
Žiga Avsec
Researcher
2
APPEARANCES
2
PODCASTS
012
DEC 30
JAN 6
JAN 13
JAN 20
JAN 27
FEB 3
FEB 10
FEB 17
FEB 24
MAR 3
MAR 10
MAR 17
MAR 24
MAR 31
APR 7
APR 14
APR 21
APR 28
MAY 5
MAY 12
MAY 19
MAY 26
JUN 2
JUN 9
JUN 16
JUN 23
JUN 30
JUL 7
JUL 14
JUL 21
JUL 28
AUG 4
AUG 11
AUG 18
AUG 25
SEP 1
SEP 8
SEP 15
SEP 22
SEP 29
OCT 6
OCT 13
OCT 20
OCT 27
NOV 3
NOV 10
NOV 17
NOV 24
DEC 1
DEC 8
DEC 15
DEC 22
DEC 29
JAN 5
JAN 12
JAN 19
JAN 26
FEB 2
FEB 9
FEB 16
FEB 23
MAR 2
MAR 9
MAR 16
MAR 23
MAR 30
APR 6
APR 13
APR 20
APR 27
MAY 4
MAY 11
MAY 18
MAY 25
JUN 1
JUN 8
JUN 15
JUN 22
JUN 29
JUL 6
JUL 13
JUL 20
JUL 27
AUG 3
AUG 10
AUG 17
AUG 24
AUG 31
SEP 7
SEP 14
SEP 21
SEP 28
OCT 5
OCT 12
OCT 19
OCT 26
NOV 2
NOV 9
NOV 16
Nov 11, 2026
AlphaGenome 2: Teaching AI to read the entire human genome
6:40
6:56

Žiga AvsecGUEST
So I think the main role of the genome is to produce proteins, which are these building blocks in the cell.

Žiga AvsecGUEST
that contained one instruction manual from our mother and one from our father, and then the cell divided and specialized into different cell types in our body.
Deeper into Genomics: Google DeepMind’s Ziga Avsec on the New AlphaGenome Atlas
1:50
1:57
2:53
3:07
3:17
T
1:30Theral TimpsonHOST
Would you agree with what I said at the outset, that biology the last few years has been going out horizontally towards spatial, multiomics, sort of a post-genomic age, but you, it seems, are going deeper and feel like there's more to get out of the genome itself?

Žiga AvsecGUEST
Yeah, I mean, this is the root or the root source of information, right, about the cells.

Žiga AvsecGUEST
And I really find it fascinating because it determines a lot about the cells, how they develop, and also whether they get diseased.

Žiga AvsecGUEST
Yeah, so we've created what we call the Alpha Genome Atlas, where, as you said, we took every position of the genome and mutated it to all the other three possible letters.

Žiga AvsecGUEST
And we made predictions with alpha genome of what would happen at that position in the genome on different layers of gene regulation and different cell types.

Žiga AvsecGUEST
And that allows you to really chart things the genome in this new way and look at it from a slightly new perspective so it allows you to see which regions are important or functional do something in terms of their regulatory activity like for example where are the different binding motifs located what cells do they regulate or what processes do they regulate and it also allows us to kind of cache these predictions and really enable large-scale analysis because you know running alpha genome for a single variant takes about a second so if you were to if you wanted to analyze millions of mutations you could wait for quite a while in order to get all those predictions so by pre-computing it we're kind of essentially creating a cache that people can then quickly look up to then analyze these large numbers of variants.