BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.scipy.org//2023//speaker//BXXPAY
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20220712T000000
TZNAME:CDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T020000
RDATE:20231105T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230312T030000
RDATE:20240310T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:tfmodisco-lite: an attribution-based motif discovery algorithm - J
 acob Schreiber
DTSTART;TZID=America/Chicago:20230712T112500
DTEND;TZID=America/Chicago:20230712T115500
DTSTAMP:20261015T205411Z
UID:pretalx-2023-AQ3Z3U@cfp.scipy.org
DESCRIPTION:An important problem in genomics is identifying the proteins t
 hat bind to DNA. Although many methods attempt to learn DNA motifs underly
 ing protein binding as position-weight matrices (PWMs)\, these PWMs cannot
  faithfully represent real biology. For instance\, a static PWM cannot des
 cribe a zinc-finger protein whose fingers can optionally include one-nucle
 otide spacing. TF-MoDISco is a framework for extracting motifs using attri
 bution scores from a machine-learning model. The learned motifs and syntax
  overcome many of the limitations presented by PWM. I will describe the TF
 -MoDISco algorithm and showcase its efficient re-implementation\, tfmodisc
 o-lite.
LOCATION:Grand Salon C
URL:https://cfp.scipy.org/2023/talk/AQ3Z3U/
END:VEVENT
END:VCALENDAR