I-Insitro Machine Learning Biology
I-Insitro ihlanganisa idatha enkulu yofuzo lomuntu kanye neselula ngokufunda komshini ukuze kutholwe okuqondiwe okungcono kwezidakamizwa kanye neziguli okungenzeka kakhulu ziphendule.
Uhlolojikelele
It matters because it tackles the biggest reason drugs fail — picking the wrong target — by grounding discovery in real human biology.
I-Deep Dive
Yasungulwa ngo-2018 isazi sebhayoloji esiyikhompyutha kanye nowayengumholi we-Stanford kanye ne-Coursera u-Daphne Koller, i-Insitro izakhele 'njengenkampani yokufunda umshini kuqala' yokuthola izidakamizwa. Umqondo wayo oyinhloko uwukukhiqiza amasethi edatha amakhulu, akhelwe inhloso endlini - kusetshenziswa amamodeli ezifo asuselwa ku-stem-cell ('in vitro'), izithombe ezinokuqukethwe okuphezulu, kanye nezilinganiso 'ze-omics - futhi zibhangqwe namaqoqo amakhulu abantu ofuzo kanye nomtholampilo njenge-UK Biobank. Ukufunda ngomshini bese kuxhumanisa amangqamuzana namasignesha eselula nesifo, kusize ukukhomba okuhlosiwe ufuzo oluphakamisa ukuthi kubangele ukugula ngempela, futhi kuhlukanise iziguli zibe ngamaqembu amancane. Igama ngokwalo lihlanganisa 'ku-silico' (ikhompuyutha) kanye 'ne-in vitro' (i-lab biology). I-Insitro ibambisene neGileyadi kanye neBristol Myers Squibb futhi igxile ezindaweni ezifana ne-metabolic, isibindi, nezifo ze-neurodegenerative.
I-Technical Insight
Indlela ye-Insitro yesiginesha isebenzisa ukufunda komshini ezithombeni zezokwelapha - isibonelo, amamodeli ajulile afunda i-MRI yesibindi noma i-histopathology - ukuze kutholwe inani 'le-phenotypes lokufunda ngomshini.' Ukuqhuba izifundo zenhlangano yofuzo olubanzi ngokumelene nalezi zici ezitholakala ku-AI kuzo zonke izilinganiso ze-biobank-scale zingaveza okuhlukile kofuzo, ngakho-ke okuhlosiwe okuyimbangela, okugeja amalebula omtholampilo angcolile. Lokhu kuhlanganisa izakhi zofuzo zomuntu, ubufakazi obuqine kakhulu bokuthi okuqondiwe kusemqoka, okunothako lwe-phenotypic resolution oluvela ku-AI.
I-Strategic Impact
Isu lomthengisi
Imephu yemigwaqo yabathengisi ithonya ukuthi yiziphi izici iqembu lakho elingazakha ngokulandelayo.
Izindleko kanye nesabelomali
Imigomo yezohwebo nezinketho zokuthunyelwa zithinta izindleko zesikhathi eside nobungozi.
Ingozi nokuphepha
Izinxephezelo zenkampani zibumba okuzenzakalelayo komkhiqizo, ukuma kokuphepha, nokuvuleleka.
Ikusasa le-Insitro Machine Learning Biology
I-Insitro iphokophela kumamodeli aqagelayo axhuma i-genotype ku-phenotype yeselula kumphumela wesiguli, okuvumela ukukhethwa okuhlosiwe kanye nokuhlelwa kwesiguli ngaphambi kokuhlolwa okumba eqolo. Lindela ukusetshenziswa okujulile kwamamodeli esisekelo kuwo wonke ama-imaging nama-omics, ukuxhumana okwengeziwe kwe-biobank, kanye nokuthuthukisa amakhandidethi amapayipi angaphakathi. Inselele enkulu ukuvala iluphu: ukufakazela ukuthi okuhlosiwe okuqokwe yi-AI, okusekelwe kufuzo kuhumushela emithini egunyaziwe esebenza ezigulini ezifanele.
Ukuqaliswa Komhlaba Wangempela
Amamodeli okuqeqesha ekuhloleni kwe-MRI yesibindi ukuze akhe ama-phenotypes amaningi, bese eqhuba izifundo zenhlangano yezofuzo ukuze kutholwe okuhlosiwe kwezidakamizwa zesifo sesibindi.
Ukusebenzisa ama-neurons asuselwa ku-stem-cell-derived womuntu ukufanisa i-ALS nezinye izifo ze-neurodeergenerative ekuhlaziyeni i-ML.
Ukusebenzisana neGileyadi ukuthola okuhlosiwe kwe-nonalcoholic steatohepatitis (NASH) kanye ne-liver fibrosis.
Ukuhlukanisa iziguli zibe ngamaqembu amancane ofuzo ukuze kubikezelwe ukuthi ubani ozosabela ekwelashweni okunikeziwe.
Izingozi & Guardrails
Izimemezelo zokwethula zingase zeqe ukuzinza ekugelezeni komsebenzi wangempela wokukhiqiza.
Izintengo ze-API noma izinguquko zenqubomgomo zingaphula ukucabanga ngobusuku obubodwa.
Ukuncika komthengisi oyedwa kukhulisa izindleko zokukhiya nokufuduka.
Ukuqalisa Umhlahlandlela
Linganisa abahlinzeki usebenzisa eyakho imisebenzi namasethi edatha.
Buyekeza ubumfihlo, ukuphepha, nemibandela yomthetho ngaphambi kokuhlanganiswa.
Gcina uhlelo lokubuyela emuva kuwo wonke amamodeli noma abathengisi.
Gada amanothi okukhululwa ukuze izinguquko zemephu yomgwaqo zingamangazi amaqembu.
Qhubeka Uhlole
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Insitro Machine Learning Biology quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Umhlahlandlela olandelayo
Izisekelo Zokufunda Ngomshini
Imibuzo evame ukubuzwa
What is Insitro Machine Learning Biology?
I-Insitro ihlanganisa idatha enkulu yofuzo lomuntu kanye neselula ngokufunda komshini ukuze kutholwe okuqondiwe okungcono kwezidakamizwa kanye neziguli okungenzeka kakhulu ziphendule. Ibalulekile ngoba ibhekana nesizathu esikhulu sokuthi izidakamizwa zihluleke - ukukhetha okuqondiwe okungalungile - ngokusungula ukutholwa kubhayoloji yomuntu yangempela.
Lihlanganisani igama elithi 'Insitro'?
Igama lihlanganisa 'in silico' computation with 'in vitro' lab biology, ithwebula indlela yayo yokuhlola ye-ML-plus-experiment.
Ubani owasungula i-Insitro?
U-Daphne Koller, isazi sebhayoloji esisebenza ngekhompyutha futhi owayengumsunguli we-Coursera, wasungula i-Insitro ngo-2018.
Kungani i-Insitro igcizelela izakhi zofuzo zomuntu ekukhetheni okuqondiwe?
Okuhlosiwe okusekelwe ubufakazi bofuzo lomuntu kungenzeka kakhulu ukuthi kube yimbangela yangempela, kunciphise ukwehluleka kwezidakamizwa.
Iyini 'i-phenotype yokufunda ngomshini' njengoba i-Insitro iyisebenzisa?
I-Insitro ithola izici zobuningi ezithombeni zisebenzisa i-ML, bese ifunda ukuhlotshaniswa kwazo kofuzo.
Iliphi iqoqo labantu elikhulu elivame ukusetshenziselwa izifundo zofuzo ze-biobank-scale njenge-Insitro?
I-Biobank yase-UK ixhumanisa idatha yofuzo, izithombe, kanye nezempilo kumakhulu ezinkulungwane zabantu.