Introducing Gnosis Data Analysis IKE Mens Ex Machina Group - - PowerPoint PPT Presentation

▶

Aug 21, 2022 255 likes •460 views

Introducing Gnosis Data Analysis IKE Mens Ex Machina Group www.gnosisda.com mensxmachina.org Ioannis Tsamardinos o Education o B.Sc. from CSD, University of Crete, 1991-1995 o M.Sc., Ph.D. Intelligent Systems Program, University of Pittsburgh,

SLIDE 1

Introducing

Gnosis Data Analysis IKE www.gnosisda.com Mens Ex Machina Group mensxmachina.org

SLIDE 2

Ioannis Tsamardinos

Education
B.Sc. from CSD, University of Crete, 1991-1995
M.Sc., Ph.D. Intelligent Systems Program, University of Pittsburgh, 1995 - 2001
Internship and Award, NASA Ames center
Previous Positions
Assistant Professor, Department of Biomedical Informatics, Vanderbilt University, 2001-

2006

Current Positions
Professor, CSD, UoC
Affiliated Faculty, Institute of Applied Mathematics, FORTH
Visiting, Huddersfield University
Founder, CEO, Gnosis Data Analysis

SLIDE 3

Recognition

110+ papers, 7000+

citations, 600 citation/year

~25 funded grants
NASA Group Achievement

Award, NASA Ames

ERC, ARISTEIA II grantee
Keynote and invited

speaker

Best paper awards

SLIDE 4

Mens Ex Machina

Ο από μηχανής νούς
4 post-docs
1 Ph.D. candidate
~10 M.Sc.
Undergrads
1 administrator!

SLIDE 5

Past MXM students and members

Assistant Professor, University of Pittsburgh
Google, Zurich
Assistant Professor, Rethymnon
Researcher, FORTH

SLIDE 6

Research Topics

Machine Learning, Data Science, and Artificial

Intelligence

Feature Selection, Causal Discovery, Automated Machine

Learning (AutoML)

Bioinformatics and Biomedical Informatics
Interdisciplinary research: medicine, biology, materials

science

SLIDE 7

Research Types

Philosophy Theory and Math Algorithms Applications for new biomedical knowledge Tools and Systems

SLIDE 8

Learning Causal Models

Google “classic” of 2006 in the field of Artificial

Intelligence

ERC Consolidator Award CAUSALPATH

SLIDE 9

Big Data Feature Selection

Select the quantities that are most predictive of an
utcome, in combination
New algorithm scaling to 40M quantities and infinite

sample size

SLIDE 10

Figure 4. Predicted causal pairs for CLCD. CLCD outputs 82 different predictions (38 unique cause-effect pairs. CLCD results for the remaining subpopulations are grouped into CD14+ surface- and monocytes (CD14+HLA−Dr−, CD14+HLA−Drhigh, CD14+HLA−Drmid, CD14−HLA−Dr−, CD14−HLA−Drhigh, CD14−HLA−Drmid) and B cells (IgM− and IgM+). Edge thickness corresponds to frequency of appearance in different contexts (activators, inhibitors, subpopulations where applicable). Green edges are confirmed in at least one KEGG pathway, while brown edges are found reversed in at least one KEGG pathway.

SLIDE 11

✓ University of Crete spin-off ✓ Headquarters and R&D in Heraklion ✓ Greek, Danish, German partners ✓ Decades long-experience in applied machine learning in life sciences ✓ 12 employees + 3 employees + new positions

SLIDE 12

International Partnerships

SLIDE 13

5 Step Analysis

JAD BI

Apply to New Data

https://www.jadbio.com/

SLIDE 14

Predicts breast cancer from blood measurements

https://www.nature.com/articles/s41388-018-0660-y

SLIDE 15

Predicts suicides

https://www.ncbi.nlm.nih.gov/pubmed/30474411

SLIDE 16

Protein function given their aminoacid sequence

https://www.nature.com/articles/s41598-017-03557-4

SLIDE 17

Predicts nanomaterial properties given structure

https://www.nature.com/articles/s41524-017-0045-8

SLIDE 18

Just Add Data Bio Release this week!