Advancing Environmental Health Research with Artificial Intelligence and Machine Learning: Session I — AI & ML Applications to Understand Chemical Mixtures, Properties, and Exposures and Their Relationship to Human Health

The NIEHS Superfund Research Program (SRP) is hosting a Risk e-Learning webinar series focused on using artificial intelligence (AI) and machine learning to advance environmental health research. The series will feature SRP-funded researchers, collaborators, and other subject-matter experts who aim to better understand and address environmental health issues by applying AI and machine learning approaches to complex issues.

Recent advances in AI and machine learning methods show promise to improve the accuracy and efficiency of environmental health research. Over the course of three sessions, presenters will discuss how they use AI and machine learning approaches to improve chemical analysis, characterize chemical risk, understand microbial ecosystems, develop technologies for contaminant removal, and more.

In the first session, AI & ML Applications to Understand Chemical Mixtures, Properties, and Exposures and their Relationship to Human Health, speakers will discuss how they apply machine learning and artificial intelligence techniques to understand chemical exposures and their effects on human health.

To learn about and register for the other sessions in this webinar series, please see the SRP website.

Naomi Halas, Ph.D., and Ankit Patel, Ph.D., will share updates on their work combining surface-enhanced spectroscopies (Raman and Infrared Absorption) with machine learning algorithms with the goal of developing simple and ultimately low-cost methods for the detection and identification of environmental toxins. As part of their discussion, they will share several approaches, including the use of machine learning algorithms to detect individual constituents in complex mixtures and the use of facial recognition strategies to identify specific chemical toxins in human placenta.

Jacob Kvasnicka, Ph.D., will present on a project he supported while he was a postdoctoral researcher at Texas A&M University SRP Center's Risk and Geospatial Sciences Core. There, his work involved developing an ML framework for predicting safe exposure levels to chemicals to avoid cancerous and reproductive/developmental effects. Most chemicals lack toxicity data related to human health, and this study uses ML to fill this gap, greatly expanding the ability to characterize chemical risks and impacts.

Trey Saddler will give attendees an overview of ToxPipe — a platform for performing retrieval augmented generation (RAG) over toxicological data. Comprised of a web interface, agentic workflows, and connections to various data sources, ToxPipe enables toxicologists to explore diverse datasets and generate toxicological narratives for a wide range of compounds.

Speakers:

• Naomi Halas, Ph.D., and Ankit Patel, Ph.D., Rice University
• Jacob Kvasnicka, Ph.D., U.S. Environmental Protection Agency
• Trey Saddler, NIEHS, Division of Translational Toxicology
• Moderator: David Reif, Ph.D., NIEHS, Division of Translational Toxicology

Naomi Halas, PhD, Rice University (halas@rice.edu)
Naomi J. Halas, Ph.D., is a University Professor and the Stanley C. Moore Professor of Electrical and Computer Engineering. She is a former Director of the Smalley-Curl Institute. Halas is best known for showing that the nanoscale internal and external morphology of noble metal nanoparticles controls their optical properties. Her work has been the force that merged chemical nanofabrication with optics, giving rise to the field of plasmonics. She pursues fundamental studies of coupled plasmonic systems as well as applications of plasmonics in many fields, including biomedicine, optoelectronics, chemical sensing, solar steam generation and water treatment, and plasmonic photocatalysis.

Ankit Patel, PhD, Rice University (ankit.patel@rice.edu)
Ankit B. Patel, Ph.D., is currently an Assistant Professor at the Baylor College of Medicine in the Department of Neuroscience, and at Rice University in the Department of Electrical and Computer Engineering. Ankit is broadly interested in the intersection between ML and computational neuroscience, two research areas that are essential for understanding and building truly intelligent systems, with a focus on learning abstractions.

Jacob Kvasnicka, PhD, U.S. EPA (kvasnicka.jacob@epa.gov)
Jacob Kvasnicka is a postdoctoral researcher in the U.S. EPA's Center for Computational Toxicology and Exposure. He obtained a Master of Science in Environmental Health Sciences from the University of Michigan, where he developed a probabilistic human health risk assessment for the Hudson River PCBs Superfund Site. Jacob then investigated impacts of human behaviors and indoor microenvironments on chemical exposures while completing his Ph.D. at the University of Toronto. After earning his Ph.D., he joined Texas A&M University as a postdoctoral researcher in the SRP Center Risk and Geospatial Sciences Core until 2024. There, he developed an ML framework for predicting safe exposure levels to chemicals for general noncancer and reproductive/developmental effects.

Trey Saddler, MS, NIEHS, Division of Translational Toxicology (trey.saddler@nih.gov)
Trey Saddler, M.S., developed ToxPipe: Semi-Autonomous AI Integration of Diverse Toxicological Data Streams. His latest work uses generative AI and retrieval augmented generation to analyze multiomic toxicological data. He works with scientists to extract, clean, transform, analyze, and visualize data using Shiny, Quarto, and other scientific publishing methods. He also helps automate analysis pipelines, interact with biological active pharmaceutical ingredients (APIs), and store and retrieve data in relational and non-relational databases. His interests include FAIR data sharing principles, clean and reusable metadata, and discoverable data sets. He earned his master's degree in data analytics at Western Governors University.

Moderator:

David Reif, PhD, NIEHS, Division of Translational Toxicology (david.reif@nih.gov)
David Reif, Ph.D., is the Chief of the Predictive Toxicology Branch in the Division of Translational Toxicology. There, he leverages the expertise of the branch in data science, toxicogenomics, spatiotemporal exposures and toxicology, computational methods development, and new approach methods to advance predictive toxicology applications with partners across NIEHS, the interagency Tox21 Program, and the Interagency Coordinating Committee on the Validation of Alternative Methods. Previously, Reif was a professor of bioinformatics at North Carolina State University in the Department of Biological Sciences. He earned his master’s in applied statistics and his doctoral degree in human genetics from Vanderbilt University. He also completed postdoctoral training in exposure science and computational toxicology at the U.S EPA.

• Slide Presentation for Naomi Halas and Ankit Patel, Rice University (6.67MB/PDF)
• Slide Presentation for Jacob Kvasnicka, U.S. EPA (2.17MB/PDF)
• Slide Presentation for Trey Saddler NIEHS (8.07MB/PDF)

Webinar Slides and References:

• Slide Presentation for Naomi Halas and Ankit Patel, Rice University (6.67MB/PDF)
• Slide Presentation for Jacob Kvasnicka, U.S. EPA (2.17MB/PDF)
• Slide Presentation for Trey Saddler NIEHS (8.07MB/PDF)

Additional Resources:

• Article: "Two-Stage Machine Learning-Based Approach to Predict Points of Departure for Human Noncancer and Developmental/Reproductive Effects" (Jacob Kvasnicka)
• Two Stage Machine Learning Point of Departure Shiny App Browser (Jacob Kvasnicka)

Thank you for participating in our webinar. We would like to receive any feedback you might have that would make this service more valuable.

Date of Seminar:

 November 4, 2024: Advancing Environmental Health Research with Artificial Intelligence and Machine Learning: Session I — AI & ML Applications to Understand Chemical Mixtures, Properties, and Exposures and Their Relationship to Human Health

Instructor Comments	Disagree	Neutral	Agree
I had trouble hearing the instructor
The instructors are knowledgeable of the subject matter
I could easily follow the instructor's presentation and slides
Ample time was allowed for Q&A
Presentation Content	Disagree	Neutral	Agree
I learned a great deal from this presentation
The content was too simplified
The presentation was too long
Will you recommend this seminar to other environmental professionals?		Yes No

What additional subject matter or changes should be made to this seminar?

Did this seminar meet your needs?
Are you likely to participate in the future?
Why or why not?

Additional comments or technical difficulties encountered:

First Name:

Last Name:

Organization:

Organization Type:

State/Local GovernmentU.S. EPAU.S. DODU.S. DOEOther Federal AgencyConsultant/Engineering FirmCommunity StakeholderSite OwnerTechnology VendorAcademiaTribal GovernmentsPressTesting LaboratoryOther

EPA Office:

NHSRCOAOAROARMOCFOOCSPPOECAOEIOGCOIGOITAOLEMOPORDORD-NCEAOtherOWR01R02R03R04R05R06R07R08R09R10

City:

State:

Select State AKALARAZCACOCTDCDEFLGAGUHIIAIDILINKSKYLAMAMDMEMIMNMOMSMTNCNDNENHNJNMNVNYOHOKORPAPRRISCSDTNTXUTVAVIVTWAWIWVWY

Country:

Select Country AfghanistanAlbaniaAlgeriaAndorraAngolaAnguillaAntigua and BarbudaArgentinaArmeniaArubaAshmore and Cartier IslandsAustraliaAustriaAzerbaijanBahamas, TheBahrainBangladeshBarbadosBassas Da IndiaBelarusBelgiumBelizeBeninBermudaBhutanBoliviaBosnia and HerzegovinaBotswanaBouvet IslandBrazilBritish Indian Ocean TerritoryBritish Virgin IslandsBruneiBulgariaBurkina FasoBurmaBurundiCambodiaCameroonCanadaCape VerdeCayman IslandsCentral African RepublicChadChileChinaChristmas IslandClipperton IslandCocos (Keeling) IslandsColombiaComorosCongoCongo, Democratic Republic of TheCook IslandsCoral Sea IslandsCosta RicaCôte D'IvoireCroatiaCubaCyprusCzech RepublicDenmarkDjiboutiDominicaDominican RepublicEcuadorEgyptEl SalvadorEquatorial GuineaEritreaEstoniaEthiopiaEuropa IslandFalkland Islands (Islas Malvinas)Faroe IslandsFijiFinlandFranceFrench GuianaFrench PolynesiaFrench Southern and Antarctic LandsGabonGambia, TheGaza StripGeorgiaGermanyGhanaGibraltarGlorioso IslandsGreeceGreenlandGrenadaGuadeloupeGuatemalaGuernseyGuineaGuinea-BissauGuyanaHaitiHeard Island and Mcdonald IslandsHondurasHong KongHungaryIcelandIndiaIndonesiaIranIraqIrelandIsle of ManIsraelItalyJamaicaJan MayenJapanJerseyJordanJuan De Nova IslandKazakhstanKenyaKiribatiKuwaitKyrgyzstanLaosLatviaLebanonLesothoLiberiaLibyaLiechtensteinLithuaniaLuxembourgMacauMacedonia, The Former Yugoslav Republic ofMadagascarMalawiMalaysiaMaldivesMaliMaltaMarshall IslandsMartiniqueMauritaniaMauritiusMayotteMexicoMicronesia, Federated States ofMoldovaMonacoMongoliaMontenegroMontserratMoroccoMozambiqueNamibiaNauruNepalNetherlandsNetherlands AntillesNew CaledoniaNew ZealandNicaraguaNigerNigeriaNiueNo Man'S LandNorfolk IslandNorth KoreaNorwayOceansOmanPakistanPalauPanamaPapua New GuineaParacel IslandsParaguayPeruPhilippinesPitcairn IslandsPolandPortugalQatarReunionRomaniaRussiaRwandaSaint HelenaSaint Kitts and NevisSaint LuciaSaint Pierre and MiquelonSaint Vincent and The GrenadinesSamoaSan MarinoSao Tome and PrincipeSaudi ArabiaSenegalSerbiaSeychellesSierra LeoneSingaporeSlovakiaSloveniaSolomon IslandsSomaliaSouth AfricaSouth Georgia and The South Sandwich IslandsSouth KoreaSpainSpratly IslandsSri LankaSudanSurinameSvalbardSwazilandSwedenSwitzerlandSyriaTaiwanTajikistanTanzaniaThailandTogoTokelauTongaTrinidad and TobagoTromelin IslandTunisiaTurkeyTurkmenistanTurks and Caicos IslandsTuvaluUgandaUkraineUndersea FeaturesUnited Arab EmiratesUnited KingdomUnited StatesUruguayUzbekistanVanuatuVatican CityVenezuelaVietnamVirgin IslandsWallis and FutunaWest BankWestern SaharaYemenZambiaZimbabwe

Phone:

Email:

 I certify that I attended this live seminar or viewed the archive in its entirety. Please send a participation certificate and feedback confirmation to this address.

Help & FAQs

• Frequently Asked Questions
• Content Questions?
  Call Dylan Williams at 202-982-5717 or dylan.williams@nih.gov
• Technical Problems?
  Leave us a comment
• Cancel Your Registration
• My Participation Records
• CEU Credits and PDHs

Zoom Resources

This seminar will be delivered through Zoom. Participants are encouraged to update to the latest version of the Zoom application for the best experience. If you are unable to install the Zoom application, most functions will be available if you join just using a modern web browser such as Chrome, Edge or Firefox. We strongly encourage you to run the Zoom Meeting Test prior to attending this seminar. Technical support on the day of the seminar will be very limited and subject to significant delays.

Rehabilitation Act Notice for Reasonable Accommodation

It is EPA's policy to make reasonable accommodation to persons with disabilities wishing to participate in the agency's programs and activities, pursuant to the Rehabilitation Act of 1973, 29 U.S.C. 791. Any request for accommodation should be made to at or , preferably one week or more in advance of the seminar, so that EPA will have sufficient time to process the request. EPA would welcome specific recommendations from requestors specifying the nature or type of accommodation needed. EPA welcomes specific recommendations from requestors specifying the nature or type of accommodation needed. Please note that CLU-IN provides both alternate phone call-in options and closed captioning for all webinars, and requests for these specific accommodations are not necessary.

Rehabilitation Act Notice for Reasonable Accommodation

It is EPA's policy to make reasonable accommodation to persons with disabilities wishing to participate in the agency's programs and activities, pursuant to the Rehabilitation Act of 1973, 29 U.S.C. 791. Any request for accommodation should be made to at or , preferably one week or more in advance of the webinar, so that EPA will have sufficient time to process the request. EPA would welcome specific recommendations from requestors specifying the nature or type of accommodation needed. EPA welcomes specific recommendations from requestors specifying the nature or type of accommodation needed. Please note that CLU-IN provides both alternate phone call-in options and closed captioning for all webinars, and requests for these specific accommodations are not necessary.

Webinar Recording

By participating in this CLU-IN webinar, you automatically agree to authorize recording of audio and visual content presented during this live event and consent to subsequent use of this recording in the public domain by the U.S. Environmental Protection Agency. This recording may include questions, comments and poll responses provided by you during the live event in addition to your name, voice, image or likeness. This recording will be made available after the conclusion of the live event as part of the CLU-IN webinar archives, and will remain available indefinitely. If you do not wish to consent to the recording, please do not join the live event, and contact Jean Balent at 202-566-0832 or balent.jean@epa.gov to discuss your concerns.

Content Disclaimer

This webinar is intended solely to provide information to the public. The views and opinions expressed as part of this webinar do not necessarily state or reflect those of the U.S. Environmental Protection Agency. It is not intended, nor can it be relied upon, to create any rights enforceable by any party in litigation with the United States, or to endorse the use of products or services provided by specific vendors. With respect to this webinar, neither the United States Government nor any of their employees, makes any warranty, express or implied, including the warranties of merchantability and fitness for a particular purpose, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights.