Salvatore Candido

Salvatore Candido

Auto-generated profile, based on publicly available information

Salvatore Candido

Loon

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 March 2023 in Science
Verified
Journal Article
Closed access
ZLZeming Lin
Zeming Lin
HAHalil Akin
Halil Akin
RRRoshan Rao
Roshan Rao
BHBrian Hie
Brian Hie
ZZZhongkai Zhu
Zhongkai Zhu
ARAlexander Rives
Alexander Rives
Recent advances in machine learning have leveraged evolutionary information in multiple sequence alignments to predict protein structure. We demonstrate direct inference of full atomic-level protein structure from primary sequence using a large language model. As language models of protein sequences are scaled up to 15 billion parameters, an atomic-resolution picture of protein structure emerges in the learned representations. This results in an order-of-magnitude acceleration of high-resolution structure prediction, which enables large-scale structural characterization of metagenomic proteins. We apply this capability to construct the ESM Metagenomic Atlas by predicting structures for >617 million metagenomic protein sequences, including >225 million that are predicted with high confidence, which gives a view into the vast breadth and diversity of natural proteins.

21 February 2025 in Science
Verified
Journal Article
Closed access
THThomas Hayes
Thomas Hayes
RRRoshan Rao
Roshan Rao
HAHalil Akin
Halil Akin
NSNicholas J. Sofroniew
Nicholas J. Sofroniew
DODeniz Oktay
Deniz Oktay
ARAlexander Rives
Alexander Rives
More than 3 billion years of evolution have produced an image of biology encoded into the space of natural proteins. Here, we show that language models trained at scale on evolutionary data can generate functional proteins that are far away from known proteins. We present ESM3, a frontier multimodal generative language model that reasons over the sequence, structure, and function of proteins. ESM3 can follow complex prompts combining its modalities and is highly responsive to alignment to improve its fidelity. We have prompted ESM3 to generate fluorescent proteins. Among the generations that we synthesized, we found a bright fluorescent protein at a far distance (58% sequence identity) from known fluorescent proteins, which we estimate is equivalent to simulating 500 million years of evolution.

2 December 2020 in Nature
Verified
Journal Article
Closed access
PDF file
MBMarc G. Bellemare
Marc G. Bellemare
SCSalvatore Candido
Salvatore Candido
PCPablo Samuel Castro
Pablo Samuel Castro
JGJun Gong
Jun Gong
MMMarlos C. Machado
Marlos C. Machado
ZWZiyu Wang
Ziyu Wang

4 June 2026 in bioRxiv
Verified
Preprint
Open access
PDF file
SCSalvatore Candido
Salvatore Candido
THThomas Hayes
Thomas Hayes
ADAlexander Derry
Alexander Derry
RRRoshan Rao
Roshan Rao
ZLZeming Lin
Zeming Lin
ARAlexander Rives
Alexander Rives
Proteins are fundamental to life. The full extent of their biology is beyond our ability to characterize with experimental approaches in the physical laboratory. Accurate digital representations could accelerate the discovery of protein biology through virtual experiments. We propose language modeling to learn unified and general representations that can be scaled to all of protein biology. Building on these representations, we develop a structure prediction model that exceeds the performance of established methods for biomolecular complex prediction across benchmarks, including for the interactions of antibodies with their targets. A simple search procedure yields high experimental success rates for the discovery of proteins with nanomolar binding affinities for both miniproteins and single-chain antibodies, a modality critical for therapeutic design. Study of the concepts in the language model's representation space reveals a systematic organization aligned with the reductionist understanding of proteins developed through empirical science. Leveraging this organization, we generate a comprehensive map of protein biology encompassing over 6.8 billion sequences and 1.1 billion predicted structures, identifying connections across known and unknown biology. As a whole, this shows language modeling as a powerful substrate for representing the biology of proteins, operating across scales from the prediction and design of protein interactions at the atomic level, to identifying properties of proteins at different levels of granularity and abstraction, to the scale of mapping connections between proteins across billions of years of evolution.

7 August 2020 in Geophysical Research Letters
Verified
Journal Article
Open access
PDF file
SCSalvatore Candido
Salvatore Candido
ASAakanksha Singh
Aakanksha Singh
LMLuca Delle Monache
Luca Delle Monache
We discuss improving forecasts of winds in the lower stratosphere using machine learning to postprocess the output of the European Centre for Medium‐Range Weather Forecasts (ECMWF) Integrated Forecast System. We postprocess global three‐dimensional predictions and demonstrate distilling the analog ensemble (AnEn) method into a deep neural network, which reduces postprocessing latency to near zero maintaining increased forecast skill. This approach reduces the error with respect to ECMWF high‐resolution deterministic prediction between 2–15% for wind speed and 15–25% for direction and is on par with ECMWF ensemble (ENS) forecast skill to hour 60. Verifying with Loon data from stratospheric balloons, AnEn has 20% lower error than ENS for wind speed and 15% for wind direction, despite significantly lower real‐time computational cost to ENS. Similar performance patterns are reported for probabilistic predictions, with larger improvements of AnEn with respect to ENS. We also demonstrate that AnEn generates a calibrated probabilistic forecast.

17 June 2020 in ESS Open Archive
Verified
Preprint
Open access
SCSalvatore Candido
Salvatore Candido
ASAakanksha Singh
Aakanksha Singh
LMLuca Delle Monache
Luca Delle Monache
We discuss improving forecasts of winds in the lower stratosphere using machine learning to post-process the output of the European Centre for Medium-Range Weather Forecasts (ECMWF) Integrated Forecast System. We post-process global three-dimensional predictions, and demonstrate distilling the analog ensemble (AnEn) method into a deep neural network which reduces post-processing latency to near zero maintaining increased forecast skill. This approach reduces the error with respect to ECMWF high-resolution deterministic prediction between 2-15% for wind speed and 15-25% for direction, and is on par with ECMWF ensemble (ENS) forecast skill to hour 60. Verifying with Loon data from stratospheric balloons, AnEn has 20% lower error than ENS for wind speed and 15% for wind direction, despite significantly lower real-time computational cost to ENS. Similar performance patterns are reported for probabilistic predictions, with larger improvements of AnEn with respect to ENS. We also demonstrate that AnEn generates a calibrated probabilistic forecast.