ProteinCLIP: enhancing protein language models with natural language
Language models have enabled a new era of biological sequence modeling. However,
extracting meaningful sequence-level embeddings from these models remains challenging …
extracting meaningful sequence-level embeddings from these models remains challenging …
NeuroFold: A Multimodal Approach to Generating Novel Protein Variants in silico
The generation of high-performance enzyme variants with desired physicochemical and
functional properties presents a formidable challenge in the field of protein engineering …
functional properties presents a formidable challenge in the field of protein engineering …
The site-specific amino acid preferences of homologous proteins depend on sequence divergence
E Ferrada - Genome Biology and Evolution, 2019 - academic.oup.com
The propensity of protein sites to be occupied by any of the 20 amino acids is known as site-
specific amino acid preferences (SSAP). Under the assumption that SSAP are conserved …
specific amino acid preferences (SSAP). Under the assumption that SSAP are conserved …
Mechanism of species dynamics and interactions under impacts of artificial barriers in coastal areas
Y Cai, Y Xu, T Sun, Q Tan, Z Yang, J Peng… - Ocean & Coastal …, 2020 - Elsevier
Coastal reclamation engineering structures are exerting significant isolation effects on
dynamics of local species. In this research, a population dynamics model was developed for …
dynamics of local species. In this research, a population dynamics model was developed for …
Deep generative models for biology: represent, predict, design
P Notin - 2023 - ora.ox.ac.uk
Deep generative models have revolutionized the field of artificial intelligence, fundamentally
changing how we generate novel objects that imitate or extrapolate from training data, and …
changing how we generate novel objects that imitate or extrapolate from training data, and …
Optimizing Protein Fitness and Function with Sparse Experimental Data
AY Shaw - 2023 - search.proquest.com
The quest to create customized protein sequences with specific functions holds great
promise across diverse fields, from healthcare to sustainable energy. While Next Generation …
promise across diverse fields, from healthcare to sustainable energy. While Next Generation …
Protein evolution and data-driven sequence landscapes
M Bisardi - 2023 - theses.hal.science
Thanks to the explosion of available protein sequence data, driven by next-generation
sequencing, unsupervised machine learning models can be harnessed to learn protein …
sequencing, unsupervised machine learning models can be harnessed to learn protein …
Generalization of the Ewens sampling formula to arbitrary fitness landscapes
P Khromov, CD Malliaris, AV Morozov - Plos one, 2018 - journals.plos.org
In considering evolution of transcribed regions, regulatory sequences, and other genomic
loci, we are often faced with a situation in which the number of allelic states greatly exceeds …
loci, we are often faced with a situation in which the number of allelic states greatly exceeds …
Evolutionary dynamics under a stability-constrained model
N Youssef - 2021 - dalspace.library.dal.ca
The space of possible proteins is vast. For all but the smallest proteins, the number of
sequences exceeds the number of atoms in the observable universe. Evolution—through …
sequences exceeds the number of atoms in the observable universe. Evolution—through …
[PDF][PDF] The transformability of genotype-phenotype
M Srivastava, JL Payne - academia.edu
The mapping from genotype to phenotype to fitness typically involves multiple nonlinearities
that can transform the 9 individual and combined effects of mutations. For example …
that can transform the 9 individual and combined effects of mutations. For example …