Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
aliFreeFold: an alignment-free approach to pred...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yuki_Hamaguchi
August 18, 2018
Science
97
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
aliFreeFold: an alignment-free approach to predict secondary structure from homologous RNA sequences
ISMB読み会2018で紹介したaliFreeFoldに関する発表スライドです。
Yuki_Hamaguchi
August 18, 2018
Other Decks in Science
See All in Science
暗号解読における量子計算の展望
neutron63zf
0
460
20260410_SystemsThinking
takusamar
1
160
AI(人工知能)の過去・現在・未来 ~AIは人類を越えるのか~
tagtag
PRO
0
170
データベース14: B+木 & ハッシュ索引
trycycle
PRO
0
970
Kritische evaluatie van GenAI-output voor literatuuronderzoek
voginip
0
250
データベース05: SQL(2/3) 結合質問
trycycle
PRO
0
1.4k
ゲームと人工知能
miyayou
0
260
「表象」を再定義するー潜在表現解析の落とし穴
ykamit
0
1.1k
Conwayの法則を"ちゃんと"使うために — 原典でConwayは何を言っていたのか
bonotake
10
7.6k
科学で迫る勝敗の法則-スポーツデータ分析の最前線 (刈谷市連携講座.2026年7月) / The principle of victory discovered by science. at Kariya City, 2027.07
konakalab
0
200
Collective Predictive Coding Hypothesis: Emergence of Language and Cooperative Behaviors
tanichu
0
180
Path integral polarons for real semiconductors
jarvist
0
110
Featured
See All Featured
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1.4k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.2k
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
600
Designing for humans not robots
tammielis
254
26k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
123
22k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
How to train your dragon (web standard)
notwaldorf
96
6.9k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
4
4.4k
Leo the Paperboy
mayatellez
10
2.4k
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
2
2.2k
Statistics for Hackers
jakevdp
799
230k
Balancing Empowerment & Direction
lara
6
1.3k
Transcript
BMJ'SFF'PME dΞϥΠϝϯτϑϦʔͳ 3/"ೋ࣍ߏ༧ଌख๏d հऀɿޱ༔و ౦ژେֶେֶӃ৽ྖҬՊֶݚڀՊ ϝσΟΧϧใੜ໋ઐ߈ ؠ࡚ݚڀࣨ M2 *4.#+PVSOBM
ࣗݾհ ۙͰࢀՃ͢Δֶձɾݚڀձ ɹɾຊਐԽֶձ ɹ ɹɾੜ໋ͷىݯٴͼਐԽֶձՆͷֶߍ ڵຯ͋Δ ɹਅ֩ੜͷىݯ ಛʹϛτίϯυϦΞ ຊਐԽֶձཁࢫू1 ̍
3/"ೋ࣍ߏ༧ଌͷΞϓϩʔν ᶃҰͭͷ3/"Ԙجྻ͔Β༧ଌ ᶄ૬ಉ3/"Ԙجྻ͔Β༧ଌ ࠷খࣗ༝ΤωϧΪʔߏମ .'& Λࢉग़ ίϯηϯαεͳೋ࣍ߏΛࢉग़ ૯߹ԘجରܗҐஔڑ ࣗ
༝ Τ ω ϧ Ϊ | Methods 103 (2016) 86–98 ૬ಉ3/"ͦΕͧΕΛൺֱ͠ɺ ೋ࣍ߏͷอଘੑΛݕग़ ࣗ༝ΤωϧΪʔύϥϝʔλʹج͖ͮɺ ೋ࣍ߏީิΛཏతʹ୳ࡧɾධՁ ̎ MJGFTDJFODFECKQIPVLPLVQEG#@pOBMQEG BMJ'SFF'PME
ᶃ3/"४࠷దߏΛ༻͍ͯ ɹҎ্ͷਖ਼ղԘجର ɹΛ࣋ͭදతͳ3/"ߏ ɹΛग़ྗ͢Δ ࣗ ༝ Τ ω ϧ Ϊ
| ૯߹ԘجରܗҐஔڑ BMJ'SFF'PMEͷڧΈ ̏ 41"34& 5VSCP'PMEJJ ᶄ࣌ؒܭࢉྔ͕͍ ɹΞϥΠϝϯτϑϦʔख๏ ɹैདྷΑΓɾਫ਼ ɹͷόϥϯε͕ྑ͍ 3/"४࠷ద TVCPQUJNBM ߏ ʼ IUUQTPQFOXFUXBSFPSHXJLJ 8JLJPNJDT3/"@TFDPOEBSZ@TUSVDUVSF@QSFEJDUJPO .94$"3/" Ex) Saccharomyces cerevisiaeͷU3/" 1IF
BMJ'SFF'PMEͷΞϓϩʔνख๏ᶃ input: ૬ಉRNAྻ ̐ :@ "$$6"$66("$6$"($((66"("(6"6 $($666$"6"$(($("("(6$"66((6 6$"""6$$""6"(6"((6" "'@ (((($$66"($6$"($6((("("($($
$6($666($"$($"(("((6$"($((6 6$("6$$$($6"(($6$$" "+@ 6$$6$"(6"($6$"(6((6"("($((6 $(($6(66""$$("66((6$(6"((66 $(""6$$6"$66(((("( 9@ "$$6"$66""$6$"(6((66"("(6"$ 6($666$"6"$(($((("(($"66((6 6$"""6$$""6"(6"((6" 7@ "$6666"""(("6"(6"(666"6$$(6 6((6$66"((""$$""""""66((6($ ""$6$$"""6""""(6" ᶃ֤૬ಉ3/"ྻͷ४࠷దߏΛ3/"TVCPQU Λ༻͍ͯࢉग़ ᶄۙྡϞνʔϑߏ ʢϚϧνϧʔϓɾεςϜʣͷΛࢉग़ ۙྡϞνʔϑߏଞʹϔΞϐϯϧʔϓɺΠϯλʔφϧϧʔϓɺ ɹɹɹɹɹɹɹɹɹόϧδɺΤΫελʔφϧϧʔϓ `ɺ` ɺγϡʔυίϯτ 7JFOOB3/"ύοέʔδͷҰͭ
BMJ'SFF'PMEͷΞϓϩʔνख๏ᶄ output දߏ ̑ ᶅϞνʔϑ͝ͱʹอଘࢦΛܭࢉɹ Τϯτϩϐʔܭࢉ ᶆ֤ϞνʔϑͷอଘࢦʹॏΈ͚ͮ ʢอଘࢦʹ࠷େείΞΛ͔͚Δʣ ᶇ֤Ϟνʔϑͷอଘࢦ͔Βશ૬ಉ3/"ͷॏ৺తߏΛࢉग़
ᶈ֤૬ಉ3/"ͷதͰॏ৺తߏʹ͍ۙͷΛநग़
S3/" U3/" άϧʔϓᶘΠϯτϩϯ 6TO3/" 3/BTF1 UN3/" 4&$*4ʜ 5SFOET#JPDIFN4DJ QQr
IUUQSOBVDTDFEVSOBDFOUFS SJCPTPNF@JNBHFTIUNM *6#.#-JGF Џ༧ଌߏͰ߹கͨ͠Ԙجର ൺֱ͢Δ༧ଌπʔϧɹ(7ͭ) 3/"DBTU طଘͷΞϥΠϝϯτϑϦʔख๏ 3/"TQB .94$"3/" $FOUSPJE'PME 3/"BMJGPME 41"34& 5VSCP'PMEJJ Dataset: طͷ૬ಉRNAྻ σʔληοτͱධՁํ๏ ධՁํ๏: Sensivity, PPV, MCC ਅͷ݁Ռ ରܗ Ԙج ରඇܗ Ԙج ରܗ Ԙج 51 '1 ରඇܗ Ԙج '/ 5/ ༧ ଌ ݁ Ռ ✖51 '/ ˓5/ '/
ೋ࣍ߏ༧ଌͷਖ਼ղԘجର ̓ ฏ ۉ ਖ਼ ղ ׂ ߹ (%)
ݸ M F E ݸ ݸ c ݸ ̍ݸ ४࠷దߏσʔλ .'&ߏΑΓ४࠷దߏͷํ͕ԘجରΛਖ਼͘͠༧ଌͰ͖Δ ४࠷దߏσʔλ͕૿Ճ͢Δ΄Ͳ༧ଌੑೳ্͕ঢ͢Δ
3/"ೋ࣍ߏ༧ଌੑೳᶃ ̔ ᶃ"MJ'SFF'PME3/"DBTUΑΓ.$$ 117 4&/4શͯͰ༏Ε͍ͯΔ ᶄ"MJ'SFF'PMEͱ5VSCP'PMEᶘ͕࠷ྑͷ༧ଌπʔϧͰ͋Δ ධՁࢦඪ ରσʔληοτ OD3/"GBNJMZ
̕ ૬ಉ3/" "MJ'SFF'PMEσʔληοτΛ૿Ճͤ͞Δͱ ͞Βʹ༧ଌೳྗ্͕ঢ͢Δ 3/"ೋ࣍ߏ༧ଌੑೳᶄ
3/"ೋ࣍ߏ༧ଌޮ ฏۉԘج OU ࣌ ؒ (log) ୯Ґඵ "MJ'SFF'PME 3/"BMJGPME
$FOUSPJE'PME 5VSCPGPMEJJ "MJ'SFF'PME$FOUSPJE'PME5VSCPGPMEͱ ಉͷ͍ղੳΛ༗͍ͯ͠Δ 3/"BMJGPMEʹରͯ͠ ྼ͍ͬͯΔ ➕ *ཧ࣌ؒܭࢉྔ O(al2+mn),O(al4+mn) B૬ಉԘجର NϞνʔϑɺOྻ O(l2),O(l4)3/"TVCPQU
ࠓޙͷओͳվળ ᶃ४࠷దߏͷܭࢉπʔϧมߋ ɹ 3/"TVCPQU ˠWT@TVCPQU γϡʔυϊοτߏ ͷݕग़ਫ਼Λ্͛Δ
3/BTF1ͷ༧ଌਫ਼Λ ͋͛ΒΕΔ ᶄอଘࢦͷΑΓਖ਼֬ͳܭࢉ 3/" r ྗֶత౷ܭख๏ͷ׆༻ ଟมྔղੳ ˠΑΓదͳදߏͷݕग़ ࠷ ྑ ४ ࠷ ద ߏ ͔ Β ͷ Ԙ ج ର ڑ .'& ͔ΒͷԘجରڑ γϡʔυϊοτߏ .PM#JP4ZTU
*RNAfold (web)Λͬͯඳը ࣮ࡍʹBMJ'SFF'PMEΛΒͤͯΈͨ ϚπϤΠάαͷ৭ૉମU3/""TO DGU3/"TDBO4& ͰͷU3/"ߏ༧ଌ αϯϓϧσʔλ U3/"ͷೋ࣍ߏ༧ଌैདྷ๏ΑΓྑͦ͞͏ʹݟ͑Δ ΞϯνίυϯྖҬ
DG$FOUSPJE'PME ͰͷU3/"ߏ༧ଌ
ίϝϯτ Cell, Vol. 113, 383–394, May 2, 2003, 7MPPQͷΑ͏ͳߏϞνʔϑΛ
ଞͷU3/"σʔλͰڞ༗͍͕ͯͨ͠ɺ ग़ྗ͞ΕͨදߏͷΈ ͦͷϞνʔϑΛอ༗͍ͯ͠ͳ͔ͬͨ Մೳੑ͕͋ΔͷͰʁ