AI Research Scientist at InstaDeep
“The people who are crazy enough to think they can change the world are the ones who do!”
Steve Jobs
Bernardo P. de Almeida
I am an AI Research Scientist at InstaDeep where I am building large language foundational models for biology. I am mostly interested in building models that can read the human genome and interpret its variation.
News
It was great to participate in the podcast Futuro do Futuro (in portuguese) and discuss my work and the future of AI in biology (December 2023)
My final PhD paper on designing synthetic enhancers for selected tissues in vivo using AI is out in Nature (December 2023)
I am very happy to have received one of the 2023 Vienna BioCenter PhD Awards! Shared with great colleagues. It's the best way to close the PhD at the IMP, in Vienna (November 2023)
Very happy to give a OLISSIPO Workshop on Decoding the genome with deep learning, including a hands-on session (April 2023)
Check the Kipoi Seminar where I presented my work on Decoding the cis-regulatory information of enhancer sequences (April 2023)
Very honoured to receive The Life Science Research Award Austria 2022 from the Austrian Society for Molecular Biosciences and Biotechnology (ÖGMBT) in the category "Basic Science" (September 2022)
Presented a poster at the 15th EMBL Conference: Transcription and Chromatin about our new preprint on the flexibility of enhancer sequences and motif syntax (August 2022)
Very happy to see our DeepSTARR paper highlighted in Nature Methods: "Predicting and designing enhancers" (July 2022)
Check the ISCBacademy Webinar where I presented my recent work DeepSTARR predicts enhancer activity from DNA sequence and enables the de novo design of synthetic enhancers (December 2021)
Research highlights
Targeted design of synthetic enhancers for selected tissues in the Drosophila embryo Nature 2023
New publication showing a major breakthrough achievement – the de novo design of synthetic enhancers for selected tissues in fruit fly embryos in vivo using deep- and transfer learning.
Enhancers display constrained sequence flexibility and context-specific modulation of motif function Genome Research 2023
New publication where we study the flexibility of enhancer sequences and motif syntax using rationally designed libraries of enhancer variants and massively parallel reporter assays.
DeepSTARR predicts enhancer activity from DNA sequence and enables the de novo design of synthetic enhancers Nature Genetics 2022
New publication where we use deep learning to predict enhancer activity from DNA sequence, learn cis-regulatory rules and the importance of TF motif instances, and design synthetic enhancers.
Allosteric Antagonist Modulation of TRPV2 by Piperlongumine Impairs Glioblastoma Progression ACS Cent. Sci. 2021
It was great to contribute with computational analyses and be part of this big effort of Gonçalo Bernardes and Vera Moiseenkova-Bell teams. We computationally identify and experimentally validate TRPV2 as a target for piperlongumine and establish a link between allosteric target engagement and impaired GBM progression.
Pan-cancer association of a centrosome amplification gene expression signature with genomic alterations and clinical outcome PLoS Computational Biology 2019
Full publications list.