[go: up one dir, main page]

WO2022013718A1 - Procédé pour classification d'échantillons biologiques en termes d'infection par des agents viraux, et utilisations - Google Patents

Procédé pour classification d'échantillons biologiques en termes d'infection par des agents viraux, et utilisations Download PDF

Info

Publication number
WO2022013718A1
WO2022013718A1 PCT/IB2021/056260 IB2021056260W WO2022013718A1 WO 2022013718 A1 WO2022013718 A1 WO 2022013718A1 IB 2021056260 W IB2021056260 W IB 2021056260W WO 2022013718 A1 WO2022013718 A1 WO 2022013718A1
Authority
WO
WIPO (PCT)
Prior art keywords
infection
viral agents
coverslip
film
biological samples
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/IB2021/056260
Other languages
English (en)
Portuguese (pt)
Inventor
Lidia Maria DE ANDRADE
Paulo Henrique RIBEIRO AMARAL
Juan Carlos GONZÁLEZ PÉREZ
Maria Ivonete NOGUEIRA DA SILVA
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Universidade Federal de Minas Gerais
Original Assignee
Universidade Federal de Minas Gerais
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from BR102020024993-2A external-priority patent/BR102020024993A2/pt
Application filed by Universidade Federal de Minas Gerais filed Critical Universidade Federal de Minas Gerais
Publication of WO2022013718A1 publication Critical patent/WO2022013718A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/21—Polarisation-affecting properties

Definitions

  • the proposed technology presents a process to perform classifications of biological samples for infection by viral agents and also describes the uses of the process.
  • the technology is based on a combination of techniques: Variable Angle Spectroscopic Ellipsometry (variable-angle spectroscopic ellipsometry - VASE), Artificial Intelligence and Machine Learning from a Decision Tree model associated with an Extreme Augmentation algorithm. of Gradient (named in English - “Extreme Gradient Boosting”) or random decision trees (“f ⁇ andom Foresf) or the noise elimination technique based on Euclidean distances, called K-Nearest Neighbors (KNN).
  • Gradient named in English - “Extreme Gradient Boosting”
  • random decision trees f ⁇ andom Foresf
  • KNN K-Nearest Neighbors
  • the technology is applied to support the diagnosis of infections caused by viral agents, especially for the agents called SARS-CoV-2, Zika and Dengue, and has settings applicable to all stages of the infection's evolution. It provides simultaneous analysis for a plurality of viral agents in multiple detection mode ( Multiplex ) and eliminates the use of markers (" label-free ). It represents a relevant resource for mitigating and controlling pandemics caused by viral etiological agents, especially the current COVID-19 pandemic caused by the coronavirus.
  • One of the proposed technology configurations can be used as an alternative to the RT-PCR technique for the detection of viral agents, detecting the presence of virus RNA fragments and cellular material modified by the viral infection in oropharyngeal scraping samples. or in cells cultured and infected in the laboratory, suitable for patients with a few weeks of infection and who do not yet have a high production of antibodies.
  • Another configuration of the technology can be used as an alternative to existing serological diagnostic methods, based on antibody reaction, helping to diagnose individuals who have been infected for more than two weeks.
  • This form of technology application presents the possibility of detecting infections by the SARS-CoV-2 and Dengue viral agents, providing support for the differential diagnosis of these viral agents. It can also be a viable technology as an alternative to be used for epidemic mapping and public policy purposes.
  • “Characterization of layered scattering media using polarized light measurements and neural networks” describes a methodology that measures the depolarization of radiation scattered by a thin tissue layer of skin from a beam of polarized light and indicates the use of an artificial neural network trained to characterization of melanoma from the measures described.
  • “Application of neural classification in ellipsometry for robust thin-film characterizations” presents the use of ellipsometry and artificial neural networks to characterize a photoresist. From ellipsometric measurements, a neural network classifies the measured photoresist according to its thickness range. [07] The Scientific article, published in 2018, entitled “Computer-aided diagnosis of glaucoma using fundus images: A reviewW' details the use of ellipsometry applied to the fundus and artificial neural networks for the characterization/diagnosis of glaucoma. Based on ellipsometric measurements, a trained neural network classifies samples measured in eyes, specifically in their fundus, as to the occurrence of glaucoma.
  • the present invention differs from the technologies present in the state of the art because it results in the exclusive combination of the following technical characteristics and technical effects: and Machine Learning from a Decision Tree model associated with the Extreme Gradient Boosting algorithm (named in the English language - “Extreme Gradient Boosting') or random decision trees (“f ⁇ andom Foresf) or the noise elimination technique based on in Euclidean distances, called K-Nearest Neighbors (KNN).
  • the data applied to the models represent ellipsometric measurements of films prepared from biological samples.
  • the technology is applied to support the diagnosis of infections caused by viral agents, especially for the agents called SARS-CoV-2, Zika and Dengue, and has settings applicable to all stages of the infection's evolution. It provides simultaneous analysis for a plurality of viral agents in multiple detection mode (Multiplex) and eliminates the use of label-free markers).
  • the proposed technology presents a process to perform classifications of biological samples for infection by viral agents and also describes the uses of the process.
  • the technology is based in the combination of techniques: Variable Angle Spectroscopic Ellipsometry (named in English - variable-angle spectroscopic ellipsometry - VASE), Artificial Intelligence and Machine Learning from a Decision Tree model associated with Extreme Gradient Augmentation algorithm (named in English language - “Extreme Gradient Boosing') or random decision trees (“Fiandom Foresf) or the noise elimination technique based on Euclidean distances, called K-Nearest Neighbors (KNN).
  • the data applied to the models represent ellipsometric measurements of films prepared from biological samples.
  • the technology is applied to support the diagnosis of infections caused by viral agents, especially for the agents called SARS-CoV-2, Zika and Dengue, and has settings applicable to all stages of the infection's evolution. It provides simultaneous analysis for a plurality of viral agents in multiple detection mode (Multiplex) and eliminates the use of label-free markers).
  • Multiplex multiple detection mode
  • the cells used in the proposed method can be obtained from cell cultures or from smears of cells collected from a patient.
  • Patient samples can be obtained by collecting material using nasal or oropharyngeal swab, or both, performed on the patient to obtain a smear of cells.
  • the preparation of the lysis film has the following steps: 1) lysis of cells obtained by cultivation or smear, for inactivation of the same and protection of the RNA of the viruses; 2) the solution containing the lysed cells, obtained in step 1, is deposited on a coverslip and left to dry until a film forms.
  • the buffer solution used to lyse cells should comprise guanidine isothiocyanate and sodium citrate in RNAse/DNAse free water, with a pH adjusted to close to 4.
  • Guanidine is a ribonuclease inhibitor that aids in the preservation of genetic material.
  • Samples can be obtained by collecting blood from the patient to obtain serum. To obtain the serum, the patient's blood is centrifuged to separate the serum from the other blood components. Serum contains the antibodies produced by the patient's immune system when infected.
  • the description for obtaining training data and test data for the elaboration and verification of the accuracy of the classification model is presented.
  • the elaboration of the model comprises the following steps: a) Focus a beam of electromagnetic radiation with well-defined linear polarization in the ultraviolet, visible and infrared spectral regions (from 242 nm to 1689 nm, in unit increments) on the region of the coverslip in which the lysis film or whey film is present for each elipsométricos angles of incidence of 45 °, 50 °, 55 °, 60 °, 65 and 70 0 with respect to the normal line to the film surface deposited on the coverslip , the film is contained in the space between two juxtaposed coverslips; b) Measure the change in polarization of the reflected radiation beam by determining the ratio (p) between the Fresnel coefficients r p r s , according to Expression (1), for each incident wavelength and angle of radiation defined in step "The”: (Expression 1)
  • steps “a” and “b” must be applied to multiple regions of the coverslip containing the lysis film or the serum film; d) Label the data obtained in the steps in steps “a”, “b” and “c”” regarding infection by viral agents (the presence of infection by viral agents is known in the training and test data, as samples are chosen infected with the viral agent or, in the case of the cultivation of cells used to generate the lysis film, the cells are intentionally infected); e) The total measurements obtained in steps “a” to “d” are organized to include two columns of data, the first column is made up of all wavelengths measured in duplicate, the second column is made up of the real part the values of p plus the imaginary part of said values; f) A training database is constituted by adding columns with the values of p for each angle of incidence, and each of the regions measured for each coverslip; g) The training database is then submitted to a standard
  • KNN K-Nearest Neighbors
  • step “h” An extreme gradient increase technique can be used alternatively in step “h”.
  • An artificial intelligence algorithm based on random decision trees (“f ⁇ andom Foresf) can be used alternatively in step “h”.
  • step “c” The probability generated in step “c” is compared with an arbitrated threshold value (Va), so that if the value of the generated probability is greater than Va the sample is classified as infection by viral agents present; if the value of the generated probability is less than Va, the sample is classified as absent infection by viral agents.
  • Va arbitrated threshold value
  • the film can be the lysis film formed by cells obtained from culture or smear, lysed with buffer containing ribonuclease inhibitor, deposited on a coverslip with drying at room temperature.
  • the film can also be obtained from blood serum, applied to the surface of a coverslip and immediately covered by a second coverslip, enclosing the sample of liquid material between the two coverslips.
  • the electromagnetic radiation beam with well-defined linear polarization can be comprised in the ultraviolet spectral regions in the range of 240 nm to 380 nm and the ellipsometric angle is 55 degrees.
  • step "a” For the blood serum film, in step "a", the infrared spectral regions above 850 nm (in unit increments) are used.
  • steps “a” and “b” can be applied preferably in 13 regions of a rectangular coverslip defined as follows: region (1): center of the coverslip; regions (2), (3), (4) and (5): the four corners of the coverslip; regions (6), (7), (8) and (9): the midpoints of each edge of the coverslip; regions (10), (11), (12) and (13): the points corresponding to 1 ⁇ 4 and 3 ⁇ 4 of each diagonal of the coverslip.
  • the numerical value of prediction can be normalized, preferably normalized in a numerical range between 0 and 1.
  • the arbitrated threshold value (Va) is preferably 0.5 or 50%.
  • the use of the biological sample classification process for infection by viral agents is preferably for classification involving SARS-CoV-2, Zika and/or Dengue viral agents.
  • the imaginary part of the values associated with the real part of the p values can be used in a complementary way, also including the depolarization and intensity, in the measurements presented in step "b” .
  • Steps “a” and “b” also include the measurement of wavelengths in quadruplicate, according to the steps described below: a) Focus a beam of electromagnetic radiation with well-defined linear polarization in the infrared spectral regions above 850 nm (in unit increments) over a region of the cover slip in the serum of film is present for each elipsométricos angles of incidence of 45 °, 50 °, 55 °, 60 °, 65 and 70 0 with respect to the normal line to the surface of the film, the film being contained in the space between two overlapping coverslips; b) Measure the change in polarization of the reflected radiation beam by determining the ratio (p) between the Fresnel coefficients r p r s , also measure the depolarization, intensity and wavelength
  • step “c” The probability generated in step “c” is compared with an arbitrated threshold value (Va), so that if the value of the generated probability is greater than Va, the sample is classified as an infection by SARS-CoV-2 and/or viral agents or Dengue present; if the value of the generated probability is lower than Va, the sample is classified as infection by SARS-CoV-2 viral agents and Dengue absent, allowing the differential identification of the type of infection.
  • Va arbitrated threshold value
  • the measurements must be applied in 5 to 9 regions of a rectangular coverslip, defined as follows: in the center of the coverslip and on the side where the light falls.
  • the process using serum film can be used for the differential diagnosis of Dengue and COVID-19.
  • PCR Polymerase Chain Reaction
  • Example 2 Process for classifying biological samples for infection by SARS-CoV-2 and Dengue viral agents
  • This example presents a possible embodiment of the technology to perform a prediction for Dengue or SARS-CoV-2 infection. It is a differential diagnosis for these two viral agents.
  • This embodiment of the invention uses serum samples taken from the patient's blood.
  • a patient's blood sample is centrifuged to separate the serum from the rest of the components.
  • the serum contains the antibodies produced by the patient's immune system, in huge quantities when the patient was infected, and does not contain remnants of cellular material or the RNA of the virus.
  • a 10 pL aliquot of blood serum is applied to the surface of a coverslip and immediately covered by a second coverslip, enclosing the sample of liquid material between the two coverslips.
  • Measurement methodology between 5 and 9 regions are used, which include the center of the sample and the left side of it (region where the light falls), not needing to measure the right side of the sample (region where the light comes out). light) nor cover most of the surface of the sample.
  • Physical parameters measured and optical configuration the physical parameters measured and used in the analysis with the aid of artificial intelligence use the measurements of two ellipsometric angles y and D to compose the imaginary part (pi) and the real part (p r ) of the ratio between the intensity of reflected light with polarization in the sample plane and out of the sample plane. Depolarization and Intensity measurements were also used at six different angles of incidence (45°, 50°, 55°, 60°, 65° and 70°). The spectral region above 850 nm was used. The Depolarization and Intensity measurements allow the anisotropy of the samples to be considered and require a PSCRA (polarizer-sample-rotary compensator-analyzer) optical configuration.
  • PSCRA polarizer-s

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

Le procédé combine les techniques : Ellipsométrie spectroscopique à angle variable (Variable-Angle Spectroscopic Ellipsometry), intelligence artificielle et apprentissage machine à partir d'un modèle d'arbres de décision associés à un algorithme d'augmentation extrême de gradient (Extreme Gradient Boosting) ou des arbres de décision randomisés (Random Forest), ou la technique d'élimination de bruit basée sur des distances euclidiennes (K-Nearest Neighbors). La technologie trouve une application dans l'appui au diagnostic d'infections causées par des agents viraux, notamment par les agents SARS-CoV-2, Zika et dengue, et possède des configurations applicables à tous les stades de l'évolution de l'infection. Il permet une analyse simultanée pour une pluralité d'agents viraux en mode de détections multiples (Multiplex) et ne nécessite pas l'utilisation de marqueurs. Il représente une ressource utile pour les mesures d'atténuation et de contrôle contre des pandémies provoquées par des agents viraux, notamment contre l'actuelle pandémie de COVID-19.
PCT/IB2021/056260 2020-07-13 2021-07-12 Procédé pour classification d'échantillons biologiques en termes d'infection par des agents viraux, et utilisations Ceased WO2022013718A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
BRBR1020200143034 2020-07-13
BR102020014303 2020-07-13
BRBR1020200249932 2020-12-07
BR102020024993-2A BR102020024993A2 (pt) 2020-07-13 2020-12-07 Processo para classificação de amostras biológicas quanto a infecção por agentes virais e usos

Publications (1)

Publication Number Publication Date
WO2022013718A1 true WO2022013718A1 (fr) 2022-01-20

Family

ID=79555097

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2021/056260 Ceased WO2022013718A1 (fr) 2020-07-13 2021-07-12 Procédé pour classification d'échantillons biologiques en termes d'infection par des agents viraux, et utilisations

Country Status (1)

Country Link
WO (1) WO2022013718A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5631171A (en) * 1992-07-31 1997-05-20 Biostar, Inc. Method and instrument for detection of change of thickness or refractive index for a thin film substrate
EP2327955A1 (fr) * 2008-09-05 2011-06-01 Universidad Politécnica De Madrid Système de détection optique pour essais biologiques à haute sensibilité sans marquage
US8486619B2 (en) * 2008-05-02 2013-07-16 University Of Rochester Arrayed imaging reflectometry (air) sensor chip comprising influenza hemagglutinin (HA) polypeptides suitable for the detection of antiviral immune responses
US9404872B1 (en) * 2011-06-29 2016-08-02 Kla-Tencor Corporation Selectably configurable multiple mode spectroscopic ellipsometry
CN106093429A (zh) * 2016-06-02 2016-11-09 滨州医学院 一种检测胃癌组织的试剂盒

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5631171A (en) * 1992-07-31 1997-05-20 Biostar, Inc. Method and instrument for detection of change of thickness or refractive index for a thin film substrate
US8486619B2 (en) * 2008-05-02 2013-07-16 University Of Rochester Arrayed imaging reflectometry (air) sensor chip comprising influenza hemagglutinin (HA) polypeptides suitable for the detection of antiviral immune responses
EP2327955A1 (fr) * 2008-09-05 2011-06-01 Universidad Politécnica De Madrid Système de détection optique pour essais biologiques à haute sensibilité sans marquage
US9404872B1 (en) * 2011-06-29 2016-08-02 Kla-Tencor Corporation Selectably configurable multiple mode spectroscopic ellipsometry
CN106093429A (zh) * 2016-06-02 2016-11-09 滨州医学院 一种检测胃癌组织的试剂盒

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
GEREIGE, I. ; ROBERT, S.: "Application of neural classification in ellipsometry for robust thin-film characterizations", THIN SOLID FILMS, ELSEVIER, AMSTERDAM, NL, vol. 518, no. 15, 31 May 2010 (2010-05-31), AMSTERDAM, NL , pages 4091 - 4094, XP027035235, ISSN: 0040-6090 *
JOHS BLAINE; WOOLLAM JOHN A.; HERZINGER CRAIG M.; HILFIKER JAMES N.; SYNOWICKI RON A.; BUNGAY COREY L.: "Overview of variable-angle spectroscopic ellipsometry (VASE): II. Advanced applications", PROCEEDINGS OF SPIE, SPIE, US, vol. 10294, 19 July 1999 (1999-07-19), US , pages 1029404 - 1029404-30, XP060094736, ISBN: 978-1-5106-1533-5, DOI: 10.1117/12.351667 *
WOOLLAM JOHN A.; JOHS BLAINE D.; HERZINGER CRAIG M.; HILFIKER JAMES N.; SYNOWICKI RON A.; BUNGAY COREY L.: "Overview of variable-angle spectroscopic ellipsometry (VASE): I. Basic theory and typical applications", PROCEEDINGS OF SPIE, SPIE, US, vol. 10294, 19 July 1999 (1999-07-19), US , pages 1029402 - 1029402-26, XP060094734, ISBN: 978-1-5106-1533-5, DOI: 10.1117/12.351660 *

Similar Documents

Publication Publication Date Title
Laue et al. Morphometry of SARS-CoV and SARS-CoV-2 particles in ultrathin plastic sections of infected Vero cell cultures
Goldsmith et al. Modern uses of electron microscopy for detection of viruses
Basso et al. Classification and histological, immunohistochemical, and molecular diagnosis of inflammatory myocardial disease
Ember et al. Saliva-based detection of COVID-19 infection in a real-world setting using reagent-free Raman spectroscopy and machine learning
Schuit et al. The stability of an isolate of the SARS-CoV-2 B. 1.1. 7 lineage in aerosols is similar to 3 earlier isolates
Nguyen et al. Serological and molecular characterization of avian metapneumovirus in chickens in Northern Vietnam
Bergmann et al. Comparison of four commercially available point-of-care tests to detect antibodies against canine distemper virus in dogs
Neagu et al. Testing antigens, antibodies, and immune cells in COVID-19 as a public health topic—experience and outlines
Marques et al. Morphological alterations in tongue epithelial cells infected by SARS‐CoV‐2: A case–control study
Hailu et al. Synergetic effects of Plasmodium, hookworm, and Schistosoma mansoni infections on hemoglobin level among febrile school age children in Jawe Worda, Northwest Ethiopia
Gomez-Gonzalez et al. Optical imaging spectroscopy for rapid, primary screening of SARS-CoV-2: a proof of concept
Bizai et al. Geographic distribution of Trypanosoma cruzi genotypes detected in chronic infected people from Argentina. Association with climatic variables and clinical manifestations of Chagas disease
Paniz‐Mondolfi et al. Genomic and ultrastructural analysis of monkeypox virus in skin lesions and in human/animal infected cells reveals further morphofunctional insights into viral pathogenicity
Hamada et al. Bicentric evaluation of stabilizing sampling tubes for assessment of monocyte HLA‐DR expression in clinical samples
Smiley Evans et al. Mountain gorilla lymphocryptovirus has Epstein-Barr virus-like epidemiology and pathology in infants
Ragosta et al. Sperm chromatin dispersion test detects sperm dna fragmentation mainly associated with unviable spermatozoa and underestimates the values with respect to tunel assay
WO2022013718A1 (fr) Procédé pour classification d'échantillons biologiques en termes d'infection par des agents viraux, et utilisations
BR102020024993A2 (pt) Processo para classificação de amostras biológicas quanto a infecção por agentes virais e usos
Okolo et al. Correlative imaging using super‐resolution fluorescence microscopy and soft X‐ray tomography at cryogenic temperatures provides a new way to assess virosome solutions for vaccine development
Carossino et al. Relationship between uveal inflammation and viral detection in 30 cats with feline infectious peritonitis
Pongkunakorn et al. Immune Response after SARS-CoV-2 Infection with Residual Post-COVID Symptoms
Corredor et al. Computational pathology reveals unique spatial patterns of immune response in H&E images from COVID-19 autopsies: preliminary findings
Mulki et al. Oral rinse as a simpler approach to exfoliative cytology: A comparative study
Glaser et al. Inter-and Intra-Observer Reliability of Epstein–Barr Virus Detection in Hodgkin Lymphoma using Histochemical Procedures
Ibrahim et al. Current Technologies for Detection of COVID-19: Biosensors, Artificial Intelligence and Internet of Medical Things (IoMT)

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21842523

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21842523

Country of ref document: EP

Kind code of ref document: A1