Image
alt="A team of MIT researchers found highly memorable images have stronger and sustained responses in ventro-occipital brain cortices, peaking at around 300ms. Conceptually similar but easily forgettable images quickly fade away (Credits: Alex Shipps/MIT CSAIL)."
CSAIL article

For nearly a decade, a team of MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers have been seeking to uncover why certain images persist in a people's minds, while many others fade. To do this, they set out to map the spatio-temporal brain dynamics involved in recognizing a visual image. And now for the first time, scientists harnessed the combined strengths of magnetoencephalography (MEG), which captures the timing of brain activity, and functional magnetic resonance imaging (fMRI), which identifies active brain regions, to precisely determine when and where the brain processes a memorable image.

Image
HLA
CSAIL article

On the surface, the movement disorder amyotrophic lateral sclerosis (ALS), also known as Lou Gehrig’s disease, and the cognitive disorder frontotemporal lobar degeneration (FTLD), which underlies frontotemporal dementia, manifest in very different ways. In addition, they are known to primarily affect very different regions of the brain.

Image
Using AI to optimize for rapid neural imaging
CSAIL article

Connectomics, the ambitious field of study that seeks to map the intricate network of animal brains, is undergoing a growth spurt. Within the span of a decade, it has journeyed from its nascent stages to a discipline that is poised to (hopefully) unlock the enigmas of cognition and the physical underpinning of neuropathologies such as in Alzheimer’s disease. 

Category
Computational Biology
Language
Python
Project Lead
Tommi S. Jaakkola

GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles

MIT License
Last Updated
Category
Computational Biology
Language
Python
Project Lead
Tommi S. Jaakkola

EquiBind, is a SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand’s bound pose and orientation. EquiBind achieves significant speed-ups compared to traditional and recent baselines. 

MIT License
Last Updated