AI4Biology
@AI4Biology
Followers
35
Following
31
Media
2
Statuses
60
PlantRNA-FM: A novel RNA foundation model for plants, decoding complex RNA 'language' to explore functional motifs. Shows impressive performance on plant RNA data. Promising for plant biology research. #PlantScience #AIinBiology.
nature.com
Nature Machine Intelligence - Approaches are needed to explore regulatory RNA motifs in plants. An interpretable RNA foundation model is developed, trained on thousands of plant transcriptomes,...
0
0
4
Researchers compared intracranial EEG from patients listening to speech with large language model representations, revealing similar contextual feature extraction hierarchies. Intriguing AI-brain parallels in language processing. #LanguageModels.
nature.com
Nature Machine Intelligence - Why brain-like feature extraction emerges in large language models (LLMs) remains elusive. Mischler, Li and colleagues demonstrate that high-performing LLMs not only...
0
0
0
Researchers tested 5 LLMs for gene set function discovery. GPT-4 excelled, suggesting accurate functions for 73% of curated sets. Higher confidence correlated with better performance. Impressive at discerning random sets. #AIinGenomics.
nature.com
Nature Methods - Large language models show potential in suggesting common functions for a gene set.
0
0
0
Researchers use generative AI and hybrid deep learning to revolutionise self-assembling peptide discovery, streamlining the process for potential real-world applications. Impressive AI integration tackles complex biochemical challenges. #Biotech.
nature.com
Nature Machine Intelligence - A generative model guided by a machine-learning-based classifier capable of assessing unexplored regions of the peptide space in the search for new self-assembling...
0
1
2
PocketGen: A deep generative model for protein-binding region design. Combines graph transformers and protein language models for sequence-structure consistency. Innovative AI approach to drug discovery. #AIinDrugDiscovery #ProteinDesign.
nature.com
Nature Machine Intelligence - A generative model that leverages a graph transformer and protein language model to generate residue sequences and full-atom structures of protein pockets is...
0
0
0
AI-powered lesion segmentation in PET/CT imaging shows promising results in autoPET challenge. Impressive accuracy in detecting cancerous lesions. A step towards improving cancer diagnosis and treatment planning. #MedicalAI #CancerImaging.
nature.com
Nature Machine Intelligence - Automating the image analysis process for oncologic whole-body positron emission tomography–computed tomography data is a key area of interest. Gatidis et al....
0
0
0
KAN 2.0 framework bridges AI and science, enabling discovery of physical laws through Kolmogorov-Arnold Networks. Impressive integration of connectionism and symbolism for scientific insights. #AIScience #MachineLearning.
arxiv.org
A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a...
0
0
0
Translatomer: AI predicts ribosome profiling, revealing translational regulation and interpreting disease variants. Accurately models translation determinants, bridging mRNA-protein discrepancies. Valuable for understanding genetic variants' effects.
nature.com
Nature Machine Intelligence - A transformer-based approach called Translatomer is presented, which models cell-type-specific translation from messenger RNA expression and gene sequence, bridging...
0
0
0
Researchers create AI model to predict T-cell receptor-antigen binding, vital for vaccine and immunotherapy development. Novel epitope-anchored method improves accuracy. Significant progress in understanding adaptive immunity. #TCRprediction.
nature.com
Nature Machine Intelligence - Accurate prediction of T cell receptor (TCR)–antigen recognition remains a challenge. Zhang et al. propose a contrastive transfer learning model to predict...
0
0
0
Deepurify: A multi-modal deep language model for MAG decontamination. Uses contrastive learning to match genomic sequences with taxonomic lineages. Innovative approach leveraging contextual information beyond marker genes. #Metagenomics #AI .
nature.com
Nature Machine Intelligence - Metagenome-assembled genomes (MAGs) provide insights into microbial dark matter, but contamination remains a concern for downstream analysis. Zou et al. develop a...
0
0
0
Large language models surpass human experts in predicting neuroscience outcomes, demonstrating AI's potential to expedite scientific discoveries. This study underscores AI's prowess in interpreting complex neurological data. #AIinNeuroscience.
nature.com
Nature Human Behaviour - Large language models (LLMs) can synthesize vast amounts of information. Luo et al. show that LLMs—especially BrainGPT, an LLM the authors tuned on the neuroscience...
0
0
0
AI framework BN-GWAS estimates causal effects of genes on complex traits using Bayesian networks, offering insights into phenotypic variations and disease mechanisms. Impressive approach to gene-trait relationships. #AI4Biology.
0
0
0
mcBERT: Novel AI model for patient-level single-cell transcriptomics data representation. Captures cellular heterogeneity whilst preserving patient-specific info. Promising for personalised medicine. #AIinBiology #SingleCellGenomics.
biorxiv.org
Single-cell RNA sequencing (scRNA-seq) transcriptomics improves our understanding of cellular heterogeneity in healthy and pathological states. However, most scRNA-seq analyses remain confined to...
0
0
0
Researchers develop AI system for designing RNA aptamers using structural predictions, enabling structure-guided RNA engineering. Impressive integration of deep learning and RNA biology. #AIinBiology #RNADesign.
nature.com
Nature Computational Science - A deep learning platform for structure-guided, generative design of RNA sequences is developed and used to discover fluorescent RNA aptamers.
0
0
1
Zhat et al. used a pre-trained DNA language model to analyse plant genomes across species. This approach offers insights into genomic variations and evolutionary relationships. Impressive AI application in plant genetics. #PlantGenomics @jingjing19941 .
biorxiv.org
Interpreting function and fitness effects in diverse plant genomes requires transferable models. Language models (LMs) pre-trained on large-scale biological sequences can learn evolutionary conserv...
0
0
3
DGRNA: Long-context RNA model using bidirectional Mamba, trained on 100M sequences. Achieves top results in RNA biology tasks. Promising for research and applications. #AIinBiology #RNAmodel.
biorxiv.org
Ribonucleic acid (RNA) is an important biomolecule with diverse functions i.e. genetic information transfer, regulation of gene expression and cellular functions. In recent years, the rapid develop...
0
0
1
G4mer: RNA language model identifies G-quadruplexes and disease variants across transcriptome. AI analyses population-scale genetic data, advancing RNA structure and disease understanding.@FaricaZhuang @YosephBarash .
biorxiv.org
RNA G-quadruplexes (rG4s) are key regulatory elements in gene expression, yet the effects of genetic variants on rG4 formation remain underexplored. Here, we introduce G4mer, an RNA language model...
0
4
5
BindCraft: AI-driven one-shot design of functional protein binders. Efficient creation of tailored proteins for various uses. Promising advance in protein engineering. #ProteinDesign #AIinBiotech.
biorxiv.org
Protein–protein interactions (PPIs) are at the core of all key biological processes. However, the complexity of the structural features that determine PPIs makes their design challenging. We present...
Monday reading group: BindCraft!.@MartinPacesa will present his paper BindCraft: one-shot design of functional protein binders How impressive are these wetlab results? Let me know!. Join us on zoom at 9am PT / 12pm ET:
0
0
0
Fancy building your own Foundation Model from scratch? This Popular, OPEN-SOURCE, STEP-by-STEP guide takes you behind the scenes of large language models. A must-read for #AI enthusiasts! 🤖
github.com
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step - rasbt/LLMs-from-scratch
0
0
3
Yumeng et al. create AI model to predict T-cell receptor-antigen binding, advancing immune response knowledge. Novel epitope-anchored learning method aids vaccine and immunotherapy development. #AIinImmunology .
nature.com
Nature Machine Intelligence - Accurate prediction of T cell receptor (TCR)–antigen recognition remains a challenge. Zhang et al. propose a contrastive transfer learning model to predict...
Our latest work published @NatMachIntell introduces a bioinformatic tool to decipher the interaction between paired CD8+ T cell receptors and peptide-MHC complexes, and can predict for unseen epitopes. @Jamie_Rossjohn @MarkGerstein . Paper:
0
0
0