Phenotype measurement systems and methods

Abstract

An image acquisition and analysis system is disclosed. The system enables high throughput, objective analysis of microbial samples over days or weeks. The system may accommodate upwards of twelve 96- or 384-well plates simultaneously (liquid or solid media). The system may acquire and analyze a large number of samples in a short period of time. For example, over 384 samples per minute or 18,432 samples per hour. The system hardware may include a multi-spectral imager (fluorescence and bright field detection), electro-mechanical assemblies, and an optional high-resolution stage. The system may automate image acquisition, image data processing, simplify data storage, and enable automated analysis tools to significantly reduce the manual labor and time associated with such tasks. The system may allow for quick processing and analysis of data into clear phenotypic classes. The analysis capabilities may include colony growth, colorimetry, and structural morphology assays, and automated phenotype classification capabilities.

1 . A system for the classification of one or more specimen, the system comprising:
 a controller configured to:
 interface with one or more instrument through an instrument gateway module configured to receive a plurality of experimental data sets from the one or more instrument, wherein the plurality of experimental data sets is produced during a plurality of experiments; 
 extract one or more feature data set from the plurality of experimental data sets; 
 store at least a portion of the one or more feature data set in a long-term data storage subsystem; 
 store at least a portion of the one or more feature data set or at least a portion of the plurality of experimental data sets in a short-term storage cache; 
 build one or more classification profile based on a classification data set comprising at least a portion of the one or more feature data set; and 
 classify one or more specimen of an experiment of the plurality of experiments using the one or more classification profile, wherein the controller receives the plurality of experimental data sets before the classifying is performed on any of the experimental data sets. 
   
     
     
         2 . The system of any  claim 1 , wherein the classification data set comprises at least a portion of each feature data set of a plurality of feature data sets, wherein a first portion of the each feature data set is produced from a first experimental data set of the plurality of experimental data sets and a second portion of the each feature data set is produced from a second experimental data set of the plurality of experimental data sets. 
     
     
         3 . The system of  claim 2 , wherein the first experimental data set comprises data from a different experiment of the one or more experiment plurality of experiments than the data of the second experimental data set, the plurality of experiments comprising 100, 200, 500, 1,000, 5,000, 10,000, or 100,000 different experiments. 
     
     
         4 . The system of  claim 1 , wherein the controller receives the plurality of experimental data sets before the extracting is performed on any of the experimental data sets. 
     
     
         5 . (canceled) 
     
     
         6 . The system of  claim 2 , wherein at least a portion of the first experimental data set is received from a different instrument of the one or more instrument than the second experimental data set. 
     
     
         7 . The system of  claim 1 , wherein the one or more specimen comprises 100, 150, 200, 500, 1,000, 2,500, 5,000, 7,500, or 10,000 different specimen and the classification of the one or more specimen comprises categorizing the one or more specimen based on one or more feature data set. 
     
     
         8 . The system of  claim 1 , wherein building the classification profile comprises supervised machine learning or unsupervised machine learning. 
     
     
         9 - 10 . (canceled) 
     
     
         11 . The system of  claim 1 , wherein classification results are determined from the classification of one or more specimen of an experiment of the plurality of experiments using the classification profile. 
     
     
         12 - 13 . (canceled) 
     
     
         14 . The system of  claim 1 , wherein the controller is further configured to display an analysis data set comprising at least a portion of the experimental data sets, at least a portion of the one or more feature data set, or at least a portion of the classification data set, wherein the analysis data set is displayed in real-time, near-real time, or batch mode. 
     
     
         15 - 21 . (canceled) 
     
     
         22 . The system of  claim 1 , wherein the one or more specimen comprises one or more colony of microbial cells. 
     
     
         23 . (canceled) 
     
     
         24 . A method for the classification of one or more specimen, the method comprising:
 receiving a plurality of experimental data sets from one or more instrument, wherein the plurality of experimental data sets is produced during a plurality of experiments;   extracting one or more feature data set from the plurality of experimental data sets;   storing at least a portion of the one or more feature data set in a long-term data storage subsystem;   storing at least a portion of the one or more feature data set or at least a portion of the plurality of experimental data sets in a short-term storage cache;   building one or more classification profile based on a classification data set comprising at least a portion of the one or more feature data set; and   classifying one or more specimen of an experiment of plurality of experiments using the one or more classification profiles, wherein the plurality of experimental data sets is received before the classifying is performed on any of the experimental data sets.   
     
     
         25 . The method of  claim 24 , wherein the classification data set comprises at least a portion of each feature data set of a plurality of feature data sets, wherein a first portion of the each feature data set is produced from a first experimental data set of the plurality of experimental data sets and a second portion of the each feature data set is produced from a second experimental data set of the plurality of experimental data sets. 
     
     
         26 . The method of  claim 25 , wherein the first experimental data set comprises data from a different experiment of the plurality of experiments than the data of the second experimental data set, the plurality of experimental data sets comprising data from 100, 200, 500, 1,000, 5,000, 10,000, or 100,000 experiments. 
     
     
         27 . The method of  claim 24 , wherein the plurality of experimental data sets is received before the extracting is performed on any of the experimental data sets of the plurality of experimental data sets. 
     
     
         28 . (canceled) 
     
     
         29 . The method of any  claim 25 , wherein at least a portion of the first experimental data set is received from a different instrument of the one or more instrument than the second experimental data set. 
     
     
         30 . The method of  claim 24 , wherein the one or more specimen comprises 100, 150, 200, 500, 1,000, 2,500, 5,000, 7,500, or 10,000 different specimen and the classification of one or more specimen comprises categorizing the one or more specimen based on one or more set of feature data. 
     
     
         31 . The method of  claim 24 , wherein building the classification profile comprises supervised machine learning or unsupervised machine learning. 
     
     
         32 - 33 . (canceled) 
     
     
         34 . The method of  claim 24 , wherein classification results are determined from the classification of one or more specimen of an experiment of the plurality of experiments using the classification profile. 
     
     
         35 - 36 . (canceled) 
     
     
         37 . The method of  claim 24 , further comprising displaying an analysis data set comprising at least a portion of the plurality of experimental data sets, at least a portion of the one or more feature data set, or at least a portion of the classification data set, wherein the analysis data set is displayed in real-time, near-real time, or batch mode. 
     
     
         38 - 44 . (canceled) 
     
     
         45 . The method of  claim 24 , wherein the one or more specimen comprises one or more colony of microbial cells. 
     
     
         46 . (canceled)