Bernardo P. de Almeida

From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling

CellScribe is a generative framework that unifies cell identity and state by using a language model to generate cell type annotations and meta-program profiles, outperforming baselines and identifying new cell types through in-context learning.

A multispecies foundation model for genome function prediction, gene annotation and sequence design

NTv3 is a foundation model that predicts genome function, annotates genes, and designs DNA sequences across species, outperforming existing models in multiple tasks.

Annotating the genome at single-nucleotide resolution with DNA foundation models

The paper introduces SegmentNT, a DNA foundation model for genome annotation, achieving state-of-the-art performance in identifying 14 genic and regulatory elements across species.

The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human Genomics

The paper introduces the Nucleotide Transformer, a foundation model for genomics, showing it can predict molecular phenotypes from DNA sequences with transfer learning across tasks and organisms.

Developmental and housekeeping transcriptional programs display distinct modes of enhancer-enhancer cooperativity in Drosophila

The paper investigates enhancer-enhancer cooperativity in Drosophila, finding that housekeeping enhancers are additive while developmental enhancers are synergistic.

Are Genomic Language Models All You Need? Exploring Genomic Language Models on Protein Downstream Tasks

This study evaluates genomic language models on protein tasks, showing they are competitive with proteomic models and benefit from joint genomic-proteomic training and optimized tokenization.

A Foundational Large Language Model for Edible Plant Genomes

This paper introduces a large language model for plant genomics that provides state-of-the-art predictions for regulatory annotations and variant prioritization, along with a benchmark dataset for deep learning methods.

ChatNT: A Multimodal Conversational Agent for DNA, RNA and Protein Tasks

ChatNT is a conversational agent that understands biological sequences and achieves state-of-the-art results on genomics tasks while being accessible to non-coders.

Enhancers display constrained sequence flexibility and context-specific modulation of motif function

The paper investigates enhancer sequence flexibility and context-specific motif function in Drosophila, finding constrained flexibility and context-dependent motif activity.

Identification and characterization of repressive domains in Drosophila transcription factors

The paper identifies and characterizes repressive domains in Drosophila transcription factors using a new high-throughput method, revealing conserved motifs and co-repressor interactions.

DeepSTARR predicts enhancer activity from DNA sequence and enables the de novo design of enhancers

This paper introduces DeepSTARR, a deep learning model that predicts enhancer activity from DNA sequence and enables the de novo design of enhancers in Drosophila and human.

Mapping of cis-regulatory variants by differential allelic expression analysis identifies candidate causal variants and target genes of 41 breast cancer risk loci