Dataset Information

From Platform to Knowledge Graph: Evolution of Laboratory Automation.

ABSTRACT: High-fidelity computer-aided experimentation is becoming more accessible with the development of computing power and artificial intelligence tools. The advancement of experimental hardware also empowers researchers to reach a level of accuracy that was not possible in the past. Marching toward the next generation of self-driving laboratories, the orchestration of both resources lies at the focal point of autonomous discovery in chemical science. To achieve such a goal, algorithmically accessible data representations and standardized communication protocols are indispensable. In this perspective, we recategorize the recently introduced approach based on Materials Acceleration Platforms into five functional components and discuss recent case studies that focus on the data representation and exchange scheme between different components. Emerging technologies for interoperable data representation and multi-agent systems are also discussed with their recent applications in chemical automation. We hypothesize that knowledge graph technology, orchestrating semantic web technologies and multi-agent systems, will be the driving force to bring data to knowledge, evolving our way of automating the laboratory.

SUBMITTER: Bai J

PROVIDER: S-EPMC8889618 | biostudies-literature | 2022 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

From Platform to Knowledge Graph: Evolution of Laboratory Automation.

Bai Jiaru J Cao Liwei L Mosbach Sebastian S Akroyd Jethro J Lapkin Alexei A AA Kraft Markus M

JACS Au 20220110 2

High-fidelity computer-aided experimentation is becoming more accessible with the development of computing power and artificial intelligence tools. The advancement of experimental hardware also empowers researchers to reach a level of accuracy that was not possible in the past. Marching toward the next generation of self-driving laboratories, the orchestration of both resources lies at the focal point of autonomous discovery in chemical science. To achieve such a goal, algorithmically accessible ...[more]

PMID: 35252980

Similar Datasets

Project description:BackgroundLINCS, "Library of Integrated Network-based Cellular Signatures", and IDG, "Illuminating the Druggable Genome", are both NIH projects and consortia that have generated rich datasets for the study of the molecular basis of human health and disease. LINCS L1000 expression signatures provide unbiased systems/omics experimental evidence. IDG provides compiled and curated knowledge for illumination and prioritization of novel drug target hypotheses. Together, these resources can support a powerful new approach to identifying novel drug targets for complex diseases, such as Parkinson's disease (PD), which continues to inflict severe harm on human health, and resist traditional research approaches.ResultsIntegrating LINCS and IDG, we built the Knowledge Graph Analytics Platform (KGAP) to support an important use case: identification and prioritization of drug target hypotheses for associated diseases. The KGAP approach includes strong semantics interpretable by domain scientists and a robust, high performance implementation of a graph database and related analytical methods. Illustrating the value of our approach, we investigated results from queries relevant to PD. Approved PD drug indications from IDG's resource DrugCentral were used as starting points for evidence paths exploring chemogenomic space via LINCS expression signatures for associated genes, evaluated as target hypotheses by integration with IDG. The KG-analytic scoring function was validated against a gold standard dataset of genes associated with PD as elucidated, published mechanism-of-action drug targets, also from DrugCentral. IDG's resource TIN-X was used to rank and filter KGAP results for novel PD targets, and one, SYNGR3 (Synaptogyrin-3), was manually investigated further as a case study and plausible new drug target for PD.ConclusionsThe synergy of LINCS and IDG, via KG methods, empowers graph analytics methods for the investigation of the molecular basis of complex diseases, and specifically for identification and prioritization of novel drug targets. The KGAP approach enables downstream applications via integration with resources similarly aligned with modern KG methodology. The generality of the approach indicates that KGAP is applicable to many disease areas, in addition to PD, the focus of this paper.

Project description:Artificial intelligence (AI) is revolutionizing scientific discovery because of its super capability, following the neural scaling laws, to integrate and analyze large-scale datasets to mine knowledge. Foundation models, large language models (LLMs) and large vision models (LVMs), are among the most important foundations paving the way for general AI by pre-training on massive domain-specific datasets. Different from the well annotated, formatted and integrated large textual and image datasets for LLMs and LVMs, biomedical knowledge and datasets are fragmented with data scattered across publications and inconsistent databases that often use diverse nomenclature systems in the field of AI for Precision Health and Medicine (AI4PHM). These discrepancies, spanning different levels of biomedical organization from genes to clinical traits, present major challenges for data integration and alignment. To facilitate foundation AI model development and applications in AI4PHM, herein, we developed BioMedGraphica, an all-in-one platform and unified text-attributed knowledge graph (TAKG), consists of 3,131,788 entities and 56,817,063 relations, which are obtained from 11 distinct entity types and harmonizes 29 relations/edge types using data from 43 biomedical databases. All entities and relations are labeled a unique ID and associated with textual descriptions (textual features). Since covers most of research entities in AI4PHM, BioMedGraphica supports the zero-shot or few-shot knowledge discoveries via new relation prediction on the graph. Via a graphical user interface (GUI), researchers can access the knowledge graph with prior knowledge of target functional annotations, drugs, phenotypes and diseases (drug-protein-disease-phenotype), in the graph AI ready format. It also supports the generation of knowledge-multi-omic signaling graphs to facilitate the development and applications of novel AI models, like LLMs, graph AI, for AI4PHM science discovery, like discovering novel disease pathogenesis, signaling pathways, therapeutic targets, drugs and synergistic cocktails.

Project description:BackgroundThere is a need to replace petroleum-derived with sustainable feedstocks for chemical production. Certain biomass feedstocks can meet this need as abundant, diverse, and renewable resources. Specific ionic liquids (ILs) can play a role in this process as promising candidates for chemical pretreatment and deconstruction of plant-based biomass feedstocks as they efficiently release carbohydrates which can be fermented. However, the most efficient pretreatment ILs are highly toxic to biological systems, such as microbial fermentations, and hinder subsequent bioprocessing of fermentative sugars obtained from IL-treated biomass.MethodsTo generate strains capable of tolerating residual ILs present in treated feedstocks, a tolerance adaptive laboratory evolution (TALE) approach was developed and utilized to improve growth of two different Escherichia coli strains, DH1 and K-12 MG1655, in the presence of two different ionic liquids, 1-ethyl-3-methylimidazolium acetate ([C2C1Im][OAc]) and 1-butyl-3-methylimidazolium chloride ([C4C1Im]Cl). For multiple parallel replicate populations of E. coli, cells were repeatedly passed to select for improved fitness over the course of approximately 40 days. Clonal isolates were screened and the best performing isolates were subjected to whole genome sequencing.ResultsThe most prevalent mutations in tolerant clones occurred in transport processes related to the functions of mdtJI, a multidrug efflux pump, and yhdP, an uncharacterized transporter. Additional mutations were enriched in processes such as transcriptional regulation and nucleotide biosynthesis. Finally, the best-performing strains were compared to previously characterized tolerant strains and showed superior performance in tolerance of different IL and media combinations (i.e., cross tolerance) with robust growth at 8.5% (w/v) and detectable growth up to 11.9% (w/v) [C2C1Im][OAc].ConclusionThe generated strains thus represent the best performing platform strains available for bioproduction utilizing IL-treated renewable substrates, and the TALE method was highly successful in overcoming the general issue of substrate toxicity and has great promise for use in tolerance engineering.

Dataset Information

From Platform to Knowledge Graph: Evolution of Laboratory Automation.

Publications

From Platform to Knowledge Graph: Evolution of Laboratory Automation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets