{"title":"通过转移学习功能转录网络进行细胞重编程设计","authors":"Thomas P. Wytock, Adilson E. Motter","doi":"arxiv-2403.04837","DOIUrl":null,"url":null,"abstract":"Recent developments in synthetic biology, next-generation sequencing, and\nmachine learning provide an unprecedented opportunity to rationally design new\ndisease treatments based on measured responses to gene perturbations and drugs\nto reprogram cells. The main challenges to seizing this opportunity are the\nincomplete knowledge of the cellular network and the combinatorial explosion of\npossible interventions, both of which are insurmountable by experiments. To\naddress these challenges, we develop a transfer learning approach to control\ncell behavior that is pre-trained on transcriptomic data associated with human\ncell fates, thereby generating a model of the network dynamics that can be\ntransferred to specific reprogramming goals. The approach combines\ntranscriptional responses to gene perturbations to minimize the difference\nbetween a given pair of initial and target transcriptional states. We\ndemonstrate our approach's versatility by applying it to a microarray dataset\ncomprising >9,000 microarrays across 54 cell types and 227 unique\nperturbations, and an RNASeq dataset consisting of >10,000 sequencing runs\nacross 36 cell types and 138 perturbations. Our approach reproduces known\nreprogramming protocols with an AUROC of 0.91 while innovating over existing\nmethods by pre-training an adaptable model that can be tailored to specific\nreprogramming transitions. We show that the number of gene perturbations\nrequired to steer from one fate to another increases with decreasing\ndevelopmental relatedness and that fewer genes are needed to progress along\ndevelopmental paths than to regress. These findings establish a\nproof-of-concept for our approach to computationally design control strategies\nand provide insights into how gene regulatory networks govern phenotype.","PeriodicalId":501325,"journal":{"name":"arXiv - QuanBio - Molecular Networks","volume":"38 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Cell reprogramming design by transfer learning of functional transcriptional networks\",\"authors\":\"Thomas P. Wytock, Adilson E. Motter\",\"doi\":\"arxiv-2403.04837\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent developments in synthetic biology, next-generation sequencing, and\\nmachine learning provide an unprecedented opportunity to rationally design new\\ndisease treatments based on measured responses to gene perturbations and drugs\\nto reprogram cells. The main challenges to seizing this opportunity are the\\nincomplete knowledge of the cellular network and the combinatorial explosion of\\npossible interventions, both of which are insurmountable by experiments. To\\naddress these challenges, we develop a transfer learning approach to control\\ncell behavior that is pre-trained on transcriptomic data associated with human\\ncell fates, thereby generating a model of the network dynamics that can be\\ntransferred to specific reprogramming goals. The approach combines\\ntranscriptional responses to gene perturbations to minimize the difference\\nbetween a given pair of initial and target transcriptional states. We\\ndemonstrate our approach's versatility by applying it to a microarray dataset\\ncomprising >9,000 microarrays across 54 cell types and 227 unique\\nperturbations, and an RNASeq dataset consisting of >10,000 sequencing runs\\nacross 36 cell types and 138 perturbations. Our approach reproduces known\\nreprogramming protocols with an AUROC of 0.91 while innovating over existing\\nmethods by pre-training an adaptable model that can be tailored to specific\\nreprogramming transitions. We show that the number of gene perturbations\\nrequired to steer from one fate to another increases with decreasing\\ndevelopmental relatedness and that fewer genes are needed to progress along\\ndevelopmental paths than to regress. These findings establish a\\nproof-of-concept for our approach to computationally design control strategies\\nand provide insights into how gene regulatory networks govern phenotype.\",\"PeriodicalId\":501325,\"journal\":{\"name\":\"arXiv - QuanBio - Molecular Networks\",\"volume\":\"38 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Molecular Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.04837\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Molecular Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.04837","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Cell reprogramming design by transfer learning of functional transcriptional networks
Recent developments in synthetic biology, next-generation sequencing, and
machine learning provide an unprecedented opportunity to rationally design new
disease treatments based on measured responses to gene perturbations and drugs
to reprogram cells. The main challenges to seizing this opportunity are the
incomplete knowledge of the cellular network and the combinatorial explosion of
possible interventions, both of which are insurmountable by experiments. To
address these challenges, we develop a transfer learning approach to control
cell behavior that is pre-trained on transcriptomic data associated with human
cell fates, thereby generating a model of the network dynamics that can be
transferred to specific reprogramming goals. The approach combines
transcriptional responses to gene perturbations to minimize the difference
between a given pair of initial and target transcriptional states. We
demonstrate our approach's versatility by applying it to a microarray dataset
comprising >9,000 microarrays across 54 cell types and 227 unique
perturbations, and an RNASeq dataset consisting of >10,000 sequencing runs
across 36 cell types and 138 perturbations. Our approach reproduces known
reprogramming protocols with an AUROC of 0.91 while innovating over existing
methods by pre-training an adaptable model that can be tailored to specific
reprogramming transitions. We show that the number of gene perturbations
required to steer from one fate to another increases with decreasing
developmental relatedness and that fewer genes are needed to progress along
developmental paths than to regress. These findings establish a
proof-of-concept for our approach to computationally design control strategies
and provide insights into how gene regulatory networks govern phenotype.