š”๊ฒŒ ์•„ ๋‚˜ ๋นผ๊ณ  ๋‹ค๋ฅธ ๊ฐœ์ธ์ง€๋†ˆ์€ ๋‹ค ์ €์งˆ NGS ๋“œ๋ž˜ํ”„ํŠธ์•ผ ๋“œ๋ฆฝ ใ…‹ใ…‹ใ…‹ใ…‹) ๋™์‹๋ฌผ ์ง€๋†ˆ์—๋„ ์„ฑ๊ณจ, ์ง„๊ณจ, 6๋‘ํ’ˆ์ด ์žˆ๋Š”์…ˆ์ธ๋“ฏ.

์„ฑ๊ณจ์€ ์ƒ๊ฑฐ๋กœ ํ•˜๊ณ  ํ”ผ๋‹ˆ์‹ฑ๊นŒ์ง€ ๊ผผ๊ผผํ•˜๊ฒŒ ๋‹ค๋œ ๋„˜๋“ค. ์ฆ‰ ์‚ฌ๋žŒ, ์ดˆํŒŒ๋ฆฌ, ๋Œ€์žฅ๊ท , ๋งˆ์šฐ์Šค, ์•„๋ผ๋น„๋‹ต์‹œ์Šค ๋“ฑ.
์ง„๊ณจ์€ ์ƒ๊ฑฐ๋กœ ๊ทธ๋ƒฅ WGS๋งŒ ํ•œ ๋„˜๋“ค, ๊ฐœ, ์†Œ, ๋ง ๋“ฑ๋“ฑ.
6๋‘ํ’ˆ์€ NGS ๋กœ ๋•Œ์šด ๋„˜๋“ค…๋ญ ํŒฌ๋”๋ผ๋“ ๊ฐ€…
์•„์ง๊นŒ์ง€ ์ง€๋†ˆ๋„ ์—†๋Š” ๋„˜๋“ค์€ ํ–ฅ…ํ–ฅ์†Œ๋ถ€๊ณก? (์•„ ํ˜ธ๋ž‘์ด, ์‚ฌ์ž, ๋ฐฑ์ˆ˜์˜ ์ œ์™• ์ข‹์•„ํ•˜๋„ค ๋„ˆ๋„จ ์ด ๋ฐ”๋‹ฅ์—์„œ๋Š” ์ฒœ๋ฏผ์ด์—ฌ ใ…‹ใ…‹ใ…‹)

์ง€๊ธˆ๊นŒ์ง€์˜ NGS ๊ธฐ๊ธฐ๊ฒฝ์Ÿ์€ ์“ฐ๋ฃจํ’‹๋งŒ์„ ์ถ”๊ตฌํ•ด ์™”์œผ๋‚˜, ์ด์ œ๋Š” ์ ˆ์‹คํžˆ ํ€„๋ฆฌํ‹ฐ (Read Length, Quality) ์—์„œ์˜ ๊ฐœ์„ ์ด ์š”๊ตฌ๋˜๋Š” ์ƒํ™ฉ์ด๋ผ๊ณ  ์ƒ๊ฐํ•จ. ๊ทธ๋ ‡์ง€ ์•Š๋‹ค๋ฉด ์ƒ๊ฑฐ ์‹œ์ ˆ์— ๋งŒ๋“ค์–ด์ง„ ๋ชจ๋ธ ์ƒ๋ฌผ์˜ ์ง€๋†ˆ ํ€„๋ฆฌํ‹ฐ์™€ NGS ์‹œ์ ˆ์— ํ›จ์”ฌ ์งˆ๋‚ฎ์€ ๋ฐ์ดํ„ฐ๋กœ ๋งŒ๋“ค์–ด์ง„ ‘๊ธฐํƒ€ ์žก์ƒ๋ฌผ’ ์˜ ์–ด์…ˆ๋ธ”๋ฆฌ ํ€„๋ฆฌํ‹ฐ๊ฐ€ ์ฐจ์ด๋‚˜๋Š” ํ˜„์ƒ์ด ๊ณ„์†๋  ๋“ฏํ•˜๋‹ค๋Š”. ๋‚˜๋…ธํฌ์–ด ๋Š๋‹˜์ด ์šฐ๋ฆฌ๋ฅผ ๊ตฌํ•ด์ค„๊นŒ? ๊ธ€์Ž„ ใ…‹

Import UCSC Annotation Data into Local MySQL Databse

1. Download and install it From hereย (Just download dmg if you are lazy ๐Ÿ™‚ )

2. make database called hg19

3. download wanted annotation file from here

download all

wget 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/*'

download kgXref (or whatever db you want)

wget 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/kgXref*'

4. Create table based on the downloaded sql file

mysql -u myid -p mypasswd < kgXref.sql

5. Insert gzipped txt file into table (You do not need to unzip txt file. Use gzcat or zcat)

gzcat kgXref.txt.gz | mysql -u myid -p mypasswd hg19 --local-infile=1  -e 'LOAD DATA LOCAL INFILE "/dev/stdin" INTO TABLE kgXref;'

6. check your db

mysql -u myid -p mypasswd hg19 -e 'describe kgXref;'
+-------------+--------------+------+-----+---------+-------+
| Field       | Type         | Null | Key | Default | Extra |
+-------------+--------------+------+-----+---------+-------+
| kgID        | varchar(255) | NO   | MUL | NULL    |       |
| mRNA        | varchar(255) | NO   | MUL | NULL    |       |
| spID        | varchar(255) | NO   | MUL | NULL    |       |
| spDisplayID | varchar(255) | NO   | MUL | NULL    |       |
| geneSymbol  | varchar(255) | NO   | MUL | NULL    |       |
| refseq      | varchar(255) | NO   | MUL | NULL    |       |
| protAcc     | varchar(255) | NO   | MUL | NULL    |       |
| description | longblob     | NO   |     | NULL    |       |
| rfamAcc     | varchar(255) | NO   | MUL | NULL    |       |
| tRnaName    | varchar(255) | NO   | MUL | NULL    |       |
+-------------+--------------+------+-----+---------+-------+

mysql -u myid -p mypasswd hg19 -e 'select kgID, refseq, description from kgXref;'
                                                                                                                                                           |
| uc022cer.1 |              | Rfam model RF00001 hit found at contig region AL450472.14/87738-87621                                                                                                                                                                                                                                                                                                         |
| uc022cey.1 |              | Rfam model RF00026 hit found at contig region AL683813.10/545-651                                                                                                                                                                                                                                                                                                             |
| uc022cez.1 |              | Rfam model RF00026 hit found at contig region AL591398.2/79459-79356                                                                                                                                                                                                                                                                                                          |
| uc022cfd.1 |              | Rfam model RF01061 hit found at contig region AL033403.1/72536-72619                                                                                                                                                                                                                                                                                                          |
| uc022cff.1 |              | Rfam model RF00066 hit found at contig region AL121875.10/53331-53391                                                                                                                                                                                                                                                                                                         |
| uc022cfk.1 |              | Rfam model RF00100 hit found at contig region AL022720.1/24706-25036                                                                                                                                                                                                                                                                                                          |
| uc022cgh.1 |              | Rfam model RF00001 hit found at contig region L29074.1/109999-109884                                                                                                                                                                                                                                                                                                          |
| uc022cha.1 |              | Rfam model RF00026 hit found at contig region AF282854.4/53205-53101                                                                                                                                                                                                                                                                                                          |
| uc022chb.1 |              | Rfam model RF00670 hit found at contig region AC108171.3/12729-12651                                                                                                                                                                                                                                                                                                          |
| uc022chc.1 |              | Rfam model RF00670 hit found at contig region AC108171.3/12954-12871                                                                                                                                                                                                                                                                                                          |
| uc022che.1 |              | Rfam model RF00670 hit found at contig region AC108171.3/13432-13352                                                                                                                                                                                                                                                                                                          |
| uc022cpe.1 |              | Rfam model RF00026 hit found at contig region AC013734.4/10137-10240                                                                                                                                                                                                                                                                                                          

7. If you want to import bunch of databases starting with ‘knownGene..’

# download all of schema and txt.gz file started with 'knownGene'
wget 'ftp://hgdownload.cse.ucsc.edu/goldenPath/hg19/database/knownGene*'
# using for loop, create databse of all of knownGene*.sql file
for f in knownGene*.sql; do mysql -u id -p yourpasswd hg19 < $f;echo $f; done
# same trick. using for loop, all of file were inserted into database. 
for f in knownGene*.txt.gz; do t=${f%.txt.gz};gzcat $f | mysql -u id -p yourpasswd hg19 --local-infile=1  -e "LOAD DATA LOCAL INFILE '/dev/stdin' INTO TABLE $t;"; done
# t=${f%.txt.gz} means strip .txt.gz extension (It is your table name) 
# Note that double quotation used for the command line option of mysql to pass variable $t

8. Same with GO databases

mysql -u suk -e "create database mygo;"
for f in *.sql; do mysql -u suk mygo < $f;echo $f; done
for f in *.txt; do t=${f%.txt};echo $f;cat $f | mysql -u suk mygo --local-infile=1  -e "LOAD DATA LOCAL INFILE '/dev/stdin' INTO TABLE $t;"; done


Good introduction for Database noob :)(Some examples for the remote access of UCSC MySQL db)

Cofactor genomics

๋งํฌ

๋ฉ”์ด์ € ์ง€๋†ˆ์„ผํ„ฐ์ธย Washington University at St. Louis ์—์„œ ์ผํ•˜๋˜ ์‚ฌ๋žŒ๋“ค์ด ๋งŒ๋“  NGS ํ† ํ„ธ ์„œ๋น„์Šค ์—…์ฒด. ์—ญ์‹œ ์—ฐ๊ตฌ์ž๋ฅผ ์œ„ํ•œ ์„œ๋น„์Šค ํ”„๋กœ๋ฐ”์ด๋”๋Š” ํ•ด๋‹น ์—ฐ๊ตฌ๋ฅผ ํ•ด๋ณธ ์‚ฌ๋žŒ์ด ํ•ด์•ผ ํ•œ๋‹ค๋Š” ๊ฒƒ์„ ์ ˆ๊ฐํ•œ๋‹ค. ํ–„๋ฒ„๊ฑฐ ์ƒ์ „ ์•ˆ ๋จน์–ด ๋ณธ ๋„˜๋“ค์ด ๋งŒ๋“œ๋Š” ํ–„๋ฒ„๊ฑฐ๊ฐ€ ๋ง›์žˆ๊ฒ ๋‚˜? ๊ฒฐ๊ตญ ์ž๊ธฐ ๊ฐœ๋ฐฅ ์ž๊ธฐ๊ฐ€ ๋จน๊ธฐ๋ฅผ ์‹ค์ฒœํ•˜๋Š” ๊ฒƒ์ด ์ค‘์š”.

http://www.cofactorgenomics.com/faq

์—์„œย How Much Do I Need to Sequence? ๋ถ€๋ถ„๋งŒ ์ฝ์–ด๋ด๋„ ๋ญ”๊ฐ€ ์‹œ์‹œ๊ป์งˆํ•œ ์„œ๋น„์Šค ํ”„๋กœ๋ฐ”์ด๋” (๊ตณ์ด ๊ตญ๋‚ด๋ผ๊ณ ๋Š” ํ•˜์ง€ ์•Š๊ฒ ๋‹ค๋งŒ. ํ•ด์™ธ์—๋„ ์‹œ์‹œ๊ป์งˆํ•œ ๋„˜๋“ค์€ ๋งŽ์œผ๋‹ˆ๊นŒ)์™€๋Š” ์ข€ ๋‹ฌ๋ผ ๋ณด์ด์ง€ ์•Š๋Š”๊ฐ€? ์ ์–ด๋„ ์˜์—…์„ ํ•˜๋ ค๋ฉด ์ž๊ธฐ๊ฐ€ ํŒŒ๋Š” ๋ฌผ๊ฑด์ด ๋ญ”์ง€ ์ •๋„๋Š” ์•„๋Š” ๊ฒƒ์€ ๊ธฐ๋ณธ์ด๋‹ค.

์•„๋งˆ ์ด๊ฒƒ์€ ์—ฌ๊ธฐ์„œ ๊ฐœ๋ฐœํ•œ RNA-Seq ๋ฐ์ดํ„ฐ๋ฅผ ๋ณผ์ˆ˜์žˆ๋Š” ์›น ๊ธฐ๋ฐ˜์˜ ๋ทฐ์–ด์ธ๋“ฏ. ย ์‚ฌ์‹ค ์›น ์ธํ„ฐํŽ˜์ด์Šค์—์„œ ๋ณต์žกํ•œ ๋ถ„์„์„ ์ˆ˜ํ–‰ํ•œ๋‹ค๋Š” ๊ฒƒ์€ ํ˜„์‹ค์ ์œผ๋กœ ์–ด๋ ค์šด ์ƒํ™ฉ์—์„œ ์ธ์œ„์ ์œผ๋กœ ๋ณต์žกํ•œ ์ธํ„ฐํŽ˜์ด์Šค ์‹น ๋นผ๊ณ  ๋ฐ์ดํ„ฐ ๋‹ค์šด๋กœ๋“œ๋ฐ›๊ณ , ํŠน์ •์กฐ๊ฑด ์ฃผ์–ด์„œ ํ…Œ์ด๋ธ” ๋ฝ‘๋Š” ๊ฒƒ ์ •๋„๋ฅผ ๊ฐ„๋‹จํ•˜๊ฒŒ ํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•˜๋Š” ๊ฒƒ์€ ๊ฝค ํ˜„๋ช…ํ•œ ์„ ํƒ์ธ๋“ฏ ์‹ถ๋‹ค. ๊ทธ๋ฆฌ๊ณ  ๊ดœํžˆ ์ž์ฒด์ ์œผ๋กœ ์–ด์„คํ”ˆ ์ง€๋†ˆ ๋ธŒ๋ผ์šฐ์ € ๊ตฌํ˜„ํ•˜์ง€ ์•Š๊ณ  ๊ทธ๋ƒฅ ์—…๊ณ„ํ‘œ์ค€ UCSC ๋ธŒ๋ผ์šฐ์ €๋กœ ๋งํฌ์ œ๊ณตํ•ด ์ฃผ๋Š” ๊ฒƒ ์—ญ์‹œ ์Šค๋งˆํŠธํ•œ ์„ ํƒ์ธ ๋“ฏ ํ•˜๊ณ . (๋“ฃ๊ณ ์žˆ๋‚˜? Sodium Dodecyl Sulfate ์‚ฌ? ใ…‹)

๊ทธ๋ฆฌ๊ณ  ์—ฌ๊ธฐ์„œ ํ‘œ๋ฐฉํ•˜๋Š” Design & Analysis, ์ฆ‰ ๋‹จ์ˆœํžˆ DNA ๋˜์ ธ์ฃผ๋ฉด ์‹œํ€€์„œ ๋Œ๋ ค์„œ ๋กœ์šฐ๋ฐ์ดํ„ฐ ๋˜์ ธ์ฃผ๋Š” ๊ฒƒ์ด ์•„๋‹ˆ๋ผ ์‹คํ—˜ ๋””์ž์ธ๋ถ€ํ„ฐ ์ ๊ทน์ ์œผ๋กœ ๊ฐœ์ž…ํ•˜์—ฌ ์ตœ์ ์˜ ํ”„๋กœ์ ํŠธ๋ฅผ ์„ฑ๊ณต์‹œํ‚ค๋Š” ๊ฒƒ์€ ์•ž์œผ๋กœ ์ € ๋ฐ”๋‹ฅ์— ์žˆ๋Š” ๋ชจ๋“  ์—…์ฒด๊ฐ€ ๋”ฐ๋ผ์•ผ ํ•  ๊ธธ์ด๋ผ๊ณ  ๋ณธ๋‹ค. ์–ผ๋งˆ๋‚˜ ๋งŽ์€ ์ง€๋…ธ๋ฏน์Šค/NGS ํ”„๋กœ์ ํŠธ๊ฐ€ ์–ด์„คํ”ˆ ๊ณ„ํš์œผ๋กœ ์ธํ•ด์„œ ‘์–ด ๋ถ„์„ํ•ด ๋ดค๋Š”๋ฐ ์šฐ๋ฆฌ๊ฐ€ ์‹คํ—˜์„ ์ž˜๋ชปํ–ˆ๋„น? ์• ์ดˆ๋ถ€ํ„ฐ ์ด๊ฒƒ๋งŒ ์‹คํ—˜ํ•ด์„œ ๊ฒฐ๊ณผ๋ฅผ ๋ณธ๋‹ค๋Š” ๊ฒƒ์€ ๋ง์ด ์•ˆ ๋˜๊ณ  ์• ์ดˆ์— ์ด์กฐ๊ฑด, ์กฐ๊ฑด, ์š”์กฐ๊ฑด์œผ๋กœ ์ถ”๊ฐ€๋กœ ์‹คํ—˜ํ•ด์•ผ ๋˜์—ˆ์—ˆ๋Š”๋ฐ’ ๋กœ ํ‘œ๋ฅ˜ํ•˜๊ณ  ์‚ฐ์œผ๋กœ ๊ฐ€๋Š”์ง€๋ฅผ ๋ณธ ์‚ฌ๋žŒ์ด๋ผ๋ฉด ์‹ค๊ฐํ•  ์ˆ˜ ์žˆ์„ ๊ฒƒ.

๋ฌผ๋ก  NGS๊ฐ€ ์ฒ˜์Œ ๋‚˜์™€์„œ ํ•ด๋‹น ๋ถ„์•ผ ์‹คํ—˜์„ ์ตœ์ดˆ๋กœ ํ•˜๋Š” ๊ฒฝ์šฐ๋ผ๋ฉด (Chip-Seq์„ ์ฒ˜์Œํ•œ๋‹ค, RNA-Seq์„ ์ฒ˜์Œํ•œ๋‹ค) ๊ทธ๋Ÿฐ ์‹œํ–‰์ฐฉ์˜ค๋ฅผ ๊ฒช๋Š” ๊ฒƒ๋„ ์ดํ•ดํ•  ์ˆ˜ ์žˆ๊ฒ ์ง€๋งŒ, ์ด๋ฏธ ์ƒ์—…ํ™”๋œ ์ˆ˜์ค€์œผ๋กœ ์ผ๋ฐ˜ํ™”๋œ ์ƒํ™ฉ์—์„œ๋„ ์ด๋Ÿฐ ใ…ˆใ„น์„ ๋ฐ˜๋ณตํ•˜๋ฉด ๋ณ‘์ง„ ์†Œ๋ฆฌ ๋“ฃ๋Š”๋‹ค. ๋งŒ์•ฝ ๊ทธ๋ ‡์ง€ ์•Š๋‹ค๋ฉด ํ•ด๋‹น ์„œ๋น„์Šค๋ฅผ ์ƒ์—…ํ™”ํ•œ๋‹ค๋Š” ๊ฒƒ ์ž์ฒด๊ฐ€ ๋ง์ด ์•ˆ ๋˜๊ฒ ์ง€?

์ฆ‰ ๋ˆ ํ•œ๋‘ํ‘ผ์ด ๋“ค์–ด๊ฐ€๋Š” ๊ฒƒ๋„ ์•„๋‹Œ ์ด๋Ÿฐ ํ”„๋กœ์ ํŠธ๋Š” ์‹œ์ž‘ํ•˜๋Š” ๋‹จ๊ณ„์—์„œ ์ฃผ๋„๋ฉด๋ฐ€ํ•˜๊ฒŒ ๊ธฐํš๋˜์–ด์•ผ ํ•˜๋ฉฐ, ๋งŒ์•ฝ ์ด๋Ÿฌํ•œ ํ”„๋กœ์ ํŠธ์— ๋Œ€ํ•œ ๊ฒฝํ—˜์ด ์—†๋Š” ํด๋ผ์ด์–ธํŠธ์™€ ์ผ์„ ์ง„ํ–‰ํ•œ๋‹ค๋ฉด ์ด๋Ÿฌํ•œ ๊ฒƒ์€ ์„œ๋น„์Šค ํ”„๋กœ๋ฐ”์ด๋”์—์„œ ์ฃผ๋„๋˜์–ด ์ง„ํ–‰๋˜์–ด์•ผ ํ•จ.

(๋‹จ, ์ด๋•Œ ํ”„๋กœ์ ํŠธ ๊ธฐํš์˜ ์ค‘์ ์€ ์–ด๋””๊นŒ์ง€๋‚˜ ‘๊ณ ๊ฐ์˜ ์‹œ์„ ’ ์—์„œ ์ด๋ฃจ์–ด์ ธ์•ผ ํ•จ. ๊ดœํžˆ ๋ฌผ๋Ÿ‰ ์ข€ ๋Š˜๋ ค์„œ ์ˆ˜์ฃผ๋‹จ๊ฐ€ ๋†’์ด๋ ค๋Š” ์–„ํŒํ•œ ์†์…ˆ์œผ๋กœ ํ”„๋กœ์ ํŠธ๋ฅผ ๊ธฐํšํ•˜๋‹ค๊ฐ€๋Š” ๋‚˜์ค‘์— ์—…๊ณ„์—์„œ ์–ด๋–ค ํ‰ํŒ์„ ๋“ฃ๊ฒŒ ๋˜๋Š”์ง€๋Š” ์•„๋งˆ ๊ฒช์–ด๋ณด๋ฉด ์•Œ ๊ฒƒ์ด๋‹ค)

๋ฌผ๋ก  ์ง€๊ธˆ ์ด ์นœ๊ตฌ๋“ค์ด ํ•˜๋Š” ๋ชจ๋ธ์˜ ๊ฒฝ์šฐ๋„ ์•„์ง ๋” ๋ณด์™„๋˜์–ด์•ผ ํ•  ๋ถ€๋ถ„์ด ์žˆ์„ ๊ฒƒ์œผ๋กœ ์ƒ๊ฐ๋˜๋Š”๋ฐ, ์ฆ‰ ํ† ํ„ธ ์†”๋ฃจ์…˜์„ ํ‘œ๋ฐฉํ•œ๋‹ค๋ฉด ๋ถ„์„์˜ ๋‹จ๊ณ„์—์„œ๋„ ๊ตณ์ด ๋ฐ์ดํ„ฐ๋ฅผ ๋‹ค์šด๋กœ๋“œ๋ฐ›์•„์„œ ๊ณ ๊ฐ์ด ์ด๊ฒƒ์ €๊ฒƒ ๋ถ„์„ํ•˜๋Š” ๊ฒƒ๋ณด๋‹ค๋Š” ์ž์‚ฌ์˜ ํด๋ผ์šฐ๋“œ ๋“ฑ์„ ๊ตฌ์ถ•ํ•ด์„œ ‘์•„ ๊ท€์ฐฎ๊ฒŒ ์™œ ๋‹ค์šด๋กœ๋“œ๋ฐ›์œผ์‚ผ. ๊ทธ๋ƒฅ ๋” ๋†€๋‹ค ๊ฐ€์„ธ์—ผ. ๊ณ ๊ฐฑ๋‹˜ํ•˜๊ฐ€ ํ•„์š”ํ•˜์‹  ๊ฒƒ์€ ์ด๋ฏธ ์จ๋ฒ„์— ๋‹ค ๊น”๋ ค์žˆ์Šต๋‹ˆ๋‹ค. ๋‹ค๋งŒ ์›” ์‚ฌ์šฉ๋ฃŒ๋งŒ ์ฉœ ๋” ๋‚ด์„ธ์—ผ. ใ…‹’ ์‹์œผ๋กœ ํ•˜๋‚˜์˜ ์„œ๋น„์Šค๋ฅผ ๋กฑํ…Œ์ผํ™”ํ•˜๋ฉด ๊ธˆ์ƒ์ฒจํ™”๊ฒ ์ง€. ใ…‹ ์•„๋‹ˆ๋ฉด ์ง์ ‘ ์ธํ•˜์šฐ์Šค์—์„œ ๋ถ„์„ํ•˜๊ธฐ๋ฅผ ์›ํ•˜๋Š” ๊ฒฝ์šฐ ๋ฐ์ดํ„ฐ์™€ ์ œ๋ฐ˜ ๋ชจ๋“  ์†Œํ”„ํŠธ์›จ์–ด๊ฐ€ ์ธ์Šคํ†จ๋œ ์„œ๋ฒ„/์›Œํฌ์Šคํ…Œ์ด์…˜์„ ๋‚ฉํ’ˆํ•˜๋˜๊ฐ€..(ํŠนํžˆ ์‹ค์ œ๋กœ ๋ˆˆ์— ๋ณด์ด๋Š” ๋ฌผ๊ฑด์ด ์žˆ์–ด์•ผ ๋ˆ๋‚ด๋ ค๊ณ  ํ•˜๋Š” ์–ด๋”˜๊ฐ€์—์„œ๋Š” ์ด๊ฒŒ ๋” ์œ ํšจํ•œ ๋ชจ๋ธ์ผ ์ˆ˜๋„ ์žˆ๋‹ค. ใ…‹ใ…‹ ์„œ๋ฒ„ ์ผ€์ด์Šค ๋ฉ‹์žˆ๋Š”๊ฑฐ ์ฐพ๋Š”๊ฒƒ์ด ์ œ์ผ ๋จผ์ € ํ• ์ผ์ด๊ฒ ๊ตฌ๋งŒ…)

 

 

6-7๋…„์ „์— ์ƒ๊ฐํ•œ ๊ฒƒ์„ ๋ˆ„๊ตฐ๊ฐ€๊ฐ€ ์ด์ œ์„œ์•ผ ์‹ค์ œ๋กœ ๊ตฌํ˜„ํ•˜๊ณ  ์žˆ๋Š” ๊ฒƒ์„ ๋ณด๋Š” ๊ฒƒ์€ ๊ทธ๋ฆฌ ์œ ์พŒํ•œ ๊ธฐ๋ถ„๋งŒ์€ ์•„๋‹ˆ๋‹ค. ใ…†ใ…‚..

๊ณผํ•™ ๋…ผ๋ฌธ ์ž˜ ์“ฐ๋Š” ๋ฐฉ๋ฒ• ์Œฉ๊ธฐ๋ณธ

Nature Structural & Molecular Biology์— ์‹ค๋ฆฐ ๊ธ€ย ์— ๋Œ€ํ•œ ์š”์  ์š”์•ฝ

์šฐ๋ฆฌ ์ž์—ฐ๋Š๋‹˜๋ฐ ์ƒˆ๋ผ์ €๋„์— ๋‚˜์˜ฌ๋งŒํผ ์ข‹์€ ๋…ผ๋ฌธ์„ ์“ฐ๋ ค๋ฉด ์–ด์บ ํ•˜๋‚˜? ๋น„๋ฐ€์„ ๊ฐˆ์ผœ์ฃผ๋งˆ.

Tell a Story

์ข‹์€ ๋…ผ๋ฌธ์ด ๋ ๋ ค๋ฉด ์ผ๋‹จ ์ข‹์€ ์ด์•ผ๊ธฐ๊ฐ€ ๋˜์–ด์•ผ ํ•จ. ๋‹จ์ˆœํžˆ ์—ฐ๋Œ€๊ธฐ์‹์œผ๋กœ ์ฒ˜์Œ์— ๋ญ ํ–ˆ๊ณ  ๋‹ค์Œ์— ๋ญ ํ–ˆ๊ณ  ์ด๋Ÿฐ์‹์œผ๋กœ ์“ฐ์ง€๋งˆ๋ผ. ๋„ˆ๋‹˜ ์ผ ๋งŽ์ด ํ–ˆ๋‹ค๊ณ  ์ž๋ž‘ํ•˜์ž๋Š”๊ฑฐ๋ƒ  -.-

๊ทธ ๋Œ€์‹ ์—, ์ผ๋‹จ ์žฌ๋ฃŒ๋กœ ์“ธ ๊บผ๋ฆฌ๋Š” ๋‹ค ์ค€๋น„๋˜์—ˆ๋‹ค๊ณ  ์น˜๊ณ .

  • ์ด์ „์— ์ด ๋ถ„์•ผ์—๋Š” ์–ด๋–ค ์ผ๋“ค์ด ์ง„ํ–‰๋˜์—ˆ๋Š”๋ฐ ์•„์ง ๋ชจ๋ฅด๋Š” ๊ฒƒ์ด ์ด๋Ÿฌ์ €๋Ÿฌํ•œ ๊ฒŒ ์žˆ๋Š”๋ฐ,
  • ๊ทธ ์ค‘์—์„œ ์ง€๊ธˆ ๋‚ด๊ฐ€ ์ด ๋…ผ๋ฌธ์—์„œ ๋‹ตํ•˜๋ ค๊ณ  ํ•˜๋Š” ์˜๋ฌธ์€ ๋ฌด์—‡์ด๊ณ 
  • ๊ทธ๊ฒŒ ๋ถ„์•ผ์—์„œ ์™œ ์ค‘์š”ํ•˜๋ƒ?
  • ๋‚ด๊ฐ€ ํ•œ ์ผ์ด ์ด๋Ÿฌ์ €๋Ÿฌํ•œ๋ฐ ย ์ฒ˜์Œ์— ๊ฐ€์ง€๊ณ  ์žˆ๋˜ ์งˆ๋ฌธ์— ๋Œ€ํ•œ ์ดํ•ด์— ์–ด๋–ป๊ฒŒ ๋ณดํƒฌ์ด ๋๋‚˜?
  • ์ƒˆ๋กญ๊ฒŒ ๋ฐœ๊ฒฌํ•œ ๊ฒƒ์€ ๋ญ๋ƒ?
  • ๋‹˜ํ•˜๊ฐ€ ํ•˜์‹  ์ผ์ด ๊ทธ๋ž˜์„œ ์™œ ์ค‘์š”ํ•œ ๊ฒƒ์ž„?
  • ์ด๊ฒŒ ์ด ๋ถ„์•ผ์˜ ์—ฐ๊ตฌ์— ์–ด๋–ป๊ฒŒ ์ค‘์š”ํ•˜๋ฉฐ ๋‹ค๋ฅธ ๋ถ„์•ผ๋กœ์˜ ํŒŒ๊ธ‰ํšจ๊ณผ๋Š” ์–ด๋–ป๊ฒŒ ๋  ๊ฒƒ์ด๋ฉฐ,
  • ์ด๋Ÿฐ ๊ฒฐ๊ณผ๋“ค์„ ๋ฐ”ํƒ•์œผ๋กœ ๋ฌด์Šจ ์—ฐ๊ตฌ๊ฐ€ ๋” ์ง„ํ–‰๋˜์—ˆ์œผ๋ฉด ์ข‹๊ฒ ๋‹ค๊ณ  ์ƒ๊ฐํ•˜๋ƒ?

…..๋กœ ์Šคํ† ๋ฆฌ๊ฐ€ ์ผ๊ด€์„ฑ์žˆ๊ฒŒ ๋˜๊ฒŒ ์†Œ์„ค์„ ์”๋‹ˆ๋‹ค. ๊ณ ๊ฐฑ๋‹˜. ใ…‹

Be clear

์ดํ•ดํ•˜๊ธฐ ์‰ฝ๊ฒŒ ์“ฐ์‚ผ. ์•„๋ฌด๋„ ๋„ˆ ๋…ผ๋ฌธ ๋„˜ ์‰ฝ๊ฒŒ ์ผ์–ด ์™€ ์กฐ๋‚ธ ์‹œ์‹œํ•œ ์ผ์ด๋„ค ์•ˆํ•œ๋‹ค. ๋Œ€์‹ ์— ๋ฆฌ๋ทฐ์–ด๋“ค์ด ์–ด ์ด ์›๊ณ  ๋Œ€์ฒด ๋ฌด์Šจ ๋ง์„ ํ•˜์ž๋Š”๊ฑฐ์ž„? ๋ชป ์•Œ์•„ ์ณ๋จน๊ฒ ์Šˆ ๋ถˆํ‰ํ•˜๋Š” ๊ฑฐ ์—ฌ๋Ÿฌ๋ฒˆ ๋“ค์—ˆ๋‹ค.

๊ทธ๋ƒฅ ๋ช…ํ™•ํ•˜๊ณ  ๋‹จ์ˆœํ•œ ์–ธ์–ด๋ฅผ ์“ฐ๋ผ๊ตฌ. ํŠนํžˆ ๋‚ด์šฉ์ด ๋ณต์žกํ• ์ˆ˜๋ก ์ด๋ ‡๊ฒŒ ๋ช…ํ™•ํ•˜๊ฒŒ ์“ฐ๋Š”๊ฒŒ ์ค‘์š”ํ•˜๋‹ค.

๋ถ„์•ผ์—์„œ๋งŒ ์“ฐ๋Š” ์ „๋ฌธ์šฉ์–ด ๋‚จ๋ฐœํ•˜์ง€ ๋ง๊ณ , ์šฉ์–ด์— ๋Œ€ํ•œ ์„ค๋ช… ์ž˜ํ•ด๋ณด์…”. ๊ธ€๊ตฌ ์›๊ณ  ๋˜๋ฉด ๋‹น์‹ ๋„ค ๋ถ„์•ผ ๋ฐ–์˜ ๊ณผํ•™์žํ•œํ…Œ ํ•œ๋ฒˆ ์ฝ์–ด๋ด ๋‹ฌ๋ผ๊ณ  ํ•ด์„œ ๊ทธ์‚ฌ๋žŒ์—๊ฒŒ ์•Œ์•„๋จน๊ธฐ ์‰ฝ๊ฒŒ ์“ฐ์˜€๋Š”์ง€ ๋งํ•ด๋‹ฌ๋ผ๊ณ  ํ•ด. ๊ทธ๋ ‡๊ฒŒ ํ•จ์œผ๋กœ์จ ๋ถ„์•ผ์—์„œ๋งŒ ์“ฐ๋Š” ์ „๋ฌธ์šฉ์–ด ๋‚จ๋ฐœ ์ค„์ผ ์ˆ˜ ์žˆ๊ณ , ์‹คํ—˜๋””์ž์ธ ๊ฒฐ๊ณผํ•ด์„ ์ด๋Ÿฐ๊ฑฐ๋ฅผ ๋ณด๋‹ค ๋” ๋ช…ํ™•ํ•˜๊ฒŒ ์“ธ ์ˆ˜ ์žˆ๊ณ , ๋‹˜ํ•˜๊ฐ€ ย ํ•˜๋Š” ์—ฐ๊ตฌ๊ฐ€ ๋‹ค๋ฅธ ๋ถ„์•ผ์—๋„ ํฅ๋ฏธ๊ฐ€ ์žˆ๋Š”๊ฑด์ง€ ์•Œ ์ˆ˜ ์žˆ์Œ.

Provide an Informative title and abstract

์ œ๋ชฉํ•˜๊ณ  ์ดˆ๋ก๋งŒ ์Šฅ ๋ณด๋ฉด ๋ฌด์Šจ ๋‚ด์šฉ์ผ์ง€ ์•Œ์•„๋“ค์„ ์ˆ˜ ์žˆ๋„๋ก ์ œ๋ชฉ/์ดˆ๋ก์— ์‹ ๊ฒฝ์“ฐ๋ผ๊ตฌ.

๋‹˜ํ•˜ ํŽ๋ฉ”๋“œ ๊ฒ€์ƒ‰ํ•ด์„œ ๋…ผ๋ฌธ์ฐพ์„๋•Œ ๋…ผ๋ฌธ ๋‚ด์šฉ ๋‹ค ๋ด„? ์•„๋‹ˆ์ง€? ๊ฑ ์ œ๋ชฉ, ์•„๋‹ˆ๋ฉด ์ดˆ๋ก๋งŒ ์Šฅ ๋ณด๊ณ  ์žฌ๋ฐŒ๊ฒ ๋‹ค ์‹ถ์œผ๋ฉด ๋…ผ๋ฌธ ๋ณด์ž๋‚˜. ๋”ฐ๋ผ์„œ ์ง€๋ฃจํ•ด ๋ณด์ด๋Š” ํƒ€์ดํ‹€ ๋…ธ๋…ธ.

๊ทธ๋ฆฌ๊ณ  ์ดˆ๋ก ๋งค์šฐ ๋ช…ํ™•ํ•˜๊ฒŒ ์“ฐ๊ณ  ์ „์ฒด์ ์ธ ํฐ ๊ทธ๋ฆผ์„ ๊ทธ๋ ค์ค„ ์ˆ˜ ์žˆ๋„๋ก ์“ฐ๋ผ๊ตฌ. ๊ธ€๊ตฌ ์ดˆ๋ก์—์„œ ์“ธ๋ฐ์—†๋Š” ์„ธ๋ถ€์‚ฌํ•ญ๊นŒ์ง€ ์“ฐ์ง€ ์ข€ ๋งˆ๋ผ. ๊ทธ๋ฆฌ๊ณ  “Studies of X and Y…” ๋‚ด์ง€๋Š” “Characterization of A and B” ์ด๋”ฐ์œ„ ์ œ๋ชฉ ์ข€ ์“ฐ์ง€๋งˆ๋ผ. ๊ทธ ์ œ๋ชฉ๋งŒ ๋ณด๊ณ ์„œ ์šฐ๋ฆฌ๊ฐ€ ์•Œ ์ˆ˜ ์žˆ๋Š” ๊ฒŒ ๋ญ๋ƒ ? ์•„๋ฌด๊ฒƒ๋„ ์—†์ž๋‚˜. ์ œ๋ชฉ์—์„œ ํŽ˜์ดํผ์˜ ์ค‘์š” ํฌ์ธํŠธ๊ฐ€ ๋‚˜์™€์•ผ๋จ. ๊ทธ๋ฆฌ๊ณ  ์ดˆ๋ก์—์„œ๋Š” ์šฐ๋ฆฌ๊ฐ€ ๋‹ตํ•˜๊ณ ์ž ํ•˜๋Š” ์˜๋ฌธ์ด ๋ฌด์—‡์ด๊ณ , ์™œ ์ค‘์š”ํ•˜๊ณ , ์–ด๋–ป๊ฒŒ ์ด ๋ฌธ์ œ๋ฅผ ํ’€์—ˆ๊ณ , ์ด๋Ÿฐ ๊ฒŒ ์—ฐ๊ตฌ๋ถ„์•ผ์—์„œ ์–ด๋–ค ์œ„์น˜๋ฅผ ๊ฐ€์ง€๋Š”์ง€๊ฐ€ ์ข ๋‚˜์™€์•ผ ํ•จ. ๊ดœํžˆ ์ดˆ๋ก์— ์“ฐ์ž˜๋ฐ ์—†์ด ์‹คํ—˜ ๋””ํ…Œ์ผํ•œ ๋‚ด์šฉ ์“ฐ๋ ค๊ณ  ํ•˜์ž๋งˆ์…”.

Make the introduction short and concise

์ € ์ธํŠธ๋กœ๋•์…˜ ์ฃผ๊ตฌ์žฅ์ฐฝ ์“ฐ์‹œ๋Š” ๋ถ„..๋‹˜ํ•˜ํ•œํ…Œ ์ง€๊ธˆ Annual Review of….๋ฆฌ๋ทฐ์ฒญํƒ ๋“ค์–ด์˜จ๊ฑฐ ์•„๋‹ˆ๊ฑฐ๋˜์š”? ๋‹จ์ง€ ์—ฌ๊ธฐ์„œ๋Š” ๋‹˜ํ•˜ ์—ฐ๊ตฌ๋ฅผ ์ดํ•ดํ•˜๋Š”๋ฐ ๊ผญ ํ•„์š”ํ•œ ๋‚ด์šฉ๋งŒ ์“ฐ์…”์•ผ ํ•จ. ๊ทธ๋ƒฅ ์ตœ์†Œํ•œ์˜ ๋ฐฐ๊ฒฝ๋งŒ ์„ค๋ช…ํ•˜๊ณ , ๋‹˜ํ•˜๊ฐ€ ์ง€๊ธˆ ํ•˜๋ ค๋Š” ์—ฐ๊ตฌ๊ฐ€ ๋ถ„์•ผ์—์„œ ํ˜„์žฌ ์•Œ๋ ค์ง€์ง€ ์•Š์€ ์–ด๋–ค ๋ฌธ์ œ๋ฅผ ํ•ด๊ฒฐํ•˜๋Š”๊ฑด์ง€์— ๋Œ€ํ•ด์„œ ์จ์•ผ ํ•จ. ๊ทผ๋ฐ ์ค‘์š”ํ•œ ๋ ˆํผ๋Ÿฐ์Šค ๋นผ๋จน์ง€ ๋งˆ๋ผ. (์šฐ๋ฆฌ๋„ ํŽ๋ฉ”๋“œ ๋ณธ๋‹จ๋‹ค) ๊ทธ๋ฆฌ๊ณ  ์ธํŠธ๋กœ๋•์…˜ ๋์€ ‘๊ทธ๋ž˜์„œ ์ด ์—ฐ๊ตฌ์—์„œ๋Š” ๋ฌด์—‡์„ ๋ณด์—ฌ์คฌ๋‹ค’ ๋กœ ๋๋‚ด๋ผ.

Clearly distinguish Results from Discussion

Results์—์„œ๋Š” ๋‹˜ํ•˜๊ฐ€ ์–ป์€ ๊ฒฐ๊ณผ์— ๋Œ€ํ•ด์„œ๋งŒ ์“ฐ๊ณ , ์ด๋Ÿฐ ๊ฒฐ๊ณผ๋ฅผ ๋„–๊ฒŒ ํ•ด์„ํ•˜๋Š” ๊ฒƒ์€ ๋””์Šค์ปค์…˜์—์„œ ํ•ด๋ผ. ๊ทธ๋ฆฌ๊ณ  ๋””์Šค์ปค์…˜์—์„œ ๊ฒฐ๊ณผ ๋˜ ์ฃผ๊ตฌ์žฅ์ฐฝ ๋ฐ˜๋ณตํ•˜์ง€ ๋งˆ๋ผ. ์ด๋ฏธ ์ฝ์—ˆ๊ฑฐ๋˜? ๋””์Šค์ปค์…˜์€ ๊ฒฐ๊ณผ์— ๋Œ€ํ•œ ํ•ด์„. ๊ทธ๋ฆฌ๊ณ  ์ด๋Ÿฌํ•œ ๊ฒฐ๊ณผ๊ฐ€ ๊ธฐ์กด์˜ ์—ฐ๊ตฌ๊ฒฐ๊ณผ์™€ ์–ด๋–ป๊ฒŒ ๋ถ€ํ•ฉ๋˜๋Š”์ง€ (ํ˜น์€ ์•ˆ๋˜๋Š”์ง€), ๊ทธ๋ฆฌ๊ณ  ๋‹˜ํ•˜์˜ ์—ฐ๊ตฌ๊ฐ€ ์–ด๋–ป๊ฒŒ ๊ธฐ์กด์˜ ๋ถ„์•ผ์— ๋น„ํ•ด์„œ ์ƒˆ๋กœ์šด ๊ฒƒ์„ ์ œ์‹œํ•ด ์ฃผ์—ˆ๋Š”์ง€์— ๋Œ€ํ•ด์„œ ์จ์•ผ ํ•œ๋‹ค. ๊ทธ๋ฆฌ๊ณ  ๋””์Šค์ปค์…˜ ๋์€ ๋‹˜ํ•˜ ์—ฐ๊ตฌ์—์„œ ์•„์ง ๊ฒฐ๋ก ์ด ์•ˆ ๋‚œ ‘Unanswered Question’ ํ˜น์€ ์ƒˆ๋กญ๊ฒŒ ๋ฐœ๊ฒฌ๋˜์„œ ์ƒ๊ธด ์˜๋ฌธ ๋“ฑ์œผ๋กœ ๋๋‚ด๋Š” ๊ฒŒ ์ข‹๋‹ค. ์•„๋งˆ ๊ธฐ์กด์˜ ์—ฐ๊ตฌ๊ฒฐ๊ณผ์™€ ๋‹˜ํ•˜๊ฐ€ ํ•˜์‹  ์—ฐ๊ตฌ๋ฅผ ์ข…ํ•ฉํ•ด์„œ ๋ชจ๋ธ ๊ทธ๋ฆผ ํ•˜๋‚˜ ๋–ก ๊ทธ๋ ค๋†“์œผ๋ฉด ์ข‹์ง€ ์•Š๊ฒ ๋ƒ ?

์•„ ๊ธ€๊ตฌ ์ปค๋ฒ„๋ ˆํ„ฐ ์ค‘์š”ํ•˜๋‹ค. ์ž˜์จ๋ผ. ๊ทผ๋ฐ ์–ด๋–ป๊ฒŒ ์ž˜์“ฐ๋Š”์ง€๋Š” ์—ฌ๋ฐฑ์ด ์—†์–ด์„œ ์„ค๋ช… ๋ชปํ•˜๊ฒ ๋‹น. ๊ทธ๋ฆฌ๊ณ  ์ œ๋ฐœ ๋…ผ๋ฌธ ๋ณด๋‚ด๊ธฐ์ „์— ์ŠคํŽ ์ฒดํฌ ์ข€ ํ•ด๋ผ. ์ŠคํŽ ๋ง ํ‹€๋ฆฌ๋ฉด ๋„ˆ๋‹˜ ๋…ผ๋ฌธ ๋‚ด์šฉ ๋ณด๊ธฐ์ „์— ์•„ ์žฌ ์ŠคํŽ ์ฒดํฌ๋„ ์•ˆํ–ˆ์œผ๋‹ˆ ์–ผ๋งˆ๋‚˜ ๊ฐœํŒ์ด๊ฒ ์Šด? ํ•˜๋Š” ์„ ์ž…๊ฒฌ ์ƒ๊ธฐ๊ฒŒ ํ•œ๋‹ค. ๊ทธ๋ฆฌ๊ณ  ๋งค๋‰ด์Šคํฌ๋ฆฝํŠธ ํŽ˜์ด์ง€ ๋ฐ ๊ทธ๋ฆผ์— ๋ฒˆํ˜ธ ์ข€ ๋‹ฌ๊ณ . ๊ทธ๋ฆฌ๊ณ  ํฐํŠธ ๋ณ„์Šค๋Ÿฌ์šด ๊ฒƒ ์“ฐ์ง€ ๋ง๊ณ  ์ข€ ์ผ๋ฐ˜์ ์ธ๊ฑฐ ์“ฐ๊ณ , ์ŠคํŽ˜์ด์‹ฑ ์ข€ ์ž˜ ๋„๊ณ . ๋„ˆ๋‹˜ ๋ฆฌ๋ทฐ์–ด๋‚˜ ์—๋””ํ„ฐ๋Š๋‹˜์ด ์ฝ๊ธฐ ํž˜๋“ค๊ฒŒ ์›๊ณ ๋‚ด๋ฉด ์ข‹์„ ๊ฒƒ ํ•˜๋‚˜๋„ ์์œผ๋‹ˆ ์•Œ์•„์„œ ์ข€ ์ž˜ ๊ธฐ์–ด๋ด๋ผ. ใ…‹ใ…‹ใ…‹