US 12,181,416 B2
Configurable handheld biological analyzers for identification of biological products based on Raman spectroscopy
Robert Joseph Soto, Thousand Oaks, CA (US); and David Meriage, Thousand Oaks, CA (US)
Assigned to AMGEN INC., Thousand Oaks, CA (US)
Appl. No. 17/770,782
Filed by AMGEN INC., Thousand Oaks, CA (US)
PCT Filed Oct. 23, 2020, PCT No. PCT/US2020/056961
§ 371(c)(1), (2) Date Apr. 21, 2022,
PCT Pub. No. WO2021/081263, PCT Pub. Date Apr. 29, 2021.
Claims priority of provisional application 63/043,976, filed on Jun. 25, 2020.
Claims priority of provisional application 62/925,893, filed on Oct. 25, 2019.
Prior Publication US 2022/0390375 A1, Dec. 8, 2022
Int. Cl. G01J 3/44 (2006.01); G01J 3/02 (2006.01); G01N 21/65 (2006.01)
CPC G01N 21/65 (2013.01) [G01J 3/0272 (2013.01); G01J 3/44 (2013.01); G01N 2201/0221 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A configurable handheld biological analyzer for identification of biological products based on Raman spectroscopy, the configurable handheld biological analyzer comprising:
a first housing adapted for handheld manipulation;
a first scanner carried by the first housing;
a first processor communicatively coupled to the first scanner; and
a first computer memory communicatively coupled to the first processor,
wherein the first computer memory is configured to load a biological classification model configuration, the biological classification model configuration comprising a biological classification model, wherein the biological classification model is configured to execute on the first processor, the first processor configured to (1) receive a first Raman-based spectra dataset defining a first biological product sample as scanned by the first scanner, and (2) identify, with the biological classification model, a biological product type based on the first Raman-based spectra dataset,
wherein the biological classification model configuration further comprises a spectral preprocessing algorithm, the first processor configured to execute the spectral preprocessing algorithm to reduce a spectral variance of the first Raman-based spectra dataset when the first Raman-based spectra dataset is received by the first processor, and
wherein the biological classification model comprises a classification component selected to reduce at least one of (1) a Q-residual error of the biological classification model, or (2) a summary-of-fit value of the biological classification model, the biological classification model configured to identify the biological product type of the first biological product sample based on the classification component.