Biohub researchers performed what they believe is the first genome-wide CRISPR study of primary human adult skin cells, then used an AI model to mine the results for overlooked drug targets for psoriasis. They found an unlikely candidate: the receptor for oxytocin, a hormone involved in childbirth and sometimes called the “love hormone” for its role in social bonding. As reported in Nature Communications, when the team formulated topical gels containing compounds that would inhibit the oxytocin receptor, as well as another promising target, both gels reduced psoriasis inflammation in mice as effectively as an injected drug used by many patients.
“A CRISPR screen at this scale, guided by AI, gave us answers the field has never had access to before, as well as a surprisingly effective potential treatment,” said Shana O. Kelley, study co-leader with Abdalla M. Abdrabou. “We think of this as a blueprint,” Abdrabou added. “The specific targets we found in psoriasis are exciting, but the method itself is what we are most proud of. This is a generalizable way to find treatments that those of us studying disease wouldn’t even know to look for.”
Psoriasis affects roughly 125 million people worldwide. Topical steroid creams often manage mild cases, but moderate-to-severe disease requires systemic therapies with trade-offs: injected biologics can cost tens of thousands of dollars per year and carry risks from broad immune suppression, while newer pill-form therapies still circulate throughout the body. What has been missing is an approach that acts locally in keratinocytes, the skin cells where psoriasis begins—cells that have resisted large-scale CRISPR screening because standard delivery chemicals are toxic to them. The Biohub team solved this using centrifuge-generated forces instead of chemicals to deliver CRISPR into cells.
Using roughly 77,000 guide RNAs, researchers knocked out about 19,000 genes in keratinocytes from two donors, measuring effects on IL17RA, a protein tied to psoriatic inflammation. Gene sequencing revealed which knockouts changed IL17RA abundance, producing a genome-wide map of its regulators in skin cells. To find genuinely novel hits, the team used VirtualCRISPR, a large language model trained on published literature, to flag genes strongly implicated in the screen but overlooked in existing research. Two candidates cleared the bar: ALOX5, targeted by the asthma drug zileuton, and OXTR, the oxytocin receptor, targeted by cligosiban.
Validated in Biohub’s 3D skin cultures, zileuton reprogrammed keratinocyte metabolism without immune cells present. As topical gels tested against an injected anti-IL17RA drug in mice, both reduced disease severity within five days and matched the injected drug’s results within a week; cligosiban produced the broadest skin restoration. Because both compounds have established human safety records, Kelley said the approach “will help get new treatments, for psoriasis and other conditions, to patients faster.”
“A CRISPR screen at this scale, guided by AI, gave us answers the field has never had access to before, as well as a surprisingly effective potential treatment,” said Shana O. Kelley, study co-leader with Abdalla M. Abdrabou. “We think of this as a blueprint,” Abdrabou added. “The specific targets we found in psoriasis are exciting, but the method itself is what we are most proud of. This is a generalizable way to find treatments that those of us studying disease wouldn’t even know to look for.”
Psoriasis affects roughly 125 million people worldwide. Topical steroid creams often manage mild cases, but moderate-to-severe disease requires systemic therapies with trade-offs: injected biologics can cost tens of thousands of dollars per year and carry risks from broad immune suppression, while newer pill-form therapies still circulate throughout the body. What has been missing is an approach that acts locally in keratinocytes, the skin cells where psoriasis begins—cells that have resisted large-scale CRISPR screening because standard delivery chemicals are toxic to them. The Biohub team solved this using centrifuge-generated forces instead of chemicals to deliver CRISPR into cells.
Using roughly 77,000 guide RNAs, researchers knocked out about 19,000 genes in keratinocytes from two donors, measuring effects on IL17RA, a protein tied to psoriatic inflammation. Gene sequencing revealed which knockouts changed IL17RA abundance, producing a genome-wide map of its regulators in skin cells. To find genuinely novel hits, the team used VirtualCRISPR, a large language model trained on published literature, to flag genes strongly implicated in the screen but overlooked in existing research. Two candidates cleared the bar: ALOX5, targeted by the asthma drug zileuton, and OXTR, the oxytocin receptor, targeted by cligosiban.
Validated in Biohub’s 3D skin cultures, zileuton reprogrammed keratinocyte metabolism without immune cells present. As topical gels tested against an injected anti-IL17RA drug in mice, both reduced disease severity within five days and matched the injected drug’s results within a week; cligosiban produced the broadest skin restoration. Because both compounds have established human safety records, Kelley said the approach “will help get new treatments, for psoriasis and other conditions, to patients faster.”