Re: invite to give a talk at AI for health webinar on zoom

Hi Mark

Sorry about the last-minute request, but I wonder if it is possible to reschedule your webinar for the fall. I have a conflict this Wednesday. Also, probably more importantly, since the semester has ended, the webinar attendance has reduced quite a bit. It will be a lot more dynamic during the fall semester. Would you be able to give the webinar on Wednesday 3-4PM EST October 15 or Oct 22?

Cheers

Jimeng

On Tue, Jun 3, 2025 at 9:10 AM jimeng sun <jimeng.sun@gmail.com> wrote:

Thanks Mark. Looking forward to hosting your webinar next Wed.

Jimeng

On Mon, Jun 2, 2025 at 2:11 PM Della L <dellaphinisee@gmail.com> wrote:

Thank you Dr. Gerstein,

I updated the webinar invite.

Della Phinisee

VA

On Sun, Jun 1, 2025 at 9:21 PM Mark Gerstein <mark@gersteinlab.org> wrote:

Title:

AI Methods for Biomedicine

ABSTRACT

My talk will focus on the following papers:

1* Current methods based on regulatory networks & deep learning

https://papers.gersteinlab.org/papers/cornerstone

https://papers.gersteinlab.org/papers/chronODE

2 * Current methods based on agents

https://papers.gersteinlab.org/papers/BioCoder
https://papers.gersteinlab.org/papers/MedAgents
https://papers.gersteinlab.org/papers/MolLM

3 * Future methods based on quantum computing

https://papers.gersteinlab.org/papers/QVAE

==
i0ai4h

Fwd: U1331 Computational Oncology Hybrid Seminar: Pr. Mark GERSTEIN - July 21th 2025

Seminar

Computational Oncology (U1331)

________________________________

Mark GERSTEIN, Institute for Foundations of Data Science / Center for
Research Computing - Yale University (USA)

________________________________

Monday, July 21th 2025
11:00 am

Centre de Recherche - Paris Amphithéâtre Hélène Martel Massignac – 11
rue Pierre et Marie Curie, Paris 5e

+ Teams (see bottom of invitation

AI approaches for biomedicine: Cancer & Brain disorders

In this talk, I'll go over these two papers. My talk will focus on the
material in:

(1) Emani et al. (2024).

Single-cell genomics is a powerful tool for studying heterogeneous
tissues such as the brain. Yet little is understood about how genetic
variants influence cell-level gene expression. Addressing this, we
uniformly processed single-nuclei, multiomics datasets into a resource
comprising >2.8 millions nuclei from the prefrontal cortex across 388
individuals with various brain-related disorders and controls. Using
this, we built cell–type–specific gene regulatory and cell-to-cell
communication networks and an integrative deep-learning model that
accurately imputes single-cell expression and simulates perturbations.
The model prioritized ~250 disease-risk genes and drug targets with
associated cell types.

(2) Kumar et al. (2020).

I will also focus on the role of non-coding mutations in cancer.
As most know, the overwhelming part of the genome is noncoding, and
there are many somatic mutations in cancer in this region. It is still
debated the degree to which many of these mutations are under positive
selection and whether these mutations could represent either strong or
weak drivers and affect cancer progression

References

Single-cell genomics and regulatory networks for 388 human brains PS
Emani et al. (2024). Science 384: eadi5199.
Passenger Mutations in More Than 2,500 Cancer Genomes: Overall
Molecular Functional Impact and Consequences. S Kumar et al. (2020).
Cell 180: 915


Invited by:

Emmanuel BARILLOT

==
eur25



________________________________________________________________________________

Re: invite to give a talk at AI for health webinar on zoom

Thanks Mark. Looking forward to hosting your webinar next Wed.

Jimeng

On Mon, Jun 2, 2025 at 2:11 PM Della L <dellaphinisee@gmail.com> wrote:

Thank you Dr. Gerstein,

I updated the webinar invite.

Della Phinisee

VA

On Sun, Jun 1, 2025 at 9:21 PM Mark Gerstein <mark@gersteinlab.org> wrote:

Title:

AI Methods for Biomedicine

ABSTRACT

My talk will focus on the following papers:

1* Current methods based on regulatory networks & deep learning

https://papers.gersteinlab.org/papers/cornerstone

https://papers.gersteinlab.org/papers/chronODE

2 * Current methods based on agents

https://papers.gersteinlab.org/papers/BioCoder
https://papers.gersteinlab.org/papers/MedAgents
https://papers.gersteinlab.org/papers/MolLM

3 * Future methods based on quantum computing

https://papers.gersteinlab.org/papers/QVAE

==
i0ai4h

Re: invite to give a talk at AI for health webinar on zoom

Thank you Dr. Gerstein,

I updated the webinar invite.

Della Phinisee

VA

On Sun, Jun 1, 2025 at 9:21 PM Mark Gerstein <mark@gersteinlab.org> wrote:

Title:

AI Methods for Biomedicine

ABSTRACT

My talk will focus on the following papers:

1* Current methods based on regulatory networks & deep learning

https://papers.gersteinlab.org/papers/cornerstone

https://papers.gersteinlab.org/papers/chronODE

2 * Current methods based on agents

https://papers.gersteinlab.org/papers/BioCoder
https://papers.gersteinlab.org/papers/MedAgents
https://papers.gersteinlab.org/papers/MolLM

3 * Future methods based on quantum computing

https://papers.gersteinlab.org/papers/QVAE

==
i0ai4h

Re: invite to give a talk at AI for health webinar on zoom

Title:

AI Methods for Biomedicine

ABSTRACT

My talk will focus on the following papers:

1* Current methods based on regulatory networks & deep learning

https://papers.gersteinlab.org/papers/cornerstone

https://papers.gersteinlab.org/papers/chronODE

2 * Current methods based on agents

https://papers.gersteinlab.org/papers/BioCoder
https://papers.gersteinlab.org/papers/MedAgents
https://papers.gersteinlab.org/papers/MolLM

3 * Future methods based on quantum computing

https://papers.gersteinlab.org/papers/QVAE

==
i0ai4h

Re: potential seminar in Center for Neural Circuit Mapping

TITLE

AI Approaches for Understanding Brain Disorders

ABSTRACT

My talk will focus on the material in:

Single-cell genomics and regulatory networks for 388 human brains
Emani et al. (2024). Science.

Specifically, I'll discuss:

Single-cell genomics is a powerful tool for studying heterogeneous
tissues such as the brain. Yet little is understood about how genetic
variants influence cell-level gene expression. Addressing this, we
uniformly processed single-nuclei, multiomics datasets into a resource
comprising >2.8 million nuclei from the prefrontal cortex across 388
individuals with various brain-related disorders and controls. Using
this, we built cell–type–specific gene regulatory and cell-to-cell
communication networks and an integrative deep-learning model that
accurately imputes single-cell expression and simulates perturbations.
The model prioritized ~250
disease-risk genes and drug targets with associated cell types.

If there's time, I'll also touch on the material in :

* A Variational Graph Partitioning Approach to Modeling Protein
Liquid-liquid Phase Separation
G Wang et al. (2024). Cell Reports Physical Science.

* Leveraging a large language model to predict protein phase
transition: a physical, multiscale and interpretable approach
M Frank et al. (2024). PNAS

* Digital phenotyping from wearables using AI characterizes
psychiatric disorders and identifies genetic associations
J Liu et al. (2024). Cell.

==
i0ucla24+uci

Re: [EXTERNAL] Re: Invitation to Science Forum Microsoft Research AI for Science

Title:

AI Approaches for Understanding Brain Disorders:
Schizophrenia, Alzheimer's disease & ADHD

Abstract:

My talk will focus on the material in:

Emani et al. (2024). Science.
Single-cell genomics and regulatory networks for 388 human brains

Specifically, I'll discuss:

Single-cell genomics is a powerful tool for studying heterogeneous
tissues such as the brain. Yet little is understood about how genetic
variants influence cell-level gene expression. Addressing this, we
uniformly processed single-nuclei, multiomics datasets into a resource
comprising >2.8 million nuclei from the prefrontal cortex across 388
individuals with various brain-related disorders and controls. For 28
harmonized neuronal and non-neuronal cell types, we assessed
population-level variation in expression and chromatin across gene
families and drug targets. Integration of expression and genotype data
revealed >1.4 million single-cell expression quantitative trait loci
(eQTLs), many of which were not seen in bulk gene-expression datasets.
The chromatin datasets allowed for the identification of >550,000
single-cell cis-regulatory elements enriched at loci linked to
brain-related traits. Combining expression, chromatin, and eQTL
datasets, we built cell type–specific gene regulatory and cell-to-cell
communication networks, which manifest cellular changes in aging and
neuropsychiatric disorders, including altered Wnt signaling in
schizophrenia and bipolar disorder. We further constructed an
integrative deep-learning model that accurately imputes single-cell
expression and simulates perturbations. The model prioritized ~250
disease-risk genes and drug targets with associated cell types,
suggesting potential precision-medicine approaches for
neuropsychiatric disorders.

If there's time, I'll also touch on the material in :

* A Variational Graph Partitioning Approach to Modeling Protein
Liquid-liquid Phase Separation
Gaoyuan Wang, Jonathan H Warrell, Suchen Zheng, Mark Gerstein (2023).
Cell Reports Physical Science.

* Leveraging a large language model to predict protein phase
transition: a physical, multiscale and interpretable approach
M Frank, P Ni, M Jensen, MB Gerstein (2024). Proc Natl Acad Sci U S A
121: e2320510121.

* Digital phenotyping from wearables using AI characterizes
psychiatric disorders and identifies genetic associations
JJ Liu, B Borsari, Y Li, SX Liu, Y Gao, X Xin, S Lou, M Jensen, D
Garrido-Martin, TL Verplaetse, G Ash, J Zhang, MJ Girgenti, W Roberts,
M Gerstein (2024). Cell.

i0msft