US-FED-00000385678 - Annual subscription of Chemical Abstracts Service (CAS) BioFinder Discovery Platform Software License - Deadline July 15,2026

Pre–Solicitation Notice Notice of Intent to award on a Single Source BasisTitle: Notice of Intent to Award a Single Source Purchase Order for an annual subscription of a Chemical Abstracts Service (CAS) BioFinder Discovery Platform Software License, a computational platform that can predict thousands of biological targets for chemicals, is accessed via the Internet, and interfaces with CAS SciFinder, a database of over 100 million chemicals and already in use by the FDA.Notice Number: NOI_REQT–OMAS–IT–202600119Agency: Department of Health and Human Services (HHS), Food and Drug Administration (FDA) Division of ToxicologyContracting Office: HHS Office of Mission Acquisition SolutionsProduct Service Code (PSC): OC code 6632 / PCS Code 10 (Analysis Instruments, Medical Laboratory Use)NAICS Code: 513210 (Software Publishers)Place of Performance: HHS/FDA, 8301 Muirkirk Road, Laurel, MD 20708Set Aside: Not Applicable (Single Source)Response Date: 07/15/2026 5:00 PM MSTDescriptionThis is a Notice of Intent to negotiate on a sole source basis for a firm–fixed–price purchase order to American Chemical Society, 2540 Olentangy River Road, Columbus, OH 43202HHS/FDA has a requirement for purchase of an annual software license. The Chemical Abstracts Service (CAS) BioFinder Discovery Platform is the only platform that meets all of the FDA Division of Toxicology`s technical requirements for advancing food chemical safety research and implementing New Approach Methodologies (NAMs).Period of Performance: 09/01/2026 08/31/2027Requirement Details:Prediction of biological targets for chemicals based on a training set of over 1 million compoundsKnown and predicted quantitative binding and functional activity for at least 3,600 targetsTarget binding prediction by at least 6 independent methods (SAS, SAR, SIM, SEA, MLM, and XPI)Confidence scores for predicted interactions using consensus approachMetabolite prediction using manually curated training dataset