Loading…
Every biological foundation model, evaluated and ranked by the bio.rodeo team
Showing 2041–2064 of 2565 models
Constrained RNA sequence design that turns an encoder-only RNA language model into a generator by greedy gradient search over nucleotides.
EEG foundation model whose dual objective aligns masked-patch features with whole-signal features, then transfers to new montages by linear probe.
Protein motion prediction from sequence alone, mapping language model embeddings to continuous 3D displacement vectors with a lightweight CNN.
Protein druggability scoring that concatenates frozen ESM-2 sequence embeddings with Gene Ontology annotations to rank candidate drug targets.
Melting-temperature regressor over frozen ProtBert embeddings that scans every single-point mutant of a sequence to hit a target Tm.
Single-cell RNA-seq framework for hierarchical cell type annotation, unknown cell type detection, and surface protein imputation from transcriptomes.
Reinforcement learning agent that proposes sets of point mutations to disrupt a chosen alpha-helix, either in isolation or inside its parent protein.
Genomic language model whose 63.6M-parameter encoder reads sequences beyond 140,000 tokens, matching far larger DNA models across the GUE benchmark.
Pathology report generation from multi-scale whole-slide images, conditioning a frozen PubMed-pretrained GPT-2 on organ-keyed tag-attended features.
Protein complex structure prediction conditioned on sparse restraints from crosslinking, covalent labeling, NMR shifts and mutational scans.
Sequence-only pKa prediction for six titratable side chains and both termini, using a frozen protein language model and isoelectric-point features.
Cell segmentation and cell-type classification for multiplexed tissue images, predicting masks, boxes and class labels from one transformer backbone.
Assembly polishing model predicting base-level corrections to a diploid genome from PacBio HiFi read alignments, cutting base errors by about half.
EEG foundation model pretrained on 1.7TB of scalp and intracranial recordings, scaling attention across both time and channels to handle any montage.
Nanobody thermostability predictor stacking regressors over frozen language model embeddings to estimate apparent melting temperature from sequence.
Manufacturing-aware generative sequence models whose parameters are DNA synthesis reaction conditions, so designs are made in vitro at petascale.
Predicts which olfactory receptors an odorant activates, fusing a molecular graph network with frozen protein language model embeddings.
De novo small molecule generation that assembles drug-like graphs atom by atom, pretrained on cheap property proxies and finetuned per objective.
Latent diffusion model for RNA sequence generation that steers non-coding RNA and 5' UTR design with reward-model gradients at sampling time.
Genomics language model tuned from Llama on curated gene, protein and phenotype records for medical-genetics QA and gene-disease relation calls.
RNA language model adapted from ESM-2 by cross-modality transfer learning, matching RNA-native baselines with 1/8 the trainable parameters.
Self-supervised 3D molecular pretraining that corrupts and rebuilds tetrahedral local structures, then transfers to toxicity and affinity prediction.