Quartz 4
Search
Search
Dark mode
Light mode
Explorer
Tag: protein-language-models/training
31 items with this tag.
Apr 21, 2026
Alternate sequence clustering schemes outperform uniform sampling when training protein language models
protein-language-models/training
Apr 21, 2026
Alternative noise schedules improve training of multimodal PLMs
protein-language-models/training
Apr 21, 2026
BERT models trained on sequence clusters outperform those trained on all data
protein-language-models/training
Apr 21, 2026
Base PLMs must usually be fine-tuned to generate functionally active sequences
protein-language-models/training
Apr 21, 2026
Diverse MSAs are better for training structure prediction neural networks than random MSAs
protein-language-models/training
structure-prediction/training
Apr 21, 2026
Fine-tuning almost always improves property prediction
protein-language-models/training
thermostability/prediction
Apr 21, 2026
Fine-tuning base models on test cases can improve the performance of variant effect and structure prediction
protein-language-models/training
structure-prediction/training
plddt
low-rank-adaptation
Apr 21, 2026
Fine-tuning can be detrimental to performance
protein-language-models/training
Apr 21, 2026
Including sequences from multiplexed ancestral sequence reconstruction improves PLM training
protein-language-models/training
ancestral-sequence-reconstruction
Apr 21, 2026
Larger PLMs generate more novel sequences from more sparsely populated protein families
protein-language-models/training
Apr 21, 2026
Logistic regression outperforms fine-tuned LMs on finding point mutations from NGS data
protein-language-models/training
Apr 21, 2026
ML models trained exclusively on experimental structures are less effective on computational models
inverse-folding/training
protein-language-models/training
Apr 21, 2026
MSA-based structure prediction models can be retrained as pathogenicity prediction models by upweighting BERT losses
protein-language-models/training
structure-prediction/training
Apr 21, 2026
Masked LMs can be fine-tuned starting from autoregressive LMs, but not vice-versa
protein-language-models/training
Apr 21, 2026
Masked PLMs are more sensitive to training imbalances than autoregressive PLMs
protein-language-models/training
Apr 21, 2026
PLMs are biased by uneven distribution of sequence data in datasets such as UniRef and UniProt
protein-language-models/training
Apr 21, 2026
Pretraining contributes nearly nothing to performance when fine-tuning protein language models in data-rich situations
protein-language-models/training
Apr 21, 2026
Protein design using sequence-based models does not benefit from scale
protein-language-models/training
plddt
Apr 21, 2026
Protein language models have a lower bound of training loss regardless of size
protein-language-models/training
Apr 21, 2026
Protein language models make equally effective predictions when trained on individual proteins or protein families
protein-language-models/training
Apr 21, 2026
Protein models designed using inverse folding can be used to supplement training DBs for PLMs and structure prediction models
protein-language-models/training
structure-prediction/training
Apr 21, 2026
Residue conservation and solvent exposure data perform comparably to PLMs at some property prediction tasks
protein-language-models/training
thermostability/prediction
Apr 21, 2026
Sequence clustering of training data affects variant effect prediction performance by PLMs
protein-language-models/training
Apr 21, 2026
Sequence-only protein language models implicitly cluster proteins at fineness levels that increase with size
protein-language-models/training
Apr 21, 2026
Training on newly updated databases doesn't guarantee better performance
protein-language-models/training
Apr 21, 2026
Unbalanced composition of sequence data prevents protein fitness from being identifiable from sequence data alone
protein-language-models/training
Apr 21, 2026
Unfreezing PLM during structure training improves prediction quality
protein-language-models/training
tm-score
Apr 21, 2026
Hybrid protein sequence-structure ML models rely more on sequence when many homologs were available during training
protein-language-models/training
inverse-folding/training
Apr 21, 2026
Including optimal growth temperature during pre-training of PLMs improves prediction and design of thermostability
protein-language-models/training
thermostability/prediction
Apr 21, 2026
Incorporating ancestral sequences during PLM training improves performance in downstream tasks
protein-language-models/training
Apr 21, 2026
Overtrained language models are more difficult to fine-tune
protein-language-models/training