Aikaterini Vriza

Aikaterini Vriza

Auto-generated profile, based on publicly available information

Aikaterini Vriza

Nanoscience and Technology Division, Argonne National Laboratory, Lemont, USA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 February 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
CWChengshi Wang
Chengshi Wang
YKYeon-Ju Kim
Yeon-Ju Kim
AVAikaterini Vriza
Aikaterini Vriza
RBRohit Batra
Rohit Batra
ABArun Baskaran
Arun Baskaran
JXJie Xu
Jie Xu
The manipulation of electronic polymers’ solid-state properties through processing is crucial in electronics and energy research. Yet, efficiently processing electronic polymer solutions into thin films with specific properties remains a formidable challenge. We introduce Polybot, an artificial intelligence (AI) driven automated material laboratory designed to autonomously explore processing pathways for achieving high-conductivity, low-defect electronic polymers films. Leveraging importance-guided Bayesian optimization, Polybot efficiently navigates a complex 7-dimensional processing space. In particular, the automated workflow and algorithms effectively explore the search space, mitigate biases, employ statistical methods to ensure data repeatability, and concurrently optimize multiple objectives with precision. The experimental campaign yields scale-up fabrication recipes, producing transparent conductive thin films with averaged conductivity exceeding 4500 S/cm. Feature importance analysis and morphological characterizations reveal key design factors. This work signifies a significant step towards transforming the manufacturing of electronic polymers, highlighting the potential of AI-driven automation in material science.

7 November 2023 in Digital Discovery
Verified
Journal Article
Open access
PDF file
RVRafael Vescovi
Rafael Vescovi
TGTobias Ginsburg
Tobias Ginsburg
KHKyle Hippe
Kyle Hippe
DODoga Y. Ozgulbas
Doga Y. Ozgulbas
CSCasey Stone
Casey Stone
IFIan Foster
Ian Foster
Advances in robotic automation, high-performance computing, and artificial intelligence encourage us to propose large, general-purpose science factories with the scale needed to tackle large discovery problems and to support thousands of scientists.

29 September 2022 in Digital Discovery
Verified
Journal Article
Open access
PDF file
AVAikaterini Vriza
Aikaterini Vriza
ISIoana Sovago
Ioana Sovago
DWDaniel Widdowson
Daniel Widdowson
VKVitaliy Kurlin
Vitaliy Kurlin
PWPeter A. Wood
Peter A. Wood
MDMatthew S. Dyer
Matthew S. Dyer
In this paper we introduce molecular set transformer, a Pytorch-based deep learning architecture designed for solving the molecular pair scoring task whilst tackling the class imbalance problem observed on datasets extracted from databases reporting only successful synthetic attempts. Our models are being trained on all the existing molecular pairs that form co-crystals and are deposited in the Cambridge Structural Database (CSD). Given any new molecular combination, the primary objective of the tool is to be able to select the most effective way to represent the pair and then assign a score coupled with an uncertainty estimation. Molecular set transformer is an attention-based framework which learns the important interactions in the various molecular combinations by trying to reconstruct its input by minimizing its bidirectional loss. Several methods to represent the input were tested, both fixed and learnt, with the Graph Neural Network (GNN) and the Extended-Connectivity Fingerprints (ECFP4) molecular representations to perform best showing an overall accuracy higher than 75% on previously unseen data. The trustworthiness of the models is enhanced by adding uncertainty estimates which aims to help chemists prioritize at the early materials design stage both the pairs with high scores and low uncertainty and pairs with low scores and high uncertainty. Our results indicate that the method can achieve comparable or better performance on specific APIs for which the accuracy of other computational chemistry and machine learning tools is reported in the literature. To help visualize and get further insights of all the co-crystals deposited in CSD, we developed an interactive browser-based explorer (https://csd-cocrystals.herokuapp.com/). An online Graphical User Interface (GUI) has also been designed for enabling the wider use of our models for rapid in silico co-crystal screening reporting the scores and uncertainty of any user given molecular pair (https://share.streamlit.io/katerinavr/streamlit/app.py).

8 December 2020 in Chemical Science
Verified
Journal Article
Open access
PDF file
AVAikaterini Vriza
Aikaterini Vriza
ACAngelos B. Canaj
Angelos B. Canaj
RVRebecca Vismara
Rebecca Vismara
LCLaurence J. Kershaw Cook
Laurence J. Kershaw Cook
TMTroy D. Manning
Troy D. Manning
MRMatthew J. Rosseinsky
Matthew J. Rosseinsky
The implementation of machine learning models has brought major changes in the decision-making process for materials design. One matter of concern for the data-driven approaches is the lack of negative data from unsuccessful synthetic attempts, which might generate inherently imbalanced datasets. We propose the application of the one-class classification methodology as an effective tool for tackling these limitations on the materials design problems. This is a concept of learning based only on a well-defined class without counter examples. An extensive study on the different one-class classification algorithms is performed until the most appropriate workflow is identified for guiding the discovery of emerging materials belonging to a relatively small class, that being the weakly bound polyaromatic hydrocarbon co-crystals. The two-step approach presented in this study first trains the model using all the known molecular combinations that form this class of co-crystals extracted from the Cambridge Structural Database (1722 molecular combinations), followed by scoring possible yet unknown pairs from the ZINC15 database (21 736 possible molecular combinations). Focusing on the highest-ranking pairs predicted to have higher probability of forming co-crystals, materials discovery can be accelerated by reducing the vast molecular space and directing the synthetic efforts of chemists. Further on, using interpretability techniques a more detailed understanding of the molecular properties causing co-crystallization is sought after. The applicability of the current methodology is demonstrated with the discovery of two novel co-crystals, namely pyrene-6H-benzo[c]chromen-6-one (1) and pyrene-9,10-dicyanoanthracene (2).

14 July 2023 in Materials Horizons
Verified
Journal Article
Closed access
PDF file
MLMingwan Leng
Mingwan Leng
NKNandu Koripally
Nandu Koripally
JHJunjie Huang
Junjie Huang
AVAikaterini Vriza
Aikaterini Vriza
KLKyeong Yeon Lee
Kyeong Yeon Lee
LFLei Fang
Lei Fang
Ladder-type structures can impart exceptional stability to polymeric electronic materials. This article introduces a new class of conductive polymers featuring a fully ladder-type backbone. A judicious molecular design strategy enables the synthesis of a low-defect ladder polymer, which can be efficiently oxidized and acid-doped to achieve its conductive state. The structural elucidation of this polymer and the characterization of its open-shell nature are facilitated with the assistance of studies on small molecular models. An autonomous robotic system is used to optimize the conductivity of the polymer thin film, achieving over 7 mS cm−1. Impressively, this polymer demonstrates unparalleled stability in strong acid and under harsh UV-irradiation, significantly surpassing commercial benchmarks like PEDOT:PSS and polyaniline. Moreover, it displays superior durability across numerous redox cycles as the active material in an electrochromic device and as the pseudocapacitive material in a supercapacitor device. This work provides structural design guidance for durable conductive polymers for long-term device operation.

26 November 2025 in Nature Materials
Verified
Journal Article
Closed access
PDF file
WLWei Liu
Wei Liu
CZCheng Zhang
Cheng Zhang
ZZZhiming Zhang
Zhiming Zhang
YLYang Li
Yang Li
SWShinya Wai
Shinya Wai
SWSihong Wang
Sihong Wang