crisprmedicinenews.com Open in urlscan Pro
178.72.21.226  Public Scan

Form analysis
1 forms found in the DOM

POST https://crisprmedicinenews.com/search/?no_cache=1

<form action="https://crisprmedicinenews.com/search/?no_cache=1" method="post"><input type="hidden" name="tx_indexedsearch_pi2[action]" value="search"><input type="hidden" name="tx_indexedsearch_pi2[controller]" value="Search"><input type="hidden"
    name="id" value="1198">
  <div class="element-wrapper"><input type="text" id="swords" class="text align-center" autocomplete="off" name="tx_indexedsearch_pi2[search][sword]" placeholder="Enter searchterms..."></div>
</form>

Text Content

CRISPR MEDICINE NEWS USES COOKIES

We use cookies to personalise content and ads, to provide social media features
and to analyse our traffic. We also share information about your use of our site
with our social media, advertising and analytics partners who may combine it
with other information that you’ve provided to them or that they’ve collected
from your use of their services. You consent to our cookies if you continue to
use our website.
Do not sell or share my personal information
Use necessary cookies only Allow all cookies Show details
OK
Allow all cookiesAllow selection Use necessary cookies only
Necessary
Preferences
Statistics
Marketing
Show details
Cookie declaration [#IABV2SETTINGS#] About
 Necessary (7)  Preferences (1)  Statistics (11)  Marketing (28)  Unclassified
(2)
Necessary cookies help make a website usable by enabling basic functions like
page navigation and access to secure areas of the website. The website cannot
function properly without these cookies.

NameProviderPurposeExpiryTypetestIterasUsed to detect if the visitor has
accepted the marketing category in the cookie banner. This cookie is necessary
for GDPR-compliance of the website. SessionHTTP
CookieCookieConsentCookiebotStores the user's cookie consent state for the
current domain1 yearHTTP Cookie1.gifCookiebotUsed to count the number of
sessions to the website, necessary for optimizing CMP product delivery.
SessionPixel Trackerli_gcLinkedInStores the user's cookie consent state for the
current domain180 daysHTTP CookiesessionIdplayer.restream.ioPreserves the
visitor's session state across page requests.SessionHTML Local
StoragebscookieLinkedInThis cookie is used to identify the visitor through an
application. This allows the visitor to login to a website through their
LinkedIn application for example.1 yearHTTP CookieJSESSIONIDLinkedInPreserves
users states across page requests.SessionHTTP Cookie

Preference cookies enable a website to remember information that changes the way
the website behaves or looks, like your preferred language or the region that
you are in.

NameProviderPurposeExpiryTypelangLinkedInSet by LinkedIn when a web page
contains an embedded "Follow us" panel.SessionHTTP Cookie

Statistic cookies help website owners to understand how visitors interact with
websites by collecting and reporting information anonymously.

NameProviderPurposeExpiryType(unnamed)SleeknoteRegisters statistical data on
users' behaviour on the website. Used for internal analytics by the website
operator. SessionPixel Tracker_gaGoogleRegisters a unique ID that is used to
generate statistical data on how the visitor uses the website.2 yearsHTTP
Cookie_ga_#GoogleUsed by Google Analytics to collect data on the number of times
a user has visited the website as well as dates for the first and most recent
visit. 2 yearsHTTP Cookie_gatGoogleUsed by Google Analytics to throttle request
rate1 dayHTTP Cookie_gidGoogleRegisters a unique ID that is used to generate
statistical data on how the visitor uses the website.1 dayHTTP
CookiepageviewCountcrisprmedicinenews.comThis cookie is used to identify the
frequency of visits and how long the visitor is on the website. The cookie is
also used to determine how many and which subpages the visitor visits on a
website – this information can be used by the website to optimize the domain and
its subpages.30 daysHTTP CookieSNSSleeknoteSets a unique ID for the session.
This allows the website to obtain data on visitor behaviour for statistical
purposes.SessionHTTP CookietimeonSitecrisprmedicinenews.comStores data on the
time spent on the website and its sub-pages, during the current session. 30
daysHTTP CookiecollectGoogleUsed to send data to Google Analytics about the
visitor's device and behavior. Tracks the visitor across devices and marketing
channels.SessionPixel
Trackersn_global_countdown_last_reset_timestampSleeknoteSets a timestamp for
when the visitor entered the website. This is used for analytical purposes on
the website. PersistentHTML Local Storagepersonalization_idTwitter Inc.This
cookie is set by Twitter - The cookie allows the visitor to share content from
the website onto their Twitter profile. 400 daysHTTP Cookie

Marketing cookies are used to track visitors across websites. The intention is
to display ads that are relevant and engaging for the individual user and
thereby more valuable for publishers and third party advertisers.

NameProviderPurposeExpiryTypelastExternalReferrer Meta Platforms, Inc.Detects
how the user reached the website by registering their last
URL-address.PersistentHTML Local StoragelastExternalReferrerTime Meta Platforms,
Inc.Detects how the user reached the website by registering their last
URL-address.PersistentHTML Local Storage_fbp Meta Platforms, Inc.Used by
Facebook to deliver a series of advertisement products such as real time bidding
from third party advertisers.3 monthsHTTP Cookie_sn_aSleeknoteImplements pop-up
advertisement on the website. 1 yearHTTP Cookie_sn_mSleeknoteImplements pop-up
advertisement on the website. 1 yearHTTP Cookie_sn_nSleeknoteImplements pop-up
advertisement on the website. 1 yearHTTP CookieNIDGoogleRegisters a unique ID
that identifies a returning user's device. The ID is used for targeted ads.6
monthsHTTP CookiebcookieLinkedInUsed by the social networking service, LinkedIn,
for tracking the use of embedded services.1 yearHTTP CookielidcLinkedInUsed by
the social networking service, LinkedIn, for tracking the use of embedded
services.1 dayHTTP CookieclientIdplayer.restream.ioUsed to track visitors on
multiple websites, in order to present relevant advertisement based on the
visitor's preferences. PersistentHTML Local Storagei/adsct [x2]Twitter Inc.The
cookie is used by Twitter.com in order to determine the number of visitors
accessing the website through Twitter advertisement content. SessionPixel
Trackermuc_adsTwitter Inc.Collects data on user behaviour and interaction in
order to optimize the website and make advertisement on the website more
relevant. 400 daysHTTP Cookie#-#YouTubeUsed to track user’s interaction with
embedded content.SessionHTML Local StorageiU5q-!O9@$YouTubeRegisters a unique ID
to keep statistics of what videos from YouTube the user has seen.SessionHTML
Local StorageLAST_RESULT_ENTRY_KEYYouTubeUsed to track user’s interaction with
embedded content.SessionHTTP CookienextIdYouTubeUsed to track user’s interaction
with embedded content.SessionHTTP CookierequestsYouTubeUsed to track user’s
interaction with embedded content.SessionHTTP
Cookieyt.innertube::nextIdYouTubeRegisters a unique ID to keep statistics of
what videos from YouTube the user has seen.PersistentHTML Local
Storageytidb::LAST_RESULT_ENTRY_KEYYouTubeUsed to track user’s interaction with
embedded content.PersistentHTML Local StorageYtIdbMeta#databasesYouTubeUsed to
track user’s interaction with embedded
content.PersistentIndexedDByt-remote-cast-availableYouTubeStores the user's
video player preferences using embedded YouTube videoSessionHTML Local
Storageyt-remote-cast-installedYouTubeStores the user's video player preferences
using embedded YouTube videoSessionHTML Local
Storageyt-remote-connected-devicesYouTubeStores the user's video player
preferences using embedded YouTube videoPersistentHTML Local
Storageyt-remote-device-idYouTubeStores the user's video player preferences
using embedded YouTube videoPersistentHTML Local
Storageyt-remote-fast-check-periodYouTubeStores the user's video player
preferences using embedded YouTube videoSessionHTML Local
Storageyt-remote-session-appYouTubeStores the user's video player preferences
using embedded YouTube videoSessionHTML Local
Storageyt-remote-session-nameYouTubeStores the user's video player preferences
using embedded YouTube videoSessionHTML Local Storage

Unclassified cookies are cookies that we are in the process of classifying,
together with the providers of individual cookies.

NameProviderPurposeExpiryTypequot;lquot;:https://#SleeknotePending1 yearHTTP
CookieccookieLinkedInPendingSessionHTTP Cookie

 [#IABV2_LABEL_PURPOSES#]  [#IABV2_LABEL_FEATURES#]  [#IABV2_LABEL_PARTNERS#]
[#IABV2_BODY_PURPOSES#]
[#IABV2_BODY_FEATURES#]
[#IABV2_BODY_PARTNERS#]
Cookies are small text files that can be used by websites to make a user's
experience more efficient.

The law states that we can store cookies on your device if they are strictly
necessary for the operation of this site. For all other types of cookies we need
your permission.

This site uses different types of cookies. Some cookies are placed by third
party services that appear on our pages.

You can at any time change or withdraw your consent from the Cookie Declaration
on our website.

Learn more about who we are, how you can contact us and how we process personal
data in our Privacy Policy.

Please state your consent ID and date when you contact us regarding your
consent.
Cookie declaration last updated on 16.08.24 by Cookiebot

Logo
mobilemenuclose
 * CMN Live
 * CMN+
 * Home
 * Clinical Trials
 * Diseases
   * CRISPR&
     * CRISPR and Acute Myeloid Leukemia
     * CRISPR and Beta-Thalassemia
     * CRISPR and Cancer
     * CRISPR and Diabetes
     * CRISPR and Duchenne Muscular Dystrophy
     * CRISPR and Herpes Simplex Virus (HSV)
     * CRISPR and HIV
     * CRISPR and Sickle Cell Disease (SCD)
 * Companies
 * CRISPRMED
   * CRISPRMED24
   * CRISPRMED25
 * Events
 * CMN Jobs
   * Job Upload Form
 * Webinars
   * CMN Webinars On-demand - All
   * CMN Webinar - Disrupting the Care of Cardiovascular Disease With
     Single-Course Gene Editing Medicines
   * CMN Webinar - Taking the Guesswork Out of Drug Development: CRISPR-Select
     Validates Drug Targets and Drug Responders Early and Conclusively
   * CMN Webinar - Clinical-Grade gRNA for Genomic Medicines: Making Sense of
     the CRISPR Regulatory Landscape
   * CMN Webinar - Enhancing T Cell Function for Cancer immunotherapy With
     CRISPR
   * CMN Webinar - Engineering Approaches to Improve CRISPR Technologies
   * CMN Webinar - Development of CRISPR/Cas9-based Therapies against
     Alzheimer's Disease
   * CMN Webinar - Epigenomic Editing Ameliorates Detrimental Effects of
     Adolescent Alcohol Exposure
   * CMN Webinar - Gene Editing for Junctional Epidermolysis Bullosa
   * CMN Webinar - Multiplexed Genome Regulation In Vivo with Hyper-efficient
     Cas12a
   * CMN Webinar - The TCR Therapy Revival
   * CMN Webinar - Deliver CRISPR to the Brain - A New Treatment Strategy for
     Mucopolysaccharidoses
   * CMN Webinar - Controllable Genome Editing With Split-Engineered Base
     Editors
   * CMN Webinar - CRISPR-based Control of Insect-borne Diseases
   * CMN Webinar - CRISPR and MLD
   * CMN Webinar - CRISPR Off-Targets II
   * CMN Webinar - Rare Diseases and CRISPR
   * CMN Webinar - CRISPR On/Off Target
   * CMN Webinar - CRISPR Off-Targets
   * CMN Webinar - CRISPR Delivery Systems
   * CMN Webinar - Certainty After CRISPR
 * Advertising
 * WDC
 * About
 * search


Selfservice|Subscriberlogin
Prime EditorsBase EditorsDeliverySafetyOff-targetMicrobiomeCAR-TTILRare
DiseasesTrialsExplainersCMN WeeklyCARBON


OPENCRISPR-1: GENERATIVE AI MEETS CRISPR

Researchers used large language models (LLMs) to expand the sequence diversity
of CRISPR-Cas proteins and generate novel, functional genome editors with
improved properties compared to natural systems. They publicly released
OpenCRISPR-1, the first AI-designed editor for precise genome editing. This
novel AI-based approach for designing CRISPR gene editors could potentially
expand the capabilities and applications of genome-editing technologies.

By: Christos Evangelou - Sep. 2, 2024
EmailFacebookLinkedinTwitter
Profluent Bio team members. Column 1 down: Aadyot Bhatnagar - Machine Learning
Scientist, Jeffrey Ruffolo - Head of Protein Design, Stephen Nayfach - Head of
Bioinformatics. Column 2 down: Ali Madani - CEO and Founder, Joseph Gallagher -
Associate Director. Photos courtesy of Profluent Bio.

In a recent study, researchers at Profluent Bio (Berkeley, CA, USA) used
artificial intelligence (AI) to design novel CRISPR gene editors that are
functional and that show comparable or improved genome-editing activity and
specificity relative to naturally occurring gene editors, despite being hundreds
of mutations away from any known natural protein. This innovative approach has
yielded OpenCRISPR-1, the first AI-generated gene editor.

In a proof-of-concept study, OpenCRISPR-1 demonstrated comparable efficiency to
the widely used Streptococcus pyogenes Cas9 (SpCas9) while offering improved
specificity. This development not only expands the CRISPR toolbox but also paves
the way for creating gene editors tailored to specific applications, which could
range from agriculture to medicine.

»Our LLMs, trained on billions of proteins in nature, are able to learn the
sequence-to-function mapping of natural proteins and can be utilised to build
functional proteins from scratch, such as OpenCRISPR-1,« said Ali Madani, PhD,
founder and CEO of Profluent Bio and senior author of the study.

»We can now use the model as a guide to install additional desired features, for
example, a set of mutations that alter PAM selectivity, a combination of
deletions to reduce size, or a set of mutations to alter thermostability while
simultaneously maintaining other key properties, such as processivity and
stability,« he added. »This can be very difficult to achieve with directed
evolution because the addition of one property may impair another. AI can
circumvent this.«

The study has not been peer-reviewed and is available as a preprint on bioRxiv.

RATIONALE: ADDRESSING LIMITATIONS OF NATURAL CRISPR-CAS SYSTEMS

CRISPR-Cas systems, originally evolved as bacterial defence mechanisms against
viruses, have been repurposed as powerful gene-editing tools. However, these
natural systems often face limitations when applied in non-native environments,
such as human cells.

Traditional approaches to optimising these tools for use in non-native
environments include directed evolution and structure-guided mutagenesis.
Although these approaches have yielded improvements, they are limited by the
need for explicit structural hypotheses or complex screening processes.

Directed evolution, for instance, can be limited by the complex nature of
‘fitness landscape’, a way to visualise how different genetic variations
perform. On the other hand, structure-guided approaches depend on solved
structures representing key functional states that are often difficult to obtain
for complex functions beyond simple binding interactions.

The objective of this study was to edit the human genome for the first time
using a gene editor that was designed entirely using AI. »This was a scientific
moon-shot, as CRISPR-Cas proteins are incredibly complex molecular machines with
precise functions that require an understanding of protein-protein as well as
protein-nucleic acid interactions,« said Dr. Madani.

APPROACH: USING AI TO DESIGN NOVEL, OPTIMISED EDITORS

To overcome the limitations of traditional approaches for optimising gene
editors, the research team leveraged the power of large language models (LLMs)
trained on vast amounts of biological data to generate novel CRISPR-Cas proteins
that could function as efficient gene editors in human cells.

To this end, the team compiled the CRISPR-Cas Atlas, an extensive dataset of
over one million CRISPR operons from diverse microbial genomes, by mining 26
terabases of assembled genomes and metagenomes.

»To our knowledge, CRISPR-Cas Atlas is the most extensive dataset of CRISPR
systems curated to date,« emphasised Dr. Madani.

Using this dataset, the researchers fine-tuned ProGen2, a protein language model
previously developed by Profluent, to specialise in generating CRISPR-Cas
proteins. The team balanced the training data for protein family representation
and sequence cluster size to ensure broad coverage. The fine-tuned models were
used to generate four million novel CRISPR-Cas protein sequences. Half were
generated directly, while the other half were prompted with short segments from
natural proteins to guide generation towards specific families.

> “Typical bioinformatic mining efforts in industry are directed toward
> searching for an ideal system in nature, akin to finding a needle in a
> haystack. Our atlas was curated with the primary objective of feeding as much
> data as possible to our LLMs to learn the underlying language and biophysical
> associations behind CRISPR systems. Once our LLMs gain mastery of this
> language, we can generate sequences across CRISPR-associated families as
> desired”Ali Madani, PhD, CEO and Founder of Profluent Bio

According to Dr. Madani, fine-tuning ProGen2 using the CRISPR-Cas Atlas enabled
the model to benefit from a general representation of proteins across the
diversity of life and a tailored understanding of CRISPR-associated systems.

Commenting on the novelty of this approach, Dr. Madani said: »Typical
bioinformatic mining efforts in industry are directed toward searching for an
ideal system in nature, akin to finding a needle in a haystack. Our atlas was
curated with the primary objective of feeding as much data as possible to our
LLMs to learn the underlying language and biophysical associations behind CRISPR
systems. Once our LLMs gain mastery of this language, we can generate sequences
across CRISPR-associated families as desired.«

»LLMs can analyse vast amounts of biological data, learning patterns and
relationships that are not immediately obvious. This allows for the generation
of novel, functional CRISPR-Cas variants with high efficiency and accuracy,
potentially uncovering designs that might be missed by traditional techniques,«
said Prof. Manuel Kaulich, PhD (Goethe University Frankfurt), who was not
involved in the study. “LLMs are novel and outpace traditional methods in
efficiency, scalability, and automation.”

Generated sequences were filtered and clustered to assess novelty and diversity.
To evaluate structural viability, the researchers used AlphaFold2 to predict the
structures of 5,000 AI-generated sequences. A subset of 209 generated Cas9-like
proteins were synthesised and tested for gene-editing activity in human cells
for experimental validation. The researchers assessed both on-target efficiency
and off-target effects across multiple genomic sites using next-generation
sequencing.

AI EXPANDS CRISPR-CAS DIVERSITY

The CRISPR-Cas Atlas included over one million CRISPR operons, offering 2.7
times more protein clusters across all Cas families compared to UniProt. The
sequences generated by the LLM represented a 4.8-fold expansion of diversity
compared to natural CRISPR-Cas proteins, with even greater expansions for
families with few natural proteins, such as Cas13 (8.4-fold expansion) and
Cas12a (6.2-fold expansion) (Figure 1).

Figure 1. Diverse CRISPR-associated protein families. a) LLMs pre-trained on
diverse proteins and fine-tuned on CRISPR data design CRISPR-Cas systems. b)
Sequence diversity for 45 Cas families, shown by clusters from natural and
generated sequences. Stacked bars indicate sequence sources. Heatmap shows
protein family frequency across Cas types. c) AlphaFold2 predicted structures
for 2,000 generated proteins. Ruffolo et al. bioRxiv preprint.
https://doi.org/10.1101/2024.04.22.590591

Despite significant sequence divergence from natural proteins (often with only
40-60% identity), the generated sequences were predicted to adopt folds highly
similar to their natural counterparts, suggesting functional viability (Figure
1). Importantly, core Cas9 domains, such as the HNH and RuvC nuclease domains,
PAM-interacting domain, and target recognition (REC) lobe, were present in most
generated proteins at rates similar to those of natural sequences.

According to Dr. Madani, these findings suggest that LLMs can generate diverse,
functional CRISPR-Cas proteins, bypassing evolutionary constraints. »Increasing
the diversity of CRISPR-like proteins and expanding virtually all known CRISPR
families beyond what exists in nature increases our ability to design bespoke
gene editors for each application,« he said.

Dr. Madani added that it is highly unlikely that there is a Cas protein that has
naturally evolved to have perfect PAM selectivity, catalytic efficiency, size,
stability, and specificity to fix a particular mutation. This approach could
help in the design of editors to fix the underlying causative mutations of
various genetic diseases.

»AI can be used to interpolate between and extrapolate beyond what nature has
explored, all the while with knobs at our disposal to optimise multiple desired
properties simultaneously,« he said.

OPENCRISPR-1: A FUNCTIONAL, HIGHLY SPECIFIC AI-DESIGNED GENE EDITOR

The team selected 209 Cas9-like proteins for experimental characterisation.
These were human codon-optimised, cloned into expression plasmids, and tested
for gene-editing activity in HEK293T cells. Of the 209 tested Cas9-like
proteins, many showed editing activity in human cells, with some performing on
par with or better than SpCas9 (Figure 2).

»This study marks a major leap in the field by not just optimising existing
proteins but creating entirely new variants with potentially superior
characteristics. The generation of novel Cas proteins with enhanced activity and
specificity has the potential to overcome some of the limitations of current
CRISPR systems, such as off-target effects, limited target range, and large
molecular weight,« noted Prof. Kaulich. »This could lead to more effective
therapies for genetic diseases and improved tools for research.«

Furthermore, receiver operating characteristic (ROC) analysis — a method for
assessing model performance or discriminate ability — showed that language model
scores were highly predictive of enzyme activity, separating active and inactive
enzymes with an area under the curve (AUC) value of 0.82.

»This is the first demonstration in human cells that AI can generate a
functional gene editor from scratch. This is one solution among the millions
that we can create from scratch,« highlighted Dr. Madani.

Figure 2. Generated nucleases as gene editors in human cells a) Phylogenetic
tree of Cas9 proteins, ancestral reconstructions, & generated effectors near
SpCas9 b) Editing efficiency of 209 AI-generated proteins across 3 target sites,
ordered by indel rates c-d) Mutational distances from natural proteins & SpCas9
for 131 active proteins e-f) On- & off-target editing efficiency for natural
Cas9s & 48 AI-generated proteins. Ruffolo et al. bioRxiv preprint.
https://doi.org/10.1101/2024.04.22.590591

OpenCRISPR-1, the top performer among the 209 tested Cas9-like proteins,
demonstrated comparable on-target editing efficiency to SpCas9 (median indel
rates of 55.7% versus 48.3%), with a 95% reduction in off-target editing across
multiple genomic sites tested (median indel rates of 0.32% versus 6.1%) (Figure
3).

»This high specificity is reminiscent of high-fidelity SpCas9 variants that have
been described in the literature,« noted Dr. Madani.

When asked about potential explanations for the high specificity of
OpenCRISPR-1, he said: »One hypothesis is that OpenCRISPR-1 may have altered
kinetics and off-rates. We are aiming to test OpenCRISPR-1 across a larger panel
of cell types and delivery methods to further explore potential trade-offs in
activity and specificity.«

Figure 3. Characterisation of OpenCRISPR-1. a-b) OpenCRISPR-1 shows similar
activity at NGG PAMs (n=49) but lower at non-NGG PAMs (n=43). c) Comparison of
SpCas9 and OpenCRISPR-1 across various PAMs. d-e) Adenine base editing
efficiency at three sites with different deaminases. f) Editing efficiency with
designed sgRNAs. g) Performance of designed sgRNAs compared to SpCas9 guide.
Ruffolo et al. bioRxiv preprint. https://doi.org/10.1101/2024.04.22.590591

OpenCRISPR-1 is 1,380 amino acids long, with 403 mutations compared to SpCas9
and 182 mutations from any natural protein in the CRISPR-Cas Atlas. Moreover,
OpenCRISPR-1 lacks immunodominant and subdominant T cell epitopes for
HLA-A*02:01 that were previously identified in SpCas9, suggesting a potentially
low immunogenicity for the AI-designed editor.

The authors have publicly released the OpenCRISPR-1 sequence to enable its broad
usage across research applications.

Commenting on their rationale for making the sequence of OpenCRISPR-1 publicly
available, Dr. Madani said: »Our goal in open-sourcing OpenCRISPR-1 is to
further democratise gene editing. We encourage the use of AI for ethical
research and commercial use, particularly in the development of medicines
leveraging CRISPR, the groundbreaking scientific discovery that is being used in
the development of new treatments for countless diseases. We’re excited to hear
from the broader scientific community regarding feedback on OpenCRISPR-1 and how
it compares with existing tools.«

BASE EDITING AND GUIDE RNA MODELLING

To expand the potential applications of OpenCRISPR-1, the team converted the
enzyme into a nickase and fused it with adenine deaminases, including the
established ABE8.20 and novel AI-generated deaminases. OpenCRISPR-1 nickase
showed robust A-to-G conversion rates (35%–60%) across multiple genomic loci
(Figure 3). These conversion rates are similar to those achieved with previously
established base editor systems, such as ABE8.20, PF-DEAM-1, and PF-DEAM-2.

»We have seen some early signs that the performance of base editors that are
generated from scratch with AI may have favourable on-target and by-stander
off-target profiles,« noted Dr. Madani.

The researchers also developed a sequence-to-sequence gRNA model to generate
optimised single-guide RNAs (sgRNAs) for the AI-designed Cas proteins. The
model-designed gRNAs were found to be similar to naturally derived gRNAs and
could accurately predict the compatibility of sgRNAs between diverse Cas9
orthologs. Testing of these sgRNAs showed enhanced editing efficiency for
several AI-generated Cas9-like proteins (Figure 3).

LOOKING AHEAD

According to Dr. Madani, this work represents the first successful precision
editing of the human genome using an entirely AI-generated CRISPR enzyme and its
associated RNA components. Although this represents a significant step forward
in the development of engineered CRISPR-Cas proteins with optimised properties,
the study primarily focused on Cas9-like proteins. Future work could expand to
other CRISPR-Cas proteins, including Cas12 and Cas13, and explore more diverse
functionalities.

»Rather than viewing OpenCRISPR-1 as a static asset, we are enthusiastically
receptive to feedback on how it performs in multiple settings in the hands of
the broader community. There is a lot of room for improvement, pivots, and
growth,« Dr. Madani said.

> “By enabling the rapid design of novel CRISPR-Cas systems with improved
> specificity and activity, this method paves the way for more precise gene
> therapies, potentially reducing off-target effects and improving patient
> outcomes. The approach could accelerate the development of treatments for
> genetic disorders, enhance research capabilities in synthetic biology, and
> enable the discovery of new therapeutic strategies”Manuel Kaulich, PhD (Goethe
> University Frankfurt)

Moreover, the study did not assess the long-term effects or potential
immunogenicity of the AI-generated proteins, which is crucial for evaluating the
potential use of AI-generated CRISPR systems for therapeutic applications.
Furthermore, future studies are needed to further characterise and optimise
OpenCRISPR-1 for potential therapeutic applications. Aspects of improvement
include the enzyme’s activity, specificity, PAM selectivity, stability, and
size.

Prof Kaulich commented on the potential of AI-designed CRISPR proteins for
developing new gene therapies: »By enabling the rapid design of novel CRISPR-Cas
systems with improved specificity and activity, this method paves the way for
more precise gene therapies, potentially reducing off-target effects and
improving patient outcomes. The approach could accelerate the development of
treatments for genetic disorders, enhance research capabilities in synthetic
biology, and enable the discovery of new therapeutic strategies.«

He noted, however, that the use of AI to generate gene-editing tools may raise
ethical concerns and exacerbate inequalities if access to these technologies is
limited to certain groups. »Ensuring the safety, accuracy, and reliability of
AI-generated tools is crucial, requiring thorough experimental validation and
robust regulatory oversight,« Prof Kaulich said. He added that addressing these
concerns involves establishing clear ethical guidelines, promoting transparency,
and ensuring equitable access to the technology.

Dr. Madani emphasised that OpenCRISPR-1 is only the first milestone in a long
journey to cure disease. »We view AI-designed gene editors as an important tool
that allows us to shift the drug development paradigm away from accidental
discovery or limited manual engineering and toward intentional and rapid design
of bespoke gene-editing solutions. Our hope is that, by lowering the costs and
barriers to entry for therapeutic applications, AI-designed gene editors will
accelerate innovation in genetic medicines.«

Link to the preprint:

Design of highly functional genome editors by modeling the universe of
CRISPR-Cas sequences

Christos Evangelou, PhD, is a freelance medical writer and science
communications consultant.


TAGS

HashtagArticleHashtagInterviewHashtagNewsHashtagAI in genome editing



LATEST NEWS

CMN Weekly (30 August 2024) - Your Weekly CRISPR...
CMN Weekly

Aug. 30, 2024

Some of the best links we picked up around the internet

CRISPR Identifies ZNF740 as Key to Venetoclax...
CMN Briefs

Aug. 29, 2024

A CRISPR-based screen has revealed that the transcription factor ZNF740 plays a
pivotal role in determining the sensitivity of acute myeloid leukaemia...

Dosing Underway in World’s First in Vivo CRISPR...
CMN Clinical

Aug. 28, 2024

YolTech Therapeutics announced last week that the first two patients have been
dosed in a Phase 1 trial of YOLT-203, an in vivo CRISPR-based...

Efficient Epigenome Editing Targets Alzheimer's...
CMN Briefs

Aug. 27, 2024

Researchers have developed a compact, all-in-one CRISPR-dCas9-based repressor
platform delivered via AAV, effectively silencing gene expression...

Minimal Type I-F2 CRISPR-Cas Activates...
CMN Briefs

Aug. 26, 2024

Researchers have engineered a minimal type I-F2 CRISPR-Cas system capable of
transcriptional activation and base editing in human cells. This...

CMN Weekly (23 August 2024) - Your Weekly CRISPR...
CMN Weekly

Aug. 23, 2024

Some of the best links we picked up around the internet

CLINICAL TRIALS

Relapsed or Refractory B-Cell Non-Hodgkin Lymphoma, NHL, (NCT05741359)
Sponsors:
Bioray Laboratories
Indicator

IND Enabling
Phase I
Phase II
Phase III
Castration-Resistant Prostate Cancer, CRPC, (NCT06228404)
Sponsors:
Shanghai Changzheng Hospital
Indicator

IND Enabling
Phase I
Phase II
Phase III
Refractory Autoimmune Diseases, (NCT06485232)
Sponsors:
Xuanwu Hospital, Beijing
Indicator

IND Enabling
Phase I
Phase II
Phase III
View all clinical trials

CRISPR Medicine

https://crisprmedicinenews.com/
CRISPR Medicine Media Aps
CVR-DK-39130327

E-mail:TheEditor@crisprmedicinenews.com
Cookies

FOLLOW US

LinkedinTwitterFacebook
TYPO3 CMS by TypoConsult A/S
close
Search CRISPR Medicine