A methodology to correctly assess the applicability domain of cell membrane permeability predictors for cyclic peptides

Author:

Geylan Gökçe12ORCID,De Maria Leonardo3ORCID,Engkvist Ola14ORCID,David Florian2,Norinder Ulf567

Affiliation:

1. Molecular AI, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden

2. Division of Systems and Synthetic Biology, Department of Life Sciences, Chalmers University of Technology, Gothenburg, Sweden

3. Medicinal Chemistry, Research and Early Development, Respiratory & Immunology, BioPharmaceuticals R&D, AstraZeneca, Gothenburg, Sweden

4. Department of Computer Science and Engineering, Chalmers University of Technology and University of Gothenburg, Gothenburg, Sweden

5. Department of Computer and Systems Sciences, Stockholm University, Kista, Sweden

6. MTM Research Centre, School of Science and Technology, Örebro University, Örebro, Sweden

7. Department of Pharmaceutical Biosciences, Uppsala University, Uppsala, Sweden

Abstract

This work outlines peptide predictive model methodology with conformal prediction, focusing on extrapolation task. Calibrating on the unseen chemical space recovers efficiency and validity enabling reliable predictions without retraining the models.

Funder

Stiftelsen för Strategisk Forskning

Publisher

Royal Society of Chemistry (RSC)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3