Preprint · 2026 · Open access

CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group

Ryan Varghese, Pooja Tiwary, Krishil Oswal

bioRxiv (Cold Spring Harbor Laboratory) · Published 23 July 2026 · DOI 10.64898/2026.07.20.739289

Free PDFView at the publisherCite this paper

In brief

“CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group” is a 2026 preprint by Ryan Varghese and 2 co-authors, published in bioRxiv (Cold Spring Harbor Laboratory). OpenAlex counts 0 citations as of 15 November 2026. It is open access: the full text is free to read at bioRxiv (Cold Spring Harbor Laboratory).

Citations
0
References
19
Authors
3

Abstract

Accurate, generalizable prediction of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties remains one of the highest-leverage unsolved problems in computational drug discovery, and late-stage attrition driven by ADMET liabilities continues to be a dominant cost driver in pharmaceutical research and development. The Therapeutics Data Commons (TDC) ADMET Group has emerged as the field’s most widely adopted public benchmark, comprising 22 endpoints under standardized scaffold-split evaluation. In this work we report a comprehensive evaluation of CHIMIYA-1, a proprietary autoselection foundation model developed by Covenant Biosciences, against the full TDC ADMET Group. Departing from common practice in the field, every reported score is the mean and standard deviation of five independently seeded end-to-end evaluation runs (TDC’s own minimum submission standard, which we find is not met by all public leaderboard entries), and all 22 endpoints were additionally subjected to an explicit train/test structural-overlap audit prior to reporting, finding zero overlaps on any endpoint. Despite this deliberately conservative evaluation standard, CHIMIYA-1 ranks first among all publicly listed methods on four endpoints, places within the top decile of the field on twenty of twenty-two endpoints (91%), and attains a mean percentile standing near the 74th percentile across the full benchmark, with particular strength on toxicity and physicochemical-property endpoints. We further show that several top-ranked public comparators on this benchmark have been independently found to exhibit confirmed data leakage, a finding that, if anything, understates CHIMIYA-1’s relative standing. All results were obtained on commodity single-GPU workstation hardware without recourse to distributed or cloud-scale training infrastructure. We discuss these results in the context of benchmark reporting norms in molecular machine learning and outline ongoing extensions, including continuous prospective-data retraining and CUDA-level throughput optimization of the underlying selection pipeline.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Varghese, R., Tiwary, P., & Oswal, K. (2026). CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.64898/2026.07.20.739289

MLA 9

Varghese, Ryan, et al. “CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group.” bioRxiv (Cold Spring Harbor Laboratory), 2026. https://doi.org/10.64898/2026.07.20.739289.

Chicago

Varghese, Ryan, Pooja Tiwary, and Krishil Oswal. 2026. “CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group.” bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.64898/2026.07.20.739289.

Harvard

Varghese, R., Tiwary, P. and Oswal, K. (2026) ‘CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group’, bioRxiv (Cold Spring Harbor Laboratory). doi:10.64898/2026.07.20.739289.

IEEE

R. Varghese, P. Tiwary, and K. Oswal, “CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group,” bioRxiv (Cold Spring Harbor Laboratory), 2026, doi: 10.64898/2026.07.20.739289.

BibTeX

@misc{varghese2026chimiya,
  title     = {{CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group}},
  author    = {Varghese, Ryan and Tiwary, Pooja and Oswal, Krishil},
  howpublished = {bioRxiv (Cold Spring Harbor Laboratory)},
  year      = {2026},
  doi       = {10.64898/2026.07.20.739289},
  url       = {https://doi.org/10.64898/2026.07.20.739289}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods

  • molecular machine learning
  • benchmark evaluation
  • data leakage
  • toxicity prediction
  • physicochemical properties
  • drug attrition

Work with this paper

Most-cited papers in Pharmacology, Toxicology and Pharmaceutics

All highly cited Pharmacology, Toxicology and Pharmaceutics papers

Questions about this paper

How do I cite this paper in APA style?

Varghese, R., Tiwary, P., & Oswal, K. (2026). CHIMIYA-1: An Autoselection Foundation Model for ADMET Property Prediction, Rigorously Benchmarked Against the Therapeutics Data Commons ADMET Group. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.64898/2026.07.20.739289

How many times has this paper been cited?

0 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at bioRxiv (Cold Spring Harbor Laboratory).

Who wrote this paper?

Ryan Varghese, Pooja Tiwary, Krishil Oswal.

What is the DOI of this paper?

10.64898/2026.07.20.739289. The permanent link is https://doi.org/10.64898/2026.07.20.739289.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.