User profiles for Nicholas Bhattacharya
Nicholas BhattacharyaPhD, UC Berkeley Verified email at berkeley.edu Cited by 1183 |
Evaluating protein transfer learning with TAPE
Protein modeling is an increasingly popular area of machine learning research. Semi-supervised
learning has emerged as an important paradigm in protein modeling due to the high …
learning has emerged as an important paradigm in protein modeling due to the high …
Necrotizing enterocolitis is preceded by increased gut bacterial replication, Klebsiella, and fimbriae-encoding bacteria
Necrotizing enterocolitis (NEC) is a devastating intestinal disease that occurs primarily in
premature infants. We performed genome-resolved metagenomic analysis of 1163 fecal …
premature infants. We performed genome-resolved metagenomic analysis of 1163 fecal …
FLIP: Benchmark tasks in fitness landscape inference for proteins
Abstract Machine learning could enable an unprecedented level of control in protein engineering
for therapeutic and industrial applications. Critical to its use in designing proteins with …
for therapeutic and industrial applications. Critical to its use in designing proteins with …
Differences in the path to exit the ribosome across the three domains of life
The ribosome exit tunnel is an important structure involved in the regulation of translation and
other essential functions such as protein folding. By comparing 20 recently obtained cryo-…
other essential functions such as protein folding. By comparing 20 recently obtained cryo-…
End-to-end learning of multiple sequence alignments with differentiable Smith–Waterman
Motivation Multiple sequence alignments (MSAs) of homologous sequences contain
information on structural and functional constraints and their evolutionary histories. Despite their …
information on structural and functional constraints and their evolutionary histories. Despite their …
Transporter genes in biosynthetic gene clusters predict metabolite characteristics and siderophore activity
Biosynthetic gene clusters (BGCs) are operonic sets of microbial genes that synthesize
specialized metabolites with diverse functions, including siderophores and antibiotics, which …
specialized metabolites with diverse functions, including siderophores and antibiotics, which …
Single layers of attention suffice to predict protein contacts
The established approach to unsupervised protein contact prediction estimates co-evolving
positions using undirected graphical models. This approach trains a Potts model on a …
positions using undirected graphical models. This approach trains a Potts model on a …
[HTML][HTML] Deep self-supervised learning for biosynthetic gene cluster detection and product classification
C Rios-Martinez, N Bhattacharya… - PLOS Computational …, 2023 - journals.plos.org
Natural products are chemical compounds that form the basis of many therapeutics used in
the pharmaceutical industry. In microbes, natural products are synthesized by groups of …
the pharmaceutical industry. In microbes, natural products are synthesized by groups of …
Interpreting potts and transformer protein models through the lens of simplified attention
The established approach to unsupervised protein contact prediction estimates coevolving
positions using undirected graphical models. This approach trains a Potts model on a …
positions using undirected graphical models. This approach trains a Potts model on a …
Randomized gates eliminate bias in sort‐seq assays
Sort‐seq assays are a staple of the biological engineering toolkit, allowing researchers to
profile many groups of cells based on any characteristic that can be tied to fluorescence. …
profile many groups of cells based on any characteristic that can be tied to fluorescence. …