May Yong

May Yong

Auto-generated profile, based on publicly available information

May Yong

Alan Turing Institute, London, UK

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
9 April 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
XXXiaodan Xing
Xiaodan Xing
HWHuanjun Wu
Huanjun Wu
LWLichao Wang
Lichao Wang
ISIain Stenson
Iain Stenson
MYMay Yong
May Yong
Guang YangGuang Yang
Guang Yang
Data quality is a key factor in the development of trustworthy AI in healthcare. A large volume of curated datasets with controlled confounding factors can improve the accuracy, robustness, and privacy of downstream AI algorithms. However, access to high-quality datasets is limited by the technical difficulties of data acquisition, and large-scale sharing of healthcare data is hindered by strict ethical restrictions. Data synthesis algorithms, which generate data with distributions similar to real clinical data, can serve as a potential solution to address the scarcity of good quality data during the development of trustworthy AI. However, state-of-the-art data synthesis algorithms, especially deep learning algorithms, focus more on imaging data while neglecting the synthesis of non-imaging healthcare data, including clinical measurements, medical signals and waveforms, and electronic healthcare records (EHRs). Therefore, in this article, we will review synthesis algorithms, particularly for non-imaging medical data, with the aim of providing trustworthy AI in this domain. This tutorial-style review article will provide comprehensive descriptions of non-imaging medical data synthesis, covering aspects such as algorithms, evaluations, limitations, and future research directions.

1 March 2013 in mAbs
Verified
Journal Article
Open access
PKPeter-Christian Klöhn
Peter-Christian Klöhn
UWUlrich Wuellner
Ulrich Wuellner
NZNora Zizlsperger
Nora Zizlsperger
YZYu Zhou
Yu Zhou
DTDaniel Tavares
Daniel Tavares
JRJanice M Reichert
Janice M Reichert
The 23rd Annual Antibody Engineering, 10th Annual Antibody Therapeutics international conferences, and the 2012 Annual Meeting of The Antibody Society, organized by IBC Life Sciences with contributions from The Antibody Society and two Scientific Advisory Boards, were held December 3–6, 2012 in San Diego, CA. The meeting drew over 800 participants who attended sessions on a wide variety of topics relevant to antibody research and development. As a prelude to the main events, a pre-conference workshop held on December 2, 2012 focused on intellectual property issues that impact antibody engineering. The Antibody Engineering Conference was composed of six sessions held December 3–5, 2012: (1) From Receptor Biology to Therapy; (2) Antibodies in a Complex Environment; (3) Antibody Targeted CNS Therapy: Beyond the Blood Brain Barrier; (4) Deep Sequencing in B Cell Biology and Antibody Libraries; (5) Systems Medicine in the Development of Antibody Therapies/Systematic Validation of Novel Antibody Targets; and (6...

1 March 2009 in Protein Engineering, Design and Selection
Verified
Journal Article
Open access
PDF file
MYM. Yong
M. Yong
BTB. Tolner
B. Tolner
SNS. Nagl
S. Nagl
RPR.B. Pedley
R.B. Pedley
KCK. Chester
K. Chester
RBR. Begent
R. Begent
Research groups developing antibody therapies generate diverse data sets; the value of these sets would be compounded when shared or amalgamated. A complete amalgamation of diverse data sets requires data standards for information collection during experiments. We propose to define elements of the data standards in the form of common data elements (CDEs) in order to clarify each experiment’s targets and data values. We have created a set of core information elements which we suggest should be collected from antibody therapy experiments. We propose these as a basis for community consultation with a view to defining a set of data standards which can be developed under the auspices of the Antibody Society.

13 December 2016 in Bioinformatics
Verified
Journal Article
Closed access
PDF file
SHSijin He
Sijin He
MYMay Yong
May Yong
PMPaul M. Matthews
Paul M. Matthews
YGYike Guo
Yike Guo
Motivation: TranSMART has a wide range of functionalities for translational research and a large user community, but it does not support imaging data. In this context, imaging data typically includes 2D or 3D sets of magnitude data and metadata information. Imaging data may summarise complex feature descriptions in a less biased fashion than user defined plain texts and numeric numbers. Imaging data also is contextualised by other data sets and may be analysed jointly with other data that can explain features or their variation. Results: Here we describe the tranSMART-XNAT Connector we have developed. This connector consists of components for data capture, organisation and analysis. Data capture is responsible for imaging capture either from PACS system or directly from an MRI scanner, or from raw data files. Data are organised in a similar fashion as tranSMART and are stored in a format that allows direct analysis within tranSMART. The connector enables selection and download of DICOM images and associated resources using subjects’ clinical phenotypic and genotypic criteria. Availability and Implementation: tranSMART-XNAT connector is written in Java/Groovy/Grails. It is maintained and available for download at https://github.com/sh107/transmart-xnat-connector.git Contact:sijin@ebi.ac.uk

6 January 2012 in BMC Research Notes
Verified
Journal Article
Open access
PDF file
AGAlejandra N González-Beltrán
Alejandra N González-Beltrán
MYMay Y Yong
May Y Yong
GDGairin Dancey
Gairin Dancey
RBRichard Begent
Richard Begent
Biology, biomedicine and healthcare have become data-driven enterprises, where scientists and clinicians need to generate, access, validate, interpret and integrate different kinds of experimental and patient-related data. Thus, recording and reporting of data in a systematic and unambiguous fashion is crucial to allow aggregation and re-use of data. This paper reviews the benefits of existing biomedical data standards and focuses on key elements to record experiments for therapy development. Specifically, we describe the experiments performed in molecular, cellular, animal and clinical models. We also provide an example set of elements for a therapy tested in a phase I clinical trial.

2 September 2016 in F1000Research
Verified
Journal Article
Open access
PDF file
MWMatthew B. Wall
Matthew B. Wall
DBDavid Birch
David Birch
MYMay Y. Yong
May Y. Yong
Neuroimaging experiments can generate impressive volumes of data and many images of the results. This is particularly true of multi-modal imaging studies that use more than one imaging technique, or when imaging is combined with other assessments. A challenge for these studies is appropriate visualisation of results in order to drive insights and guide accurate interpretations. Next-generation visualisation technology therefore has much to offer the neuroimaging community. One example is the Imperial College London Data Observatory; a high-resolution (132 megapixel) arrangement of 64 monitors, arranged in a 313 degree arc, with a 6 metre diameter, powered by 32 rendering nodes. This system has the potential for high-resolution, large-scale display of disparate data types in a space designed to promote collaborative discussion by multiple researchers and/or clinicians. Opportunities for the use of the Data Observatory are discussed, with particular reference to applications in Multiple Sclerosis (MS) research and clinical practice. Technical issues and current work designed to optimise the use of the Data Observatory for neuroimaging are also discussed, as well as possible future research that could be enabled by the use of the system in combination with eye-tracking technology.