Computer science

PCCFD - Predictive Complex Computational Fluid Dynamics

-

B9 L2 H1

The PCCFD workshop will focus on cutting-edge research in the field of algorithmic development for CFD and multi-scale complex flow simulations.

Reproducibility in Computer Science - Part 1

-

B9 L3 R3223

Roy Maxion will give three lectures focusing broadly on different aspects of an increasingly important topic: reproducibility. Reproducibility tests the reliability of an experimental result and is one of the foundations of the entire scientific enterprise. We often hear that certain foods are good for you, and a few years later we learn that they're not. A series of results in cancer research was examined to see if they were reproducible. A startling number of them - 47 out of 53 - were not. Matters of reproducibility are now cropping up in computer science, and given the importance of computing in the world, it's essential that our own results are reproducible -- perhaps especially the ones based on complex models or data sets, and artificial intelligence or machine learning. This lecture series will expose attendees to several issues in ensuring reproducibility, with the goal of teaching students (and others) some of the crucial aspects of making their own science reproducible. Hint: it goes much farther than merely making your data available to the public.

Reproducibility in Computer Science - Part 2

-

B9 L3 R3223

Roy Maxion will give three lectures focusing broadly on different aspects of an increasingly important topic: reproducibility. Reproducibility tests the reliability of an experimental result and is one of the foundations of the entire scientific enterprise. We often hear that certain foods are good for you, and a few years later we learn that they're not. A series of results in cancer research was examined to see if they were reproducible. A startling number of them - 47 out of 53 - were not. Matters of reproducibility are now cropping up in computer science, and given the importance of computing in the world, it's essential that our own results are reproducible -- perhaps especially the ones based on complex models or data sets, and artificial intelligence or machine learning. This lecture series will expose attendees to several issues in ensuring reproducibility, with the goal of teaching students (and others) some of the crucial aspects of making their own science reproducible. Hint: it goes much farther than merely making your data available to the public.

Reproducibility in Computer Science - Part 3

-

B9 L3 R3223

Roy Maxion will give three lectures focusing broadly on different aspects of an increasingly important topic: reproducibility. Reproducibility tests the reliability of an experimental result and is one of the foundations of the entire scientific enterprise. We often hear that certain foods are good for you, and a few years later we learn that they're not. A series of results in cancer research was examined to see if they were reproducible. A startling number of them - 47 out of 53 - were not. Matters of reproducibility are now cropping up in computer science, and given the importance of computing in the world, it's essential that our own results are reproducible -- perhaps especially the ones based on complex models or data sets, and artificial intelligence or machine learning. This lecture series will expose attendees to several issues in ensuring reproducibility, with the goal of teaching students (and others) some of the crucial aspects of making their own science reproducible. Hint: it goes much farther than merely making your data available to the public.

Knowledge-based methods in life sciences

-

B9 L2 H2 R2325

In my research I aim to understand how formalized knowledge bases can be used to systematically structure and integrate biological knowledge, and how to utilize these formalized knowledge bases as background knowledge to improve scientific discovery in biology and biomedicine. To achieve these aims, I develop methods for representing, integrating, and analyzing data and knowledge with the specific aim to make the combination of data and formalized knowledge accessible to data analytics and machine learning in bioinformatics. Biomedicine, and life sciences in general, are an ideal domain for knowledge-driven data analysis methods due to the large number of formal knowledge bases that have been developed to capture the broad, diverse, and heterogeneous data and knowledge.

On Studying Computer Science - 2020-03-16

-

KAUST

In this talk, I will discuss a wide range of ideas on studying computer science and doing research in computer science. Peter Wonka is the program chair of the computer science program. His research interests are deep learning, computer graphics, computer vision, and remote sensing.

Situational Awareness and Decision-Making Support for Crowd Management in Mina, A Grand Challenge Project Funded by the Ministry of Education

-

KAUST

Recent real disastrous crowd incidents have shown that crowded places can be exposed to significant safety dangers and that the presence of many pedestrians can potentially result in injuries and fatalities at large scales if not planned and managed reasonably. This fact has resulted in significant challenges for managing the safety of large volumes of pedestrians in dense areas. In retrospect, many such real crowd disasters could have been avoided with better crowd management. Better tools and methodologies to predict crowd behavior during planning for potential emergencies would enable authorities to plan and prepare for improved public safety in crowded environments. Better still, real-time management of crowds might avert disasters if live event data could be used to make rapid predictions of crowd dynamics over the immediate future, allowing management to be optimized as an event unfolds. Such tools do not yet exist, and the technical demands of creating them are not trivial; they will require innovative approaches to both empirical research and modeling.

On Studying Computer Science - 2020-09-07

-

KAUST

The talk will be pre-recorded and a youtube link will be provided to seminar participants. During the seminar time, Prof. Wonka will mainly answer some questions from the audience.

CBRC Dual Seminar - Analysis of COVID-19 Severity - DeepSVP computational method

Sakhaa Al-Saedi, PhD Student; Azza Althagafi, PhD Student

-

KAUST

Sakhaa Al-Saedi: We conduct a systematic genetic analysis of risk variants related to increasing the severity of COVID-19. It leads to a better understanding of its genetic basis and identifies the host genes to be targeted to tackle the COVID-19 pandemic and reduce its death toll. Azza Althagafi: We developed DeepSVP, a computational method to prioritize structural variants involved in genetic diseases by combining genomic and gene functions information. DeepSVP significantly improves the success rate of finding causative variants in several benchmarks and can identify novel pathogenic structural variants in consanguineous families.

RC3 Advisory Board Distinguished Lectures Workshop

RC3 Advisory Board

-

B5 L5 R5220

Machine learning (ML) has witnessed remarkable advancements in recent years, demonstrating its effectiveness in a wide array of applications, including intrusion detection systems (IDS). However, when operating in adversarial environments, ML-based systems are susceptible to a range of attacks.

Finding the Face in the Crowd

1 min read ·
An algorithm that maximizes the difference between data categories achieves high accuracy in classifying faces.

Disease researchers have a way with words

1 min read ·
Specialized word search method sheds light on phenotypic similarity of diseases.

Honey bee behavior is in the genes

1 min read ·
An integrated set of genetic mechanisms controls whether bees behave as foragers or nurses.

Choosing the right scheme for green communications

1 min read ·
Performance analysis reveals how different resource allocation schemes may impact the energy efficiency of a cognitive radio system.

Unlocking complex interactions

1 min read ·
Functions of interacting molecular complexes are uncovered through a novel method of aligning the interaction interface of each complex.

Bringing computational engineering into the fold

1 min read ·
An interactive computational tool opens new possibilities for "developable" surfaces.

Noisy cells produce bursts of protein

1 min read ·
A new mathematical model explains how random factors affect the production of proteins within the cells.

Faster prediction of wireless downtime

1 min read ·
An efficient simulation scheme that hones in on the rarest elements in a dataset can help predict capacity exceedances in wireless networks.

Sharing movement aids learning

1 min read ·
Automated learning of an individual’s movement patterns shared over mobile and social networks could help us to connect better.

Exploring protein form to find function

1 min read ·
Existing systems for predicting protein structure are outperformed by a newly developed method.

Exploring artificial biosynthesis

1 min read ·
Metabolic route explorer helps to optimize the pathways for artificial biosynthesis of valuable products.

Filling in the blanks of virtual cities

1 min read ·
New software generates three-dimensional models of buildings, with applications for disaster relief support.

Technology search for relationships

1 min read ·
A sketch-based query for searching for relationships among objects in images could enhance the power and utility of image search tools.

Divide and conquer pattern searching

1 min read ·
Searching for recurring patterns in network systems has become a fundamental part of research and discovery in fields as diverse as biology and social media. KAUST researchers have developed a pattern or graph-mining framework that promises to significantly speed up searches on massive network data sets. “A graph is a data structure that models complex relationships among objects,” explained Panagiotis Kalnis, leader of the research team from the KAUST Extreme Computing Research Center. “Graphs are widely used in many modern applications, including social networks, biological networks like

Giving power to demand-driven electricity

1 min read ·
A new approach to analyzing household electricity: smart-meter data could improve the performance and efficiency of national power grids.

Algorithm scours datasets to diagnose medical mysteries

1 min read ·
A new tool uses genetic and clinical information to find the root cause of unexplained illnesses.

Sharing expert experimental knowledge to expedite design

1 min read ·
A repository of metabolic information provides a quick reference tool for designing useful synthetic biological systems.

The crest of waveforms for next-gen radar

1 min read ·
A new method for shaping the waveform generated by multi-antenna radar systems is inexpensive and practical.

Streamlining space structures

1 min read ·
A new computational framework marries ideas from computer graphics with civil engineering to reduce times and costs of constructing frame-based structures.

Xiangliang Zhang joins CBRC

1 min read ·
Xiangliang Zhang, KAUST associate professor of computer science and principal investigator of the Machine Intelligence & Knowledge Engineering Lab, joined the Computational Bioscience Research Center (CBRC) on July 1, 2018. In CBRC, Xiangliang will work on the problems of modeling biological networks using machine learning models.

Polymers offer a better view

1 min read ·
A window opens for analyzing the distribution of small molecules in biological and medical tissue samples.

Simple statistics can be good enough

1 min read ·
Study of the mismatch between spatial environmental data and a commonly used statistical analysis suggests simpler statistics are sufficient in many cases.

Querying big data just got universal

1 min read ·
A universal query engine for big data that works across computing platforms could accelerate analytics research.

Mastering a prickly problem in ferrofluids

1 min read ·
Computer simulation accurately captures the beguiling motion of a liquid magnetic material.

AI learns complex gene-disease patterns

1 min read ·
A deep learning model improves the ability to identify genes potentially involved in disease.

Database to support infectious disease research

1 min read ·
Linking disease pathogens to clinical signs and symptoms through a database could support research into the molecular mechanisms of infectious diseases.

Less chat leads to more work for machine learning

1 min read ·
Deep analysis of the way information is shared among parallel computations increases efficiency to accelerate machine learning at scale.

Symbol of change for AI development

1 min read ·
Bridging the knowledge gap in artificial intelligence requires an embedding function that helps step between different types of "thinking."

Machine learning models gather momentum

1 min read ·
New methods for training machine learning models are quicker and more accurate than current approaches, previously considered state-of-the-art.

AI reveals nature of RNA-protein interactions

1 min read ·
A deep learning tool could help in structure-based drug discovery.

AI uses your imagination

1 min read ·
The psychology of human creativity helps artificial intelligence imagine the unseen.

Algorithm turns cancer gene discovery on its head

1 min read ·
A method for finding genes that spur tumor growth takes advantage of machine learning algorithms to sift through reams of molecular data collected from studies of cancer cell lines, mouse models and human patients.

Peeling back the layers of deep machine learning

1 min read ·
A layer-based approach raises the efficiency of training artificial intelligence models.

Training agents to walk with purpose

1 min read ·
By training a search agent to make smarter exploratory decisions, relational data can be classified more accurately and efficiently.

Angling for underwater WiFi

1 min read ·
Scuba divers could send sea life shots in real time using an aquatic internet service.

Computers excel in chemistry class

1 min read ·
Machine learning models can rapidly and accurately estimate key chemical parameters related to molecular reactivity.

Peering under the hood of SARS-CoV-Two

1 min read ·
Microscope and protein data are incorporated into an easy-to-use-and-update tool that can model an organism’s 3D appearance.

Simulating evolution to understand a hidden switch

1 min read ·
Some organisms evolve an internal switch that can remain hidden for generations until stress flicks it on.

Ferrofluid surface simulations go more than skin deep

1 min read ·
Computer models efficiently and accurately simulate the magnetic responses of ferrofluids by considering only the fluid’s surface.

Xin Gao promoted to rank of professor

1 min read ·
Computational Bioscience Research Center (CBRC) would like to congratulate Xin Gao for being promoted to the rank of Professor, effective January 1, 2021. Prof. Gao joined KAUST in October 2010 and became a CBRC PI in January 2013. He has since then produced tremendous work in the areas of computational biology, bioinformatics, machine learning, and algorithms. Dr. Xin Gao is also the Acting Associate Director of the Computational Bioscience Research Center and the lead of the Structural and Functional Bioinformatics Group at KAUST. Prior to joining KAUST, he was a Lane Fellow at Lane Center

First 3D Visualizations of SARS-CoV-2 Cryo-EM Tomography Data

1 min read ·
Together with our partners from Tsinghua University and Nanographics, our group has succeeded in depicting the first 3D visualizations of Cryo-EM microscopy tomography directly from the data. We are advancing the technology to allow for clear, noise-free visualization of this challenging data modality. Once we succeed with that our next challenge is to integrate such 3D visualization into the structural modeling process. Stay tuned!

Cloud simulations get a dose of realism

1 min read ·
A focus on the fundamental physics of cloud formation leads to highly realistic simulations of different types of clouds.

Machine learning at speed

1 min read ·
Optimizing network communication accelerates training in large-scale machine-learning models.

The IEEE CS Global Student Challenge seeks top KAUST CS talent

1 min read ·
The annual IEEE Computer Society Global Student Challenge provides an avenue for students worldwide to create innovative solutions to big data problems. This year’s competition, IEEE CS GSC 2021, encourages each individual or team (max three students) to present solutions to pre-determined problem/issue statement of relevance in CS today.

Training an AI eye on the Moon

1 min read ·
Machine learning accelerates the search for promising Moon sites for energy and mineral resources.

Viruses as communication molecules

1 min read ·
Electrical and computer engineers take on complex modeling questions that can further our understanding of virus spread in small spaces.

Divided attention could ease wireless congestion

1 min read ·
Predicting wireless traffic using artificial intelligence could improve the reliability of future wireless communications.

Wildfire simulation heats up

1 min read ·
Computational models capture the capricious behavior of forest fires.

Harnessing the particle-tracking power of the algorithm

1 min read ·
A simple camera system paired with a sophisticated image-processing algorithm can achieve faster and more accurate reconstructions of particle flow.

Drop the zeros for a performance boost

1 min read ·
An eight-fold speed up of deep machine learning can be achieved by skipping the transmission of zero values.

MS Thesis Defense: Embedding Ontologies using Category Theory Semantics by Fernando Zhapa Camacho

1 min read ·
Fernando Patricio Zhapa Camacho an M.S./Ph.D. candidate in the KAUST Bio-Ontology research group under the supervision of Professor Robert Hoehndorf successfully defended his thesis "Embedding Ontologies using Category Theory Semantics".

New database to "SpUR" on cancer research

1 min read ·
Xin Gao's team developed an interactive web portal where cancer scientists can interrogate how RNA splicing in noncoding parts of genes fuels the growth of different types of tumors.

Computer learns to write captions with feeling

1 min read ·
Mohamed Elhoseiny and his PhD student Youssef Mohamed are teaching AI to capture the full spectrum of human emotions when annotating artwork in order to reduce emotional bias in computer-generated captions.

AI helps diagnose post-COVID lung problems

1 min read ·
A new AI diagnostic tool developed by KAUST scientists allows doctors to visualize lung damage caused by COVID-19 in more detail.

Watching viscous flow, but faster

1 min read ·
A state-of-the-art method for modeling the behavior of liquids described by the Computational Sciences Group represents a breakthrough in computational speed for viscous liquids.

Alumni in focus: Abdullah AlGziwi

1 min read ·
Abdullah AlGziwi, a visiting student under Professor Xin Gao's supervision, was recently awarded the “Second Place Grand Award” at the Saudi National Olympiad for Scientific Creativity. He presented his research project on “A Novel exosome-encapsulated-miRNA-based machine learning model for multiple cancer prediction and prognosis”.

MS Thesis Defense | Learning 3D structures for protein function prediction

1 min read ·
Student Nurul Muttakin from the Bio-Ontology Research Group (BORG) under the supervision of Assoc. Prof. Robert Hoehndorf successfully defends his Masters thesis. He presented his research on the topic " Learning 3D structures for protein function prediction".

PhD Dissertation Defense | Ontology design patterns and methods for integrating phenotype ontologies

1 min read ·
CBRC PhD student Sarah Alghamdi successfully defended her dissertation last week. She has been an essential member of the Bio-Ontology Research Group (BORG) since 2015.Her research interests include the applications of artificial intelligence and statistical methods to genomics and healthcare.

PhD Dissertation Defense | Prioritizing Causative Genomic Variants by Integrating Molecular and Functional Annotations from Multiple Biomedical Ontologies

1 min read ·
CBRC PhD Student Azza Althagafi successfully defends her dissertation under the supervision of Associate Professor Robert Hoehndorf. She has been a member of the Bio-Ontology Research Group (BORG) since 2016. Her research interest lies in the crossroads of computer science and biology, leveraging AI techniques to explore the human genome's intricacies and its link to various diseases.

Prof. Xin Gao assumes the position of CEMSE CS Program Chair

1 min read ·
Prof. Xin Gao has assumed the role of CEMSE CS Program Chair, marking a significant development for our academic community.

Former CBRC PhD Student Ibrahim Alabdulmohsin Highlighted for AI Contributions on Saudi National TV

1 min read ·
Former CBRC PhD student Dr. Ibrahim Alabdulmohsin, now a senior research scientist at Google DeepMind in Zurich, was featured by the Josoor Program on Saudi National TV. The program, meaning "Bridges" in Arabic, highlighted Dr. Alabdulmohsin's journey from his education at the University of Nebraska, Lincoln, and Stanford University to his leadership roles at Aramco's Advanced Analytics team. After graduating from KAUST under the supervision of Prof. Xin Gao, he joined DeepMind in 2019, contributing to groundbreaking AI research. The 24-minute episode explores his career and contributions to the field. Dr. Alabdulmohsin's commitment to advancing AI underscores his pivotal role in shaping the future of technology.

Razen Al Harbi

Razen Al Harbi obtained his Ph.D. degree in Computer Science under the supervision of Professor Panagiotis Kalnis at InfoCloud Research Group (CLOUD) in King Abdullah University of Science and Technology (KAUST) in 2016. Research Interests Razen's research interests included ​Large scale data management with an emphasis on managing and querying large-scale graphs. Selected Publications Ali H. Dogru, Larry S. K. Fung, Usuf M, Tareq M. Al-Shaalan, Jorge A. Pita, K. Hemanthkumar, H. J. Su, James C. Tan, H. Hoy, W. T. Dreiman, W. A. Hahn, R. Al-Harbi, A. Al-Youbi, N. M. Al-Zamel, M. Mezghani “A

Elisa Chiapponi

I am currently a PhD student in Digital Security enrolled in the Sorbonne Université. I work on my research project at EURECOM and Amadeus, under the supervision of prof. Marc Dacier at KAUST My areas of interest include Network and Web security. My thesis focuses on the analysis and mitigation of the new generation of botnets, in particular the ones performing web scraping. My goal is to find practical means to defeat them. The starting point of my project is understanding the ecosystem of scraping bots. This consists of identifying the actors behind this business and their motivations