Machine Learning Approaches to Categorize Carbonaceous Nanomaterials Based on Patterns of Inflammatory Markers and Pathological Outcomes in Lungs

Details

• Personal Author:
  Desai I ; Erdely A ; Kodali V ; Miller, William E. ; Roberts J ; Syamlal G ; Yanamala N
• Description:
  As technology advances to incorporate nanoparticles (NP) in various industries, the exposures associated with these particles also increase. Exposure to carbonaceous NPs has been found to be associated with substantial pulmonary toxicity, including inflammation, fibrosis, and/or granuloma formation. Despite several attempts made previously, grouping or categorizing NPs based on their intrinsic properties and certain inflammatory endpoints remains a challenge. The inconsistency and a large number of variables across studies considered by different groups for evaluating toxicity responses of NPs, the lack of precise understanding of the role of different NP characteristics on various biological responses, as well as missing NP data under in vivo biological conditions and pathological outcomes often the result of chronic inflammatory responses further complicates hazard ranking of NPs. This study attempts to categorize the toxicity profiles of various carbon allotropes, in particular, carbon black, different multi-walled carbon nanotubes, graphene-based materials and their derivatives. Statistical and machine learning based approaches were used to identify groups of CNMs with similar pulmonary toxicity responses from a panel of proteins measured in bronchoalveolar lavage (BAL) fluid samples and with similar pathological outcomes in the lungs. Thus, grouped particles based on their pulmonary toxicity profiles, were used to select a small set of proteins that could potentially identify and discriminate between the biological responses associated within each group. Specifically, MDC/CCL22 and MIP-3beta/CCL19 were identified as common protein markers associated with both toxicologically distinct groups of CNMs. In addition, the persistent expression of other selected protein markers in BAL fluid from each group suggested their ability to predict toxicity in the lungs, i.e., fibrosis and/or microgranuloma formation. The advantages of approaches described in this study can have positive implications for further research in toxicity profiling. [Description provided by NIOSH]
• Subjects:
  Biomarkers Chemistry Computers Hazardous Substances Lung Occupational Health Pathology Respiratory System Safety Toxicology
• Keywords:
  Artificial Intelligence Biological Effects Carbon Carbon Black Carbon Nanotubes Chemical Composition Chemical Hazards Chemical Properties CNT Emerging Technology Graphene Hazard Banding Health Effects Health Hazards Multi-walled Carbon Nanotubes MWCNT Nanoparticles Nanotechnology Proteins Pulmonary Effects Pulmonary Function Toxic Effects Toxic Materials

  More +
• ISSN:
  1096-6080
• Document Type:
  Text
• Genre:
  Abstract or Summary
• Place as Subject:
  Maryland ; Ohio ; OSHA Region 3 ; OSHA Region 5 ; West Virginia
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Division:
  HELD - Health Effects Laboratory Division
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Pages in Document:
  178-179
• Volume:
  168
• Issue:
  1
• NIOSHTIC Number:
  nn:20054919
• Citation:
  Toxicologist 2019 Mar; 168(1):178-179
• CAS Registry Number:
  Carbon (CAS RN 7440-44-0) ; Carbon black (CAS RN 1333-86-4) ; Carbon nanotubes (CAS RN 308068-56-6) ; Graphene (CAS RN 1034343-98-0)
• Federal Fiscal Year:
  2019
• NORA Priority Area:
  Manufacturing
• Peer Reviewed:
  False
• Source Full Name:
  The Toxicologist. Society of Toxicology 58th Annual Meeting and ToxExpo, March 10-14, 2019, Baltimore, Maryland
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:554727d6e1d255b4abb2c587bfa3bb2b6a3392235e633eab2ed20d387b04b77af73e0cf4e24108743bc6eb436e433821374d08b3a4d714d88d832cbf4c2ee3de
• Download URL:
  https://stacks.cdc.gov/view/cdc/217329/cdc_217329_DS1.pdf
• File Type:
  [PDF - 937.68 KB ]